CN116843203B

CN116843203B - Service access processing method, device, equipment, medium and product

Info

Publication number: CN116843203B
Application number: CN202311121604.7A
Authority: CN
Inventors: 曾文璇; 黄金生; 雷植程; 陈平; 闫颖异
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2023-09-01
Filing date: 2023-09-01
Publication date: 2024-09-24
Anticipated expiration: 2043-09-01
Also published as: CN116843203A

Abstract

The embodiment of the application discloses a service access processing method, a device, equipment, a medium and a product, comprising the following steps: responding to a service access request of a target object, and acquiring feature data corresponding to the target object in a past service request process; determining a service evaluation factor of the target object according to the characteristic data, wherein the service evaluation factor is used for representing factor information influencing service cost; calculating service cost scores of the target objects according to the service evaluation factors, wherein the service cost scores are used for representing the demand degree of the target objects on the resources to be allocated; and determining the access sequence of the target object in the service access queue based on the service cost score of the target object. The technical scheme of the embodiment of the application provides a new dimension reference for the service access sequence, so that queuing becomes more reasonable and intelligent, and the overall service efficiency is facilitated to be optimized.

Description

Service access processing method, device, equipment, medium and product

Technical Field

The present application relates to the field of computer technology, and in particular, to a service access processing method, a service access processing apparatus, an electronic device, a computer readable storage medium, and a computer program product.

Background

Many organizations currently offer services such as consultation, problem solving, problem handling, and complaints, and as the demand for these services by objects continues to increase, the resources of the services are limited, resulting in the frequent need to wait in line when an object attempts to request the resources of the services by accessing the services. Currently, the main basis of queuing is access request time of an object, but it is not reasonable to rely on access time alone for queuing, which may cause poor experience of the object in the waiting process.

Disclosure of Invention

The embodiment of the application provides a service access processing method, a service access processing device, electronic equipment, a computer readable storage medium and a computer program product, which provide new dimension references for service access sequences, so that queuing becomes more reasonable and intelligent and the overall service efficiency is facilitated to be optimized.

Other features and advantages of the application will be apparent from the following detailed description, or may be learned by the practice of the application.

According to an aspect of an embodiment of the present application, there is provided a service access processing method, including: responding to a service access request of a target object, and acquiring feature data corresponding to the target object in a past service request process; determining a service evaluation factor of the target object according to the characteristic data, wherein the service evaluation factor is used for representing factor information influencing service cost; calculating service cost scores of the target objects according to the service evaluation factors, wherein the service cost scores are used for representing the demand degree of the target objects on resources to be allocated; and determining the access sequence of the target object in a service access queue based on the service cost score of the target object.

According to an aspect of an embodiment of the present application, there is provided a service access processing apparatus, the apparatus including: the acquisition module is used for responding to the service access request of the target object and acquiring the characteristic data corresponding to the target object in the process of the past service request; the determining module is used for determining a service evaluation factor of the target object according to the characteristic data, wherein the service evaluation factor is used for representing factor information influencing service cost; the computing module is used for computing service cost scores of the target objects according to the service evaluation factors, wherein the service cost scores are used for representing the demand degree of the target objects on resources to be allocated; and the determining module is also used for determining the access sequence of the target object in the service access queue based on the service cost score of the target object.

In an embodiment of the application, the feature data includes track data of the target object for a past service request and service data for the target object; the determining module is further used for determining a first evaluation factor corresponding to the target object access service channel according to the track data, and the first evaluation factor is used for representing the influence degree of the service channel access frequency on the service cost; determining a second evaluation factor corresponding to the target object service demand according to the service data, wherein the second evaluation factor is used for representing the influence degree of the resolution degree of the service demand on the service cost; and determining the service evaluation factor according to the first evaluation factor and the second evaluation factor.

In an embodiment of the application, the number of service valuation factors includes a plurality; the computing module is further used for acquiring a weight value of each service evaluation factor and acquiring an object value of each object on each service evaluation factor aiming at each service evaluation factor; calculating an abnormal value corresponding to each service evaluation factor according to the object value of each object on each service evaluation factor; and calculating the service cost score of the target object according to the value corresponding to each service evaluation factor, the weight value of each service evaluation factor and the abnormal value corresponding to each service evaluation factor.

In an embodiment of the present application, the calculating module is further configured to calculate a service cost score of the service evaluation factor according to a weight value of the service evaluation factor if the value corresponding to the service evaluation factor is greater than the abnormal value corresponding to the service evaluation factor; if the value corresponding to the service evaluation factor is smaller than the abnormal value corresponding to the service evaluation factor, calculating the service cost of the service evaluation factor according to the proportion between the value corresponding to the service evaluation factor and the abnormal value corresponding to the service evaluation factor and the weight value of the service evaluation factor; and calculating the service cost score of the target object according to the service cost score of each service evaluation factor.

In an embodiment of the present application, the computing module is further configured to configure a first weight value for each service evaluation factor in a first weight configuration manner; respectively configuring a second weight value for each service evaluation factor through a second weight configuration mode, wherein the second weight configuration mode is different from the first weight configuration mode; and determining the weight value of each service evaluation factor according to the first weight value and the second weight value of each service evaluation factor.

In an embodiment of the application, the computing module is further configured to determine an initial weight value of a target service assessment factor according to the first weight value and the second weight value of the target service assessment factor; acquiring a target object group to which the target object belongs according to characteristic data corresponding to the target object in a past service request process; and adjusting the initial weight value of the target service evaluation factor according to the service preference corresponding to the target object group to obtain the weight value of the target service evaluation factor.

In an embodiment of the present application, the calculation module is further configured to obtain mathematical expectations and standard deviations corresponding to values of the plurality of objects on the target service evaluation factors if the values of the plurality of objects on the target service evaluation factors conform to a normal distribution; and calculating an abnormal value corresponding to the target service evaluation factor according to the mathematical expectation and the standard deviation to obtain an abnormal value corresponding to each service evaluation factor.

In an embodiment of the present application, the apparatus further includes a construction module, configured to obtain a sample service cost score with a cost score greater than a preset cost score threshold, and a sample service evaluation factor corresponding to the sample service cost score; extracting the characteristics of the sample service evaluation factors to obtain sample service characteristics; constructing a service cost prediction model according to the sample service characteristics and the sample service cost score; the computing module is further configured to predict a service cost score for the target object based on the service cost prediction model and a service assessment factor for the target object.

In an embodiment of the present application, the computing module is further configured to input a service evaluation factor of the target object to the service cost prediction model, where the service cost prediction model is configured to perform feature extraction on the service evaluation factor to obtain a service feature, and calculate a similarity between the service feature and the sample service feature; and predicting the service cost score of the target object according to the similarity output by the service cost prediction model and the preset cost score threshold.

In an embodiment of the application, the determining module is further configured to calculate an outlier of the historical service cost score according to a plurality of historical service cost scores; comparing the service cost of the target object with an outlier of the historical service cost score; and if the service cost score of the target object is larger than the abnormal value of the historical service cost score, performing queue inserting processing on the target object in the service access queue so as to assign the target object access service preferentially.

In an embodiment of the present application, the determining module is further configured to score-sort the plurality of historical service cost scores to obtain a sorting result, and determine at least two quartiles in the plurality of historical service cost scores according to the sorting result; and calculating an outlier of the historical service cost score according to the at least two quartiles.

In an embodiment of the present application, the determining module is further configured to obtain a preset queue policy; if the current resource to be allocated is greater than a preset resource threshold, acquiring target feature data corresponding to the target object in the current service request process, and determining whether the target object accords with the preset queue inserting strategy according to the target feature data; and if the target object accords with the preset queue inserting strategy, performing queue inserting processing on the target object in the service access queue.

According to one aspect of an embodiment of the present application, an electronic device is provided, including one or more processors; and storage means for storing one or more computer programs which, when executed by the one or more processors, cause the electronic device to implement the service access processing method as described above.

According to an aspect of an embodiment of the present application, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor of an electronic device, causes the electronic device to perform a service access processing method as described above.

According to an aspect of the embodiments of the present application, there is provided a computer program product including a computer program stored in a computer-readable storage medium, from which a processor of an electronic device reads and executes the computer program, causing the electronic device to execute the service access processing method as described above.

In the technical scheme provided by the embodiment of the application, the service end obtains the characteristic data corresponding to the target object in the process of the past service request by responding to the service access request of the target object, and determines the service evaluation factors of the target object according to the characteristic data, wherein the factors accurately reflect the factor information influencing the service cost, further calculates the service cost of the target object according to the service evaluation factors, thereby more accurately evaluating the demand degree of the target object for the resources to be allocated, and then reasonably determining the access sequence of the target object in the service access queue according to the demand degree of the target object for the resources to be allocated, namely comprehensively evaluating the characteristic data corresponding to the target object in the process of the past service request, and providing a new dimension reference for the service access sequence, so that the queuing becomes more reasonable and intelligent, thereby being beneficial to optimizing the whole service efficiency and the resource utilization rate, and improving the service quality and the customer satisfaction.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application as claimed.

Drawings

FIG. 1 is a schematic diagram of an implementation environment in which the present application is directed.

Fig. 2 is a flowchart illustrating a service access processing method according to an exemplary embodiment of the present application.

Fig. 3 is a flowchart illustrating another service access processing method according to an exemplary embodiment of the present application.

Fig. 4 is a flowchart illustrating another service access processing method according to an exemplary embodiment of the present application.

Fig. 5 is a flowchart illustrating another service access processing method according to an exemplary embodiment of the present application.

Fig. 6 is a flowchart illustrating another service access processing method according to an exemplary embodiment of the present application.

Fig. 7 is a flowchart illustrating another service access processing method according to an exemplary embodiment of the present application.

Fig. 8 is a flowchart illustrating another service access processing method according to an exemplary embodiment of the present application.

Fig. 9 is a flowchart illustrating another service access processing method according to an exemplary embodiment of the present application.

Fig. 10 is a flowchart illustrating a service access processing method according to an exemplary embodiment of the present application.

Fig. 11 is a flowchart illustrating a service access processing method according to an exemplary embodiment of the present application.

Fig. 12 is a flowchart illustrating a service access processing method according to an exemplary embodiment of the present application.

Fig. 13 is a flowchart illustrating another service access processing method according to an exemplary embodiment of the present application.

Fig. 14 is a flowchart illustrating another service access processing method according to another exemplary embodiment of the present application.

Fig. 15 is a block diagram showing a structure of a service access processing apparatus according to an exemplary embodiment of the present application.

Fig. 16 shows a schematic diagram of a computer system suitable for use in implementing an embodiment of the application.

Detailed Description

Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the application. Rather, they are merely examples of apparatus and methods consistent with aspects of the application as detailed in the accompanying claims.

The block diagrams depicted in the figures are merely functional entities and do not necessarily correspond to physically separate entities. That is, the functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.

The flow diagrams depicted in the figures are exemplary only, and do not necessarily include all of the elements and operations/steps, nor must they be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the order of actual execution may be changed according to actual situations.

Also to be described is: in the present application, the term "plurality" means two or more. "and/or" describes an association relationship of an association object, meaning that there may be three relationships, e.g., a and/or B may represent: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship.

The technical scheme of the embodiment of the application relates to the technical field of artificial intelligence (ARTIFICIAL INTELLIGENCE, AI), and before the technical scheme of the embodiment of the application is introduced, the AI technology is introduced briefly. AI is a theory, method, technique, and application system that utilizes a digital computer or a digital computer-controlled machine to simulate, extend, and extend human intelligence, sense the environment, acquire knowledge, and use knowledge to obtain optimal results. In other words, AI is an integrated technology of computer science that attempts to understand the essence of intelligence and to produce a new intelligent machine that can react in a similar way to human intelligence. AI is the design principle and the realization method of researching various intelligent machines, and the machines have the functions of perception, reasoning and decision.

The machine learning (MACHINE LEARNING, ML) is a multi-domain interdisciplinary, and relates to a plurality of disciplines such as probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and the like. It is specially studied how a computer simulates or implements learning behavior of a human to acquire new knowledge or skills, and reorganizes existing knowledge structures to continuously improve own performance. Machine learning is the core of AI, which is the fundamental way for computers to have intelligence, which applies throughout the various areas of AI. Machine learning and deep learning typically include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, induction learning, teaching learning, and the like.

The technical scheme of the embodiment of the application relates to a machine learning technology in AI, in particular to a method for constructing a service cost score prediction model based on the machine learning technology so as to predict service cost scores.

The following describes the technical scheme of the embodiment of the present application in detail in connection with the implementation environment.

Referring to fig. 1, fig. 1 is a schematic diagram of an implementation environment according to the present application. The implementation environment includes a terminal 10, a server 20, and a network.

A terminal 10, configured to initiate a service access request for a target object, where the service access request may be for a specified service or for any service; the terminal may send a service access request to a corresponding server that may process the request.

The server 20 is configured to respond to a service access request of a target object, so as to obtain feature data corresponding to the target object in a past service request process; determining a service evaluation factor of the target object according to the characteristic data, wherein the service evaluation factor is used for representing factor information influencing service cost; and then calculating the service cost score of the target object according to the service evaluation factor, wherein the service cost score is used for representing the demand degree of the target object for the resources to be allocated, and further determining the access sequence of the target object in the service access queue based on the service cost score of the target object.

It can be understood that, for different service scenarios, the service end is different, for example, the service scenario corresponding to the service access request is the service of the operator, and the service end is the operator; the service scene corresponding to the service access request is after-sales service of the product, and the service end is the product seller.

The terminal 10 may be any electronic device capable of displaying content, such as a smart phone, a tablet, a notebook computer, a computer, an intelligent voice interaction device, an intelligent home appliance, a terminal specially used on a vehicle, an aircraft, etc., and the server 20 may be an independent physical server, may be a server cluster or a distributed system formed by a plurality of physical servers, may also be a cloud server that provides cloud services, a cloud database, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network, content distribution network), and basic cloud computing services such as big data and an intelligent platform, which are not limited herein.

The terminal 10 and the server 20 previously establish a communication connection through a network so that the terminal 10 and the server 20 can communicate with each other through the network. The network may be a wired network or a wireless network, and is not limited in this regard.

It should be noted that, in the specific embodiment of the present application, the service access request and/or the feature data relate to the usage object, when the embodiment of the present application is applied to the specific product or technology, the usage object permission or consent needs to be obtained, and the collection, use and processing of the related data need to comply with the relevant regulations and standards of the relevant country and region.

Various implementation details of the technical solutions of the embodiments of the present application are set forth in detail below.

As shown in fig. 2, fig. 2 is a flowchart illustrating a service access processing method according to an embodiment of the present application, which may be applied to the implementation environment shown in fig. 1, and the method may be performed by a server, and the service access processing method may include steps S210 to S240, which will be described in detail below.

S210, responding to a service access request of a target object, and acquiring feature data corresponding to the target object in a past service request process.

In the embodiment of the application, the service access request of the target object is used for indicating the request of accessing the service so as to provide corresponding service for the target object; for example, requesting access to a service line so that customer service provides customer service for the target object; after the service end obtains the service access request, the service end responds to the service access request, and the service end obtains the characteristic data corresponding to the target object in the process of the service request in the past from a database.

The historical service request process comprises the whole process from the initiation of the request service to the termination of the service, and the characteristic data corresponding to the historical service request process comprises track data of a target object aiming at the historical service request, namely data such as operation data generated by the target object in the process from the initiation of the service request to the termination of the historical service request; the feature data also includes service data, such as response data, for the target object at the server.

Taking a request for accessing a service hotline as an example, the step of the server responding to the current service access request of the target object to obtain the characteristic data of the target object in the past service request process comprises the following steps: the system comprises request initiation times, request initiation time, waiting time of accessing hotline, access time of accessing customer service, service requirements and the like, and also comprises response contents, switching times, upgrading times and the like of a service end aiming at the service requirements.

In an example, in order to improve the service quality, the server may acquire feature data corresponding to the target object in the history service request process in a preset time period before the current moment, where the preset time period may be flexibly adjusted according to the actual situation, for example, may be determined according to the activity of the target object, where the activity is positively related to the number of times that the target object initiates the service access request, and the higher the activity is, the shorter the preset time period is; the object identity level of the target object can be determined according to the object identity level, and the higher the object identity level is, the longer the preset time period is.

It can be appreciated that the service types provided by the service end include a plurality of service types, such as consultation, problem solution, problem processing, complaint, etc., and the service access request includes a target service type; in an example, the server may obtain, for the target service type, feature data corresponding to the target object in a past service request process; feature data corresponding to the target object in the past service request process can also be acquired for all service types.

S220, determining a service evaluation factor of the target object according to the feature data, wherein the service evaluation factor is used for representing factor information affecting service cost.

In the embodiment of the application, the service evaluation factors of the target object are determined according to the feature data, and each factor represents the interaction condition of the target object and the service end and can be used for quantifying the service cost of the target object, namely, extracting some factors which can influence the service cost, namely, the service evaluation factors, from the feature data, wherein the service cost refers to the service cost of the object in the whole service process, and comprises time cost, input resource cost and the like, and the input resource cost comprises manpower resources, article resources and the like.

It will be appreciated that different service valuation factors may have different effects on the cost of service, e.g., the more requests are initiated, the higher the time cost devoted to the target object is, the more the cost of service is affected, and in one example, the service valuation factor is used to characterize the extent of the impact of the factor on the cost of service in addition to the factor that affects the cost of service.

In an example, the service evaluation factor of the target object is determined according to the feature data, a first factor related to the time cost spent by the target object may be determined from the feature data, a second factor related to the resource cost invested by the target object may be determined from the feature data, and then the first factor and the second factor are screened, the repeated factor is preferentially used as the service evaluation factor, and the remaining factors are determined according to the service requirement.

S230, calculating service cost scores of the target objects according to the service evaluation factors, wherein the service cost scores are used for representing the demand degrees of the target objects on the resources to be allocated.

In the embodiment of the application, the service end calculates the service cost score of the target object according to the service evaluation factor, and the higher the service cost score is, the higher the demand level of the target object for the allocated resource is, and the higher the urgency level of the target object for accessing the service is; the resources to be allocated are service resources which can be provided by the service end, the service requirements of the resources to be allocated on the target object correspond to each other, the service requirements are different, and the resources to be allocated are different.

In an example, if the service evaluation factor characterizes the influence degree of the factor on the service cost, the sum of the service evaluation factors can be taken as the service cost score of the target object; weights may also be configured for each service valuation factor, with a weighted sum of multiple service valuations factors being the service cost score of the target object.

S240, determining the access sequence of the target object in the service access queue based on the service cost of the target object.

When the object accesses the service, the service access queue is set up because the service resources are limited, the object is put into the service access queue for queuing, and the service is provided for the object in sequence. In the embodiment of the application, as the service cost score characterizes the demand degree of the target object to the allocated resource, the service end can determine the access sequence of the target object in the service access queue based on the demand degree, for example, if the service cost score of the target object is higher than the service cost scores of other objects in the service access queue, the access sequence of the target object is determined as the first one in the service access queue; for another example, if the service cost score of the target object is higher than the preset service cost score, the access sequence of the target object is determined to be prioritized, but if there are a plurality of objects higher than the preset service cost score, the access sequence among the plurality of objects is determined based on the access time.

In the embodiment of the application, the service end obtains the characteristic data corresponding to the target object in the process of the past service request by responding to the service access request of the target object, determines the service evaluation factors of the target object according to the characteristic data, and accurately reflects the factor information influencing the service cost, further calculates the service cost of the target object according to the service evaluation factors, thereby more accurately evaluating the demand level of the target object for the resources to be allocated, and then reasonably determining the access sequence of the target object in the service access queue according to the demand level of the target object for the resources to be allocated, namely comprehensively evaluating the characteristic data corresponding to the target object in the process of the past service request, and providing a new dimension reference for the service access sequence, so that the queuing becomes more reasonable and intelligent, is beneficial to optimizing the whole service efficiency and the resource utilization rate, and further improves the service quality.

In one embodiment of the present application, another service access processing method is provided, where the service access processing method may be applied to the implementation environment shown in fig. 1, and the method may be performed by a server, as shown in fig. 3, where the service access processing method extends, on the basis of S210 to S240 shown in fig. 2, step S220 shown in fig. 2 to steps S310 to S330; the characteristic data comprise track data of a target object aiming at a past service request and service data aiming at the target object; steps S310 to S330 are described in detail below.

S310, determining a first evaluation factor corresponding to the target object access service channel according to the track data, wherein the first evaluation factor is used for representing the influence degree of the service channel access frequency on the service cost.

In the embodiment of the application, the service end can provide a plurality of service channels to provide services for the objects, wherein the association relationship can exist among part of the service channels, for example, the service channels comprise self-service channels and non-self-service channels needing to be relied on, and the self-service channels comprise FAQ (common problem) services and self-service tool services; non-self-service channels include robotic services and manual service channels. The server side can provide access modes of the self-service channel and the non-self-service channel at the same time, if a target object initiates an access request aiming at the non-self-service channel, in order to save service resources, the target object can access to the robot service channel before accessing to the manual service channel, and when the robot service channel cannot meet the service requirement of the target object, the target object can be guided to access to the manual service channel.

In the embodiment of the present application, the service access request of the target object in S210 may be for a certain service channel, but the obtained feature data includes feature data of the target object for each service channel, and then the track data includes track data of the target object for each service channel, so that the access frequency of the target object for accessing each service channel may be determined according to the track data, and the corresponding first evaluation factor is determined based on the access frequency of the service channel; wherein, the higher the access frequency of a certain service channel, the higher the influence degree on the service cost.

In an example, if the track data is track data in a preset time period before the current time, the service channel access frequency may be calculated directly based on the access times of each service channel in the preset time period, and the access frequency threshold corresponding to each service channel may use, as the first evaluation factor, a target service channel whose service channel access frequency is greater than the corresponding access frequency threshold; and determining the influence degree of the target service channel on the service cost according to the target service channel access frequency, for example, taking the target service channel access frequency value as the influence degree of the target service channel on the service cost.

In another example, if the track data is track data in a preset time period before the current time, a part of the time period closest to the current time may be selected from the preset time period, and then the service channel access frequency is calculated based on the part of the time period.

S320, determining a second evaluation factor corresponding to the target object service demand according to the service data, wherein the second evaluation factor is used for representing the influence degree of the resolution degree of the service demand on the service cost.

In the embodiment of the application, the service data is the data of which the service end side is the service target object; the service requirement of the target object in S320 is a service requirement in the process of a past service request, a service mode proposed by the service requirement of the target object is determined according to service data, then the solution degree of the service mode for the service requirement is obtained, the solution degree of the service requirement can be fed back by the target object, or can be judged according to whether the service requirements of the past service request continuously initiated by the target object are the same, for example, the target object initiates the service request at the past time 1, the service requirement 1 is proposed, the service end provides the service mode 1, the service request is initiated at the past time 2, the same service requirement 1 is proposed, the fact that the target object is not satisfied with the service mode 1 is indicated, and the solution degree of the service requirement at the past time 1 is lower. The resolution of the service requirement can also be determined based on the service mode transition provided by the service end, for example, if the service mode provided by the service end aiming at the service requirement 1 is internal transition, the resolution of the service requirement 1 is lower.

After determining to acquire the solution degree of the service mode aiming at the service requirement, determining a second evaluation factor based on the solution degree of the service requirement, taking the service mode aiming at the service requirement as the second evaluation factor, and taking the solution degree of the service requirement as the value of the second evaluation factor.

S330, determining a service evaluation factor according to the first evaluation factor and the second evaluation factor.

In an example, both the first and second assessment factors may be considered as service assessment factors.

In an example, the weight values of the first and second evaluation factors may be set separately, and the service evaluation factor may be determined by weighted summation.

It should be noted that, for other detailed descriptions of the steps S210, S230 to S240 shown in fig. 3, please refer to the steps S210, S230 to S240 shown in fig. 2, and the detailed descriptions are omitted here.

In the embodiment of the application, the first evaluation factor and the second evaluation factor are respectively determined from the object track data of the object side and the service data of the service side, so that the factor information influencing the service cost is accurately reflected by combining the first evaluation factor and the second evaluation factor, and the comprehensiveness of the determination of the service evaluation factor is ensured.

The embodiment of the application provides another service access processing method, which can be applied to the implementation environment shown in fig. 1, and can be executed by a server, as shown in fig. 4, and the service access processing method expands the step S230 shown in fig. 2 into steps S410 to S430 on the basis of the one shown in fig. 2. The number of service evaluation factors includes a plurality of service evaluation factors, and steps S410 to S430 are described in detail below.

S410, acquiring a weight value of each service evaluation factor, and acquiring an object value of each object on each service evaluation factor according to each service evaluation factor.

In the embodiment of the application, in order to ensure that the service evaluation factors are more objective, the weight value configured for each service evaluation factor is preset, so that the weight value of each service evaluation factor needs to be extracted from a local database.

Wherein the object value for each object on each service valuation factor refers to the object value for each object on each service valuation factor over a period of time; as shown in Table 1 below, each row represents an object, each column represents a factor, and each cell represents an object value.

For example, the service valuation factor is the access of a specified service channel, and the value refers to the number of times each object accesses the specified service channel in a time period, and the value of the object on the service valuation factor may reflect the behavior and the demand of the object in the service system and the consumption of service resources and time, while different objects have different object values on different service valuation factors, which results in the difference of service cost points, so that the service cost points are calculated more objectively by considering the value of the object on each service valuation factor.

S420, calculating an abnormal value corresponding to each service evaluation factor according to the object value of each object on each service evaluation factor.

And determining an abnormal value corresponding to each service evaluation factor according to the distribution of the object values of each object on each service evaluation factor, wherein the extreme value exceeding the normal range can be used as the abnormal value.

In an example, based on the object value of each object on each service evaluation factor, the server may perform data analysis and trend prediction, and may use statistical methods, time series analysis, and other techniques to identify the fluctuation mode, periodicity, and trend change of the object value, and then automatically identify the abnormal situation by using an anomaly detection algorithm, that is, detect, based on the fluctuation mode, periodicity, and trend change, the data points inconsistent with the historical data distribution, or the data points beyond the prediction range, as the anomaly values.

S430, calculating the service cost score of the target object according to the numerical value corresponding to each service evaluation factor, the weight value of each service evaluation factor and the abnormal value corresponding to each service evaluation factor.

In the embodiment of the application, the service evaluation factors correspond to values, namely the influence degree on the service cost, and the service end calculates the service cost score of each service evaluation factor according to the values corresponding to each service evaluation factor, the weight value of each service evaluation factor and the abnormal value corresponding to each service evaluation factor, so that the sum of the service cost scores of all the service evaluation factors is taken as the service cost score of the target object.

Wherein, the abnormal value corresponding to each service evaluation service factor is obtained based on the distribution of all object values, namely the corresponding global direction; the corresponding value of each service evaluation factor is specific to the target object, namely the corresponding local direction, so that the local direction and the global direction are compared to reflect the difference of the service evaluation factor of the target object relative to the whole service evaluation factor, and the corresponding value of the service evaluation factor of the target object is determined. Namely, comparing the numerical value corresponding to each service evaluation factor with the abnormal value corresponding to each service evaluation factor, and calculating the service cost score of each service evaluation factor according to the comparison result and the weight value of each service evaluation factor.

It should be noted that, the detailed description of steps S210 to S220 and S240 shown in fig. 4 is please refer to steps S210 to S220 and S240 shown in fig. 3, and the detailed description is omitted here.

In the embodiment of the application, not only the weight value of each service evaluation factor and the corresponding value of each service evaluation factor are considered, but also the object value of each object on each service evaluation factor is considered, so that the abnormal value of each service evaluation factor is calculated, and the service cost is calculated more objectively.

The embodiment of the application also provides another service access processing method, which can be applied to the implementation environment shown in fig. 1, and can be executed by a server, as shown in fig. 5, and based on the embodiment shown in fig. 4, the step S430 shown in fig. 4 is expanded into steps S510-S530. The steps S510 to S530 are described in detail below.

S510, if the value corresponding to the service evaluation factor is larger than the abnormal value corresponding to the service evaluation factor, calculating the service cost score of the service evaluation factor according to the weight value of the service evaluation factor.

In the embodiment of the present application, if the value corresponding to the service evaluation factor is greater than or equal to the abnormal value corresponding to the service evaluation factor, it indicates that the target object has a higher service requirement for the service evaluation factor, and the full score of the weight value of the service evaluation factor may be used as the service cost score of the service evaluation factor, for example, the weight value of the service evaluation factor is 0.4, and the service cost score of the service evaluation factor is 40.

S520, if the value corresponding to the service evaluation factor is smaller than the abnormal value corresponding to the service evaluation factor, calculating the service cost score of the service evaluation factor according to the proportion between the value corresponding to the service evaluation factor and the abnormal value corresponding to the service evaluation factor and the weight value of the service evaluation factor.

If the value corresponding to the service evaluation factor is smaller than the abnormal value corresponding to the service evaluation factor, the target object has a lower service requirement for the service evaluation factor, and the service cost score of the service evaluation factor can be calculated according to the value corresponding to the service evaluation factor and the abnormal value corresponding to the service evaluation factor, for example, according to the ratio of the value corresponding to the factor and the abnormal value, and according to the ratio and the weight value of the service evaluation factor.

In an example, a full score of the weight value of the service evaluation factor may be used as an initial service cost score of the service evaluation factor, a ratio of a value corresponding to the service evaluation factor and an outlier corresponding to the service evaluation factor may be used as a weight value of the initial service cost score, and the service cost score of the service evaluation factor may be calculated according to the weight value of the initial service cost score and the initial service cost score, e.g., a product of the weight value of the initial service cost score and the initial service cost score may be used as the service cost score.

S530, calculating the service cost score of the target object according to the service cost scores of the service evaluation factors.

And taking the sum of the service cost scores of the service evaluation factors as the service cost score of the target object.

It should be noted that, for other detailed descriptions of steps S210 to S220, S410 to S420, S240 shown in fig. 5, please refer to steps S210 to S220, S410 to S420, S240 shown in fig. 4, and the detailed descriptions thereof are omitted.

In the embodiment of the application, the service cost scores of the service evaluation factors are calculated by adopting different results of different comparison of the corresponding numerical values of the service evaluation factors and the abnormal values of the service evaluation factors, so that the accuracy and the reliability of the service cost scores of the service evaluation factors are ensured.

In an embodiment of the present application, another service access processing method is provided, where the service access processing method may be applied to the implementation environment shown in fig. 1, and the method may be performed by a server, as shown in fig. 6, where the service access processing method extends the obtaining manner of the weight value in step S410 shown in fig. 4 to S610 to S640 on the basis of the one shown in fig. 4. The steps S610 to S640 are described in detail below.

S610, respectively configuring a first weight value for each service evaluation factor in a first weight configuration mode.

In the embodiment of the application, weights are configured for each service evaluation factor through at least two weight configuration modes, wherein a first weight configuration mode is a mode of comparing two service evaluation factors, a score matrix is constructed, the higher the importance is, the higher the weight is according to the importance comparison of the two service evaluation factors, and then the comparison result is filled into the score matrix to obtain a first weight value of each service evaluation factor; the importance of the service evaluation factor may correspond to a value corresponding to the service evaluation factor.

S620, respectively configuring a second weight value for each service evaluation factor through a second weight configuration mode, wherein the second weight configuration mode is different from the first weight configuration mode.

The second weight configuration mode is different from the first weight configuration mode, wherein the second weight configuration mode is as follows: constructing an index by using the contrast intensity and the conflict of the numerical values corresponding to the service evaluation factors, wherein the contrast intensity is expressed by a standard deviation, and if the larger the data standard deviation is, the larger the fluctuation is, the higher the weight is; the conflict is expressed by using a correlation coefficient, and if the larger the correlation coefficient value between factors is, the smaller the conflict is, the lower the weight is; and when the weight is calculated, multiplying the contrast strength by the conflict index, and carrying out normalization processing to obtain a final second weight value.

S630, determining the weight value of each service evaluation factor according to the first weight value and the second weight value of each service evaluation factor.

In an example, an average of the first weight value and the second weight value of each service valuation factor is taken as the weight value of each service valuation factor.

In an example, the weights of the two methods may be multiplied and then divided by the sum of the weight products of all the service evaluation factors to obtain the weight value of each service evaluation factor, so that the influence of the two methods can be balanced, and the problem that the weight of one method is too large or too small to cause the comprehensive weight distortion is avoided. As shown in table 2 below, table 2 is an example of a weight value shown in the present application.

Based on Table 2, the weight value of service valuation factor 1 isThe weight value of the service evaluation factor 2 is 0.209, and the weight value of the service evaluation factor 3 is 0.605.

In one example, the formula may also be used: and obtaining a weight value of each service evaluation factor, wherein t is smaller than 1.

S640, for each service evaluation factor, obtaining an object value of each object on each service evaluation factor.

It should be noted that, for other detailed descriptions of steps S210 to S220, S420 to S430, S240 shown in fig. 6, please refer to steps S210 to S220, S420 to S430, S240 shown in fig. 4, and the detailed descriptions thereof are omitted.

In the embodiment of the application, the weight value is configured for each service evaluation factor through two different weight configuration modes, and the final weight value of the service evaluation factor is obtained by combining the weight values configured by the different weight configuration modes, so that the reliability of the weight value is ensured.

It should be noted that in an embodiment of the present application, another service access processing method is provided, where the service access processing method may be applied to the implementation environment shown in fig. 1, and the method may be performed by a server, as shown in fig. 7, and the service access processing method extends step S630 to S710 to S730 on the basis of the one shown in fig. 6. Steps S710 to S730 are described in detail below.

S710, determining an initial weight value of the target service evaluation factor according to the first weight value and the second weight value of the target service evaluation factor.

The initial weight value of the target service valuation factor may be calculated by any of the examples in S630.

S720, obtaining a target object group to which the target object belongs according to the characteristic data corresponding to the target object in the past service request process.

Because different object types may have different sensitivities to different service assessment factors, in the embodiment of the present application, the personalized service assessment factors are weighted by considering different object groups, so that the object groups need to be divided first.

The method comprises the steps of acquiring feature data corresponding to a plurality of sample objects in a multi-time service request process, extracting features with representativeness and distinguishing degree from the feature data, such as age, service request times, service request modes, service request types and the like of target objects, performing data cleaning, conversion, normalization and the like on the selected features to ensure accuracy and consistency of the data, and dividing the plurality of sample objects into different groups by using a clustering algorithm such as K-means clustering, hierarchical clustering and the like, wherein the sample objects in each group have similar features, and feature differences among the different groups are larger. In order to facilitate the subsequent configuration of weights of different service evaluation factors for different groups, the embodiment of the application can allocate a meaningful name or identifier to each group according to the clustering result; weights for the personalized factors are formulated for each divided object population. The personalized factors may include factors related to characteristics of the group, such as high value objects may be more focused on quality of service, common objects may be more focused on cost of service, and the weights may be adjusted based on the importance and degree of influence of the group. For example, if the personalized factor corresponding to the high-value object is a service mode, the weight corresponding to the service mode is important, and if the personalized factor corresponding to the common object is a service time, the weight corresponding to the service time is important.

When the weight of the personalized service evaluation factor is formulated, the object group to which the target object belongs needs to be determined, namely, the characteristic with the representativeness and the distinguishing degree is extracted from the characteristic data corresponding to the target object in the past service request process, and the extracted characteristic is compared with each object group to determine the object group to which the target object belongs.

And S730, adjusting the initial weight value of the target service evaluation factor according to the service preference corresponding to the target object group to obtain the weight value of the target service evaluation factor.

In the embodiment of the application, the initial weight value of the service preference corresponding to the target object group to the target service evaluation factor is the personalized service evaluation factor corresponding to the target object group; for example, the target object group to which the target object belongs is a high-value object group, the service preference is the service quality, and the initial weight value of the target service evaluation factor related to the service quality is adjusted; and if the target service evaluation factor is in the service mode, increasing the initial weight value on the basis of the initial weight value of the service mode to obtain the weight value of the target service evaluation factor.

In an example, the manner of increasing or decreasing the initial weight value can be flexibly adjusted according to the actual situation, for example, increasing the initial weight value can be increasing the designated ratio based on the initial weight value, for exampleThe x is the specified ratio.

In an example, if the demand of a certain object group changes, the factor weight thereof can be updated and adjusted accordingly to adapt to the new demand.

It should be noted that, for other detailed descriptions of steps S210 to S220, S610 to S620, S640, S420 to S430, S240 shown in fig. 7, please refer to steps S210 to S220, S610 to S620, S640, S420 to S430, S240 shown in fig. 6, and the detailed descriptions thereof are omitted.

In the embodiment of the application, the requirements of different groups can be more accurately understood through object group division, and more refined and personalized services are realized through establishing the weight of the personalized service evaluation factors for the object groups.

In an embodiment of the present application, another service access processing method is provided, where the service access processing method may be applied to the implementation environment shown in fig. 1, and the method may be performed by a server, as shown in fig. 8, where the service access processing method extends S420 to S810 to S820 on the basis of the one shown in fig. 4, which is described in detail below.

S810, if the numerical values of the plurality of objects on the target service evaluation factors accord with normal distribution, obtaining mathematical expectations and standard deviations corresponding to the numerical values of the plurality of objects on the target service evaluation factors.

In the embodiment of the application, when the numerical value of each object on each service evaluation factor is obtained, a target service evaluation factor can be selected, and the target service evaluation factor can be any one service evaluation factor, so as to further judge whether the numerical values of all the objects on the target service evaluation factors accord with normal distribution.

The normal distribution is a distribution of a continuous random variable having two parameters μ (mathematical expectation) and σ2 (standard deviation), the first parameter μ being the mean of the random variable following the normal distribution and the second parameter σ2 being the variance of the random variable; and if the numerical values of the plurality of objects on the target service evaluation factors accord with normal distribution, acquiring mathematical expectations and standard deviations corresponding to the numerical values of the plurality of objects on the target service evaluation factors.

S820, calculating an abnormal value corresponding to the target service evaluation factor according to the mathematical expectation and the standard deviation to obtain an abnormal value corresponding to each service evaluation factor.

According to 3 sigma law, in a normally distributed dataset, about 68% of the values are distributed in (μ -sigma, μ+sigma), about 95% of the values are distributed in (μ -2σ, μ+2σ), and about 99.7% of the values are distributed in (μ -3σ, μ+3σ). In the embodiment of the application, mu+3σ is taken as an outlier demarcation point of the target service evaluation factor, namely mu+3σ is taken as an outlier.

For each service evaluation factor, through S810 and S820, an outlier corresponding to each service evaluation factor may be obtained.

In other embodiments of the present application, if the values of the plurality of objects on the target service evaluation factor do not conform to the normal distribution, a Z-Score method may be used, where the Z-Score may also be used to normalize the data, and then determine which values deviate from the average value, and the server determines an outlier according to the plurality of target values deviating from the average value, for example, an average value of the plurality of target values deviating from the average value may be used as the outlier; local anomaly factors (LOFs) may also be used, which may identify data points in the dataset that are less dense relative to their neighbors, from which the server determines anomalies.

It will be appreciated that in determining outliers, a suitable method may be selected based on the actual situation of the data, and in combination with domain knowledge, determine which values are truly outliers, and for complex data distributions, various methods may be used to determine outliers.

It should be noted that, for other detailed descriptions of the steps S210 to S220, S410, S430, S240 shown in fig. 8, please refer to the steps S210 to S220, S410, S430, S240 shown in fig. 4, and the detailed descriptions thereof are omitted.

In the embodiment of the application, the numerical values of the plurality of objects on the target service evaluation factors accord with normal distribution, and the abnormal values of the service evaluation factors are determined according to 3 sigma law, so that the abnormal conditions are more accurately considered in the calculation of the service cost score, and the accuracy and the reliability of service evaluation are further improved.

In an embodiment of the present application, another service access processing method is provided, where the service access processing method may be applied to the implementation environment shown in fig. 1, and the method may be performed by a server, as shown in fig. 9, where S910 to S930 are added to the service access processing method on the basis of the one shown in fig. 2, and S230 is extended to S940, which is described in detail below.

S910, acquiring a sample service cost score with the cost score larger than a preset cost score threshold and a sample service evaluation factor corresponding to the sample service cost score.

In the embodiment of the present application, a sample service cost score is generated for a sample object in advance, and in an example, a calculation process of the sample service cost score may be shown in fig. 3 to 8; in another example, the sample service cost score may also be a scoring of the sample object.

Firstly, acquiring a sample service cost score with the cost score larger than a preset threshold value, determining a corresponding sample object based on the sample service cost score, and acquiring a service evaluation factor corresponding to the sample object.

S920, extracting features of the sample service evaluation factors to obtain sample service features.

In the embodiment of the application, the feature extraction can be performed on the sample service evaluation factors, wherein the sample service evaluation factors comprise characters and numerical values, the feature extraction can be performed on the characters and the numerical values through a neural network respectively, and the character features and the numerical features are combined to obtain the sample service features.

S930, constructing a service cost prediction model according to the sample service characteristics and the sample service cost.

In the embodiment of the application, a neural network is predetermined, a sample service cost score is used as a label, the sample service characteristics and the sample service cost score are input into the neural network, and training is performed by the neural network, so that the neural network learns the association relationship between the sample service characteristics and the label, and further a service success prediction model is obtained, and whether the service cost score of an object is higher than a preset threshold value can be predicted by training the service success prediction model.

S940, predicting the service cost score of the target object according to the service cost prediction model and the service evaluation factor of the target object.

After determining the service evaluation factor of the target object through S220, the service evaluation factor is input to a service cost prediction model, and whether the service cost score of the target object is higher than a preset threshold is predicted through the service cost prediction model.

In other embodiments of the present application, sample service cost scores of the respective scores and corresponding sample service evaluation factors may also be obtained, so as to construct a service cost prediction model, so that the service cost prediction model may predict the service cost scores of the respective scores.

It should be noted that, for other detailed descriptions of the steps S210 to S220 and S240 shown in fig. 9, please refer to the steps S210 to S220 and S240 shown in fig. 2, and the detailed descriptions are omitted here.

In the embodiment of the application, the service cost prediction model is constructed through the sample service cost score and the corresponding sample service evaluation factor, so that the service cost prediction model can be applied, the service cost score is predicted by combining the service evaluation factor of the target object, and the calculation efficiency is improved while the accuracy is ensured.

In an embodiment of the present application, another service access processing method is provided, where the service access processing method may be applied to the implementation environment shown in fig. 1, and the method may be performed by a server, as shown in fig. 10, where the service access processing method extends step S940 to steps S1010 to S1020 on the basis of the one shown in fig. 9. The steps S1010 to S1020 are described in detail below.

S1010, inputting a service evaluation factor of the target object into a service cost prediction model, wherein the service cost prediction model is used for extracting features of the service evaluation factor to obtain service features, and calculating the similarity between the service features and sample service features.

In the embodiment of the application, the service evaluation factor of the target object is input into the service cost prediction model, the service cost prediction model firstly performs feature extraction on the service evaluation factor to obtain the service feature, wherein the feature extraction process is the same as that of the sample service evaluation factor, then the service cost prediction model calculates the similarity between the service feature and the sample service feature, and the cosine distance can be used as the similarity between the features by calculating the cosine distance between the service feature and the sample service feature.

S1020, predicting the service cost score of the target object according to the similarity output by the service cost prediction model and a preset cost score threshold.

In the embodiment of the application, if the similarity is greater than the preset similarity threshold, the service cost of the target object is higher than the preset threshold, and the score of the service cost corresponding to the target is predicted by further combining the score of the preset cost threshold; for example, a difference between the similarity and a preset similarity threshold may be calculated, and on the basis of the sample service cost score, a score corresponding to the difference is increased to obtain the service cost score of the target object. For example, the difference between the similarity and the preset similarity threshold is 10, and the preset cost threshold is 85, the service cost is divided into:。

if the similarity is smaller than the preset similarity threshold, the service cost score of the target object is lower than the preset threshold, and the specific score does not need to be calculated at this time.

It is understood that S1020 may be a service prediction cost model execution.

It should be noted that, for other detailed descriptions of steps S910 to S930, S210 to S220, and S240 shown in fig. 10, please refer to steps S910 to S930, S210 to S220, and S240 shown in fig. 9, and the detailed descriptions thereof are omitted herein.

In the embodiment of the application, the service evaluation factors of the target object are input into the service cost prediction model, and the similarity between the service characteristics corresponding to the service evaluation factors and the sample service characteristics can be obtained through the service prediction model, so that the service cost of the target object is predicted, the accuracy is ensured, and the calculation efficiency is improved.

In an embodiment of the present application, another service access processing method is provided, where the service access processing method may be applied to the implementation environment shown in fig. 1, and the method may be performed by a server, as shown in fig. 11, where the service access processing method extends S240 to S1110 to S1130 on the basis of the descriptions shown in fig. 2 to 10, and the steps S1110 to S1130 are described in detail below.

S1110, calculating an abnormal value of the historical service cost point according to the historical service cost points.

In the embodiment of the present application, a plurality of historical service cost scores need to be acquired first, wherein a plurality of historical service cost scores may be selected from the historical service cost scores of the day before the current time, and the plurality of historical service cost scores include a plurality of historical service cost scores of fractional stages, that is, a historical service cost score including a low segment, a middle segment and a high segment. The number of the plurality of historical service cost points may be determined based on the total number of historical service cost points for a day prior to the current time, e.g., the number of the plurality of historical service cost points is 1/3 of the total number of historical service cost points for the previous day.

And calculating the abnormal value of the historical service cost by the historical service cost to avoid fluctuation and instability of the data in the same day. Wherein the outlier is a value deviating from the normal cost score.

In an example, a value range of a normal service cost score may be set first, an abnormal historical service cost score deviating from the value range is extracted from the historical service cost score, an abnormal value is determined according to the abnormal historical service cost score, for example, a standard deviation of the abnormal historical service cost score is obtained, the standard deviation is used for representing the discrete degree of data, that is, the deviation of the data from an average value is larger, and the more scattered the data is illustrated; the smaller the standard deviation, the more concentrated the description data; and taking the corresponding abnormal historical service cost with the largest standard deviation as an abnormal value.

S1120, comparing the service cost of the target object with the abnormal value of the historical service cost.

And S1130, if the service cost score of the target object is greater than the abnormal value of the historical service cost score, performing queue insertion processing on the target object in the service access queue so as to assign the target object access service preferentially.

If the service cost of the target object is greater than the abnormal value of the historical service cost, the target object indicates that the object has high service demand and sense of urgency, and the target object in the service access queue is subjected to queue insertion processing, and it can be understood that the more the target is in front of the service access queue, the more the target is preferentially accessed to the service.

In an example, the dequeuing process may be performed according to a fractional ordering of the service cost scores of the target objects in the service access queue; the dequeuing process may also be performed in combination with a fractional ordering of the group to which the target object belongs in the service access queue.

In one example, in addition to the dequeue process, target objects exceeding outliers may be assigned to specialized processing teams to more quickly solve their problems, thereby improving service response speed.

The service cost of the target object is smaller than the abnormal value of the historical service cost, and the access sequence of the target object in the service access queue is not required to be adjusted, namely the target object is arranged in the service access queue according to the time sequence.

It should be noted that, for other detailed descriptions of the steps S210 to S230 shown in fig. 11, please refer to the steps S210 to S230 shown in fig. 2, and the detailed descriptions are omitted here.

In the embodiment of the application, when calculating the abnormal value of the historical service cost, the service cost of the target object is compared with the abnormal value of the historical service cost to determine whether the object has high service demand and urgent sense, and then the target object is preferentially allocated to access the service through the queue insertion processing, so that more reasonable queuing is performed in the service access queue, and the discontent emotion of the object with higher urgent degree is reduced.

The embodiment of the application provides another service access processing method, which can be applied to the implementation environment shown in fig. 1, and can be executed by a server, as shown in fig. 12, and the service access processing method expands step S1110 into steps S1210-S1220 on the basis of the one shown in fig. 11; the steps S1210-S1220 are described in detail below.

S1210, sorting the historical service cost scores to obtain a sorting result, and determining at least two quartiles in the historical service cost scores according to the sorting result.

S1220, calculating an abnormal value of the historical service cost according to at least two quartiles.

In the embodiment of the application, a plurality of historical service cost scores are subjected to fractional ranking, and ranking results are obtained by ranking from low to high. In an example, if the service side provides multiple service types, the multiple historical service cost scores belonging to the same service type are ranked.

Dividing a plurality of historical service costs into four equal parts according to the sorting result, and determining the numerical value at the position of a separation point to be used as quartiles, wherein the quartiles are three, the first quartiles are called lower quartiles, the second quartiles are called middle quartiles, and the third quartiles are called upper quartiles and are respectively represented by Q1, Q2 and Q3; by calculating the quartile of the value and the quartile range, which is the third quartile minus the first quartile, a range of outliers can be derived (Inter Quartile Range, IQR). In one example, the outlier is a value of q3+1.5 IQR.

It should be noted that, for other detailed descriptions of steps S210 to S230 and S1120 to S1130 shown in fig. 12, please refer to steps S210 to S230 and S1120 to S1130 shown in fig. 11, and the detailed descriptions are omitted here.

The embodiment of the application provides another service access processing method, which can be applied to the implementation environment shown in fig. 1, and the method can be executed by a server, as shown in fig. 13, and the service access processing method expands the steps S1130 shown in fig. 11 into the steps S1310 to S1330 on the basis of the steps shown in fig. 11, and the steps S1310 to S1330 are described in detail below.

S1310, if the service cost of the target object is greater than the abnormal value of the historical service cost, acquiring a preset queue inserting strategy.

In the embodiment of the application, other factors need to be considered when the queue insertion processing is performed, so as to ensure that the whole service quality and the object experience are balanced and improved. The preset queue inserting strategy is a preset queue inserting condition, and for example, the preset queue inserting strategy comprises a maximum queue inserting number, a maximum waiting time, a queue inserting list and the like. The preset queue inserting strategy can be flexibly adjusted according to actual conditions on the basis of preset queue inserting conditions.

S1320, if the current resource to be allocated is greater than a preset resource threshold, obtaining target feature data corresponding to the current service request process of the target object, and determining whether the target object accords with a preset queue inserting strategy according to the target feature data.

It can be understood that the current resource to be allocated is a resource required by the target object, if the current resource to be allocated is greater than the preset resource threshold, it means that the current resource to be allocated can meet a certain amount of objects, and the target object is subjected to the queue-inserting processing, so that the resource imbalance of other objects is not caused, and the overall service quality is not affected, and therefore the target object can be subjected to the queue-inserting processing, and whether the target object meets the preset queue-inserting condition is required to be judged.

In the embodiment of the application, the target feature data corresponding to the current service request process of the target object is required to be acquired, wherein the target feature data is related to the service access request of the target object, for example, the target feature data comprises the request requirement of the service access request; the maximum waiting time which can be born by the target object and the service time spent for serving the target object can be estimated according to the target characteristic data, and whether the target object accords with the preset queue inserting strategy or not is determined according to the maximum waiting time which can be born by the target object and the service time spent for serving the target object.

It can be understood that whether the target object is a list object in the preset queue inserting strategy should be judged first, if the target object is not an object in the list, the maximum waiting time born by the target object is greater than the maximum waiting time in the preset queue inserting strategy, and the target object is indicated to conform to the preset queue inserting strategy; when the service time spent on serving the target object is smaller than the maximum service time of the preset queue inserting strategy, the target object is indicated to accord with the preset queue inserting strategy; if the queue inserting times of the target object are larger than the maximum queue inserting times in the preset queue inserting strategy, the target object is not in accordance with the preset queue inserting strategy.

S1330, if the target object accords with the preset queue inserting strategy, the queue inserting process is performed on the target object in the service access queue.

If the target object accords with the preset queue inserting strategy, queue inserting processing can be carried out on the target object in the service access queue; in order to balance the waiting time of each object in the service access queue, in an example, the preset queue inserting strategy further includes a queue inserting mode, for example, when queue inserting is performed, queue inserting can be performed according to a preset queue inserting interval, and if the target object is arranged at the 7 th bit of the service access queue according to time sequencing, the target object service access queue is inserted into the 5 th bit according to the preset queue inserting interval 2 bits; the preset queue interval can be flexibly adjusted according to actual requirements.

If the target object does not accord with the preset queue inserting strategy, queue inserting processing is not needed.

It should be noted that, for other detailed descriptions of steps S210 to S230 and S1110 to S1120 shown in fig. 13, please refer to steps S210 to S230 and S1110 to S1120 shown in fig. 11, and the detailed descriptions are omitted here.

In the embodiment of the application, various factors are required to be fully considered when the queue insertion processing is performed, and when the target object accords with the preset queue insertion strategy, the queue insertion processing is performed on the target object in the service access queue, so that the service experience of the target object can be improved and the satisfaction degree of other objects can be maintained when the target object is processed by the queue insertion.

In order to facilitate understanding, the embodiment of the present application further provides a service access processing method, which is illustrated by taking a customer service scenario as an example, as shown in fig. 14, where the service access processing method includes:

s1410, when receiving a service access request of an object, inquiring object track data and service data in a time period T from a database.

The object initiates a service access request by making a call, and then behavior data of the object in the customer service system is collected in a period of time before making the call, so as to analyze the service requirement and cost of the object. The evaluation time period T may be adjusted according to practical situations, for example, the evaluation time period T is set as the first 7 days of the time when the subject makes a call. The object track data queried from the database comprises data generated by the object in various channels of the customer service system, such as IVR (Voice communication) channels, IMC (instant Messaging) channels, AI intelligent customer service channels and the like. Taking IVR channels as an example, track data includes, but is not limited to: object dialing time, object waiting time, object access manual time and object call ending time. The service data includes data generated by the client system for the object, such as IVR transfer, manual upgrade, issued information, etc.

S1420, determining a service evaluation factor for calculating a service cost score of the object based on the trajectory data and the service dataN is the number of factors.

In the embodiment of the application, some service evaluation factors capable of reflecting the service cost of the object need to be extracted from the object track data and the service data. Different service assessment factors may have different impact on service costs, e.g., the more times FAQ (common problem) is accessed, the more manual services may be required when making a call, indicating that an object may have attempted to resolve the problem by itself; the more IMC services, the more often the description object may have communicated with the human customer service, and the faster the response and processing may be required to place a call. Thus, depending on the actual situation and the traffic demands, some suitable factors may be determined.

In the embodiment of the application, aiming at a customer service system, a plurality of service channel modes are generally adopted, and the customer is guided to pass through a self-service mode in a biased manner, so that the self-service mode can be automatically solved without manual intervention, such as FAQ service and self-service tool service; and part of the guiding objects submit worksheets, and the later stage of the guiding objects manually process asynchronously. Meanwhile, a manual service channel is also arranged, a robot customer service system is generally accessed before the robot customer service system is accessed, if the robot customer service system cannot solve the problem of object consultation, an online channel can guide an object to access an IMC, and a hot wire channel can guide the object to access a corresponding hot wire group according to the object problem. According to the above business processes, the overall channel access frequency correlation factor is determined: FAQ access times, IMC service times, IVR dialing times, asynchronous bill establishment times and intelligent session service times.

After the object is connected with the person, the customer service person group of the customer service system can communicate with the object, some problems can be solved through language communication, some problems need to be solved by a issuing tool to assist the object, and if the group can not solve the problem of the object, the group can be switched or upgraded. Aiming at the business flow, the object problem unresolved degree related factor can be obtained: IVR transfer times, manual upgrade times, and self-help tool issuing times.

Therefore, in the embodiment of the application, the service evaluation factor of the object, such as the FAQ access times of the object in the time period T, is determined from the channel access frequency correlation factor and the problem unresolved degree correlation factor according to the track data and the service data of the object.

S1430, calculating the service cost score of the object by using the service evaluation factor through the rule engine.

In the embodiment of the application, the service cost score of the object needs to be calculated, and the service cost score is used for representing the demand degree of the object on service resources and time when the object makes a call.

First, it is necessary to determine an abnormal value of each service evaluation factor, that is, an extreme value exceeding a normal range. The abnormal value of each factor can be determined according to 3 sigma law according to the distribution condition of each object value of each factor every day. Before that, it is necessary to determine whether each object value of each factor per day accords with normal distribution, if the data does not accord with normal distribution, determining an abnormal value using 3σ law may be inaccurate or invalid; if the data conforms to a normal distribution, the 3 sigma law can be used to determine outliers. Specifically, the average value is added to 3 standard deviations to obtain an upper limit, and the upper limit is defined as an outlier. For example, if the average value of each object value per day is 10, the standard deviation is 2, and the upper limit is 16 (10+3×2) as an outlier; where the object value refers to a specific value of each object on each factor in the process of calculating the object service cost score. For example, if one factor is the number of FAQ accesses, then the object value is the number of times the object has accessed FAQ within the evaluation time period T.

Second, the weights of the individual service valuation factors, i.e., their contribution to the service cost score, need to be determined. Based on CRITIC weight method and expert score matrix method, the weight of each factor can be calculated through a certain mathematical formula and expert evaluation。

Wherein, constructing expert scoring matrix, comparing factors pairwise, when longitudinal data is more important than transverse data, marking as 1, otherwise marking as 0, transversely summarizing total score obtained by the factors, scoring by multiple experts according to the same steps, and averaging to obtain weight score of the factorsTable 3 below is an example scoring for an expert.

Then using CRITIC weight method to make factor weight decision, randomly extracting one day data as sample set, calculating n factors of m objects whose period is nearly 7 days to form matrixWhere m is the object identifier and n is the factor identifier.

In order to eliminate the influence of different dimensions, orders of magnitude, the variables need to be standardized. The factor j has a value ofThe variables were normalized using the min-max method. Wherein the j-th factor of the i-th object is normalized to:。

Obtaining a standardized sample matrix: 。

the CRITIC weight method utilizes the contrast intensity and conflict of the data to construct an index, wherein the contrast intensity quantization index of the jth factor is the standard deviation ,

The j factor conflict quantization index is,. Wherein the method comprises the steps ofRefers to the correlation coefficient before factors i and j,,。

Calculating the information amount of the j-th factor as=Determining the j-th factor weight。

Can obtain the reference of weight obtained by CRITIC methodWeights scored by expertAverage to obtain final weight。

Finally, the total service cost score of the object needs to be calculated according to the value and weight of each factor. Wherein all factors of an object are acquired asOutlier valueWeighting of。

When (when)In the time-course of which the first and second contact surfaces,; When (when)In the time-course of which the first and second contact surfaces,Service cost score。

S1440, adjusting the customer service hot line access sequence of the object according to the service cost of the object.

In the embodiment of the application, the efficiency and quality of the hotline service are optimized according to the object service cost. First, it is necessary to obtain a cost score value when an object dials a hotline, and then, it is necessary to sort the objects requesting the same hotline group according to the historical service cost score value using all the historical service cost scores of yesterday, and calculate an outlier E from high to low, in order to avoid fluctuation and instability of data in the same day. According to the quartile method, the outlier E can be represented by Q3+1.5IQR, where Q3 is the third quartile, i.e., 75% quantile; IQR is the quartile range, i.e., Q3-Q1, where Q1 is the first quartile, i.e., 25% of the quantiles. Finally, the service cost score value of the current object needs to be compared with the abnormal value E, if the service cost score value exceeds the abnormal value E, the object can be subjected to queue insertion processing under the condition that other strategies are met, and the object is preferentially allocated to enter the corresponding hotline group, so that the object satisfaction degree and the problem solving efficiency are improved.

In the embodiment of the application, index statistics is carried out according to the use track of the object in the customer service system, the access frequency of each channel of the object and the service damage service evaluation factor of the service unresolved degree are used, abnormal values and weights are determined according to service experience and a statistical method, and further service cost components are calculated, so that comprehensive systematic evaluation is carried out on the use cost of the object and the urgency of accessing the hotline, a new dimension reference is provided for the access sequence of the hotline, and compared with the sequencing according to the access time, the method is more flexible, the discontent emotion of the object with higher urgency degree is reduced, and the limited manual customer service resources are better utilized.

The embodiments of the apparatus of the present application are described herein and may be used to perform the service access processing method in the above embodiments of the present application. For details not disclosed in the embodiments of the apparatus of the present application, please refer to the embodiments of the service access processing method of the present application.

The embodiment of the application provides a service access processing device, as shown in fig. 15, which comprises the following components.

The obtaining module 1510 is configured to obtain, in response to a service access request of the target object, feature data corresponding to the target object in a past service request process.

A determining module 1520, configured to determine a service evaluation factor of the target object according to the feature data, where the service evaluation factor is used to characterize factor information affecting service cost.

The calculating module 1530 is configured to calculate a service cost score of the target object according to the service evaluation factor, where the service cost score is used to characterize a demand level of the target object for the resource to be allocated.

The determining module 1520 is further configured to determine an access order of the target object in the service access queue based on the service cost score of the target object.

In one embodiment of the present application, based on the foregoing scheme, the feature data includes trajectory data of the target object for the past service request and service data for the target object; the determining module is further used for determining a first evaluation factor corresponding to the target object access service channel according to the track data, and the first evaluation factor is used for representing the influence degree of the service channel access frequency on the service cost; determining a second evaluation factor corresponding to the target object service demand according to the service data, wherein the second evaluation factor is used for representing the influence degree of the resolution degree of the service demand on the service cost; a service valuation factor is determined based on the first valuation factor and the second valuation factor.

In one embodiment of the present application, based on the foregoing scheme, the number of service evaluation factors includes a plurality of; the computing module is further used for acquiring a weight value of each service evaluation factor and acquiring an object value of each object on each service evaluation factor aiming at each service evaluation factor; calculating an abnormal value corresponding to each service evaluation factor according to the object value of each object on each service evaluation factor; and calculating the service cost score of the target object according to the numerical value corresponding to each service evaluation factor, the weight value of each service evaluation factor and the abnormal value corresponding to each service evaluation factor.

In one embodiment of the present application, based on the foregoing scheme, the calculating module is further configured to calculate a service cost score of the service evaluation factor according to a weight value of the service evaluation factor if a value corresponding to the service evaluation factor is greater than an abnormal value corresponding to the service evaluation factor; if the value corresponding to the service evaluation factor is smaller than the abnormal value corresponding to the service evaluation factor, calculating the service cost score of the service evaluation factor according to the proportion between the value corresponding to the service evaluation factor and the abnormal value corresponding to the service evaluation factor and the weight value of the service evaluation factor; and calculating the service cost score of the target object according to the service cost score of each service evaluation factor.

In one embodiment of the present application, based on the foregoing solution, the computing module is further configured to configure a first weight value for each service evaluation factor separately by using a first weight configuration manner; respectively configuring a second weight value for each service evaluation factor in a second weight configuration mode, wherein the second weight configuration mode is different from the first weight configuration mode; and determining the weight value of each service evaluation factor according to the first weight value and the second weight value of each service evaluation factor.

In one embodiment of the present application, based on the foregoing scheme, the calculation module is further configured to determine an initial weight value of the target service evaluation factor according to the first weight value and the second weight value of the target service evaluation factor; acquiring a target object group to which the target object belongs according to characteristic data corresponding to the target object in the past service request process; and adjusting the initial weight value of the target service evaluation factor according to the service preference corresponding to the target object group to obtain the weight value of the target service evaluation factor.

In one embodiment of the present application, based on the foregoing scheme, the calculation module is further configured to obtain mathematical expectations and standard deviations corresponding to values of the plurality of objects on the target service evaluation factors if the values of the plurality of objects on the target service evaluation factors conform to a normal distribution; and calculating an abnormal value corresponding to the target service evaluation factor according to the mathematical expectation and the standard deviation to obtain an abnormal value corresponding to each service evaluation factor.

In one embodiment of the present application, based on the foregoing scheme, the apparatus further includes a construction module, configured to obtain a sample service cost score with a cost score greater than a preset cost score threshold, and a sample service evaluation factor corresponding to the sample service cost score; extracting characteristics of the sample service evaluation factors to obtain sample service characteristics; constructing a service cost prediction model according to the sample service characteristics and the sample service cost score; the computing module is further configured to predict a service cost score for the target object based on the service cost prediction model and the service valuation factor for the target object.

In one embodiment of the present application, based on the foregoing solution, the computing module is further configured to input a service evaluation factor of the target object into a service cost prediction model, where the service cost prediction model is configured to perform feature extraction on the service evaluation factor to obtain service features, and calculate a similarity between the service features and sample service features; and predicting the service cost score of the target object according to the similarity output by the service cost prediction model and a preset cost score threshold.

In one embodiment of the present application, based on the foregoing, the determining module is further configured to calculate an outlier of the historical service cost score from the plurality of historical service cost scores; comparing the service cost of the target object with an outlier of the historical service cost score; if the service cost of the target object is greater than the abnormal value of the historical service cost, the target object is subjected to queue insertion processing in the service access queue so as to assign the target object access service preferentially.

In one embodiment of the present application, based on the foregoing scheme, the determining module is further configured to score-sort the plurality of historical service cost scores to obtain a sorted result, and determine at least two quartiles in the plurality of historical service cost scores according to the sorted result; an outlier of the historical service cost score is calculated from the at least two quartiles.

In one embodiment of the present application, based on the foregoing scheme, the determining module is further configured to obtain a preset queue policy; if the current resource to be allocated is greater than a preset resource threshold, acquiring target feature data corresponding to the current service request process of the target object, and determining whether the target object accords with a preset queue inserting strategy according to the target feature data; and if the target object accords with the preset queue inserting strategy, performing queue inserting processing on the target object in the service access queue.

It should be noted that, the apparatus provided in the foregoing embodiments and the method provided in the foregoing embodiments belong to the same concept, and the specific manner in which each module and unit perform the operation has been described in detail in the method embodiments, which is not repeated herein.

The embodiment of the application also provides an electronic device, which comprises one or more processors, and a storage device, wherein the storage device is used for storing one or more computer programs, and when the one or more computer programs are executed by the one or more processors, the electronic device is enabled to realize the service access processing method.

It should be noted that, the computer system 1600 of the electronic device shown in fig. 16 is only an example, and should not impose any limitation on the functions and the application scope of the embodiments of the present application.

As shown in fig. 16, the computer system 1600 includes a processor (Central Processing Unit, CPU) 1601 that can perform various appropriate actions and processes, such as performing the method in the above-described embodiment, according to a program stored in a Read-Only Memory (ROM) 1602 or a program loaded from a storage portion 1608 into a random access Memory (Random Access Memory, RAM) 1603. In the RAM 1603, various programs and data required for system operation are also stored. The CPU 1601, ROM 1602, and RAM 1603 are connected to each other by a bus 1604. An Input/Output (I/O) interface 1605 is also connected to bus 1604.

In some embodiments, the following components are connected to the I/O interface 1605: an input portion 1606 including a keyboard, a mouse, and the like; an output portion 1607 including a Cathode Ray Tube (CRT), a Liquid crystal display (Liquid CRYSTAL DISPLAY, LCD), and a speaker, etc.; a storage portion 1608 including a hard disk or the like; and a communication section 1609 including a network interface card such as a LAN (Local Area Network ) card, a modem, or the like. The communication section 1609 performs communication processing via a network such as the internet. The drive 1610 is also connected to the I/O interface 1605 as needed. A removable medium 1611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is installed as needed on the drive 1610 so that a computer program read out therefrom is installed into the storage section 1608 as needed.

In particular, according to embodiments of the present application, the process described above with reference to the flowcharts may be implemented as a computer program. For example, embodiments of the present application include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising a computer program for performing the method shown in the flowchart. In such embodiments, the computer program may be downloaded and installed from a network via the communication portion 1609, and/or installed from the removable media 1611. When executed by a processor (CPU) 1601, performs various functions defined in the system of the present application.

It should be noted that, the computer readable medium shown in the embodiments of the present application may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium may be, for example, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-Only Memory (ROM), an erasable programmable read-Only Memory (Erasable Programmable Read Only Memory), a flash Memory, an optical fiber, a portable compact disc read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer-readable signal medium may comprise a data signal propagated in baseband or as part of a carrier wave, with a computer-readable computer program embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. A computer program embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. Where each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer programs.

The units or modules involved in the embodiments of the present application may be implemented in software, or may be implemented in hardware, and the described units or modules may also be disposed in a processor. Where the names of the units or modules do not in some way constitute a limitation of the units or modules themselves.

Another aspect of the application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor implements a service access handling method as before. The computer-readable storage medium may be included in the electronic device described in the above embodiment or may exist alone without being incorporated in the electronic device.

Another aspect of the present application also provides a computer program product comprising a computer program stored in a computer readable storage medium. The processor of the electronic device reads the computer program from the computer-readable storage medium, and the processor executes the computer program to cause the electronic device to execute the service access processing method provided as described in the above embodiments.

It should be noted that although in the above detailed description several modules or units of a device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functions of two or more modules or units described above may be embodied in one module or unit in accordance with embodiments of the application. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.

Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains.

The foregoing is merely illustrative of the preferred embodiments of the present application and is not intended to limit the embodiments of the present application, and those skilled in the art can easily make corresponding variations or modifications according to the main concept and spirit of the present application, so that the protection scope of the present application shall be defined by the claims.

Claims

1. A service access processing method, comprising:

Responding to a service access request of a target object, and acquiring feature data corresponding to the target object in a past service request process, wherein the feature data comprises track data of the target object aiming at the past service request and service data of a service end aiming at the target object;

determining the access frequency of the target object to each service channel according to the track data, taking the target service channel with the access frequency of the service channel being greater than the corresponding access frequency threshold as a first evaluation factor, and taking the value of the access frequency of the target service channel as the value of the first evaluation factor;

Determining a service mode proposed by a service demand aiming at a target object according to service data, determining the resolution of the service demand based on service mode conversion provided by a service end, taking the service mode aiming at the service demand as a second evaluation factor, and taking the resolution of the service demand as a value of the second evaluation factor;

Taking the first evaluation factor and the second evaluation factor as service evaluation factors of the target object, wherein the service evaluation factors are used for representing factor information influencing service cost, and the service cost refers to the service cost of the target object in the whole service process, and the service cost comprises time cost and input resource cost;

Calculating service cost scores of the target objects according to the service evaluation factors, wherein the service cost scores are used for representing the demand degree of the target objects on resources to be allocated;

Calculating an abnormal value of a historical service cost score according to a plurality of historical service cost scores;

if the service cost of the target object is greater than the abnormal value of the historical service cost, acquiring a preset queue inserting strategy containing preset queue inserting conditions, wherein the queue inserting conditions comprise maximum queue inserting times and maximum waiting time; if the current resource to be allocated is greater than a preset resource threshold, acquiring target feature data related to a service access request of the target object in the current service request process of the target object, and determining whether the target object accords with the queue inserting condition according to the target feature data; if the target object meets the queue inserting condition, queue inserting processing is carried out on the target object in a service access queue;

The number of service valuation factors includes a plurality; the calculating the service cost score of the target object according to the service evaluation factor comprises the following steps:

acquiring a weight value of each service evaluation factor, and acquiring an object value of each object on each service evaluation factor aiming at each service evaluation factor;

calculating an abnormal value corresponding to each service evaluation factor according to the object value of each object on each service evaluation factor;

comparing the value corresponding to each service evaluation factor with the abnormal value corresponding to each service evaluation factor, and if the value corresponding to the service evaluation factor is larger than the abnormal value corresponding to the service evaluation factor, calculating the service cost score of the service evaluation factor according to the weight value of the service evaluation factor; if the value corresponding to the service evaluation factor is smaller than the abnormal value corresponding to the service evaluation factor, calculating the service cost score of the service evaluation factor according to the proportion between the value corresponding to the service evaluation factor and the abnormal value corresponding to the service evaluation factor and the weight value of the service evaluation factor, and calculating the service cost score of the target object according to the service cost score of each service evaluation factor.

2. The method of claim 1, wherein the obtaining a weight value for each service valuation factor comprises:

Respectively configuring a first weight value for each service evaluation factor in a first weight configuration mode;

Respectively configuring a second weight value for each service evaluation factor through a second weight configuration mode, wherein the second weight configuration mode is different from the first weight configuration mode;

And determining the weight value of each service evaluation factor according to the first weight value and the second weight value of each service evaluation factor.

3. The method of claim 2, wherein said determining the weight value for each service valuation factor based on the first weight value and the second weight value for each service valuation factor comprises:

Determining an initial weight value of a target service evaluation factor according to the first weight value and the second weight value of the target service evaluation factor;

Acquiring a target object group to which the target object belongs according to characteristic data corresponding to the target object in a past service request process;

And adjusting the initial weight value of the target service evaluation factor according to the service preference corresponding to the target object group to obtain the weight value of the target service evaluation factor.

4. The method of claim 1, wherein calculating the outlier corresponding to each service valuation factor from the object value of each object on each service valuation factor comprises:

If the numerical values of the plurality of objects on the target service evaluation factors accord with normal distribution, acquiring mathematical expectations and standard deviations corresponding to the numerical values of the plurality of objects on the target service evaluation factors;

and calculating an abnormal value corresponding to the target service evaluation factor according to the mathematical expectation and the standard deviation to obtain an abnormal value corresponding to each service evaluation factor.

5. The method according to claim 1, wherein the method further comprises:

Acquiring a sample service cost score with the cost score being greater than a preset cost score threshold, and a sample service evaluation factor corresponding to the sample service cost score;

Extracting the characteristics of the sample service evaluation factors to obtain sample service characteristics;

constructing a service cost prediction model according to the sample service characteristics and the sample service cost score;

Calculating the service cost score of the target object according to the service evaluation factor, including:

And predicting the service cost score of the target object according to the service cost prediction model and the service evaluation factor of the target object.

6. The method of claim 5, wherein predicting the service cost score for the target object based on the service cost prediction model and the service valuation factor for the target object comprises:

Inputting the service evaluation factors of the target objects into the service cost prediction model, wherein the service cost prediction model is used for extracting the characteristics of the service evaluation factors to obtain service characteristics, and calculating the similarity between the service characteristics and the sample service characteristics;

and predicting the service cost score of the target object according to the similarity output by the service cost prediction model and the preset cost score threshold.

7. The method of claim 1, wherein calculating an outlier of the historical service cost score from a plurality of historical service cost scores comprises:

the historical service cost scores are subjected to fractional sequencing to obtain a sequencing result, and at least two quartiles in the historical service cost scores are determined according to the sequencing result;

And calculating an outlier of the historical service cost score according to the at least two quartiles.

8. A service access order handling apparatus, comprising:

The acquisition module is used for responding to the service access request of the target object and acquiring the characteristic data corresponding to the target object in the process of the past service request, wherein the characteristic data comprises track data of the target object aiming at the past service request and service data of a service end aiming at the target object;

The determining module is used for determining the access frequency of the target object to each service channel according to the track data, taking the target service channel with the access frequency greater than the corresponding access frequency threshold as a first evaluation factor, and taking the access frequency value of the target service channel as the value of the first evaluation factor; determining a service mode proposed by a service demand aiming at a target object according to service data, determining the resolution of the service demand based on service mode conversion provided by a service end, taking the service mode aiming at the service demand as a second evaluation factor, and taking the resolution of the service demand as a value of the second evaluation factor; taking the first evaluation factor and the second evaluation factor as service evaluation factors of the target object, wherein the service evaluation factors are used for representing factor information influencing service cost, and the service cost refers to the service cost of the target object in the whole service process, and the service cost comprises time cost and input resource cost;

the computing module is used for computing service cost scores of the target objects according to the service evaluation factors, wherein the service cost scores are used for representing the demand degree of the target objects on resources to be allocated;

The determining module is also used for calculating an abnormal value of the historical service cost points according to the plurality of historical service cost points; if the service cost of the target object is greater than the abnormal value of the historical service cost, acquiring a preset queue inserting strategy containing preset queue inserting conditions, wherein the queue inserting conditions comprise maximum queue inserting times and maximum waiting time; if the current resource to be allocated is greater than a preset resource threshold, acquiring target feature data related to a service access request of the target object in the current service request process of the target object, and determining whether the target object accords with the queue inserting condition according to the target feature data; if the target object meets the queue inserting condition, queue inserting processing is carried out on the target object in a service access queue;

The number of service valuation factors includes a plurality; the computing module is used for: acquiring a weight value of each service evaluation factor, and acquiring an object value of each object on each service evaluation factor aiming at each service evaluation factor; calculating an abnormal value corresponding to each service evaluation factor according to the object value of each object on each service evaluation factor; comparing the value corresponding to each service evaluation factor with the abnormal value corresponding to each service evaluation factor, and if the value corresponding to the service evaluation factor is larger than the abnormal value corresponding to the service evaluation factor, calculating the service cost score of the service evaluation factor according to the weight value of the service evaluation factor; if the value corresponding to the service evaluation factor is smaller than the abnormal value corresponding to the service evaluation factor, calculating the service cost score of the service evaluation factor according to the proportion between the value corresponding to the service evaluation factor and the abnormal value corresponding to the service evaluation factor and the weight value of the service evaluation factor, and calculating the service cost score of the target object according to the service cost score of each service evaluation factor.

9. An electronic device, comprising:

One or more processors;

Storage means for storing one or more programs that, when executed by the one or more processors, cause the electronic device to perform the method of any of claims 1-7.

10. A computer readable storage medium, having stored thereon a computer program which, when executed by a processor of an electronic device, causes the electronic device to perform the method of any of claims 1 to 7.

11. A computer program product, characterized in that it comprises a computer program stored in a computer readable storage medium, from which computer readable storage medium a processor of an electronic device reads and executes the computer program causing the electronic device to perform the method of any one of claims 1 to 7.