CN114117193B

CN114117193B - Control method, device, equipment and medium for updating content in content recommendation pool

Info

Publication number: CN114117193B
Application number: CN202010881664.9A
Authority: CN
Inventors: 陈天明; 邓华光; 崔津源; 王申
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2020-08-26
Filing date: 2020-08-26
Publication date: 2024-09-06
Anticipated expiration: 2040-08-26
Also published as: CN114117193A

Abstract

The application provides a control method, a device, equipment and a medium for updating content in a content recommendation pool, relates to the technical field of computers, and aims to improve the prediction accuracy of the content in the content recommendation pool and further improve the overall efficiency of a recommendation system. The method comprises the following steps: obtaining user feedback information of recommended content from an information platform; obtaining a second corresponding relation between the stock content and the number of times the recommended content is operated when the number of people operating the recommended content is the target number according to a first corresponding relation among the stock content, the number of people operating the recommended content and the number of times the recommended content is operated, which are formed by fitting historical data; obtaining target inventory content corresponding to the target times based on the second corresponding relation; based on the target stock content and the current stock content, controlling the amount of content in the recommendation pool and updating the content in the recommendation pool.

Description

Control method, device, equipment and medium for updating content in content recommendation pool

Technical Field

The present application relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, and a medium for controlling content in a content recommendation pool.

Background

The recommendation system is an information filtering system, and mainly performs content filtering and screening for each user, so that suitable content can be recommended for the corresponding user. The content recommended to the user by the recommendation system is derived from different content types and different structure types of content contained in the recommendation pool.

In the related art, content is mainly introduced through subjective recommendation Chi Yunwei, the efficiency of a recommendation system and the feedback condition of a user are directly affected by the amount of content in a recommendation pool, and no specific scheme exists in the prior art for controlling the content in the recommendation pool.

Disclosure of Invention

The embodiment of the application provides a control method, a device, equipment and a medium for updating content in a content recommendation pool, which are used for improving the prediction accuracy of the content in the content recommendation pool and further improving the overall efficiency of a recommendation system.

The first aspect of the present application provides a control method for updating content in a content recommendation pool, including:

obtaining user feedback information of the recommended content from an information platform, wherein the user feedback information comprises the number of times of operation of the recommended content and the number of target people for operating the recommended content;

obtaining a second corresponding relation between the stock content and the number of times the recommended content is operated when the number of people operating the recommended content is the target number according to a first corresponding relation among the stock content, the number of people operating the recommended content and the number of times the recommended content is operated, which are formed by fitting historical data;

obtaining target inventory content corresponding to the target times based on the second corresponding relation;

based on the target stock content and the current stock content, controlling the amount of content in the recommendation pool and updating the content in the recommendation pool.

In a second aspect of the present application, there is provided a control apparatus for updating contents in a content recommendation pool, comprising:

the information processing device comprises a user feedback information acquisition unit, a control unit and a control unit, wherein the user feedback information acquisition unit is used for acquiring user feedback information of recommended content from an information platform, and the user feedback information comprises the target times of the operation of the recommended content and the target number of people for operating the recommended content;

The corresponding relation determining unit is used for obtaining a second corresponding relation between the stock content and the number of times the recommended content is operated when the number of people operating the recommended content is the target number according to a first corresponding relation among the stock content, the number of people operating the recommended content and the number of times the recommended content is operated, which are formed by fitting historical data;

The target inventory content obtaining unit is used for obtaining target inventory content corresponding to the target times based on the second corresponding relation;

And the control unit is used for controlling the content quantity in the recommendation pool and updating the content in the recommendation pool based on the target stock content and the current stock content.

In one possible implementation manner, the target inventory content amount obtaining unit is specifically configured to:

And obtaining the target inventory content when the target profit is obtained by the target times based on the second corresponding relation.

Obtaining a curve representing the relationship between the inventory content and the number of times the recommended content is operated according to the second corresponding relationship;

obtaining a straight line representing the relationship between the historical target times and the highest benefit;

Determining the benefits corresponding to the tangent points on the straight line when the straight line is tangent to the curve as target benefits;

and determining the target inventory content when the target profit is obtained by the target times based on the inventory content corresponding to the tangent point in the curve.

In one possible implementation manner, the correspondence determining unit is specifically configured to:

determining historical data fit between the stock content, the number of people operating the recommended content and the number of times the recommended content is operated to form an intermediate corresponding relation;

and converting the intermediate corresponding relation based on the intermediate variable to obtain the corresponding relation among the stock content, the number of people operating the recommended content and the number of times the recommended content is operated.

The user feedback information further includes a complete rate and a fully-manipulated content, wherein the complete rate is a specific gravity of the fully-manipulated content in the inventory content;

Fitting historical data between the stock content and the number of people operating the recommended content according to the ratio of the stock content to the number of people operating the recommended content to form a first intermediate corresponding relation;

and fitting a second intermediate corresponding relation according to historical data between the content which is completely operated, the number of times the recommended content is operated and the ratio of the number of people who operate the recommended content.

When the content which is completely operated is determined to be the product of the consumption rate and the inventory content, the first intermediate corresponding relation and the second intermediate corresponding relation are converted to obtain the corresponding relation among the inventory content, the number of people who operate the recommended content and the number of times that the recommended content is operated.

In a third aspect the application provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of the first aspect when executing the program.

In a fourth aspect of the application, there is provided a computer readable storage medium storing computer instructions which, when run on a computer, cause the computer to perform the method of the first aspect.

Due to the adoption of the technical scheme, the embodiment of the application has at least the following technical effects:

Because the stock content in the recommendation pool affects the number of people operating the recommendation content, the stock content and the number of people operating the recommendation content affect the number of times the recommendation content is operated, when the content in the recommendation pool is controlled, the application considers the influence of the number of people operating the recommendation content and the number of times the recommendation content is operated, based on the historical corresponding relation between the stock content, the number of people operating the recommendation content and the number of times the recommendation content is operated, the unique target stock content is determined on the basis that the number of times the recommendation content is operated meets the requirement, and because the number of people operating the recommendation content is a relatively stable value in a time period, the number of people operating the recommendation content can be taken as a constant, thereby determining the corresponding relation between the stock content and the number of times the recommendation content is operated, after the target stock content is obtained, determining the shortage condition of the stock content based on the current stock content, and formulating a corresponding content introduction strategy, thereby updating the content quantity in the recommendation pool, optimizing the content quality in the recommendation pool to a certain extent, and improving the efficiency of the recommendation system.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present application, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.

Fig. 1 is a schematic diagram of an application scenario to which an embodiment of the present application is applicable;

FIG. 2 is a flowchart illustrating a method for controlling content in an updated content recommendation pool according to an embodiment of the present application;

FIG. 3 is an exemplary diagram of a correspondence relationship between a representation inventory content and a number of operations corresponding to the content provided by an embodiment of the present application;

FIG. 4 is a diagram illustrating an exemplary amount of target inventory content when a target revenue is obtained for a target number of times according to an embodiment of the present application;

FIG. 5 is a schematic diagram showing the correspondence between the ratio of the stock content of different structure types of content under different content categories and the number of people operating the recommended content and the consumption rate according to the embodiment of the present application;

Fig. 6 is a schematic diagram of the correspondence between the content amounts of different structure types of content being completely operated under different content categories and the ratio of the number of times the recommended content is operated to the number of people who operate the recommended content, provided in the embodiment of the present application;

FIG. 7 is a schematic diagram showing the correspondence between the content of the inventory, the number of people operating the recommended content and the number of times the recommended content is operated according to the embodiment of the present application;

FIG. 8 is a flowchart illustrating a method for controlling content in an updated content recommendation pool according to an embodiment of the present application;

fig. 9 is a schematic structural diagram of a control device for updating contents in a content recommendation pool according to an embodiment of the present application;

FIG. 10 is a schematic diagram of a computing device in an embodiment of the application.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments of the present application. All other embodiments, which can be made by those skilled in the art without the inventive effort, are intended to be within the scope of the present application. Embodiments of the application and features of the embodiments may be combined with one another arbitrarily without conflict. Also, while a logical order is depicted in the flowchart, in some cases, the steps depicted or described may be performed in a different order than presented herein.

The terms first and second in the description and claims of the application and in the above-mentioned figures are used for distinguishing between different objects and not for describing a particular sequential order. Furthermore, the term "include" and any variations thereof is intended to cover non-exclusive protection. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus. The term "plurality" in the present application may mean at least two, for example, two, three or more, and embodiments of the present application are not limited.

In addition, the term "and/or" herein is merely an association relationship describing an association object, and means that three relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist together, and B exists alone. The character "/" herein generally indicates that the associated object is an "or" relationship unless otherwise specified.

In order to facilitate the technical solution of the present application to be better understood by those skilled in the art, the following description of technical terms related to the present application is provided.

1. Information flow: the information stream is a content stream that can be scrolled through; these content streams may appear in sections that are displayed next to each other with similar appearance. For example, the information stream may be an editorial selection information stream (e.g., chapter or news listing) or product details (e.g., product listing, service listing, etc.);

2. and (3) an information flow platform: the information flow platform is used for bearing information flows, so that the information flows are displayed on the information flow platform, and the information flow platform can be divided into a social platform, a video platform, an information platform, a search platform and the like according to types;

3. c end: consumer terminals are usually clients used by consumers and personal terminal users, the users log in the platform through the C terminals of different information flow platforms and consume the content displayed on the platform, the specific ways of the users consuming the content are many, the specific ways of the users consuming the content are represented by various operation behaviors, and any operation of the users on the content can possibly form consumption, such as operation behaviors of browsing, playing, commenting or forwarding sharing;

4. Inventory content and inventory content capacity: the stock content refers to the content which can be used for displaying the recommendation at the C end in the recommendation pool, and the stock content refers to the quantity of the stock content in the recommendation pool; the inventory content can be divided into a picture-text type, a video type and the like according to the structure type, wherein the inventory content can comprise but is not limited to a fun type, a game type, an entertainment type and the like according to the content type;

5. Recommendation system and content: the recommendation system is an information filtering system, which is used for predicting the scoring or preference of the user to the items so as to recommend the items interested by the user to the user, in the embodiment of the application, the recommendation system recommends the stock contents in the recommendation pool to the information flow platform according to a certain rule, the content in the embodiment of the application mainly refers to the content recommended to the user through a recommendation system, and can comprise information, short videos, music, news, books, application programs and other types; the content recommended to the information platform by the recommendation system in the historical data is called recommended content.

6. VV (Visit View), PV (PageView) and PN (Quantile);

The VV is the number of times the content is consumed by the user, that is, the number of times the user consumes various operation behaviors of the content. For different types of information stream contents, the consumption mode of the user may be different, for example, if the information stream contents are articles or news types, the consumption of the user may be represented as that the user browses the articles or news, and if the contents are video types, the consumption of the user may be represented as that the user plays the video; PV is the number of times any content is consumed by a user; PN is 95% quantile of the number VV of times of consuming all the content by the user in a preset statistical period;

7. Click UV (Unique Visitor): the number of people consuming the content is also the number of people operating the recommended content in the embodiment of the application;

8. fully consumed content and fully consumed content amount: the fully consumed content is defined as PV > Pn content, the number of fully consumed content being the amount of fully consumed content;

the content that is completely consumed is obtained specifically by the following process:

Counting the consumed times VV of all the contents in a preset counting period, and sequencing the contents according to the consumed times PV of each content, wherein at least one content with the sum of the consumed times of the first N times being more than 95% VV in the sequenced queue is the completely consumed content.

9. Rate of complete elimination: the ratio of the fully consumed content to the stock content; wherein, the higher the consumption rate, the more content in the stock content is consumed completely.

The following describes the design concept of the present application.

In the related art, stock contents of a recommendation pool are mainly generated by the following technologies:

Content texting, machine auditing, manual auditing, content starting, C-terminal special filtering rules, and finally obtaining stock content in a recommendation pool;

The content delivery means that a user creates content on an information flow platform or builds an editing team to create content and the like; the machine audit and the manual audit are to screen out some unsatisfactory contents and perform preliminary quality evaluation, wherein a specific quality evaluation mode is to score the quality of the contents, fit a score by utilizing relevant characteristics based on a scoring model, and filter low-quality and inferior contents according to the score; the manual auditing also comprises the steps of combining specific recommended scenes and business targets, performing some human intervention such as adjusting diversity and the like; and the content enabling is to issue the content to the information flow platform, further filter the content through a special filtering rule of the C end, for example, according to feedback data of a recommendation algorithm, and finally obtain inventory content in a recommendation pool.

In the prior art, although the stock content in the recommendation pool can be obtained according to the above manner, there is no specific scheme how to determine the stock content in the recommendation pool, the content architecture of the recommendation pool, etc., and the content in the recommendation pool is divided into a plurality of different content classes and different structure types, and the content quantity of each structure type under each content class is currently only subjectively controlled by a person recommending Chi Yunwei according to some feedback information of the user, which results in an inaccurate condition of the content quantity in the recommendation pool, the stock content in the recommendation pool is related to the cost, the feedback information of the user such as the number of times the recommended content is operated is related to the income, the content quantity in the recommendation pool also affects the income of the information flow platform after directly affecting the experience of the user, if the quantity of the whole or a certain content class in the recommendation pool is less, the recommendation quality of the recommendation system is affected, and the experience of the user is further reduced, and when the whole or a certain content class in the recommendation pool is more, the consumption quantity of the user tends to be limited, the feedback information of the user tends to have a stable condition, and the income of the content flow is further reduced because the income of the cost of the content flow is increased.

In order to control the content in the recommendation pool and further improve the recommendation quality of a recommendation system, an embodiment of the present application provides a control method, a device, equipment and a storage medium for updating the content in the content recommendation pool, wherein user feedback information of the recommended content includes a target number of times the recommended content is operated and a target number of times the recommended content is operated, the target number of times the recommended content is operated is historical data of the number of times the recommended content is operated, the historical data of the number of times the recommended content is operated is obtained from an information leveling platform in the embodiment of the present application, and the target number of times the recommended content is operated is historical data of the number of people operating the recommended content, the number of people is obtained from the information leveling platform in the embodiment of the present application. Since the stock content in the recommendation pool affects the number of people who operate the recommended content, the stock content and the number of people who operate the recommended content affect the number of times the recommended content is operated at the same time, and therefore, when the content amount in the recommendation pool is controlled, the effect of the number of people who operate the recommended content and the number of times the recommended content is operated needs to be considered at the same time, and therefore, the inventor considers that the unique target stock content can be determined on the basis that the number of times the recommended content is operated meets the requirement based on the historical correspondence between the stock content, the number of people who operate the recommended content and the number of times the recommended content exists, and it is required to say that the number of people who operate the recommended content can be regarded as a constant because the number of people who operate the recommended content is a relatively stable value in one time period, so that the correspondence between the stock content and the number of times the recommended content is operated, namely, a plurality of different stock content and a corresponding plurality of different recommended content are determined.

Because the stock content can be divided according to the content types and the structure types, the embodiment of the application can determine the corresponding relation between the stock content of each content type and the number of times the recommended content is operated according to the historical data of the stock content of each content type and the corresponding user feedback information, so that the target stock content of each content type is respectively obtained on the basis that the number of times the recommended content is operated meets the requirement; or determining the corresponding relation between the inventory content of each structure type and the number of times the recommended content is operated according to the historical data of the inventory content of each structure type and the corresponding user feedback information, so that the target inventory content of each structure type is respectively obtained on the basis that the number of times the recommended content is operated meets the requirement; as another alternative implementation manner, according to the historical data of the stock content of each structure type under each content category and the corresponding user feedback information, determining the corresponding relation between the stock content of each structure type under each content category and the number of times the recommended content is operated, so as to respectively obtain the target stock content of each structure type under each content category on the basis that the number of times the recommended content is operated meets the requirement; optionally, according to the historical data of the integral inventory content in the recommendation pool and the corresponding user feedback information, determining a corresponding relation between the inventory content of the integral inventory content in the recommendation pool and the number of times the recommendation content is operated, so that the integral inventory content number of the recommendation pool is obtained on the basis that the number of times the recommendation content is operated meets the requirement.

In order to better understand the technical solution provided by the embodiments of the present application, some simple descriptions are provided below for application scenarios applicable to the technical solution provided by the embodiments of the present application, and it should be noted that the application scenarios described below are only used to illustrate the embodiments of the present application, but not limited thereto. In the specific implementation, the technical scheme provided by the embodiment of the application can be flexibly applied according to actual needs.

Referring to fig. 1, fig. 1 is an application scenario to which a method for controlling content in a content recommendation pool is applicable in an embodiment of the present application. In this application scenario, a plurality of terminal devices (e.g., terminal device 101, terminal device 102, terminal device 103) and a server 104 are included, where the server 104 may be a server serving a recommendation pool. And each terminal equipment is in communication connection with the server 104, wherein the C ends of different information flow platforms are arranged on each terminal, each terminal equipment can send content to the server 104 to store the content in a recommendation pool served by the server 104, and each terminal also needs to send feedback information of a user on the information flow platform to the server 104, and can also receive the recommendation content sent by the server 104.

Taking the short video type information flow platform as an example, the server 104 sends the recommended content in the recommendation pool to the short video type information flow platform of a plurality of terminal devices through the recommendation system, the server 104 obtains the user feedback information of the recommended content on each information flow platform from the plurality of terminal devices, further, the server 104 can determine the target inventory content under the short video category, namely the demand of the inventory content by adopting the control method for updating the content in the content recommendation pool in the embodiment of the application, and further, the content quantity in the recommendation pool is controlled according to the target inventory content and the current inventory content, thereby improving the recommendation quality of the recommendation system and increasing the income of the information flow platform.

Taking an information type information flow platform as an example, the server 104 sends the recommended content in the recommendation pool to the information type information flow platform of a plurality of terminal devices through the recommendation system, the server 104 obtains user feedback information of the recommended content on each information flow platform from the plurality of terminal devices, further, the server 104 can determine the target inventory content under the information article, namely the required quantity of the inventory content by adopting the control method for updating the content in the content recommendation pool in the embodiment of the application, and further, the content quantity in the recommendation pool is controlled according to the target inventory content and the current inventory content, so that the recommendation quality of the recommendation system can be improved, and the income of the information flow platform is increased.

The server 104 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs (Content Delivery Network, content delivery networks), basic cloud computing services such as big data and artificial intelligence platforms, and the like. The terminal device 101, the terminal device 102, and the terminal device 103 may be, but are not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart television, a smart wearable device, and the like.

In order to further explain the technical solution provided by the embodiments of the present application, the following details are described with reference to the accompanying drawings and the detailed description. Although embodiments of the present application provide the method operational steps shown in the following embodiments or figures, more or fewer operational steps may be included in the method based on routine or non-inventive labor. In steps where there is logically no necessary causal relationship, the execution order of the steps is not limited to the execution order provided by the embodiments of the present application. The methods may be performed sequentially or in parallel as shown in the embodiments or the drawings when the actual processing or the apparatus is performed.

The present application provides a control method for updating content in a content recommendation pool, which may be performed by a recommendation pool server, such as server 104 in fig. 1. The method for controlling the updating of the content in the content recommendation pool provided by the embodiment of the application is shown in fig. 2, and a flowchart shown in fig. 2 is described as follows.

Step S201, obtaining user feedback information of the recommended content from an information platform, wherein the user feedback information comprises the target number of times the recommended content is operated and the target number of people who operate the recommended content;

The recommended content is content in a recommendation pool is sent to an information flow platform by a recommendation system through a certain recommendation rule, and is used for content consumed by a user, and it is to be noted that the embodiment of the application comprises different types of information flow platforms, if the overall content in the recommendation pool is required to be controlled, user feedback information of all recommended content can be obtained from all types of information flow platforms, alternatively, if the content of different content types in the recommendation pool is required to be controlled, user feedback information of the recommended content of different content types can be obtained from all types of information flow platforms respectively, similarly, if the content of different structure types in the recommendation pool is required to be controlled, user feedback information of different structure types of recommended content can be obtained from all types of information flow platforms respectively, as another alternative implementation mode, content of the recommendation pool corresponding to the different types of information flow platforms can also be controlled, for example, if the content of the information flow platform of a short video type in the recommendation pool is required to be controlled, user feedback information of different types of the information flow platforms can be obtained from the short video type of the information flow platform, and the actual requirements of the user can be set up in the field according to the actual requirements.

In the embodiment of the application, the user feedback information is data information sent by the information platform, the user consumption operation recommended content correspondingly increases the number of times the recommended content is operated and the number of times the recommended content is operated, and the like, specifically, the stock content and the user feedback information can be data obtained by taking a preset time period as a statistics period, can be average values of the data in the statistics period, can be taken as an optional implementation mode, can be taken as a statistics period by ten days, can count the total historical data of the user feedback information in ten days if the stock content is not changed in ten days, and can count the daily average value of the stock content in ten days and the daily average value of the user feedback information in ten days if the stock content is changed in ten days.

Step S202, obtaining a second corresponding relation between the stock content and the number of times the recommended content is operated when the number of people operating the recommended content is the target number according to a first corresponding relation between the stock content, the number of people operating the recommended content and the number of times the recommended content is operated by fitting historical data;

The number of times the recommended content is operated is related to the number of people operating the recommended content and the number of times the recommended content is operated, and the increase of the number of people operating the recommended content can increase the number of times the recommended content is operated to a certain extent, so that the embodiment of the application firstly determines the corresponding relation among the number of people operating the recommended content, the number of people operating the recommended content and the number of times the recommended content is operated.

The embodiment of the application can determine the corresponding relation among the stock content, the number of people operating the recommended content and the number of times the recommended content is operated by the following modes:

determining an intermediate corresponding relation formed by fitting historical data among the stock content, the number of people operating the recommended content and the number of times the recommended content is operated, and converting the intermediate corresponding relation based on intermediate variables to obtain the corresponding relation among the stock content, the number of people operating the recommended content and the number of times the recommended content is operated;

It should be noted that, the corresponding relationship may be obtained by directly fitting the historical data of the stock content, the historical data of the number of times the recommended content is operated, and the historical data of the number of people operating the recommended content, but because the three-dimensional corresponding relationship is obtained by directly fitting the stock content, the number of times the recommended content is operated, and the number of people operating the recommended content as variables, there is a large error in the fitting process, and the fitting effect is poor, the embodiment of the application adopts a method of firstly determining the intermediate corresponding relationship formed by fitting the historical data between the stock content, the number of people operating the recommended content, and the number of times the recommended content is operated, and then converting the intermediate corresponding relationship based on the intermediate variables to obtain the corresponding relationship among the stock content, the number of people operating the recommended content, and the number of times the recommended content is operated.

The user feedback information may include a complete rate, which is a specific gravity of the content in the stock content that is completely operated, for example, 100, and a content that is completely operated, which is 90%, and the content that is completely operated, for example, the complete rate is 90%. In the embodiment of the application, the intermediate variable can be the complete rate alone or the content of complete operation alone, and the complete rate and the content of complete operation are related to the stock content, so that the complete rate and the content of complete operation can be used as the intermediate variable at the same time;

As an alternative implementation manner, a first intermediate corresponding relation can be formed by fitting historical data among the stock content, the number of people operating the recommended content and the consumption rate, and a second intermediate corresponding relation can be formed by fitting historical data among the completely operated content, the number of people operating the recommended content and the number of people operating the recommended content, and the first intermediate corresponding relation and the second intermediate corresponding relation are converted based on the consumption rate, the completely operated content and the relation of the stock content to obtain the corresponding relation among the stock content, the number of people operating the recommended content and the number of people operating the recommended content; it should be noted that if there are three variables to perform function fitting, the fitting result is a three-dimensional corresponding relationship, so that the fitting effect is poor, and therefore, in the embodiment of the application, a variable can be obtained according to the ratio of the historical data of two variables in the process of fitting the middle corresponding relationship, so as to obtain a two-dimensional middle corresponding relationship, and specific embodiments can be set by those skilled in the art according to actual conditions, and are not limited herein.

The user number of the information flow platform tends to be stable within a period of time, so that the number of people who operate the recommended content tends to be stable, namely, within a period of time or within a range of change of the stock content, the change of the number of people who operate the recommended content is small, so that the corresponding relation between the number of people who operate the recommended content and the number of times the recommended content is operated can be eliminated when the stock content is determined, but because the influence of the number of people who operate the recommended content on the number of times the recommended content is large, if historical data between the stock content and the number of people who operate the recommended content are directly fitted, a large error exists, so that the embodiment of the application can firstly obtain the corresponding relation between the stock content, the number of people who operate the recommended content and the number of times the recommended content is operated, and according to the obtained target number of people who operate the recommended content from the information flow platform, the corresponding relation between the stock content, the number of people who operate the recommended content and the number of times the recommended content is substituted as constants into the corresponding relation between the stock content, and the number of times the recommended content is determined.

In the embodiment of the present application, the correspondence between the inventory internal volume and the number of times the content is operated is shown in fig. 3, fig. 3 is a curve representing the relationship between the inventory internal volume and the number of times the corresponding recommended content is operated, the abscissa is the inventory internal volume, and the ordinate is the number of times the recommended content is operated, it should be noted that fig. 3 only represents the approximate correspondence between the inventory internal volume and the number of times the corresponding recommended content is operated, and along with the change of the historical data in the statistical period or the change of the target number of people who operate the recommended content, the curve in fig. 3 may be changed based on the whole coordinate axis, such as rising, falling or moving left and right.

Step S203, obtaining target stock content corresponding to the target times based on the second corresponding relation;

The correspondence between the stock content and the number of times the recommended content is operated can only obtain different stock content and the corresponding number of times the recommended content is operated, and only obtain the constraint relationship between the stock content and the number of times the recommended content is operated, but the unique target stock content cannot be determined, in the embodiment of the present application, by limiting the target number of times the recommended content is operated, and obtaining a corresponding target inventory content according to the number of times the recommended content is operated, wherein the number of times the recommended content is operated can be a preset value or a value correspondingly determined according to target benefits, and optionally, other index values related to the number of times the recommended content is operated can also be used for determining the number of times the recommended content is operated, so that the corresponding target inventory content is determined.

In the embodiment of the present application, based on the correspondence between the inventory content and the number of times the recommended content is operated, the manner of obtaining the target inventory content when obtaining the target revenue with the target number of times is as follows:

According to the embodiment of the application, the benefits are related to the number of times the recommended content is operated and the stock content amount, if only the corresponding relation among the benefits, the number of times the recommended content is operated and the stock content amount is determined, the corresponding image is a straight line in fig. 4, the straight line in fig. 4 represents the relation between the historical target number of times and the highest benefits, wherein the abscissa is the stock content amount, the ordinate is the number of times the content is operated, the intercept of the straight line can represent the benefits, and it is required to explain that the slope of the straight line is certain, if the benefits corresponding to the target number of any point on the straight line are equal after the intercept is determined, the benefits of the straight line can be increased or decreased based on the coordinate axis, and at the moment, the benefits of the information flow platform are correspondingly increased or decreased, and the greater the intercept of the straight line is the higher the benefits of the information flow platform; the target profit in the present application may be, but not limited to, the maximum profit or the profit greater than the preset threshold, based on fig. 4, it is known that the point where the straight line and the curve intersect satisfies the constraint relation between the inventory content and the number of times the recommended content is operated, the profit corresponding to the tangent point when the straight line is tangent to the curve on the straight line is determined as the target profit, because the intercept of the straight line is maximum when the straight line is tangent to the curve, the maximum profit can be achieved, and a unique tangent point can be determined, the ordinate of the tangent point represents the number of times of the target, and the target inventory content when the target profit is obtained with the target number of times can be determined based on the inventory content corresponding to the tangent point at the curve.

In the embodiment of the application, after the corresponding relation between the stock content and the number of times the recommended content is operated is obtained, if the corresponding target stock content is determined based on the preset target number of times and the target profit respectively in the preset time period, the corresponding relation can be formed by fitting historical data among the same stock content, the number of people operating the recommended content and the number of times the recommended content is operated without re-fitting, and the corresponding relation between the stock content and the number of times the recommended content is operated can be obtained by directly substituting the target number of people operating the recommended content obtained from the information leveling platform into the corresponding relation formed by fitting the historical data among the stock content, the number of people operating the recommended content and the number of times the recommended content is operated;

As another alternative implementation manner, the corresponding relationship between the same stock content and the number of times the recommended content is operated may be based on the same stock content when the target stock content is determined according to the target number of times in the preset time period, or of course, the corresponding relationship may be formed by fitting again according to the historical data between the stock content, the number of people operating the recommended content and the number of times the recommended content is operated each time the target stock content is determined, and the corresponding relationship between the stock content and the number of times the recommended content is operated may be obtained according to the target number of people operating the recommended content.

Step S204, controlling the content quantity in the recommendation pool and updating the content in the recommendation pool based on the target stock content and the current stock content.

After the target stock content is obtained, the operation and maintenance personnel of the recommendation pool can reduce or increase the content quantity in the recommendation pool according to the comparison result of the target stock content and the current stock content, if the target stock content is higher than the current stock content, the current stock content is indicated to be less, corresponding stock content needs to be introduced, and corresponding stock content is quantitatively introduced according to the difference value of the target stock content and the current stock content, if the target stock content is lower than the current stock content, the current stock content is indicated to be more, and the operation and maintenance personnel can reduce the content of the stock according to the difference value of the current stock content and the target stock content.

The method for determining the correspondence between the inventory content and the number of operations of the recommended content and the manner of obtaining the target inventory content when the target revenue is obtained by the target number of operations in the embodiment of the application will be described with reference to specific embodiments.

The method comprises the steps of determining the corresponding relation among the stock content, the number of people operating the recommended content and the number of times the recommended content is operated according to historical data fit to form an intermediate corresponding relation, and converting the intermediate corresponding relation based on intermediate variables to obtain the corresponding relation among the stock content, the number of people operating the recommended content and the number of times the recommended content is operated, wherein one specific implementation mode is as follows:

The consumption rate is the ratio of the content quantity which is completely operated to the stock content quantity, so that the consumption rate and the content quantity which is completely operated are respectively used as intermediate variables, and the corresponding relation among the content quantity, the number of people who operate the recommended content and the number of times the recommended content is operated can be obtained by converting the corresponding relation among the two variables;

Step 1: determining a first intermediate correspondence between the rate of consumption, the inventory content and the number of people operating the recommended content, as shown in formula 1;

Performing function fitting on historical data of the consumption rate, the stock content and the number of people operating the recommended content to obtain a first intermediate corresponding relation, wherein the ratio of the stock content to the number of people operating the recommended content is taken as an independent variable x ₁, the consumption rate is taken as a dependent variable y ₁, the historical data related to the information flow table is used for fitting to obtain the first intermediate corresponding relation of the independent variable and the dependent variable, and the coefficient of the first intermediate corresponding relation can be obtained; the specific formula is expressed as follows:

x ₁ = N/click UV

Y ₁ = rate of complete elimination

y₁＝a*x₁ ^b (1)

Wherein y ₁ is the rate of consumption, x ₁ is the ratio of the stock content to the number of people operating the recommended content, N is the stock content, a and b are coefficients obtained by function fitting, and are specific values, and since y ₁ decreases exponentially with increasing x ₁ in fig. 1, b is a value smaller than zero, formula (1) characterizes the historical correspondence between the different rates of consumption, the different stock content and the number of people operating the recommended content, and is specifically expressed as the rate of consumption increases exponentially with increasing the ratio of the stock content to the number of people operating the recommended content;

In order to better show the historical correspondence between the rate of consumption and the ratio of the stock content to the number of people operating the recommended content, the actual meaning represented by each letter is brought into formula (1) to obtain formula (2):

As shown in fig. 5, the image of the first intermediate correspondence is a power function. The first intermediate correspondence lists the relationship between the ratio of the stock content of the different structure types under the different content types and the number of people who operate the recommended content and the consumption rate, wherein the abscissa is x ₁, and the ordinate is y ₁, as can be seen from fig. 5, since the content of the different structure types under the different content types is different in popularity of users, even though the ratio of the stock content to the number of people who operate the recommended content is the same, the corresponding consumption rate is different, but the trend of the corresponding line segments of the content of the different structure types under the different content types is the same, the larger the ratio of the stock content to the number of people who operate the recommended content is, the smaller the corresponding consumption rate is, that is, the content amount which is fully operated in the recommended pool is smaller, because the ratio of the stock content to the number of people who operate the recommended content is larger, the content amount of the stock content is indicated to be smaller, and the consumption capability of users is limited at this time, and the content amount which is fully operated in the stock content is reduced.

Step 2: determining a second intermediate correspondence between the amount of content that is fully manipulated, the number of times the recommended content is manipulated, and the number of people manipulating the recommended content, as shown in formula (3);

Performing function fitting on the content quantity which is completely operated, the number of times of operation of the recommended content and the historical data of the number of people who operate the recommended content to obtain a second intermediate corresponding relation, wherein the content quantity which is completely operated is taken as an independent variable x ₂, the ratio of the number of times of operation of the recommended content to the number of people who operate the recommended content is taken as a dependent variable y ₂, the second intermediate corresponding relation is obtained through fitting of historical data related to an information platform, and the coefficient of the second intermediate corresponding relation can be obtained; the specific formula is expressed as follows:

x ₂ = content amount fully manipulated

Y ₂ = VV/click UV

y₂＝c*x₂ (3)

Wherein y ₂ is the ratio of the number of times the recommended content is operated to the number of people who operate the recommended content, x ₂ is the amount of content which is fully operated, the amount of content which is fully operated is the product of the stock content and the rate of consumption, c is a coefficient obtained by function fitting, which is a specific value, and is a value greater than 1, and formula (4) characterizes the historical correspondence of the ratio of the number of times the different recommended content is operated to the number of people who operate the recommended content, and is specifically expressed in that the ratio of the number of times the recommended content is operated to the number of people who operate the recommended content increases linearly with the increase of the amount of content which is fully operated;

in order to better show the ratio of the number of times the recommended content is operated to the number of people operating the recommended content, the historical correspondence with the fully operated content is obtained by substituting the actual meaning represented by each letter into formula (3) to obtain formula (4):

As shown in fig. 6, the image of the second intermediate correspondence is a linear function, and the second intermediate correspondence lists the content amounts of the content of different structure types under different content categories that are completely operated, and the relationship of the ratio of the number of times the recommended content is operated to the number of people who operate the recommended content, where the abscissa is x ₂, the ordinate is y ₂, as can be seen from fig. 6, since the contents of different structure types under different content categories are different in popularity of users, even if the amounts of the contents to be completely operated are the same, the ratio of the number of times the corresponding recommended contents are operated to the number of people who operate the recommended contents is different, but the trends of the corresponding images of the contents of different structure types under different content categories are consistent, the more the amounts of the contents to be completely operated, the more the recommended contents are operated.

Step 3: determining the corresponding relation among the stock content, the number of people operating the recommended content and the number of times the recommended content is operated, as shown in a formula (6);

Since y ₁ is the completion rate and the product of y ₁ and the stock content is the content amount that is fully manipulated, i.e., x ₂, formula (1) can be substituted into formula (3) to yield formula (5):

The formula (5) is deformed to obtain the formula (6):

In the formula (6), a, b and c are coefficients obtained in the fitting process; the formula (6) characterizes the historical correspondence between different stock content, the number of times different recommended content is operated and the number of people who operate the recommended content, and as b is a value smaller than zero, b-1 is smaller than zero, so that the number of times the recommended content is operated linearly increases along with the exponential increase of the stock content and the number of people who operate the recommended content;

As shown in fig. 7, a three-dimensional relationship image obtained according to formula (6), wherein the x-axis is the number of people operating the recommended content, the y-axis is the stock content, and the z-axis is the number of times the recommended content is operated, as can be obtained from fig. 7, on the basis that the stock content amount is fixed, when the number of people operating the recommended content of the information flow platform increases, the number of times the recommended content is operated is significantly increased, on the basis that the number of people operating the recommended content is fixed, and on the basis that the number of people operating the recommended content increases, although the number of times the recommended content is operated is gradually increased, the increase of the number of times the recommended content is operated tends to be gentle due to the limited consumption ability of the user; it should be noted that, the above-mentioned deduction process is only a specific implementation manner provided by the embodiment of the present application, and a person skilled in the art may set the deduction process according to actual requirements, for example, in another alternative implementation manner, the complete consumption rate may be used as an intermediate variable, first, historical data between the ratio of the complete consumption rate, the stock content and the number of people operating the recommended content is fitted to form a first intermediate corresponding relationship, second, historical data between the complete consumption rate, the number of times the recommended content is operated and the ratio of the number of people operating the recommended content is fitted to form a second intermediate corresponding relationship, and then, based on the complete consumption rate, the first intermediate corresponding relationship and the second intermediate corresponding relationship are converted to obtain the corresponding relationship among the stock content, the number of people operating the recommended content and the number of times the recommended content is operated.

As can be seen from the above analysis, when the number of people operating the recommended content is relatively stable, the number of consumption times caused by increasing the inventory content converges marginally, and at this time, the number of people operating the recommended content in the formula (6) is used as a constant, so as to obtain a correspondence between the inventory content and the number of times the recommended content is operated, as shown in the formula (7):

wherein a' = (a×c)/click UV ^b-1;

The formula (7) characterizes the historical correspondence between different inventory contents and the number of times the recommended content is operated, and is also a constraint condition between the inventory contents and the number of times the recommended content is operated, the number of times the recommended content is operated linearly increases with the exponential increase of the inventory contents, the image corresponding to the formula (7) is shown in fig. 3, and as can be seen from fig. 3, the number of times the recommended content is operated increases faster and then becomes slower, which is caused by the limited consumption capability of the user.

Equation (8) is Ke Bu-the douglas production function:

Y＝A(t)L^1-εK^ε (8)

Wherein Y is an industrial total yield value, a (t) is a comprehensive technical level, L is a labor input number, K is a capital input, and Ke Bu-dolas production function verifies that a certain economic relationship is satisfied between the inventory content and the number of times the recommended content is operated from a certain degree, and since the inventory content is related to cost and the number of times the recommended content is operated is related to income, the inventory content and the number of times the recommended content is operated can be converted into a relationship between cost and income.

The corresponding relation between the stock content and the number of times the recommended content is operated is determined by the formula (8), then one variable in the formula (8) can be constrained to determine the other variable, for example, the number of times the recommended content is required to be operated is as large as possible, then the stock content can be enabled to be in an acceptable range, and the specific value of the stock content can be determined; as another alternative, there is an optimal inventory content, such that the overall yield of the information flow platform is maximized, and assuming cost-yield maximization is the goal, a unique target inventory content may be determined based on constraints and goals.

The income of the information flow platform business mainly comes from flow rate change and is related to the number of times the recommended content is operated; the cost mainly comes from the content investment, and is related to the inventory content quantity, and the set income and cost formulas are respectively as follows:

Revenue = K yuan per consumption;

cost = M yuan/piece of content;

Then the benefit formula can be derived as:

revenue = revenue-cost = K VV-M N (9)

After the above formula is deformed, the target relational expression of VV-N is obtained as formula (10):

VV = k '. Times.n+m'. Times.gain (10)

Wherein, the formula (10) is a linear function, since k ' =m/N is a constant, M ' =1/k is a constant, so the slope of the target relation is determined, the intercept is M '. Times of return, and the formula (10) characterizes the corresponding relation among different stock contents, the number of times different recommended contents are operated, and the corresponding returns;

Since the number of times the recommended content is operated and the inventory content amount both satisfy the target relational expression and satisfy the constraint condition, the point at which the target relational expression and the constraint condition intersect is the point at which the condition is satisfied, the abscissa of the intersecting point is the inventory content amount, and the ordinate is the number of times the recommended content is operated, as shown in fig. 4, when the target relational expression and the corresponding relational expression of the constraint condition are tangent, the intercept of the target relational expression is maximum, and since the intercept is the product of the benefit and the constant, the greater the intercept, the higher the benefit, and the tangent point is the optimal solution for cost-benefit maximization.

As shown in fig. 8, the process of controlling the content in the recommendation pool specifically includes:

Step S801, obtaining user feedback information of recommended content from an information platform;

wherein the user feedback information includes a target number of times the recommended content is operated, a target number of people who operate the recommended content, a rate of consumption, and a number of times the recommended content is fully operated.

Details of this step can be found in the foregoing, and the description thereof will not be repeated here.

Step S802, fitting historical data between the stock content and the number of people operating the recommended content to form a first intermediate corresponding relation according to the ratio of the stock content to the number of people operating the recommended content;

Step S803, fitting a second intermediate corresponding relation according to historical data between the content which is completely operated, the number of times the recommended content is operated and the ratio of the number of people who operate the recommended content;

Step S804, when the content which is completely operated is determined to be the product of the consumption rate and the stock content, the first intermediate corresponding relation and the second intermediate corresponding relation are converted to obtain the corresponding relation among the stock content, the number of people who operate the recommended content and the number of times that the recommended content is operated;

step S805, when the number of people operating the recommended content is the target number of people, a second corresponding relationship between the stock content and the number of times the recommended content is operated is obtained;

Step S806, obtaining a curve representing the relation between the inventory content and the number of times the recommended content is operated according to the second corresponding relation between the inventory content and the number of times the recommended content is operated;

Step S807, obtaining a straight line representing the relationship between the historical target times and the highest benefit;

Step S808, determining the benefits corresponding to the tangent points on the straight line when the straight line is tangent to the curve as target benefits;

Step S809, determining the target inventory volume when the target revenue is obtained by the target number of times based on the inventory volume corresponding to the tangent point in the curve.

Based on the same inventive concept, the embodiment of the application provides a control device for updating content in a content recommendation pool, wherein the control device for updating content in the content recommendation pool can be a hardware structure, a software module or a hardware structure plus a software module. The control device for updating the content in the content recommendation pool may be, for example, the server 104 in fig. 1, or may be a functional device disposed in the server 104, where the control device for updating the content in the content recommendation pool may be implemented by a chip system, and the chip system may be formed by a chip, or may include a chip and other discrete devices. Referring to fig. 9, the control device for updating content in a content recommendation pool in the embodiment of the present application includes a user feedback information obtaining unit 901, a correspondence determining unit 902, a target stock content amount obtaining unit 903, and a control unit 904, where:

A user feedback information obtaining unit 901, configured to obtain user feedback information of recommended content from an information platform, where the user feedback information includes a target number of times the recommended content is operated and a target number of people who operate the recommended content;

a correspondence determining unit 902, configured to obtain a second correspondence between the stock content and the number of times the recommended content is operated when the number of people operating the recommended content is the target number according to a first correspondence between the stock content, the number of people operating the recommended content, and the number of times the recommended content is operated, which are obtained by fitting historical data between the stock content and the number of times the recommended content is operated;

a target inventory content obtaining unit 903, configured to obtain a target inventory content corresponding to the target number of times based on the second correspondence;

A control unit 904 for controlling the amount of content in the recommendation pool and updating the content in the recommendation pool based on the target stock content and the current stock content.

In one possible implementation, the target inventory content amount obtaining unit 903 is specifically configured to:

In one possible implementation manner, the correspondence determining unit 902 is specifically configured to:

All relevant contents of each step involved in the foregoing embodiment of the method for controlling contents in the updated content recommendation pool may be cited to the functional description of the functional module corresponding to the device for controlling contents in the updated content recommendation pool in the embodiment of the present application, which is not described herein.

The division of the modules in the embodiments of the present application is schematically only one logic function division, and there may be another division manner in actual implementation, and in addition, each functional module in each embodiment of the present application may be integrated in one processor, or may exist separately and physically, or two or more modules may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules.

Based on the same inventive concept, an embodiment of the present application provides a computing device, for example, the foregoing server 104 in fig. 1, and the computing device is capable of executing the control method for updating the content in the content recommendation pool provided in the embodiment of the present application, as shown in fig. 10, where the computing device in the embodiment of the present application includes at least one processor 1001, and a memory 1002 and a communication interface 1003 connected to the at least one processor 1001, in the embodiment of the present application, a specific connection medium between the processor 1001 and the memory 1002 is not limited, and in fig. 10, a connection between the processor 1001 and the memory 1002 is taken as an example, and in fig. 10, the bus 1000 is shown in bold, and a connection manner between other components is merely illustrative, and not limited to. The bus 1000 may be divided into an address bus, a data bus, a control bus, etc., and is shown with only one thick line in fig. 10 for convenience of illustration, but does not represent only one bus or one type of bus.

In an embodiment of the present application, the memory 1002 stores a computer program executable by the at least one processor 1001, and the at least one processor 1001 may execute the steps included in the method of recommending content by executing the computer program stored in the memory 1002.

The processor 1001 is a control center of a computing device, and may use various interfaces and lines to connect various parts of the entire computing device, and by executing or executing instructions stored in the memory 1002 and invoking data stored in the memory 1002, various functions of the computing device and process data, thereby performing overall monitoring of the computing device. Alternatively, the processor 1001 may include one or more processing modules, and the processor 1001 may integrate an application processor and a modem processor, wherein the processor 1001 primarily processes an operating system, a user interface, an application program, and the like, and the modem processor primarily processes wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 1001. In some embodiments, the processor 1001 and the memory 1002 may be implemented on the same chip, and in some embodiments they may be implemented separately on separate chips.

The processor 1001 may be a general purpose processor, such as a Central Processing Unit (CPU), digital signal processor, application specific integrated circuit, field programmable gate array or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, which may implement or perform the methods, steps and logic block diagrams disclosed in embodiments of the present application. The general purpose processor may be a microprocessor or any conventional processor or the like. The steps of a method disclosed in connection with the embodiments of the present application may be embodied directly in a hardware processor for execution, or in a combination of hardware and software modules in the processor for execution.

The memory 1002 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. The Memory 1002 may include at least one type of storage medium, and may include, for example, flash Memory, hard disk, multimedia card, card Memory, random access Memory (Random Access Memory, RAM), static random access Memory (Static Random Access Memory, SRAM), programmable Read-Only Memory (Programmable Read Only Memory, PROM), read-Only Memory (ROM), charged erasable programmable Read-Only Memory (ELECTRICALLY ERASABLE PROGRAMMABLE READ-Only Memory, EEPROM), magnetic Memory, magnetic disk, optical disk, and the like. Memory 1002 is any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to such. The memory 1002 in embodiments of the present application may also be circuitry or any other device capable of performing memory functions for storing program instructions and/or data.

The communication interface 1003 is a transmission interface that can be used for communication, and data can be received or transmitted through the communication interface 1003, for example, data interaction with other devices can be performed through the communication interface 1003 for the purpose of communication.

Further, the computing device also includes a basic input/output system (I/O system) 1004 for facilitating the transfer of information between the various devices within the computing device, a mass storage device 1008 for storing an operating system 1005, application programs 1006, and other program modules 1007.

Basic input/output system 1004 includes a display 1009 for displaying information and an input device 1010, such as a mouse, keyboard, etc., for user input of information. Where a display 1009 and an input device 1010 are connected to the processor 1001 through a basic input/output system 1004 that is connected to the system bus 1000. The basic input/output system 1004 may also include an input/output controller for receiving and processing input from a number of other devices, such as a keyboard, mouse, or electronic stylus. Similarly, the input-output controller also provides output to a display screen, a printer, or other type of output device.

The mass storage device 1008 is connected to the processor 1001 through a mass storage controller (not shown) connected to the system bus 1000. The mass storage device 1008 and its associated computer-readable media provide non-volatile storage for the server package. That is, the mass storage device 1008 may include a computer readable medium (not shown), such as a hard disk or CD-ROM drive.

According to various embodiments of the application, the computing device package may also be operated by a remote computer connected to the network through a network, such as the Internet. I.e., the computing device may be connected to the network 1011 via a communication interface 1003 connected to the system bus 1000, or may be connected to other types of networks or remote computer systems (not shown) using the communication interface 1003.

Based on the same inventive concept, the embodiments of the present application also provide a storage medium, which may be a computer-readable storage medium, having stored therein computer instructions that, when run on a computer, cause the computer to perform the steps of the control method of updating content in a content recommendation pool as described above.

Based on the same inventive concept, the embodiment of the application also provides a chip system, which comprises a processor and can also comprise a memory, wherein the memory is used for realizing the steps of the control method for updating the content in the content recommendation pool. The chip system may be formed of a chip or may include a chip and other discrete devices.

In some possible implementations, aspects of the method for recommending content provided by the embodiments of the present application may also be implemented in the form of a program product including program code for causing a computer to perform the steps in the control method for updating content in a content recommendation pool according to various exemplary embodiments of the present application as described above when the program product is run on the computer.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, magnetic disk storage, optical storage, and the like) having computer-usable program code embodied therein.

It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, it is intended that the present application also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.

Claims

1. A control method for updating content in a content recommendation pool, the method comprising:

Obtaining a second corresponding relation between the stock content and the number of times the recommended content is operated when the number of people operating the recommended content is the target number according to a first corresponding relation between the stock content, the number of people operating the recommended content and the number of times the recommended content is operated, which are formed by fitting historical data;

acquiring target inventory content corresponding to the target times based on the second corresponding relation;

And controlling the content quantity in the recommendation pool and updating the content in the recommendation pool based on the target stock content and the current stock content.

2. The method of claim 1, wherein obtaining a target inventory content corresponding to the target number of times based on the second correspondence, comprises:

3. The method according to claim 2, wherein the obtaining, based on the second correspondence, the target inventory content when obtaining the target revenue by the target number of times, specifically includes:

determining that the return corresponding to the tangent point when the straight line is tangent to the curve on the straight line is the target return;

And determining the stock content corresponding to the tangent point on the curve as the target stock content when the target profit is obtained according to the target times.

4. A method according to claim 1, 2 or 3, wherein the first correspondence, which is formed by fitting historical data between the stock content, the number of people operating the recommended content and the number of times the recommended content is operated, is obtained by:

And converting the intermediate corresponding relation based on an intermediate variable to obtain the corresponding relation among the stock content, the number of people operating the recommended content and the number of times the recommended content is operated.

5. The method of claim 4, wherein the determining an intermediate correspondence between the inventory content, the number of people operating the recommended content, and the number of times the recommended content is operated, comprises:

the user feedback information further comprises a consumption rate and a fully operated content, wherein the consumption rate is the specific gravity of the fully operated content in the stock content;

6. The method of claim 5, wherein converting the intermediate correspondence based on intermediate variables to obtain the correspondence between the stock content, the number of people operating the recommended content, and the number of times the recommended content is operated, comprises:

When the fully operated content is determined to be the product of the consumption rate and the stock content, the first intermediate corresponding relation and the second intermediate corresponding relation are converted to obtain the corresponding relation among the stock content, the number of people operating the recommended content and the number of times the recommended content is operated.

7. A control apparatus for updating contents in a content recommendation pool, comprising:

a target inventory content obtaining unit, configured to obtain a target inventory content corresponding to the target number of times based on the second correspondence;

8. The apparatus of claim 7, wherein the target inventory content amount obtaining unit is specifically configured to:

9. The apparatus according to claim 8, wherein the target stock content quantity obtaining unit is specifically configured to:

10. The apparatus according to claim 7, 8 or 9, wherein the correspondence determination unit is specifically configured to:

11. The apparatus according to claim 10, wherein the correspondence determination unit is specifically configured to:

12. The apparatus according to claim 11, wherein the correspondence determination unit is specifically configured to:

13. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method of any of claims 1-6 when the program is executed.

14. A computer readable storage medium storing computer instructions which, when run on a computer, cause the computer to perform the method of any one of claims 1-6.