CN114117193A

CN114117193A - Control method, device, equipment and medium for updating content in content recommendation pool

Info

Publication number: CN114117193A
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: 2022-03-01
Anticipated expiration: 2040-08-26
Also published as: CN114117193B

Abstract

The application provides a control method, device, equipment and medium for updating content in a content recommendation pool, relates to the technical field of computers, and aims to improve the prediction precision of the content amount 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 flow platform; according to a first corresponding relation among the inventory content amount, the number of people operating the recommended content and the number of times the recommended content is operated, when the number of people operating the recommended content is a target number of people, obtaining a second corresponding relation between the inventory content amount and the number of times the recommended content is operated; obtaining a target inventory content amount corresponding to the target times based on the second corresponding relation; controlling the amount of content in the recommendation pool and updating the content in the recommendation pool based on the target and current inventory content amounts.

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 updating of content in a content recommendation pool.

Background

The recommendation system is an information filtering system, is mainly used for filtering and screening contents for each user, and can recommend proper contents for corresponding users. The content recommended to the user by the recommendation system is from different content types and different structure types contained in the recommendation pool.

In the related technology, the content is introduced by the operation and maintenance personnel of the recommendation pool subjectively, the efficiency of the recommendation system and the feedback condition of the user are directly influenced by the content amount in the recommendation pool, and at present, no specific scheme exists for controlling the content amount in the recommendation pool.

Disclosure of Invention

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

In a first aspect of the present application, a control method for updating content in a content recommendation pool is provided, including:

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

according to a first corresponding relation among the inventory content amount, the number of people operating the recommended content and the number of times the recommended content is operated, when the number of people operating the recommended content is a target number of people, obtaining a second corresponding relation between the inventory content amount and the number of times the recommended content is operated;

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

controlling the amount of content in the recommendation pool and updating the content in the recommendation pool based on the target and current inventory content amounts.

In a second aspect of the present application, a control device for updating content in a content recommendation pool is provided, which includes:

the system comprises a user feedback information acquisition unit, a recommendation information acquisition unit and a recommendation information processing unit, wherein the user feedback information acquisition unit is used for acquiring user feedback information of recommended contents from an information flow platform, and the user feedback information comprises the target times of operating the recommended contents and the target number of people operating the recommended contents;

the corresponding relation determining unit is used for obtaining a second corresponding relation between the inventory content amount and the number of times of operating the recommended content when the number of people operating the recommended content is a target number of people according to a first corresponding relation among the inventory content amount, the number of people operating the recommended content and the number of times of operating the recommended content, wherein the first corresponding relation is formed by matching historical data among the recommended content;

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

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

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

and obtaining the target inventory content amount when the target income is obtained at the target times based on the second corresponding relation.

according to the second corresponding relation, obtaining a curve representing the relation between the amount of the stock content and the operation times of the recommended content;

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

determining the corresponding income of the tangent point of the straight line and the curve on the straight line as the target income;

and determining the target inventory content amount when the target income is obtained at the target times based on the inventory content amount corresponding to the tangent point in the curve.

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

determining an intermediate corresponding relation formed by historical data fitting among the inventory content amount, 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 the intermediate variable to obtain the corresponding relation among the inventory content amount, the number of people operating the recommended content and the operation frequency of the recommended content.

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

fitting historical data between the inventory content amount and 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 among the ratio of the amount of the completely operated contents, the operated times of the recommended contents and the number of people operating the recommended contents.

and when the completely operated content amount is determined to be the product of the completion rate and the stock content amount, converting the first intermediate corresponding relation and the second intermediate corresponding relation to obtain the corresponding relation among the stock content amount, the number of persons operating the recommended content and the operated times of the recommended content.

In a third aspect of the present application, a computer device is provided, which comprises a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of the first aspect when executing the program.

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

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

since the stock content amount in the recommendation pool affects the number of persons operating the recommendation content, and the stock content amount and the number of persons operating the recommendation content simultaneously affect the number of times the recommendation content is operated, the present application considers the influence of the number of persons operating the recommendation content and the number of times the recommendation content is operated at the same time when controlling the content amount in the recommendation pool, and determines a unique target stock content amount based on the historical correspondence existing between the stock content amount, the number of persons operating the recommendation content, and the number of times the recommendation content is operated, on the basis that the number of times the recommendation content is operated satisfies the requirement, and since the number of persons operating the recommendation content is a relatively stable value within a time period, the number of persons operating the recommendation content can be taken as a constant to determine the correspondence between the stock content amount and the number of times the recommendation content is operated, and after obtaining the target stock content amount, the method comprises the steps of determining the lack requirement of the stock content based on the current stock content, and making a corresponding content introduction strategy, so that the content quantity in a recommendation pool can be updated, the content quality in the recommendation pool is optimized to a certain extent, and the efficiency of a recommendation system is improved.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only the embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.

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

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

FIG. 3 is an exemplary diagram illustrating a corresponding relationship between a quantity of characterizing inventory contents and a number of times corresponding to the contents are operated according to an embodiment of the present disclosure;

FIG. 4 is an exemplary diagram of target inventory content volume for obtaining target revenue at target times, as provided by an embodiment of the present application;

fig. 5 is a schematic diagram of a corresponding relationship between the ratio of the stock content amount of the content with different structure types to the number of persons operating the recommended content and the consumption rate of the content with different content types according to the embodiment of the present application;

fig. 6 is a schematic diagram of a correspondence relationship between content amounts of different structural types of content that are completely operated under different content categories and a ratio of the number of times that recommended content is operated to the number of persons who operate the recommended content, provided by an embodiment of the present application;

FIG. 7 is a diagram illustrating a corresponding relationship between an amount of inventory content, a number of people who operate recommended content, and a number of times the recommended content has been operated according to an embodiment of the present application;

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

FIG. 9 is a schematic structural diagram of a control apparatus for updating content in a content recommendation pool in an embodiment of the present application;

fig. 10 is a schematic structural diagram of a computing device in an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions in the embodiments of the present application will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by one of ordinary skill in the art from the embodiments given herein without making any creative effort, shall fall within the scope of the claimed protection. In the present application, the embodiments and features of the embodiments may be arbitrarily combined with each other without conflict. Also, while a logical order is shown in the flow diagrams, in some cases, the steps shown or described may be performed in an order different than here.

The terms "first" and "second" in the description and claims of the present application and the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the term "comprises" and any variations thereof, which are 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 steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus. The "plurality" in the present application may mean at least two, for example, two, three or more, and the embodiments of the present application are not limited.

In addition, the term "and/or" herein is only one kind of association relationship describing an associated object, and means that there may be three kinds of relationships, for example, a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" in this document generally indicates that the preceding and following related objects are in an "or" relationship unless otherwise specified.

In order to facilitate those skilled in the art to better understand the technical solutions of the present application, the following description refers to the technical terms of the present application.

1. Information flow: the information flow is a content flow which can be browsed in a scrolling way; these content streams may appear in tiles that are similar in appearance, displayed next to each other. For example, the information stream may be an edit culled information stream (e.g., an article or news listing) or product details (e.g., a product listing, a service listing, etc.);

2. an information flow platform: the system comprises an information flow platform, a social contact platform, a video platform, an information platform, a search platform and the like, wherein the information flow platform is used for bearing information flow and displaying the information flow on the information flow platform;

3. c end: a Consumer end, which is a client used by consumers and personal terminal users generally, logs in a platform through C ends of different information flow platforms, and consumes contents displayed on the platform, wherein the specific ways in which the users consume the contents are many and are expressed as various operation behaviors, and any operation of the users on the contents may form consumption, such as operation behaviors of browsing, playing, commenting or forwarding and sharing, and the like;

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

5. recommendation system and content: the recommendation system is an information filtering system and is used for predicting the scores or preferences of users on articles and recommending articles which the users are interested in to the users, in the embodiment of the application, the recommendation system recommends stock contents in a recommendation pool to an information flow platform according to a certain rule, the contents in the embodiment of the application mainly refer to contents recommended to the users through the recommendation system and can include information, short videos, music, news, books, application programs and other types; the content recommended by the recommendation system to the information flow platform in the historical data is called recommended content.

6. Vv (view), pv (pageview), and pn (quantile);

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

7. click on uv (unique viewer): the number of people consuming the content is the number of people operating the recommended content in the embodiment of the application;

8. content that is completely consumed and amount of content that is completely consumed: the fully consumed content is defined as PV > Pn content, and the quantity of the fully consumed content is the quantity of the fully consumed content;

the fully consumed content is obtained by the following process:

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

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

The following explains the concept of the present application.

In the related art, the stock content of the recommendation pool is mainly generated by the following techniques:

content publishing → machine review → manual review → content launching → C end special filtering rule, finally obtaining the stock content in the recommendation pool;

the content sending refers to that a user creates content on an information flow platform or an editing team is built to create content and the like; machine review and manual review are to screen out some content which does not meet the requirements and carry out preliminary quality evaluation, wherein one specific quality evaluation mode is to score the content quality, fit a score by utilizing relevant characteristics based on a scoring model, and filter low-quality and poor-quality content according to the score; the manual review also comprises the steps of combining the specific recommended scenes and the service targets, and performing some manual interventions such as adjusting diversity and the like; the content is enabled by publishing the content to the information flow platform, and further filtering the content through a special filtering rule of the C terminal, for example, according to feedback data of a recommendation algorithm, so as to finally obtain stock content in the recommendation pool.

Although the stock content in the recommendation pool can be obtained according to the above-mentioned manner in the prior art, how to determine the stock content amount in the recommendation pool, the content architecture of the recommendation pool, and the like, there is no specific solution at present, the content in the recommendation pool is divided into a plurality of different content categories and different structure types, the content amount of each structure type in each content category is controlled subjectively by the operation and maintenance personnel of the recommendation pool according to some feedback information of the user, which may cause the content amount in the recommendation pool to be inaccurate, the stock content amount in the recommendation pool is related to the cost, the feedback information of the user, such as the number of times the recommendation content is operated, is related to the income, the amount of the content in the recommendation pool may also affect the benefit of the information flow platform after directly affecting the experience of the user, if the amount of the whole or a certain content category in the recommendation pool is small, the recommendation quality of the recommendation system is affected, so that the user experience is reduced, and the profit of the information flow platform is reduced, while when the number of the whole or a certain content category in the recommendation pool is large, the feedback information of the user tends to be stable due to limited consumption of the user, and at this time, the cost is increased due to the increase of the number of the stock content, so that the profit of the information flow platform is reduced.

In order to control the content amount in the recommendation pool and further improve the recommendation quality of the recommendation system, an embodiment of the present application provides a control method, an apparatus, a device, and a storage medium for updating content in the content recommendation pool, where the user feedback information of the recommended content includes a target number of times that the recommended content is operated and a target number of people who operate the recommended content, the target number of times that the recommended content is operated is history data of the number of times that the recommended content is operated, which is obtained from an information flow platform in the embodiment of the present application, and the target number of people who operate the recommended content is history data of the number of people who operate the recommended content, which is obtained from the information flow platform in the embodiment of the present application. Since the stock content amount in the recommendation pool affects the number of persons operating the recommendation content, and the stock content amount and the number of persons operating the recommendation content affect the number of times the recommendation content is operated at the same time, the applicant needs to consider the influence of the number of persons operating the recommendation content and the number of times the recommendation content is operated at the same time when controlling the content amount in the recommendation pool, and therefore, the applicant determines the only target stock content amount on the basis that the number of times the recommendation content is operated satisfies the requirement, considering that the number of persons operating the recommendation content is a relatively stable value in a period of time, the number of persons operating the recommendation content can be regarded as a constant, thereby determining the correspondence between the stock content amount and the number of times the recommendation content is operated, i.e. a number of different amounts of stock content and a corresponding number of different recommended content operations.

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

In order to better understand the technical solution provided by the embodiment of the present application, some brief descriptions are provided below for application scenarios to which the technical solution provided by the embodiment of the present application is applicable, and it should be noted that the application scenarios described below are only used for illustrating the embodiment of the present application and are not limited. In 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 in which the control method for updating content in a content recommendation pool in the embodiment of the present application is applied. In the 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 the recommendation pool. Each terminal device is connected with the server 104 in a communication manner, wherein each terminal is provided with a terminal C of a different information flow platform, each terminal device can send content to the server 104 to store the content in a recommendation pool served by the server 104, each terminal simultaneously needs to send feedback information of a user on the information flow platform to the server 104, and simultaneously can receive the recommended content sent by the server 104.

Taking an information flow platform of a short video type as an example, the server 104 sends the recommended content in the recommendation pool to the information flow platforms of the short video type of the plurality of terminal devices through the recommendation system, and the server 104 obtains the user feedback information of the recommended content on each information flow platform from the plurality of terminal devices.

Taking an information flow platform of an information type as an example, the server 104 sends the recommended content in the recommendation pool to information flow platforms of a plurality of terminal devices through a recommendation system, and the server 104 obtains user feedback information of the recommended content on each information flow platform from the plurality of terminal devices.

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 providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a CDN (Content Delivery Network), a big data and artificial intelligence platform, and the like. The

terminal devices

101, 102, 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.

To further illustrate the technical solutions provided by the embodiments of the present application, the following detailed description is made with reference to the accompanying drawings and the detailed description. Although the embodiments of the present application provide method steps as shown in the following embodiments or figures, more or fewer steps may be included in the method based on conventional or non-inventive efforts. In steps where no necessary causal relationship exists logically, the order of execution of the steps is not limited to that provided by the embodiments of the present application. The method can be executed in sequence or in parallel according to the method shown in the embodiment or the figure when the method is executed in an actual processing procedure or a device.

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 control method for updating the content in the content recommendation pool provided by the embodiment of the application is shown in fig. 2, and the flowchart shown in fig. 2 is described as follows.

Step S201, obtaining user feedback information of the recommended content from an information flow platform, wherein the user feedback information comprises the target times of operating the recommended content and the target number of people operating the recommended content;

the recommended content is a content that the recommendation system sends to the information flow platform through a certain recommendation rule, and is used for the user to consume, it should be noted that, in the embodiment of the present application, different types of information flow platforms are included, if it is necessary to control the entire content volume in the recommendation pool, user feedback information of all recommended contents can be obtained from all types of information flow platforms, optionally, if it is necessary to control the content volume of different content categories in the recommendation pool, user feedback information of the recommended contents of different content categories can be respectively obtained from all types of information flow platforms, and similarly, if it is necessary to control the content volume of different structure types in the recommendation pool, user feedback information of the recommended contents of different structure types can be respectively obtained from all types of information flow platforms, as another optional implementation manner, for example, if the content amount of the short video type information flow platform in the recommendation pool needs to be controlled, user feedback information of all types of recommended content can be obtained from the short video type information flow platform, and specifically, a person skilled in the art can set the recommended content according to actual requirements, which is not limited herein.

In the embodiment of the application, the user feedback information is data information sent by an information flow platform, user consumption operation of recommended content correspondingly increases user feedback information such as the number of times that the recommended content is operated and the number of target persons who operate the recommended content, specifically, the stock content amount and the user feedback information may be data obtained by taking a preset time period as a statistical period, or may be an average value of data in the statistical period, and may be, but are not limited to, taking a day as a unit, as an optional implementation manner, if ten days are taken as the statistical period and the stock content amount does not change within ten days, the total historical data of the user feedback information within ten days may be counted, and if the stock content amount changes within ten days, the daily average value of the stock content amount within ten days and the daily average value of the user feedback information within ten days may be counted.

Step S202, according to a first corresponding relation among the inventory content amount, the number of people operating the recommended content and the number of times the recommended content is operated, when the number of people operating the recommended content is a target number of people, obtaining a second corresponding relation between the inventory content amount and the number of times the recommended content is operated;

the number of times the recommended content is operated is related to both the number of persons who operate the recommended content and the stock content amount, and both the increase in the content stock amount and the number of persons who operate the recommended content can increase the number of times the recommended content is operated to some extent.

The embodiment of the application can determine the corresponding relation among the inventory content amount, the number of people operating the recommended content and the operation times of the recommended content by the following modes:

determining an intermediate corresponding relation formed by historical data fitting among the inventory content amount, 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 an intermediate variable to obtain the corresponding relation among the inventory content amount, the number of people operating the recommended content and the number of times the recommended content is operated;

it is also possible to directly fit the historical data of the amount of stock content, the historical data of the number of times the recommended content has been operated, and the historical data of the number of people who operated the recommended content to obtain a correspondence relationship, however, since the three-dimensional correspondence relationship is obtained by directly fitting the amount of the stock content, the number of times the recommended content is operated, and the number of persons operating the recommended content as variables, in the fitting process, a large error exists, and the fitting effect is poor, so in the embodiment of the present application, a mode is adopted in which an intermediate correspondence relationship, which is obtained by fitting historical data between the stock content amount, the number of people who operate the recommended content, and the number of times the recommended content is operated, is determined first, and then the intermediate correspondence relationship is converted based on an intermediate variable to obtain a correspondence relationship among the stock content amount, the number of people who operate the recommended content, and the number of times the recommended content is operated.

The user feedback information may further include a completion rate and a fully operated content amount, and the completion rate is a proportion of the fully operated content amount in the stock content amount, for example, the stock content amount is 100, and the completion rate is 90% if the fully operated content amount is 90%. In this embodiment of the present application, the intermediate variable may be an end consumption rate alone or a fully operated content amount alone, and since the end consumption rate and the fully operated content amount are related to the inventory content amount, the end consumption rate and the fully operated content amount may also be simultaneously used as the intermediate variable;

as an alternative embodiment, a first intermediate corresponding relationship may be first fit according to history data among the stock content amount, the number of persons operating the recommended content, and the completion rate, a second intermediate corresponding relationship may be fit according to history data among the content amount fully operated, the number of times the recommended content is operated, and the number of persons operating the recommended content, and the first intermediate corresponding relationship and the second intermediate corresponding relationship may be converted to obtain a corresponding relationship among the stock content amount, the number of persons operating the recommended content, and the number of times the recommended content is operated based on the relationship among the completion rate, the content amount fully operated, and the stock content amount; it should be noted that, if there are three variables to perform function fitting, the fitting result is a three-dimensional corresponding relationship, and the fitting effect is poor, so in the process of fitting the intermediate corresponding relationship in the present application example, one variable may be obtained according to the ratio of the historical data of the two variables, so as to obtain a two-dimensional intermediate corresponding relationship.

Since the number of users operating the recommended content tends to be stable for a certain period of time, that is, the number of people operating the recommended content varies little within a certain period of time or the amount of the stock content varies within a certain range, the corresponding relationship with the number of people operating the recommended content may not be considered when determining the amount of the stock content, but since the influence of the number of people operating the recommended content on the number of times the recommended content is operated is large, if history data is directly fitted between the amount of the stock content and the number of people operating the recommended content, a large error may occur, and therefore, in the embodiment of the present application, the corresponding relationship among the amount of the stock content, the number of people operating the recommended content, and the number of times the recommended content is operated may be obtained first, and the target number of people operating the recommended content may be substituted as a constant into the amount of the stock content, based on the target number of people operating the recommended content obtained from the information flow platform, The corresponding relation between the number of persons operating the recommended content and the number of times the recommended content is operated is determined.

In the embodiment of the present application, the correspondence between the amount of the stock content and the number of times the content is operated is shown in fig. 3, fig. 3 is a graph representing the relationship between the amount of the stock content and the number of times the corresponding recommended content is operated, the abscissa is the amount of the stock content, the ordinate is the number of times the recommended content is operated, and it should be noted that fig. 3 represents only the approximate correspondence between the amount of the stock content and the number of times the corresponding recommended content is operated, and the graph in fig. 3 may be changed such as rising, falling, or moving left and right based on the coordinate axis as the history data in the statistical period changes or the number of target persons who operate the recommended content changes.

Step S203, obtaining a target inventory content amount corresponding to the target times based on the second corresponding relation;

the correspondence between the amount of stock content and the number of times the recommended content has been operated can only obtain the amount of different stock content and the corresponding number of times the different recommended content has been operated, can only obtain the constraint relationship between the amount of stock content and the number of times the recommended content has been operated, however, the unique target amount of the stock content cannot be determined, and in the embodiment of the present application, by limiting the target number of times the recommended content is operated, so that a corresponding target amount of the in-stock content is obtained according to the target number of times the recommended content has been operated, the target number of times that the recommended content is operated may be, but is not limited to, a preset value or a value correspondingly determined according to the target profit, and optionally, other index values related to the target number of times the recommended content has been operated may also be used to determine the target number of times the recommended content has been operated, and further determine the corresponding target amount of the stock content.

In the embodiment of the present application, based on the correspondence between the amount of the stock content and the number of times the recommended content is operated, a manner of obtaining the target amount of the stock content when the target revenue is obtained by the target number of times is as follows:

the profit in the embodiment of the present application is related to both the number of times the recommended content is operated and the amount of the stock content, if only the corresponding relationship between the profit, the number of times the recommended content is operated and the amount of the stock content is determined, the corresponding image is a straight line in fig. 4, the straight line in fig. 4 represents the relationship between the historical target number and the highest profit, where the abscissa is the amount of the stock content, the ordinate is the number of times the content is operated, the intercept of the straight line can represent the profit, it should be noted that the slope of the straight line is constant, after the intercept is determined, the profits corresponding to any one target number of times on the straight line are equal, the straight line can be raised or lowered based on the coordinate axis, at this time, the profit of the information flow platform is correspondingly increased or decreased, and the larger the intercept of the straight line is, the higher the profit of the information flow platform is; in the present application, the target profit may be, but is not limited to, the maximum profit or the profit greater than the preset threshold, as can be seen from fig. 4, a point where the straight line and the curve intersect satisfies a constraint relationship between the amount of the stock content and the number of times the recommended content is operated, and the profit corresponding to the tangent point on the straight line when the straight line is tangent to the curve is determined as the target profit because the intercept of the straight line when the straight line is tangent to the curve is maximum, the maximum profit can be achieved, and a unique tangent point can be determined, and the ordinate of the tangent point represents the target number of times, and then the target amount of the stock content when the target profit is obtained with the target number of times can be determined based on the amount of the stock content corresponding to the tangent point on the curve.

In the embodiment of the application, after the corresponding relationship between the inventory content amount and the number of times the recommended content is operated is obtained, if the corresponding target inventory content amount is determined based on the preset target number of times and the target profit in the preset time period, the corresponding relationship can be fitted based on the same inventory content amount, the number of people operating the recommended content and the number of times the recommended content is operated, and no refitting is needed, the target number of people operating the recommended content obtained from the information leveling platform can be directly substituted into the corresponding relationship fitted by the historical data among the inventory content amount, the number of people operating the recommended content and the number of times the recommended content is operated, so that the corresponding relationship between the inventory content amount and the number of times the recommended content is operated is obtained;

as another alternative embodiment, when the target amount of stock content is determined according to the target number of times within a preset time period, the same corresponding relationship between the amount of stock content and the number of times the recommended content is operated may be used, and of course, each time the target amount of stock content is determined, the corresponding relationship may be obtained by fitting the amount of stock content, the number of persons who operate the recommended content, and the number of times the recommended content is operated again according to the history data among the amount of stock content, the number of persons who operate the recommended content, and the number of times the recommended content is operated according to the target number of persons who operate the recommended content.

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

After the target inventory content amount is obtained, the operation and maintenance staff of the recommendation pool may decrease or increase the content amount in the recommendation pool according to the comparison result between the target inventory content amount and the current inventory content amount, if the target inventory content amount is higher than the current inventory content amount, it indicates that the current inventory content amount is too small and the corresponding inventory content needs to be introduced, and quantitatively introduces the corresponding inventory content according to the difference between the target inventory content amount and the current inventory content amount, and if the target inventory content amount is lower than the current inventory content amount, it indicates that the current inventory content is too large, and the operation and maintenance staff may decrease the inventory content according to the difference between the current inventory content amount and the target inventory content amount.

The following describes, with reference to specific embodiments, a method for determining a correspondence between an amount of stock content and a number of times a recommended content has been operated, and a method for obtaining a target amount of stock content when a target profit is obtained with a target number of times.

Determining an intermediate corresponding relationship formed by fitting historical data among the inventory content amount, the number of people operating the recommended content and the number of times the recommended content is operated, and converting the intermediate corresponding relationship based on an intermediate variable to obtain the corresponding relationship among the inventory content amount, the number of people operating the recommended content and the number of times the recommended content is operated, wherein a specific implementation mode is as follows:

since the consumption rate is a ratio of the amount of the completely operated contents to the amount of the stock contents, the intermediate correspondence may be converted to obtain a correspondence between the amount of the stock contents, the number of persons who operate the recommended contents, and the number of times the recommended contents are operated, by using the consumption rate and the amount of the completely operated contents as intermediate variables, respectively;

step 1: determining a first intermediate correspondence between the rate of completion, the amount of the stock content, and the number of people operating the recommended content, as shown in formula 1;

performing function fitting on the historical data of the consumption rate, the stock content amount and the number of people operating the recommended content to obtain a first intermediate corresponding relation, wherein the ratio of the stock content amount to the number of people operating the recommended content is taken as an independent variable x₁The consumption rate is used as a dependent variable y₁Fitting is carried out through the related historical data of the information flow platform to obtain a first intermediate corresponding relation between the independent variable and the dependent variable, and a coefficient of the first intermediate corresponding relation can be obtained; the specific formula is expressed as follows:

x₁UV-click ═ N/click

y₁Rate of complete elimination

y₁＝a*x₁ ^b (1)

Wherein, y₁To complete the elimination rate, x₁The ratio of the amount of stock content to the number of persons operating the recommended content, N is the amount of stock content, a and b are coefficients obtained by function fitting, and are specific numerical values, since x is associated with FIG. 1₁Increase of y₁The consumption rate is exponentially reduced, so b is a numerical value less than zero, and the formula (1) represents the historical corresponding relation among different consumption rates, different stock content amounts and the ratio of the number of people operating the recommended content, and particularly shows that the consumption rate is exponentially increased along with the increase of the ratio of the stock content amount to the number of people operating the recommended content;

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

FIG. 5 is a diagram of a first intermediate correspondence, which is a power function. The first intermediate corresponding relation lists the relation between the stock content amount of the contents with different structure types under different content types and the ratio and the complete consumption rate of the number of people operating the recommended contents, wherein the abscissa is x₁Ordinate is y₁As can be seen from fig. 5, since the contents of different structure types in different content categories are different in popularity of users, even though the ratio of the stock content amount to the number of people who operate the recommended content is the same, the corresponding consumption rates are different, but the line segments corresponding to the contents of different structure types in different content categories have the same trend, and the larger the ratio of the stock content amount to the number of people who operate the recommended content is, the smaller the corresponding consumption rate is, that is, the smaller the content amount that is completely operated in the recommendation pool is, because the larger the ratio of the stock content amount to the number of people who operate the recommended content is, the larger the stock content amount is or the smaller the number of people who operate the recommended content is, the consumption capacity of the user is limited at this time, and the content amount that is completely operated in the stock content is reduced.

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

performing function fitting on the fully operated content quantity, the operated times of the recommended content and the historical data of the number of people operating the recommended content to obtain a second intermediate corresponding relation, wherein the fully operated content quantity is taken as an independent variable x₂The ratio of the number of times the recommended content is operated to the number of persons operating the recommended content is used as the dependent variable y₂Fitting is carried out through the related historical data of the information flow platform to obtain a second intermediate corresponding relation, and a coefficient of the second intermediate corresponding relation can be obtained; the specific formula is expressed as follows:

x₂the amount of content that is fully manipulated

y₂VV/click UV

y₂＝c*x₂ (3)

Wherein, y₂For the ratio of the number of times the recommended content is operated to the number of persons operating the recommended content, x₂The method comprises the steps that the content quantity to be fully operated is the product of the stock content quantity and the complete consumption rate, c is a coefficient obtained through function fitting, is a specific numerical value and is a numerical value larger than 1, the formula (4) represents the different fully operated content quantities, and the historical corresponding relation of the operated times of different recommended contents and the ratio of the number of people operating the recommended contents is specifically shown in the way that the ratio of the operated times of the recommended contents to the number of people operating the recommended contents linearly increases along with the increase of the fully operated content quantity;

in order to better show the historical correspondence between the ratio of the number of times the recommended content is operated to the number of people who operate the recommended content and the amount of the content that is fully operated, the actual meaning represented by each letter is substituted into the formula (3) to obtain the formula (4):

as shown in fig. 6, the image of the second intermediate correspondence relationship is a linear function, and the second intermediate correspondence relationship lists the fully operated content amount of the contents with different structure types under different content categories and the relationship between the number of times the recommended content is operated and the ratio of the number of persons operating the recommended content, wherein the abscissa is x₂Ordinate is y₂As can be seen from fig. 6, since contents of different structure types are different in popularity among users in different content categories, even if the amount of the completely-operated contents is the same, the ratio of the number of times the corresponding recommended content is operated to the number of persons who operate the recommended content is different, but the tendency of the images corresponding to the contents of different structure types in different content categories is the same, and the larger the amount of the completely-operated contents is, the more the images are pushedThe larger the number of times the referrer content is operated.

And step 3: determining the corresponding relation among the amount of the stock content, the number of persons operating the recommended content and the number of times the recommended content is operated, as shown in formula (6);

due to y₁To complete the extinction rate, and y₁The product of the amount of content in inventory is the amount of content that is fully manipulated, i.e., x₂Therefore, formula (5) can be obtained by substituting formula (1) into formula (3):

obtaining formula (6) after the formula (5) is deformed:

in the formula (6), a, b and c are coefficients obtained in the fitting process; the formula (6) represents the historical corresponding relation among different stock content amounts, the operated times of different recommended contents and the number of people operating the recommended contents, and b-1 is smaller than zero because b is a numerical value smaller than zero, so that the operated times of the recommended contents are increased linearly along with the exponential increase of the stock content amounts and the number of people operating the recommended contents;

as shown in fig. 7, the three-dimensional relationship image obtained according to the formula (6), where the x-axis is the number of people who operate the recommended content, the y-axis is the amount of stock content, and the z-axis is the number of times that the recommended content is operated, as can be obtained from fig. 7, on the basis that the amount of stock content is fixed, when the number of people who operate the recommended content of the information flow platform increases, the number of times that the recommended content is operated increases significantly, and on the basis that the number of people who operate the recommended content is fixed, although the number of times that the recommended content is operated gradually increases as the amount of stock content increases, the increase of the number of times that the recommended content is operated tends to be gentle due to the limited consuming ability of the user; it should be noted that the derivation 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 derivation process according to actual requirements, for example, in another alternative implementation manner, the extinction rate may be used as an intermediate variable, first history data between the extinction rate and the ratio of the stock content amount to the number of persons operating the recommended content is fitted to form a first intermediate corresponding relationship, then history data between the extinction rate and the ratio of the number of times the recommended content is operated and the ratio of the number of persons operating the recommended content is fitted to form a second intermediate corresponding relationship, and then based on the extinction rate, the first intermediate corresponding relationship and the second intermediate corresponding relationship are converted to obtain the corresponding relationship between the stock content amount and the number of times the recommended content is operated.

As can be seen from the above analysis, when the number of persons operating the recommended content is relatively stable, the number of consumption times by increasing the amount of the stock content converges marginally, and at this time, the number of persons operating the recommended content in the formula (6) is regarded as a constant, and the correspondence between the amount of the stock content and the number of times the recommended content is operated is obtained, as shown in the formula (7):

wherein, a' ═ c)/click UV^b-1；

Formula (7) represents the historical correspondence between different stock content amounts and the number of times the recommended content is operated, and is also a constraint condition between the stock content amounts and the number of times the recommended content is operated, the number of times the recommended content is operated increases linearly with the exponential increase of the stock content amounts, and the image corresponding to formula (7) is shown in fig. 3, as can be seen from fig. 3, the number of times the recommended content is operated increases faster first and then becomes slower, which is caused by the limited consuming ability of the user.

Equation (8) is the kobub-douglas production function:

Y＝A(t)L^1-εK^ε (8)

wherein, Y is an industry total value, corresponding to the number of times the recommended content is operated in the embodiment of the present application, a (t) is a comprehensive technical level, L is the number of invested labor forces, corresponding to the number of people operating the recommended content in the embodiment of the present application, K is the invested capital, corresponding to the stock content amount of the present application, and the cobb-douglas production function verifies to some extent that the stock content amount and the number of times the recommended content is operated satisfy a certain economic relationship.

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

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

income is K yuan/consumption;

cost M dollars/piece of content;

then the benefit formula can be derived as:

income-cost K VV-M N (9)

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

(vi) VV + N + m + yield (10)

The formula (10) is a linear function, since k ' ═ M/N is a constant and M ' ═ 1/k is a constant, the slope of the target relational expression is determined, the intercept is M ' × revenue, and the formula (10) represents the corresponding relationship among different inventory content amounts, the number of times different recommended contents are operated and the corresponding revenue;

since the number of times the recommended content is operated and the amount of the stock content both satisfy the target relational expression and satisfy the constraint condition, the point where the target relational expression and the constraint condition intersect is the point that satisfies the condition, the abscissa of the intersecting point is the amount of the stock content, 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 relational expression corresponding to the constraint condition are tangent, the intercept of the target relational expression is the largest, and since the intercept is the product of the profit and the constant, the larger the intercept is, the higher the profit is, and the tangent point is the optimal solution of cost-profit maximization.

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

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

the user feedback information comprises the target number of times that the recommended content is operated, the target number of people who operate the recommended content, the consumption rate and the number of times of complete operation.

The details of this step can be found in the above description, and will not be repeated here.

Step S802, fitting historical data between the inventory content amount and the number of people operating the recommended content and the consumption rate to form a first intermediate corresponding relation;

step S803, fitting a second intermediate corresponding relation according to historical data among the fully operated content amount, the operated times of the recommended content and the ratio of the number of people operating the recommended content;

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

step S805, obtaining a second corresponding relation between the amount of the stock content and the operated times of the recommended content when the number of people who operate the recommended content is a target number;

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

step S807, obtaining a straight line representing the relation between the historical target times and the highest profit;

step S808, determining the income corresponding to the tangent point on the straight line when the straight line is tangent to the curve as the target income;

step S809 determines the target stock content amount when the target profit is obtained at the target number of times, based on the stock content amount corresponding to the tangent point on the curve.

Based on the same inventive concept, the embodiment of the present application provides a control device for updating content in a content recommendation pool, where the control device for updating content in the content recommendation pool may 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, and 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, a 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 inventory 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 the recommended content from the information flow platform, where the user feedback information includes a target number of times that the recommended content is operated and a target number of people who operate the recommended content;

a correspondence determining unit 902, configured to obtain, according to a first correspondence between the amount of the stock content, the number of people who operate the recommended content, and the number of times the recommended content is operated, a second correspondence between the amount of the stock content and the number of times the recommended content is operated when the number of people who operate the recommended content is a target number of people;

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

a control unit 904 for controlling the number of contents in the recommendation pool and updating the contents in the recommendation pool based on the target inventory content amount and the current inventory content amount.

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

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

All relevant contents of each step involved in the embodiment of the control method for updating the content in the content recommendation pool can be cited to the functional description of the functional module corresponding to the control device for updating the content in the content recommendation pool in the embodiment of the present application, and are not described herein again.

The division of the modules in the embodiments of the present application is schematic, and only one logical function division is provided, and in actual implementation, there may be another division manner, and in addition, each functional module in each embodiment of the present application may be integrated in one processor, may also exist alone physically, or may also be integrated in one module by two or more modules. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode.

Based on the same inventive concept, an embodiment of the present application provides a computing device, for example, the server 104 in fig. 1, which 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, 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, a specific connection medium between the processor 1001 and the memory 1002 is not limited in the embodiment of the present application, in fig. 10, a connection between the processor 1001 and the memory 1002 through a bus 1000 is taken as an example, the bus 1000 is represented by a thick line in fig. 10, and a connection manner between other components is only schematically illustrated and is not taken as a limitation. 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 ease of illustration, but does not represent only one bus or one type of bus.

In the 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 foregoing method for recommending content by executing the computer program stored in the memory 1002.

The processor 1001 is a control center of the computing device, and may connect various parts of the entire computing device by using various interfaces and lines, and perform various functions of the computing device and process data by executing or executing instructions stored in the memory 1002 and calling data stored in the memory 1002, thereby performing overall monitoring of the computing device. Optionally, the processor 1001 may include one or more processing modules, and the processor 1001 may integrate an application processor and a modem processor, where the processor 1001 mainly processes an operating system, a user interface, an application program, and the like, and the modem processor mainly processes wireless communication. 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, or 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), a digital signal processor, an application specific integrated circuit, a field programmable gate array or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or the like, that implements or performs the methods, steps, and logic blocks disclosed in embodiments of the present application. A 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 directly implemented by a hardware processor, or may be implemented by a combination of hardware and software modules in a processor.

Memory 1002, which is a non-volatile computer-readable storage medium, may 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, a flash Memory, a hard disk, a multimedia card, a card-type Memory, a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Programmable Read Only Memory (PROM), a Read Only Memory (ROM), a charge Erasable Programmable Read Only Memory (EEPROM), a magnetic Memory, a magnetic disk, an optical disk, and so on. The 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 the embodiments of the present application may also be circuitry or any other device capable of performing a storage function for storing program instructions and/or data.

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

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

The basic input/output system 1004 includes a display 1009 for displaying information and an input device 1010 such as a mouse, keyboard, etc. for a user to input information. Wherein a display 1009 and input device 1010 are connected to the processor 1001 via the basic input/output system 1004, which 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, an input-output controller may also provide 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 present application, the computing device package may also be operated by a remote computer connected to the network through a network, such as the Internet. That is, the computing device may be connected to the network 1011 via the communication interface 1003 coupled to the system bus 1000, or may be connected to another type of network or remote computer system (not shown) using the communication interface 1003.

Based on the same inventive concept, the present application also provides a storage medium, which may be a computer-readable storage medium, and the storage medium stores computer instructions, which, when executed on a computer, cause the computer to execute the steps of the control method for updating the content in the content recommendation pool as described above.

Based on the same inventive concept, the embodiment of the present application further provides a chip system, where the chip system includes a processor and may further include a memory, and is configured to implement the steps of the control method for updating the content in the content recommendation pool. The chip system may be formed by a chip, and may also include a chip and other discrete devices.

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

As will be appreciated by one skilled in the art, 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, 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 changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.

Claims

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

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

according to a first corresponding relation among the inventory content amount, the number of people operating the recommended content and the number of times the recommended content is operated, and a second corresponding relation between the inventory content amount and the number of times the recommended content is operated when the number of people operating the recommended content is the target number is obtained;

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

and obtaining the target inventory content amount when the target income is obtained by the target times based on the second corresponding relation.

3. The method according to claim 2, wherein the obtaining a target amount of the content in the inventory at the time of obtaining the target revenue at the target number of times based on the second corresponding relationship specifically includes:

determining the corresponding income of the tangent point of the straight line when the straight line is tangent to the curve on the straight line, and determining the income as the target income;

and determining the target inventory content amount when the target income is obtained at the target times based on the inventory content amount corresponding to the tangent point on the curve.

4. The method according to claim 1, 2 or 3, wherein the first correspondence relationship fitted with history data among the amount of the stock content, the number of persons who operate 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 inventory content amount, the number of people operating the recommended content and the operation frequency of the recommended content.

5. The method of claim 4, wherein determining an intermediate correspondence fit from historical data between the amount of inventory content, the number of people operating the recommended content, and the number of times the recommended content was operated comprises:

6. The method according to claim 4, wherein converting the intermediate correspondence based on intermediate variables to obtain correspondence between the amount of stock content, the number of persons operating the recommended content, and the number of times the recommended content was operated comprises:

and when the completely operated content volume is determined to be the product of the consumption rate and the stock content volume, converting the first intermediate corresponding relation and the second intermediate corresponding relation to obtain the corresponding relation among the stock content volume, the number of persons operating the recommended content and the operated times of the recommended content.

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

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

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

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

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

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

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

12. The apparatus according to claim 10, wherein the correspondence determining 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 steps of the method of any of claims 1-6 are implemented when the program is executed by the processor.

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