CN117611289A

CN117611289A - Object information pushing method, device, computer equipment and storage medium

Info

Publication number: CN117611289A
Application number: CN202311643294.5A
Authority: CN
Inventors: 何雯; 何剑斌; 李一男; 成文洁
Original assignee: China Southern Power Grid Internet Service Co ltd
Current assignee: China Southern Power Grid Internet Service Co ltd
Priority date: 2023-11-30
Filing date: 2023-11-30
Publication date: 2024-02-27

Abstract

The present application relates to an object information pushing method, an object information pushing apparatus, a computer device, a storage medium and a computer program product. The method comprises the following steps: obtaining object attribute information corresponding to each resource object in a target resource interaction platform under at least two preset pushing dimensions; inputting object attribute information corresponding to each pushing dimension into a pushing evaluation value prediction model corresponding to the corresponding pushing dimension to obtain pushing evaluation value information corresponding to each resource object under each pushing dimension respectively; according to the push evaluation value information corresponding to each resource object under each push dimension and the push weight information corresponding to the corresponding push dimension, obtaining the integral push score value information corresponding to each resource object; and pushing the related information of the resource objects to the user account to be pushed according to the integral pushing score value information corresponding to each resource object. By adopting the method, the resource utilization rate in information pushing can be improved.

Description

Object information pushing method, device, computer equipment and storage medium

Technical Field

The present invention relates to the field of internet technologies, and in particular, to an object information pushing method, an object information pushing device, a computer device, a storage medium, and a computer program product.

Background

In the current society, with technological development and social progress, information technology has become an important component of modern life and production. Electronic commerce is used as a mainstream shopping mode, and convenient online shopping experience is provided for people.

If the audience of different commodities is different, the proper commodity needs to be determined for different users to push information. However, due to the problems of information overload, price fluctuation, difficulty in commodity screening and the like, in the related art, commodities suitable for users are difficult to determine according to screening results, so that proper commodity information cannot be accurately pushed to the users, and resource waste is caused when information is pushed.

Therefore, there is a problem in the related art that resource waste is excessive when information is pushed.

Disclosure of Invention

In view of the foregoing, it is desirable to provide an object information pushing method, apparatus, computer device, computer readable storage medium, and computer program product that can improve the resource utilization at the time of information pushing.

In a first aspect, the present application provides an object information pushing method, including:

obtaining object attribute information corresponding to each resource object in a target resource interaction platform under at least two preset pushing dimensions; the target resource interaction platform is a resource interaction platform currently accessed by a user account to be pushed;

Inputting object attribute information corresponding to each push dimension into a push evaluation value prediction model corresponding to the corresponding push dimension to obtain push evaluation value information corresponding to each resource object under each push dimension respectively;

according to the push evaluation value information corresponding to each resource object under each push dimension and the push weight information corresponding to the corresponding push dimension, obtaining the integral push score value information corresponding to each resource object;

and pushing the related information of the resource objects to the user account to be pushed according to the integral pushing credit value information corresponding to each resource object.

In one embodiment, the push dimension includes a push dominance difference dimension; the corresponding object attribute information under the push dominance difference dimension comprises object parameter information;

inputting the object attribute information corresponding to each push dimension into a push evaluation value prediction model corresponding to the corresponding push dimension to obtain push evaluation value information corresponding to each resource object under each push dimension, wherein the method comprises the following steps:

obtaining object parameter information corresponding to a resource object belonging to a target resource category in each resource interaction platform; the target resource category is a resource category to which a resource object in the target resource interaction platform belongs;

Determining push advantage information of each resource category in the target resource interaction platform relative to other resource interaction platforms according to the object parameter information corresponding to each resource interaction platform;

and inputting the pushing dominance information corresponding to each resource object into a dominance difference evaluation value prediction model corresponding to the pushing dominance difference dimension to obtain dominance difference evaluation value information corresponding to each resource object under the pushing dominance difference dimension.

In one embodiment, the push dominance level information includes a push dominance level;

inputting the push dominance information corresponding to each resource object to a dominance difference evaluation value prediction model corresponding to the push dominance difference dimension, to obtain dominance difference evaluation value information corresponding to each resource object under the push dominance difference dimension, including:

according to the push dominance grade of each resource object, giving dominance difference evaluation value information corresponding to each resource object through the dominance difference evaluation value prediction model;

the dominance difference evaluation value information includes a dominance difference evaluation value; the advantage difference evaluation value and the push advantage level are in positive correlation.

In one embodiment, the push dimension includes an object parameter dimension; the object attribute information corresponding to the object parameter dimension comprises object parameter information corresponding to each object parameter type;

determining the importance degree corresponding to each object parameter type;

inputting object parameter information corresponding to each resource object into an object parameter evaluation value prediction model corresponding to the object parameter dimension, wherein the object parameter evaluation value prediction model obtains object parameter evaluation value information corresponding to each resource object under the object parameter dimension through the importance degree corresponding to each object parameter type; the object parameter evaluation value information includes an object parameter evaluation value; the object parameter evaluation value and the importance degree have a positive correlation.

In one embodiment, the inputting the object parameter information corresponding to each resource object to the object parameter evaluation value prediction model corresponding to the object parameter dimension, where the object parameter evaluation value prediction model obtains the object parameter evaluation value information corresponding to each resource object in the object parameter dimension according to the importance degree corresponding to each object parameter type, includes:

Dividing object parameter information corresponding to each resource object into different quadrants according to the importance degree corresponding to each object parameter type by adopting a four-quadrant method through the object parameter evaluation value prediction model;

determining evaluation value information of object parameter information corresponding to each resource object according to quadrants of the object parameter information corresponding to each resource object through the object parameter evaluation value prediction model;

and determining object parameter evaluation value information corresponding to each resource object under the object parameter dimension according to the evaluation value information of the object parameter information corresponding to each resource object.

In one embodiment, the push dimension includes a user behavior dimension; the corresponding object attribute information under the user behavior dimension comprises user behavior data; the user behavior data are used for recording the operation behaviors of the user account to be pushed for the resource object;

And inputting the user behavior data corresponding to each resource object into a user behavior evaluation value prediction model corresponding to the user behavior dimension to obtain user behavior evaluation value information corresponding to each resource object under the user behavior dimension.

In a second aspect, the present application further provides an object information pushing device, including:

the acquisition module is used for acquiring object attribute information corresponding to each resource object in the target resource interaction platform under at least two preset pushing dimensions; the target resource interaction platform is a resource interaction platform currently accessed by a user account to be pushed;

the input module is used for inputting the object attribute information corresponding to each pushing dimension into a pushing evaluation value prediction model corresponding to the corresponding pushing dimension to obtain pushing evaluation value information corresponding to each resource object under each pushing dimension respectively;

the evaluation module is used for obtaining the integral push score value information corresponding to each resource object according to the push evaluation value information corresponding to each resource object under each push dimension and the push weight information corresponding to the corresponding push dimension;

and the pushing module is used for pushing the resource object related information to the user account to be pushed according to the integral pushing score value information corresponding to each resource object.

In a third aspect, the present application also provides a computer device. The computer device comprises a memory and a processor, the memory storing a computer program which, when executed by the processor, implements the steps of the method described above.

In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the method described above.

In a fifth aspect, the present application also provides a computer program product. The computer program product comprising a computer program which, when executed by a processor, implements the steps of the method described above.

The object information pushing method, the device, the computer equipment, the storage medium and the computer program product are used for obtaining object attribute information corresponding to each resource object in the target resource interaction platform under at least two preset pushing dimensions; the target resource interaction platform is a resource interaction platform currently accessed by the user account to be pushed; inputting object attribute information corresponding to each pushing dimension into a pushing evaluation value prediction model corresponding to the corresponding pushing dimension to obtain pushing evaluation value information corresponding to each resource object under each pushing dimension respectively; according to the push evaluation value information corresponding to each resource object under each push dimension and the push weight information corresponding to the corresponding push dimension, obtaining the integral push score value information corresponding to each resource object; and pushing the related information of the resource objects to the user account to be pushed according to the integral pushing score value information corresponding to each resource object.

In this way, according to the object attribute information corresponding to each resource object under at least two preset pushing dimensions, the pushing evaluation value information of each resource object is comprehensively considered by the multidimensional factor of each resource object, so that the integral pushing evaluation value information corresponding to each resource object can be obtained, the pushing value of each resource object in the target resource interaction platform is comprehensively and accurately estimated, the relevant information of the appropriate resource object is accurately pushed to the user account to be pushed, the probability of clicking the pushed resource object information by the user account to be pushed is improved, the resource waste during information pushing can be reduced, and the resource utilization rate during information pushing is effectively improved.

Drawings

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

FIG. 1 is a flowchart of an object information pushing method according to an embodiment;

FIG. 2 is a flowchart illustrating a step of obtaining the dominant variance estimation value information in one embodiment;

FIG. 3 is a flowchart illustrating steps for obtaining object parameter evaluation value information in one embodiment;

FIG. 4 is a flowchart of an object information pushing method according to another embodiment;

FIG. 5 is a block diagram of an object information pushing device according to one embodiment;

fig. 6 is an internal structural diagram of a computer device in one embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.

It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the foregoing figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the disclosure described herein may be capable of operation in sequences other than those illustrated or described herein. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as detailed in the accompanying claims.

In one embodiment, as shown in fig. 1, an object information pushing method is provided, where the method is applied to a terminal to illustrate the method, it is understood that the method may also be applied to a server, and may also be applied to a system including the terminal and the server, and implemented through interaction between the terminal and the server.

In this embodiment, the method includes the steps of:

step S110, object attribute information corresponding to each resource object in the target resource interaction platform under at least two preset pushing dimensions is obtained.

The target resource interaction platform is a resource interaction platform currently accessed by the user account to be pushed.

The resource interaction platform is a platform for resource interaction. For example, the resource interaction platform may be an e-commerce platform upon which merchants and consumers may conduct online transactions for resources. In the following embodiments, a resource interaction platform is taken as an e-commerce platform as an example for illustration.

The resource object may be an item that obtains ownership through a network, including at least one of a virtual item and a physical item. The virtual items may include, but are not limited to, at least one of account numbers, funds, avatar products, virtual rechargeable cards, game pieces, virtual and encrypted money, service rights for online or offline services (e.g., membership of online platforms, discount coupons for offline stores), and the like. The physical item may be any item that may be in the physical form of a user, and may include, for example, but not limited to, an electronic product, a toy, a artwork, a signed photo, or the like.

Embodiments of the present disclosure are not limited in terms of the particular form of the resource object. Accordingly, the related information of the resource object can be published to the resource interaction platform. The related information of the resource object may include object attribute information.

The user account to be pushed is a user account to be pushed with the relevant information of the resource object.

In a specific implementation, a resource interaction platform currently accessed by a user account to be pushed can be used as a target resource interaction platform, and a terminal can acquire object attribute information corresponding to each resource object in the target resource interaction platform under at least two preset pushing dimensions.

The pushing dimension may be a dimension factor to be considered when pushing related information of the resource object. The preset at least two push dimensions may include at least a resource object own dimension and a user dimension.

For example, taking a resource object as a commodity of the e-commerce platform as an example, the dimension of the resource object may be a commodity parameter dimension, and the dimension of the user may be a behavior dimension (for example, browsing, collecting, etc. behaviors) of the user account to be pushed on the commodity.

Step S120, inputting object attribute information corresponding to each pushing dimension into a pushing evaluation value prediction model corresponding to the corresponding pushing dimension to obtain pushing evaluation value information corresponding to each resource object under each pushing dimension.

The push evaluation value information may also be named as push evaluation weight information in practical application. And judging a specific corresponding weight (evaluation value) for the object attribute information of the resource object under each pushing dimension by setting a modeling scoring standard, thereby obtaining pushing evaluation value information.

In a specific implementation, different push dimensions adopt different push evaluation value prediction models. The terminal can input the object attribute information corresponding to each pushing dimension into a pushing evaluation value prediction model corresponding to the corresponding pushing dimension to obtain pushing evaluation value information corresponding to each resource object under each pushing dimension.

Step S130, according to the push evaluation value information corresponding to each resource object under each push dimension and the push weight information corresponding to the corresponding push dimension, obtaining the integral push score value information corresponding to each resource object.

The push weight information is quantized value information for measuring the importance degree of the corresponding push dimension in the evaluation system. Can be determined by social investigation, big data analysis and expert review.

In a specific implementation, the terminal can obtain push weight information corresponding to each push dimension, so that integral push score value information corresponding to each resource object can be obtained according to push evaluation value information corresponding to each resource object under each push dimension and push weight information corresponding to the corresponding push dimension.

In an optional embodiment of the present application, for any resource object, the terminal may perform weighted summation on push evaluation value information corresponding to each push dimension of the any resource object according to push weight information corresponding to each push dimension, to obtain overall push score value information corresponding to the any resource object. Thus, based on the same method, the terminal can obtain the integral push score value information corresponding to each resource object.

In practical application, the method for carrying out weighted summation on push evaluation value information corresponding to any resource object under each push dimension respectively according to push weight information corresponding to each push dimension can be realized by calculating mathematical expectations corresponding to the resource objects.

For example, the push evaluation value information includes a push evaluation value; the push weight information comprises a push weight value; the overall push score information includes an overall push score. If the push evaluation value of the resource object under each push dimension is X1, X2, X3 … … and XN; the corresponding push weights are P1, P2, P3 and … … PN; n is the number of preset push dimensions.

Then, the mathematical expectation value corresponding to the resource object

The calculated mathematical expectation value can be used as a whole to push the grading value.

And step S140, pushing the related information of the resource objects to the user account to be pushed according to the integral pushing score value information corresponding to each resource object.

In a specific implementation, the terminal can push the related information of the resource object to the user account to be pushed according to the integral push score value information corresponding to each resource object.

Specifically, the terminal may sort the resource objects in descending order according to the corresponding overall push score values, and push the related information of the resource objects with the previous ranks to the user account to be pushed preferentially. The related information of the resource object may include picture information, parameter information (for example, the parameter information may include price information, sales information, comment information, and the like) of the resource object.

In the object information pushing method, object attribute information corresponding to each resource object in the target resource interaction platform under at least two preset pushing dimensions is obtained; the target resource interaction platform is a resource interaction platform currently accessed by the user account to be pushed; inputting object attribute information corresponding to each pushing dimension into a pushing evaluation value prediction model corresponding to the corresponding pushing dimension to obtain pushing evaluation value information corresponding to each resource object under each pushing dimension respectively; according to the push evaluation value information corresponding to each resource object under each push dimension and the push weight information corresponding to the corresponding push dimension, obtaining the integral push score value information corresponding to each resource object; and pushing the related information of the resource objects to the user account to be pushed according to the integral pushing score value information corresponding to each resource object.

In one exemplary embodiment, the push dimension includes a push dominance difference dimension; the corresponding object attribute information under the push dominance difference dimension comprises object parameter information. The terminal inputs object attribute information corresponding to each pushing dimension into a pushing evaluation value prediction model corresponding to the corresponding pushing dimension, and the terminal can acquire object parameter information corresponding to each resource object in each resource interaction platform in the process of obtaining pushing evaluation value information corresponding to each resource object under each pushing dimension respectively; and comparing the object parameter information corresponding to each resource object in the target resource interaction platform with the object parameter information corresponding to each resource object in the rest of the resource interaction platforms, so as to determine push advantage information of the resource objects in the target resource interaction platform relative to the rest of the resource interaction platforms.

Further, in determining the pushing advantage information of the resource object in the target resource interaction platform relative to the other resource interaction platforms, the terminal can specifically determine the resource category of the target resource interaction platform having pushing advantages relative to the other resource interaction platforms.

Specifically, in an optional embodiment of the present application, as shown in fig. 2, step S120, inputting object attribute information corresponding to each push dimension into a push evaluation value prediction model corresponding to the corresponding push dimension, to obtain push evaluation value information corresponding to each resource object under each push dimension, includes steps S210 to S230. Wherein:

step S210, object parameter information corresponding to the resource object belonging to the target resource category in each resource interaction platform is obtained.

The target resource category is a resource category to which the resource object in the target resource interaction platform belongs.

Taking a resource object as an example of a commodity, the object parameter information may include commodity parameters such as price, sales quantity, heat, and the like.

In a specific implementation, when the push dimension includes a push dominance difference dimension, the terminal inputs object attribute information corresponding to each push dimension to a push evaluation value prediction model corresponding to the corresponding push dimension, so as to obtain push evaluation value information corresponding to each resource object under each push dimension, and the terminal can determine a resource category to which the resource object in the target resource interaction platform belongs as the target resource category and obtain object parameter information corresponding to the resource object belonging to the target resource category in each resource interaction platform.

Further, the terminal can automatically crawl object parameter information corresponding to the category of the target resource in all resource interaction platforms of the public network by utilizing the crawler system, and check the object parameter information of the resource object in the target resource interaction platform.

Wherein, the crawler is divided into four parts:

1. and acquiring a data source, and uniformly scheduling and executing a request to a server of a website corresponding to each resource interaction platform by utilizing a crawler process to be executed for managing the crawler scheduling, wherein a returned response body is a webpage source code and is analyzed.

2. Extracting information, analyzing the webpage source code after acquiring the webpage source code, extracting effective information from the disordered data by adopting a regular expression, and facilitating subsequent processing and analysis of the data.

3. And storing the data, and after the information is extracted, storing the data for subsequent use.

4. And the automatic program performs various operations such as exception handling, error retry and the like in the grabbing process, and continuously and efficiently automatically completes the work of acquiring the webpage, extracting the information and storing the data.

Thus, the crawler system collects object parameter information of each resource interaction platform to form a data collection system of the crawler system. The method and the device realize the provision of wider resource object recommendation references, are not limited to the resource interaction platform currently accessed by the user, and solve the problem of difficult acquisition of the data source.

Step S220, pushing advantage information of each resource category in the target resource interaction platform relative to other resource interaction platforms is determined according to the object parameter information corresponding to each resource interaction platform.

Step S230, pushing advantage information corresponding to each resource object is input to a advantage difference evaluation value prediction model corresponding to the pushing advantage difference dimension, and the advantage difference evaluation value information corresponding to each resource object under the pushing advantage difference dimension is obtained.

After the object parameter information corresponding to the resource object belonging to the target resource category in each resource interaction platform is obtained, the terminal can determine push advantage information of each resource category in the target resource interaction platform relative to other resource interaction platforms according to the object parameter information corresponding to each resource interaction platform. Thus, the push advantage information corresponding to the resource objects belonging to different resource categories in the target resource interaction platform can be determined according to the push advantage information corresponding to each resource category. Therefore, the terminal can determine the corresponding dominance difference evaluation value information of each resource object under the dominance difference dimension according to the pushing dominance information corresponding to each resource object.

Specifically, the terminal may input the pushing dominance information corresponding to each resource object to a dominance difference evaluation value prediction model corresponding to the pushing dominance difference dimension, to obtain dominance difference evaluation value information corresponding to each resource object under the pushing dominance difference dimension. The advantage difference evaluation value information is corresponding push evaluation value information under the push advantage difference dimension.

According to the technical scheme, the pushing dimension comprises a pushing advantage difference dimension; pushing object attribute information corresponding to the dominant difference dimension to comprise object parameter information; obtaining object parameter information corresponding to a resource object belonging to a target resource category in each resource interaction platform; the target resource category is a resource category to which a resource object in the target resource interaction platform belongs; determining push advantage information of each resource category in the target resource interaction platform relative to other resource interaction platforms according to the object parameter information corresponding to each resource interaction platform; inputting the pushing dominance information corresponding to each resource object to a dominance difference evaluation value prediction model corresponding to the pushing dominance difference dimension to obtain dominance difference evaluation value information corresponding to each resource object under the pushing dominance difference dimension. Therefore, the object reference information of the same resource category in each resource interaction platform can be widely referred to so as to accurately determine the push advantage information of each resource category in the target resource interaction platform relative to other resource interaction platforms, and accordingly, the corresponding advantage difference evaluation value information of each resource object under the push advantage difference dimension can be accurately determined according to the push advantage information corresponding to each resource object.

In one embodiment, the push dominance level information comprises push dominance levels; inputting the pushing dominance information corresponding to each resource object to a dominance difference evaluation value prediction model corresponding to the pushing dominance difference dimension to obtain dominance difference evaluation value information corresponding to each resource object under the pushing dominance difference dimension, wherein the method comprises the following steps: giving corresponding dominant difference evaluation value information to each resource object according to the push dominant level to which each resource object belongs through a dominant difference evaluation value prediction model; the dominant variance evaluation value information includes dominant variance evaluation values; the dominance difference assessment value is in positive correlation with the push dominance level.

In a specific implementation, the push dominance level information includes a push dominance level; in the process that the terminal inputs pushing dominance information corresponding to each resource object into a dominance difference evaluation value prediction model corresponding to a pushing dominance difference dimension to obtain dominance difference evaluation value information corresponding to each resource object under the pushing dominance difference dimension, the terminal can endow each resource object with a dominance difference evaluation value corresponding to each resource object according to the pushing dominance grade to which each resource object belongs through the dominance difference evaluation value prediction model; the advantage difference evaluation value and the push advantage level are in positive correlation, so that the advantage difference evaluation information corresponding to each resource object can be obtained according to the advantage difference evaluation value corresponding to each resource object.

In practical application, the big data processing and analyzing method can utilize big data technology to analyze, deeply mine and preprocess huge data so as to realize automatic and intelligent task processing. For example, the terminal may utilize the commodity parameter information such as price, sales quantity, heat, etc. of the same or similar commodities in each large electronic mall of the public network to perform data analysis with the commodities in the target electronic mall accessed by the user, so as to obtain the commodity type with push advantage in the target electronic mall. And then, according to the push dominance difference system definition weight (namely the push dominance evaluation value), storing the push dominance difference system definition weight in a database, and starting a timing task to automatically update a data analysis result so as to refresh the real-time property and consistency of maintenance data. Specifically, a corresponding push advantage level may be assigned to each commodity category, and then push advantage evaluation values corresponding to different push advantage levels are defined by using a push advantage difference system, so as to obtain push advantage evaluation values corresponding to each commodity in the target electronic mall. The data integration of a plurality of e-commerce platforms is realized, and the quality and accuracy of the data are ensured by means of big data analysis.

According to the technical scheme, the push dominance grade information comprises push dominance grades; giving corresponding dominant difference evaluation value information to each resource object according to the push dominant level to which each resource object belongs through a dominant difference evaluation value prediction model; the dominant variance evaluation value information includes dominant variance evaluation values; the dominance difference assessment value is in positive correlation with the push dominance level. Therefore, the advantage difference corresponding to each resource object can be accurately quantized according to the push advantage level to which each resource object belongs, so that the push value of the resource object under the push advantage difference dimension can be more accurately quantized and evaluated, and the advantage difference evaluation value corresponding to each resource object can be accurately obtained.

In one embodiment, the object parameter dimension is included in the push dimension; in the case that the object attribute information corresponding to the object parameter dimension includes the object parameter information corresponding to each object parameter type, as shown in fig. 3, step S120 includes inputting the object attribute information corresponding to each push dimension into a push evaluation value prediction model corresponding to the corresponding push dimension to obtain push evaluation value information corresponding to each resource object in each push dimension, including steps S310 to S320. Wherein:

in step S310, the importance level corresponding to each object parameter type is determined.

Taking a resource object as an example of a commodity, the object parameter information may include a product specification parameter, a total sales volume, a time period sales volume, a commodity price, a good rate, a purchase rate, a discount rate, and other commodity parameters. These object parameter information all belong to different object parameter types.

In a specific implementation, the terminal may determine the importance level corresponding to each object parameter type. For example, from the perspective of commodity marketing, the terminal may divide the importance level corresponding to the object parameter type into a parameter that is most important for commodity marketing, a parameter that is more important for commodity marketing, and a parameter that is generally important for commodity marketing. In practical applications, other manners may be used to divide the importance degrees corresponding to the object parameter types, which is not limited herein.

Step S320, inputting the object parameter information corresponding to each resource object to an object parameter evaluation value prediction model corresponding to the object parameter dimension, and obtaining the object parameter evaluation value information corresponding to each resource object under the object parameter dimension by the object parameter evaluation value prediction model according to the importance degree corresponding to each object parameter type.

Wherein the object parameter evaluation value information includes an object parameter evaluation value.

Wherein, the object parameter evaluation value and the importance degree have positive correlation.

In a specific implementation, the terminal may input object parameter information corresponding to each resource object to an object parameter evaluation value prediction model corresponding to an object parameter dimension, where the object parameter evaluation value prediction model obtains an object parameter evaluation value corresponding to each resource object in the object parameter dimension according to an importance degree corresponding to each object parameter type, so that object parameter evaluation value information corresponding to each resource object in the object parameter dimension can be obtained according to the object parameter evaluation value corresponding to each resource object. The object parameter evaluation value information is push evaluation value information corresponding to the object parameter dimension.

According to the technical scheme of the embodiment, the pushing dimension comprises an object parameter dimension; the object attribute information corresponding to the object parameter dimension comprises object parameter information corresponding to each object parameter type; determining the importance degree corresponding to each object parameter type; inputting object parameter information corresponding to each resource object into an object parameter evaluation value prediction model corresponding to object parameter dimensions, and obtaining object parameter evaluation value information corresponding to each resource object under the object parameter dimensions by the object parameter evaluation value prediction model according to the importance degree corresponding to each object parameter type; the object parameter evaluation value information includes an object parameter evaluation value; the object parameter evaluation value has a positive correlation with the importance level. Therefore, under the object parameter dimension, the push value of the resource object under the object parameter dimension can be accurately quantized and evaluated according to the importance degree corresponding to each object parameter type, so as to obtain the object parameter evaluation value information which corresponds to each resource object under the object parameter dimension and has positive correlation with the importance degree, and the object parameter evaluation value corresponding to each resource object under the object parameter dimension can be accurately quantized according to the importance degree corresponding to each object parameter type.

In one embodiment, object parameter information corresponding to each resource object is input to an object parameter evaluation value prediction model corresponding to an object parameter dimension, and the object parameter evaluation value prediction model obtains object parameter evaluation value information corresponding to each resource object under the object parameter dimension through importance degrees corresponding to each object parameter type, including: dividing object parameter information corresponding to each resource object into different quadrants according to the importance degree corresponding to each object parameter type by using a four-quadrant method through an object parameter evaluation value prediction model; determining the evaluation value information of the object parameter information corresponding to each resource object according to the quadrant to which the object parameter information corresponding to each resource object belongs by using an object parameter evaluation value prediction model; and determining object parameter evaluation value information corresponding to each resource object under the object parameter dimension according to the evaluation value information of the object parameter information corresponding to each resource object.

In the specific implementation, when the terminal inputs object parameter information corresponding to each resource object into an object parameter evaluation value prediction model corresponding to object parameter dimensions, and the object parameter evaluation value prediction model obtains object parameter evaluation value information corresponding to each resource object under the object parameter dimensions through importance degrees corresponding to each object parameter type, the terminal can divide the object parameter information corresponding to each resource object into different quadrants according to the importance degrees corresponding to each object parameter type by adopting a four-quadrant method through the object parameter evaluation value prediction model; determining evaluation value information of object parameter information corresponding to each resource object according to quadrants of the object parameter information corresponding to each resource object through an object parameter evaluation value prediction model (the evaluation value information comprises object parameter evaluation values); and determining object parameter evaluation value information corresponding to each resource object under the object parameter dimension according to the evaluation value information of the object parameter information corresponding to each resource object.

Wherein, the corresponding quadrant weight ratio of each quadrant is different. Specifically, the weight ratios of the quadrants corresponding to the first quadrant, the second quadrant, the third quadrant and the fourth quadrant are sequentially reduced.

In an optional embodiment of the present application, in determining, by using an object parameter evaluation value prediction model, evaluation value information of object parameter information corresponding to each resource object according to a quadrant to which the object parameter information corresponding to each resource object belongs, for any resource object, a terminal may obtain, according to a product of a quadrant weight corresponding to a quadrant to which the object parameter information belongs and a specific parameter value of the object parameter information corresponding to any resource object, a quadrant parameter evaluation value corresponding to each object parameter information of the any resource object, so that an object parameter evaluation value corresponding to any resource object may be obtained according to a sum of quadrant parameter evaluation values corresponding to each object parameter information of the any resource object, thereby obtaining, according to the object parameter evaluation value corresponding to any resource object, object parameter evaluation value information corresponding to any resource object under an object parameter dimension.

According to the technical scheme of the embodiment, a four-quadrant method is adopted by an object parameter evaluation value prediction model, and object parameter information corresponding to each resource object is divided into different quadrants according to the importance degree corresponding to each object parameter type; determining the evaluation value information of the object parameter information corresponding to each resource object according to the quadrant to which the object parameter information corresponding to each resource object belongs by using an object parameter evaluation value prediction model; and determining object parameter evaluation value information corresponding to each resource object under the object parameter dimension according to the evaluation value information of the object parameter information corresponding to each resource object. Therefore, according to the four-quadrant method, the evaluation value information of each object parameter information can be determined according to the importance degree of the object parameter type.

In one embodiment, the push dimension includes a user behavior dimension; the corresponding object attribute information under the user behavior dimension comprises user behavior data; the user behavior data is used for recording the operation behavior of the user account to be pushed for the resource object.

Inputting object attribute information corresponding to each pushing dimension into a pushing evaluation value prediction model corresponding to the corresponding pushing dimension to obtain pushing evaluation value information corresponding to each resource object under each pushing dimension, wherein the method comprises the following steps: and inputting the user behavior data corresponding to each resource object into a user behavior evaluation value prediction model corresponding to the user behavior dimension to obtain user behavior evaluation value information corresponding to each resource object under the user behavior dimension.

The operation behavior of the user account to be pushed for the resource object may include at least one behavior of browsing behavior, collecting behavior and recommending behavior of the resource object.

The user behavior data corresponding to the resource object in the user behavior dimension may include browsed data of the resource object and collected data of the resource object. Specifically, the user behavior data corresponding to each resource object in the target resource interaction platform under the user behavior dimension can be obtained by counting at least one behavior data in the total operation behavior characteristics of the user on each resource object, including the total number of times that all user accounts browse each resource object in the target resource interaction platform, the total number of times that all user accounts collect each resource object, the total number of times that all user accounts recommend each resource object, the total duration that all user accounts browse each resource object, and the final deadline time that all user accounts browse each resource object.

For example, the terminal may collect, in the target e-commerce platform, at least one behavior data, such as a total number of times that all user accounts browse each commodity, a total number of times that all user accounts collect each commodity, a total number of times that all user accounts recommend each commodity, a total duration that all user accounts browse each commodity, a final cut-off time that all user accounts browse each commodity, and the like, in a specified period of time, and send the at least one behavior data to the analysis unit, so as to analyze the user behavior data corresponding to each resource object. Thus, the user behavior data corresponding to the commodity can comprise at least one of browsed total times, collectable total times, recommended total times, browsed total duration and last browsed time.

In a specific implementation, the terminal may input the user behavior data corresponding to each resource object to a user behavior evaluation value prediction model corresponding to the user behavior dimension, so as to obtain weight information corresponding to each resource object in the user behavior dimension, where the weight information may be used as user behavior evaluation value information. The user behavior evaluation value information is push evaluation value information corresponding to the user behavior dimension.

In addition, branches can be distinguished by user attribute difference categories in addition to inclusion of user behavior dimensions to provide different push policies under different user scenarios. Specifically, the user attribute difference can be divided by acquiring attribute information corresponding to the user account to be pushed under different user attributes. Therefore, the algorithm difference in the multi-user scene can change the pushing direction of the resource object, and a more suitable pushing result is provided for different user attribute differences.

In an optional embodiment of the present application, the pushing dimension may further include an optional pushing dimension, where the optional pushing dimension may be a pushing dimension that does not include a pushing advantage difference dimension, an object parameter dimension, and a user behavior dimension and affects a user account to select a resource object, and pushing evaluation value information and pushing weight information in the optional pushing dimension may be determined according to big data analysis, social investigation, and a current social wind direction.

According to the technical scheme, the pushing dimension comprises a user behavior dimension; the corresponding object attribute information under the user behavior dimension comprises user behavior data; the user behavior data are used for recording the operation behavior of the user account to be pushed for the resource object; and inputting the user behavior data corresponding to each resource object into a user behavior evaluation value prediction model corresponding to the user behavior dimension to obtain user behavior evaluation value information corresponding to each resource object under the user behavior dimension. Therefore, the pushing value of the resource object under the user behavior dimension can be accurately quantized and evaluated according to the user behavior data corresponding to each resource object, so that the user behavior evaluation value information corresponding to each resource object under the user behavior dimension can be obtained.

In another embodiment, as shown in fig. 4, there is provided an object information pushing method, which is described by taking application of the method to a terminal as an example, and includes the following steps:

step S402, object attribute information corresponding to each resource object in the target resource interaction platform under at least two preset pushing dimensions is obtained.

Step S404, obtaining object parameter information corresponding to the resource object belonging to the target resource category in each resource interaction platform.

Step S406, pushing advantage information of each resource category in the target resource interaction platform relative to other resource interaction platforms is determined according to the object parameter information corresponding to each resource interaction platform.

Step S408, pushing advantage information corresponding to each resource object is input to a advantage difference evaluation value prediction model corresponding to the pushing advantage difference dimension, and the advantage difference evaluation value information corresponding to each resource object under the pushing advantage difference dimension is obtained.

In step S410, the importance level corresponding to each object parameter type is determined.

Step S412, inputting the object parameter information corresponding to each resource object to an object parameter evaluation value prediction model corresponding to the object parameter dimension, and obtaining the object parameter evaluation value information corresponding to each resource object under the object parameter dimension by the object parameter evaluation value prediction model according to the importance degree corresponding to each object parameter type.

Step S414, inputting the user behavior data corresponding to each resource object to a user behavior evaluation value prediction model corresponding to the user behavior dimension to obtain user behavior evaluation value information corresponding to each resource object in the user behavior dimension.

Step S416, according to the push evaluation value information corresponding to each resource object under each push dimension and the push weight information corresponding to the corresponding push dimension, the overall push score value information corresponding to each resource object is obtained.

Step S418, pushing the related information of the resource objects to the user account to be pushed according to the integral pushing score value information corresponding to each resource object.

It should be noted that, the specific limitation of the above steps may be referred to the specific limitation of an object information pushing method.

It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.

Based on the same inventive concept, the embodiment of the application also provides an object information pushing device for realizing the above related object information pushing method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in the embodiments of the object information pushing device or devices provided below may refer to the limitation of the object information pushing method hereinabove, and will not be repeated herein.

In an exemplary embodiment, as shown in fig. 5, there is provided an object information pushing apparatus, including: an acquisition module 510, an input module 520, an evaluation module 530, and a push module 540, wherein:

the obtaining module 510 is configured to obtain object attribute information corresponding to each resource object in the target resource interaction platform in at least two preset pushing dimensions; the target resource interaction platform is a resource interaction platform currently accessed by the user account to be pushed.

The input module 520 is configured to input object attribute information corresponding to each push dimension to a push evaluation value prediction model corresponding to the corresponding push dimension, so as to obtain push evaluation value information corresponding to each resource object under each push dimension.

The evaluation module 530 is configured to obtain overall push score value information corresponding to each resource object according to push evaluation value information corresponding to each resource object in each push dimension and push weight information corresponding to the corresponding push dimension.

And the pushing module 540 is configured to push the information related to the resource object to the user account to be pushed according to the overall push score information corresponding to each resource object.

In one embodiment, the push dimension includes a push dominance difference dimension; the corresponding object attribute information under the push dominance difference dimension comprises object parameter information; the input module 520 is specifically configured to obtain object parameter information corresponding to a resource object belonging to a target resource category in each resource interaction platform; the target resource category is a resource category to which a resource object in the target resource interaction platform belongs; determining push advantage information of each resource category in the target resource interaction platform relative to other resource interaction platforms according to the object parameter information corresponding to each resource interaction platform; and inputting the pushing dominance information corresponding to each resource object into a dominance difference evaluation value prediction model corresponding to the pushing dominance difference dimension to obtain dominance difference evaluation value information corresponding to each resource object under the pushing dominance difference dimension.

In one embodiment, the push dominance level information includes a push dominance level; the input module 520 is specifically configured to assign, according to the push dominance class to which each of the resource objects belongs, dominance difference evaluation value information corresponding to each of the resource objects through the dominance difference evaluation value prediction model; the dominance difference evaluation value information includes a dominance difference evaluation value; the advantage difference evaluation value and the push advantage level are in positive correlation.

In one embodiment, the push dimension includes an object parameter dimension; the object attribute information corresponding to the object parameter dimension comprises object parameter information corresponding to each object parameter type; the input module 520 is specifically configured to determine an importance level corresponding to each of the object parameter types; inputting object parameter information corresponding to each resource object into an object parameter evaluation value prediction model corresponding to the object parameter dimension, wherein the object parameter evaluation value prediction model obtains object parameter evaluation value information corresponding to each resource object under the object parameter dimension through the importance degree corresponding to each object parameter type; the object parameter evaluation value information includes an object parameter evaluation value; the object parameter evaluation value and the importance degree have a positive correlation.

In one embodiment, the input module 520 is specifically configured to divide the object parameter information corresponding to each resource object into different quadrants according to the importance level corresponding to each object parameter type by using a four-quadrant method through the object parameter evaluation value prediction model; determining evaluation value information of object parameter information corresponding to each resource object according to quadrants of the object parameter information corresponding to each resource object through the object parameter evaluation value prediction model; and determining object parameter evaluation value information corresponding to each resource object under the object parameter dimension according to the evaluation value information of the object parameter information corresponding to each resource object.

In one embodiment, the push dimension includes a user behavior dimension; the corresponding object attribute information under the user behavior dimension comprises user behavior data; the user behavior data are used for recording the operation behaviors of the user account to be pushed for the resource object; the input module 520 is specifically configured to input the user behavior data corresponding to each resource object to a user behavior evaluation value prediction model corresponding to the user behavior dimension, so as to obtain user behavior evaluation value information corresponding to each resource object in the user behavior dimension.

The above-mentioned respective modules in the object information pushing apparatus may be implemented in whole or in part by software, hardware, and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

In one exemplary embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 6. The computer device includes a processor, a memory, an Input/Output interface (I/O) and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing push weight information data. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement an object information pushing method.

It will be appreciated by those skilled in the art that the structure shown in fig. 6 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.

In an embodiment, there is also provided a computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, carries out the steps of the method embodiments described above.

In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments described above.

It should be noted that, the user information (including, but not limited to, user equipment information, user personal information, etc.) and the data (including, but not limited to, data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use, and processing of the related data are required to meet the related regulations.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.

Claims

1. An object information pushing method, characterized in that the method comprises:

2. The method of claim 1, wherein the push dimension comprises a push dominance difference dimension; the corresponding object attribute information under the push dominance difference dimension comprises object parameter information;

3. The method of claim 2, wherein the push dominance level information comprises a push dominance level;

4. The method of claim 1, wherein the push dimension comprises an object parameter dimension; the object attribute information corresponding to the object parameter dimension comprises object parameter information corresponding to each object parameter type;

determining the importance degree corresponding to each object parameter type;

5. The method according to claim 4, wherein inputting the object parameter information corresponding to each resource object into the object parameter evaluation value prediction model corresponding to the object parameter dimension, the object parameter evaluation value prediction model obtaining the object parameter evaluation value information corresponding to each resource object under the object parameter dimension by the importance degree corresponding to each object parameter type, includes:

6. The method of claim 1, wherein the push dimension comprises a user behavior dimension; the corresponding object attribute information under the user behavior dimension comprises user behavior data; the user behavior data are used for recording the operation behaviors of the user account to be pushed for the resource object;

7. An object information pushing apparatus, characterized in that the apparatus comprises:

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.

9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.