CN111753204A

CN111753204A - Information pushing method and device, electronic equipment and storage medium

Info

Publication number: CN111753204A
Application number: CN202010595999.4A
Authority: CN
Inventors: 王鑫宇; 张永华
Original assignee: Beijing ByteDance Network Technology Co Ltd
Current assignee: Douyin Vision Co Ltd; Douyin Vision Beijing Co Ltd
Priority date: 2020-06-28
Filing date: 2020-06-28
Publication date: 2020-10-09
Anticipated expiration: 2040-06-28
Also published as: CN111753204B

Abstract

The present disclosure provides an information pushing method, an information pushing device, an electronic device, and a storage medium, where the information pushing method includes: acquiring search information of a client; in a pre-established media content library, acquiring media content matched with search information according to multiple matching dimensions to obtain multiple target media content; acquiring user behavior data corresponding to each target media content in a plurality of target media contents, the correlation degree between each target media content and search information, and the number of media contents matched with the search information in a media content library under various matching dimensions; determining a corresponding display position of each target media content when the target media content is displayed at the client based on the acquired user behavior data, the correlation and the number of the media contents; and sending the plurality of target media contents and the display position corresponding to each target media content to the client.

Description

Information pushing method and device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to an information pushing method and apparatus, an electronic device, and a storage medium.

Background

For some media clients, a user may enter search information at an input box of the media client to find media content that is desired to be viewed.

When the server receives the search information, the server can search the media contents related to the search information under different dimensions based on the search information, so that a large number of media contents related to the search information are recalled, when the recalled large number of media contents are displayed, the media contents in the related technology are sorted mechanically and simply, the accuracy is low, the media contents which are provided for the user and are ranked ahead may not contain articles which the user is interested in, and the real requirements of the user cannot be met.

Disclosure of Invention

The embodiment of the disclosure provides at least one information pushing scheme to improve the accuracy of pushing information to a client.

In a first aspect, an embodiment of the present disclosure provides an information pushing method, including:

acquiring search information of a client;

in a pre-established media content library, acquiring media content matched with the search information according to multiple matching dimensions to obtain multiple target media content;

acquiring user behavior data corresponding to each target media content in the plurality of target media contents, the correlation degree between each target media content and the search information, and acquiring the number of media contents matched with the search information in the media content library under the plurality of matching dimensions;

determining a corresponding display position of each target media content when the target media content is displayed at the client based on the acquired user behavior data, the correlation and the number of the media contents;

and sending the plurality of target media contents and the display position corresponding to each target media content to the client so that the client can display the target media contents based on the display position corresponding to each target media content.

In a possible implementation manner, the obtaining, in a pre-established media content library, media content matched with the search information according to different matching dimensions to obtain a plurality of target media contents includes:

in a pre-established media content library, acquiring a plurality of media contents matched with the search information under various matching dimensions according to the characteristic information of each media content under various matching dimensions;

and extracting a set number of media contents as the plurality of target media contents according to the correlation degree of each media content and the search information in the plurality of acquired media contents.

In a possible implementation manner, the determining, based on the obtained user behavior data, the relevancy, and the number of the media contents, a presentation position corresponding to each target media content when presented at the client includes:

determining a ranking score corresponding to each target media content based on user behavior data corresponding to each target media content in the plurality of target media contents and the correlation degree of the target media content and the search information;

determining initial display positions corresponding to the target media contents respectively based on the sequencing scores corresponding to the target media contents;

and adjusting the initial display position based on the sequencing score corresponding to each target content, the user behavior data corresponding to the target media content, the matching dimension corresponding to the target media content and the number of the media contents, and determining the corresponding display position of the target media content when the target media content is displayed at the client.

In one possible implementation manner, the determining, by the user behavior data corresponding to the target media content, a ranking score corresponding to each target media content based on the user behavior data corresponding to each target media content in the plurality of target media contents and the relevance between the target media content and the search information includes:

and carrying out weighted summation on the click rate, the number of comments and the playing time corresponding to each target media content in the plurality of target media contents and the correlation degree of the target media content and the search information to obtain the ranking score corresponding to each target media content.

In a possible implementation manner, the adjusting the initial display position based on the ranking score corresponding to each target content, the user behavior data corresponding to the target media content, the matching dimension corresponding to the target media content, and the number of the media content, and determining a corresponding display position of the target media content when the target media content is displayed at the client includes:

acquiring a preset number of target media contents in the plurality of target media contents before sequencing based on the sequencing score corresponding to each target media content;

determining a ranking score weight corresponding to the target media content under each matching dimension in the set number of target media contents before ranking based on user behavior data corresponding to each target content, the matching dimension corresponding to the target media content, and the number of media contents matched with the search information under each matching dimension in the media content library;

and adjusting the initial display position based on the ranking score weight corresponding to the target media content in each matching dimension, and determining the corresponding display position of the target media content when the target media content is displayed at the client.

In one possible implementation, the determining, based on the user behavior data corresponding to each target content, the matching dimension corresponding to the target media content, and the number of media contents matched with the search information in each matching dimension in the media content library, a ranking score weight corresponding to the target media content in each matching dimension includes:

determining user behavior data corresponding to the target media content in the set number of target media contents before sorting based on the user behavior data corresponding to each target media content and the matching dimension corresponding to the target media content;

and determining the ranking score weight corresponding to the target media content in each matching dimension based on the user behavior data and the number corresponding to the target media content in each matching dimension and the number of the media contents matched with the search information in each matching dimension in the media content library in the target media contents with the set number before ranking.

In one possible implementation, the determining, based on the user behavior data and the number of the target media content in each matching dimension and the number of the media contents matched with the search information in each matching dimension in the media content library, a ranking score weight corresponding to the target media content in each matching dimension includes:

determining a first number ratio of the target media contents of the matching dimension in the set number of target media contents before the sorting based on the number of the target media contents of each matching dimension;

determining the proportion of user behavior data in a set number of target media contents of the matching dimension before the sequencing based on the user behavior data corresponding to the target media contents of each matching dimension;

determining, in the media content repository, media content matching the search information in each matching dimension based on a number of media content matching the search information in that matching dimension, a second number ratio among the media content matching the search information in the media content repository;

and for each matching dimension, summing the first number ratio, the second number ratio and the user behavior data ratio corresponding to the matching dimension to obtain the ranking score weight corresponding to the target media content under the matching dimension.

In a possible implementation manner, the user behavior data corresponding to the target media content includes a click rate, a number of comments, and a play duration of the target media content, and the determining, based on the user behavior data corresponding to the target media content in each matching dimension, a ratio of the user behavior data in a set number of target media contents of the target media content in the matching dimension before the sorting includes:

based on the matching dimension corresponding to each target media content, respectively summing the click rate, the number of comments and the playing time of the target media content corresponding to the same matching dimension to obtain the sum of the click rate, the sum of the number of comments and the sum of the playing time corresponding to the target media content under each matching dimension;

and respectively determining the click rate ratio, the comment quantity ratio and the play duration ratio of the target media content in the matching dimension in the set number of target media contents before the sorting based on the sum of the click rate, the sum of the comment quantity and the sum of the play duration corresponding to the target media content in each matching dimension.

In a second aspect, an embodiment of the present disclosure provides an information pushing apparatus, including:

the acquisition module is used for acquiring the search information of the client; acquiring the media content matched with the search information according to multiple matching dimensions in a pre-established media content library to obtain multiple target media contents; acquiring user behavior data corresponding to each target media content in the plurality of target media contents, the correlation degree between each target media content and the search information, and acquiring the number of media contents matched with the search information in the media content library under the plurality of matching dimensions;

the determining module is used for determining a corresponding display position of each target media content when the target media content is displayed at the client side based on the acquired user behavior data, the correlation and the number of the media contents;

and the sending module is used for sending the plurality of target media contents and the display position corresponding to each target media content to the client so that the client can display the target media contents based on the display position corresponding to each target media content.

In a possible implementation manner, the obtaining module is specifically configured to:

In a possible implementation, the determining module is specifically configured to:

In a possible implementation manner, the user behavior data corresponding to the target media content includes a click rate, a number of comments, and a play duration of the target media content, and the determining module is specifically configured to:

In a third aspect, an embodiment of the present disclosure provides an electronic device, including: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory communicating via the bus when the electronic device is running, the machine-readable instructions when executed by the processor performing the steps of the information pushing method according to the first aspect.

In a fourth aspect, the disclosed embodiments provide a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform the steps of the information pushing method according to the first aspect.

According to the information pushing method provided by the embodiment of the disclosure, when the display position corresponding to each target media is determined jointly based on the user behavior data, the relevancy and the number of the media contents in different matching dimensions, a relatively accurate display position can be obtained, and based on the accurate display position, the target media contents which meet the user requirements better can be pushed to the client, namely, the accuracy of information pushing is improved.

In order to make the aforementioned objects, features and advantages of the present disclosure more comprehensible, preferred embodiments accompanied with figures are described in detail below.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for use in the embodiments will be briefly described below, and the drawings herein incorporated in and forming a part of the specification illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the technical solutions of the present disclosure. It is appreciated that the following drawings depict only certain embodiments of the disclosure and are therefore not to be considered limiting of its scope, for those skilled in the art will be able to derive additional related drawings therefrom without the benefit of the inventive faculty.

Fig. 1 shows a flowchart of an information pushing method provided by an embodiment of the present disclosure;

FIG. 2 is a flow chart illustrating a method for determining a display location provided by an embodiment of the present disclosure;

FIG. 3 is a flow chart of a method for specifying a display position according to an embodiment of the present disclosure;

FIG. 4 illustrates a flow chart of a method of determining rank score weights provided by an embodiment of the present disclosure;

FIG. 5 illustrates a flow chart of a method for determining rank score weights in particular, according to an embodiment of the present disclosure;

fig. 6 shows a schematic structural diagram of an information pushing apparatus provided in an embodiment of the present disclosure;

fig. 7 shows a schematic diagram of an electronic device provided by an embodiment of the present disclosure.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present disclosure more clear, the technical solutions of the embodiments of the present disclosure will be described clearly and completely with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are only a part of the embodiments of the present disclosure, not all of the embodiments. The components of the embodiments of the present disclosure, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present disclosure, presented in the figures, is not intended to limit the scope of the claimed disclosure, but is merely representative of selected embodiments of the disclosure. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the disclosure without making creative efforts, shall fall within the protection scope of the disclosure.

The above-mentioned drawbacks are the results of the inventor after practical and careful study, and therefore, the discovery process of the above-mentioned problems and the solutions proposed by the present disclosure to the above-mentioned problems should be the contribution of the inventor in the process of the present disclosure.

For some media clients, media contents of a large number of titles can be provided for users to watch, when the users generate search requirements, the media contents can also be searched based on input search information, for example, when the users want to watch videos related to "mango", the search information of "mango" can be input in the media clients, so that when the servers receive the search information, the media contents related to the search information can be searched in a media library, when searching, the media contents matched with the search information can be obtained according to various dimensions, for example, the media contents of which the media titles contain "mango", the media contents of which the music contents contain "mango" and the media contents of which the user names contain "mango" can be obtained, a large number of media contents can be obtained in such a way, when the recommended media contents are returned to the media clients, how to find the media content suitable for being displayed at the front position, that is, how to improve the accuracy of recommendation, is a problem to be studied in the embodiment of the present disclosure.

Based on the above research, the present disclosure provides an information pushing method, after a plurality of target media contents matching with search information of a client are obtained according to a plurality of matching dimensions, user behavior data corresponding to each target media content, such as click rate, playing duration, number of comments, and the like, are obtained, and these features may be used to indicate the popularity of the target media content, in general, a user is more inclined to view media contents with higher popularity, and in addition, the correlation between each target media content and the search information is obtained, in general, the user wants to search media contents with higher relevancy to the input search information, and in addition, the number of media contents matching with the search information in a media content library in a plurality of matching dimensions is also obtained, and this feature may be used to represent that the user performs a search based on the search information, the user behavior data, the relevancy and the number of media contents in different matching dimensions are comprehensively based on the media contents in the different matching dimensions, so that when the display position corresponding to each target media is determined together, a more accurate display position can be obtained, and based on the accurate display position, the target media contents which meet the user requirements better can be pushed to the client, namely the accuracy of information pushing is improved.

To facilitate understanding of the present embodiment, first, an information pushing method disclosed in the embodiments of the present disclosure is described in detail, and an execution subject of the information pushing method provided in the embodiments of the present disclosure is generally a server corresponding to a media client. In some possible implementations, the information pushing method may be implemented by a processor calling computer readable instructions stored in a memory.

Referring to fig. 1, a flowchart of an information pushing method provided in the embodiment of the present disclosure is shown, where the method includes steps S101 to S105, where:

s101, obtaining search information of a client.

The Client (Client) or called user side herein refers to a program corresponding to the server and providing local services for the Client, and is generally installed on a common Client, and needs to cooperate with the server to run, for example, some application apps.

Here, the search information is a term, such as "mango" mentioned above, which is input by the user at the client for searching.

S102, in a pre-established media content library, media content matched with the search information is obtained according to multiple matching dimensions, and multiple target media contents are obtained.

When the media content is a video, that is, a large number of videos are stored, each media content may include a media title, music content, a user name for publishing the media content, and the like, which may be referred to as different dimensions, and then when the media content matching the search information is searched in the media content library based on the search information, the media content may be obtained according to different matching dimensions, for example, the media content is searched in the media content library according to the matching of the media title and the search information, that is, the media content including the search information in the media title, the media content including the search information in the music content, and the media content including the search information in the search user name, so that the media content matching the search information may be obtained.

Considering that a large amount of media content may be obtained when the media content matched with the search information is obtained according to multiple matching dimensions, and when the media content matched with the search information input by the client is sent to the client, interception may need to be performed in the large amount of media content, for example, a set number of media content, that is, the target media content is obtained, and how to obtain the plurality of target media content will be specifically explained later.

S103, acquiring user behavior data corresponding to each target media content in the plurality of target media contents, the correlation degree between each target media content and the search information, and acquiring the number of media contents matched with the search information in the media content library under various matching dimensions.

The user behavior data corresponding to each target media content herein refers to an operation performed by a user for the target media content when the target media content is played at a client, for example, when the target media content is a video, the user behavior data may include a number of praise for the video, a number of comments, a playing time length, and a click rate corresponding to the video when the video is displayed at the client, and the click rate of any media content may be represented by a ratio of the number of clicks clicked by the user to the number of display times when the any media content is displayed at the client within a set time length.

Here, the correlation between each target media content and the search information may be determined by determining a text included in the search information and a similarity between texts included in the target media content, and when the target media content includes a media title, a music content, and a user name, the similarities between a text included in the search information and a corresponding text of the media title, a corresponding text of the music content, and a corresponding text of the user name of the target media content may be determined respectively, for example, by determining in a cosine similarity manner, so as to obtain a cosine similarity between the search information and a media title of the target media content, a cosine similarity between the search information and a music content of the target media content, and a cosine similarity between the search information and a music content of the target media content, and summing the cosine similarity to obtain the similarity between the search information and the target media content.

The number of media contents in the media content library matched with the search information in the multiple matching dimensions obtained here refers to the number of media contents in the media content library matched with the search information in each matching dimension, and by this feature, it can be characterized that a user may want to search for media contents in which dimension based on the search information when searching based on the search information.

And S104, determining a corresponding display position of each target media content when the target media content is displayed at the client based on the acquired user behavior data, the correlation and the number of the media contents.

The popularity of each target media content can be represented through the user behavior data corresponding to the target media content; the number of media contents in the media content library, which are matched with the search information under various matching dimensions, can represent that a user probably wants to search the media contents under which dimensions based on the search information when searching based on the search information, and then the corresponding display position of each target media content when the client displays is determined together according to the user behavior data, the relevance and the number of the media contents, that is, the media contents which have higher popularity, higher similarity with the search information of the client and are matched with the dimensions which the client tends to search are placed at the front position, so that the search requirement of the user is met.

S105, sending the plurality of target media contents and the display position corresponding to each target media content to the client so that the client can display the target media contents based on the display position corresponding to each target media content.

When the display position corresponding to each target media content is obtained, the plurality of target media contents and the display position corresponding to each target media content can be sent to the client, and the client can display the plurality of target media contents in sequence based on the display position corresponding to each target media content.

In the seed information pushing method proposed in steps S101 to S105, after a plurality of target media contents matching with the search information of the client are obtained according to a plurality of matching dimensions, user behavior data corresponding to each target media content, such as click rate, playing duration, number of comments, etc., are obtained, and these features may be used to indicate the popularity of the target media content, in general, the user is more inclined to view the media content with higher popularity, in addition, the correlation between each target media content and the search information is obtained, in general, the user wants to search for the media content with higher relevance to the input search information, in addition, the number of media contents matching with the search information in the media content library in a plurality of matching dimensions is also obtained, and the features may be used to represent that the user performs a search based on the search information, the user behavior data, the relevancy and the number of media contents in different matching dimensions are comprehensively based on the media contents in the different matching dimensions, so that when the display position corresponding to each target media is determined together, a more accurate display position can be obtained, and based on the accurate display position, the target media contents which meet the user requirements better can be pushed to the client, namely the accuracy of information pushing is improved.

The above-mentioned S101 to S105 will be specifically described with reference to specific embodiments.

For the above S102, when media content matched with the search information is obtained according to different matching dimensions in a pre-established media content library to obtain a plurality of target media content, the method may include:

(1) and in a pre-established media content library, acquiring a plurality of media contents matched with the search information under various matching dimensions according to the characteristic information of each media content under various matching dimensions.

The feature information of each media content in multiple matching dimensions may be feature information of each media content in a media title dimension, feature information of each media content in a music content dimension, and feature information of each media content in a user name dimension, specifically, the feature information in the media title dimension may be obtained based on a text corresponding to a media title, the feature information in the music content dimension may be obtained based on a text corresponding to a music content, and the feature information in the user name dimension may be obtained based on a text corresponding to a user name, for example, performing word segmentation on the text to obtain a plurality of word units, then converting the obtained word units into word features, and representing the feature information here by the word features.

And then, acquiring a plurality of media contents matched with the search information under various matching dimensions through the characteristic information of each media content under various matching dimensions, wherein the acquired media contents can comprise media contents with media titles matched with the search information, media contents with music contents matched with the search information and media contents with user names matched with the search information.

Taking the above search information as "mango" as an example, the obtained plurality of media contents may include media contents including "mango" in the media title, media contents including "mango" in the music content, and media contents including "mango" in the user name.

(2) And extracting a set number of media contents from the acquired plurality of media contents as a plurality of target media contents according to the correlation degree between each media content and the search information.

Since the number of the obtained media contents may be larger, here, the media contents may be intercepted from the plurality of media contents based on the correlation between each media content and the search information, so as to obtain a set number of media contents as a plurality of target media contents therein, such as 10000 media contents obtained above, where the 10000 media contents are sorted in a descending order according to the correlation between each media content of the 10000 media contents and the search information, and then the top 1000 media contents are selected as the plurality of target media contents therein.

After the correlation is filtered, the proportion of the media content reserved under a certain matching dimension may be reduced, for example, in the case that the search information is "mango law", the proportion of the reserved user name and the media content matched with the search information will be reduced, and the proportion of the media title and the media content matched with the search information will be increased.

In the embodiment of the disclosure, a plurality of media contents obtained based on the search information may be preliminarily screened according to the correlation degree between each media content and the search information to obtain a set number of target media contents with a relatively high correlation degree with the search information, so that the number of data processing is reduced, and the information push efficiency is improved.

For the above S104, that is, when determining the corresponding display position of each target media content when the target media content is displayed at the client based on the obtained user behavior data, the correlation, and the number of the media content, as shown in fig. 2, the method may specifically include the following steps S201 to S203:

s201, determining a ranking score corresponding to each target media content based on user behavior data corresponding to each target media content in a plurality of target media contents and the correlation degree of the target media content and search information.

After obtaining a plurality of target media contents, firstly selecting the target media contents which are more in line with the requirements of the user from the target media contents, so as to determine the media contents in which matching dimension the client tends to retrieve when searching based on the search information.

Specifically, the user behavior data corresponding to the target media content includes a click rate, a number of comments, and a play duration of the target media content, and when determining a ranking score corresponding to each target media content based on the user behavior data corresponding to each target media content in the plurality of target media contents and a correlation between the target media content and the search information, the method includes:

During specific weighted summation, the click rate, the comment number, the play time and the correlation degree of the target media content and the search information corresponding to each target media content can be weighted and summed through a preset click rate weight, a preset comment number weight, a preset play time weight and a preset correlation degree weight, wherein the weights of various user behavior data such as the click rate weight, the comment number weight, the play time weight and the like and the correlation degree weight and the like can be obtained through statistics of a large amount of experimental data, and therefore more reasonable weights can be obtained.

S202, determining initial display positions corresponding to the target media contents respectively based on the sequencing scores corresponding to the target media contents.

Based on the ranking score corresponding to each target media content in the target media, the initial display positions corresponding to the target media contents can be determined according to the sequence from high to low of the ranking scores.

S203, based on the sorting score corresponding to each target content, the user behavior data corresponding to the target media content, the matching dimension corresponding to the target media content and the number of the media contents, adjusting the initial display position, and determining the corresponding display position of the target media content when the target media content is displayed at the client.

For example, in the set number of target media contents before sorting, the user behavior data and the number corresponding to the target media contents in each matching dimension can be used, and the number of media contents matched with the search information in each matching dimension in the media content library, determining which matching dimension the search information sent by the client is more inclined to search for the media contents, such as the set number of target media contents before sorting, the number of target media content in the media title dimension is highest, the number of target media content in the user name dimension is second, the number of target media content in the music content dimension is minimal, as is the ordering of the number of media content matching the search information in each matching dimension in the media content library, it may be stated that the user is more inclined to search for target media content matching the search information on the media title based on the search information.

The initial display position can be adjusted by determining which media content under the matching dimensionality is more prone to be searched by the search information sent by the client, so that the more accurate display positions corresponding to the target media contents when the client displays the target media contents are determined.

In the embodiment of the disclosure, the display positions of a plurality of target media contents are determined in two stages, the initial display positions corresponding to the plurality of target media contents are determined based on the ranking score corresponding to each target media content, and then the initial display positions are adjusted based on a plurality of parameters, so that the display positions with higher accuracy can be obtained.

Specifically, for the above S203, the initial display position is adjusted based on the ranking score corresponding to each target content, the user behavior data corresponding to the target media content, the matching dimension corresponding to the target media content, and the number of the media contents, and the display position corresponding to the target media content when displayed at the client is determined, as shown in fig. 3, the method may include the following steps S301 to S303:

s301, based on the sorting score corresponding to each target media content, acquiring a preset number of target media contents in the plurality of target media contents before sorting.

After the ranking score corresponding to each target media content is obtained, the target media contents can be ranked in a descending order according to the ranking score, and then the target media contents with the preset number are selected, for example, the top 10 target media contents are selected from the 1000 target media contents according to the order that the ranking score is changed from high to low.

And further screening a set number of target media contents before sorting from the plurality of target media contents according to the sorting score corresponding to each target media content, so that the number of the target media contents can be reduced, and the efficiency is higher when the initial display position is adjusted subsequently through the reduced number of the target media contents.

S302, in the set number of target media contents before sorting, based on the user behavior data corresponding to each target content, the matching dimension corresponding to the target media content and the number of the media contents matched with the search information in each matching dimension in the media content library, determining the sorting score weight corresponding to the target media content in each matching dimension.

In the target media contents with the set number before sorting, the user behavior data corresponding to each target media content, the matching dimension corresponding to the target media content and the number of the media contents matched with the search information in each matching dimension in the media content library can reflect that the search information sent by the client side is more inclined to search the media contents in which matching dimension, and the sorting score weight corresponding to the target media content in each matching dimension is determined based on the media contents.

S303, based on the ranking score weight corresponding to the target media content under each matching dimension, adjusting the initial display position, and determining the corresponding display position of the target media content when the target media content is displayed at the client.

Here, based on the ranking score weight corresponding to the target media content in each matching dimension, the ranking scores corresponding to the target media contents obtained in step S201 are adjusted, for example, the ranking score weight corresponding to the target media content in the media title dimension is 0.6, the ranking score weight corresponding to the target media content in the music content dimension is 0.2, and the ranking score weight corresponding to the target media content in the user name dimension is 0.1, the ranking scores of the target media contents in the media title dimension in the target media contents are uniformly multiplied by 0.6, the ranking scores of the target media contents in the music content dimension in the target media contents are uniformly multiplied by 0.2, and the ranking scores of the target media contents in the user name dimension in the target media contents are uniformly multiplied by 0.1, that is, the ranking scores are adjusted again, making the user more inclined to the location of the searched media content further forward.

In the embodiment of the present disclosure, when adjusting the initial display positions of multiple target media contents, it is proposed in the embodiment of the present disclosure that based on multiple parameters, such as user behavior data corresponding to each target content, matching dimensions corresponding to the target media contents, and the number of media contents matched with search information in each matching dimension in a media content library, it is determined that search information sent by a client is more inclined to search for media contents in which matching dimension is more inclined, and based on adjusting the initial display positions, a display position more meeting the requirements of the client can be obtained.

In one embodiment, for the above S302, when determining the ranking score weight corresponding to the target media content in each matching dimension based on the user behavior data corresponding to each target content, the matching dimension corresponding to the target media content, and the number of media contents matched with the search information in each matching dimension in the media content library, as shown in fig. 4, the method includes the following S401 to S402:

s401, determining user behavior data corresponding to the target media content in the set number of target media contents before sorting based on the user behavior data corresponding to each target media content and the matching dimension corresponding to the target media content.

After the set number of target media contents before sorting is obtained, the target media contents in each matching dimension and the user behavior data corresponding to the target media contents in the matching dimension in the set number of target media contents before sorting can be determined.

For example, in the top 10 pieces of target media content in the sequence, the target media content in the 7 media title dimension and the target media content in the 3 user name dimension are included, that is, the media title of the 7 pieces of target media content matches with the search information, and the user name of the 3 pieces of target media content matches with the search information, for example, still taking the above search information as "mango" as an example, the media title of the 7 pieces of target media content includes "mango", and the user name of the other 3 pieces of target media content includes "mango".

S402, in the set number of target media contents before sorting, based on the user behavior data and the number corresponding to the target media contents in each matching dimension and the number of the media contents matched with the search information in each matching dimension in the media content library, determining the sorting score weight corresponding to the target media contents in each matching dimension.

Illustratively, in order to reflect that the search information sent by the client is more inclined to search for the media content in which matching dimension, the media content is classified according to the matching dimension, so that the ranking score weight for adjusting the initial display positions of the target media contents is jointly determined based on the user behavior data and the number of the target media contents in each matching dimension and the number of the media contents matched with the search information in each matching dimension in the media content library.

Specifically, for the above S402, when determining the ranking score weight corresponding to the target media content in each matching dimension based on the user behavior data and the number corresponding to the target media content in each matching dimension and the number of media contents matched with the search information in each matching dimension in the media content library, as shown in fig. 5, the following S501 to S504 may be included:

s501, based on the number of the target media contents in each matching dimension, determining the first number ratio of the target media contents in the matching dimension in the set number of the target media contents before sorting.

In this embodiment, in the target media contents with the set number before sorting, the number of the target media contents in each matching dimension may be divided by the number of the target media contents with the set number before sorting, so as to obtain the first number ratio corresponding to the target media contents in the matching dimension.

For example, for the above-mentioned 10 top-ranked target media contents, if the target media contents in the 7 media title dimensions, the target media contents in the 3 user name dimensions, and the target media contents in the 0 music content dimensions are included, the first number ratio corresponding to the target media contents in the media title dimensions is 0.7, the first number ratio corresponding to the target media contents in the user name dimensions is 0.3, and the first number ratio corresponding to the target media contents in the music content dimensions is 0.

S502, determining the user behavior data ratio of the target media contents of the matching dimensions in the set number of target media contents before the sequencing based on the user behavior data corresponding to the target media contents of each matching dimension.

Specifically, the user behavior data corresponding to the target media content includes a click rate, a number of comments, and a playing time length of the target media content, and when determining a ratio of the user behavior data in a set number of target media contents of the target media content of the matching dimension before sorting based on the user behavior data corresponding to the target media content of each matching dimension, the method may include:

(1) based on the matching dimension corresponding to each target media content, respectively summing the click rate, the number of comments and the playing time of the target media content corresponding to the same matching dimension to obtain the sum of the click rate, the sum of the number of comments and the sum of the playing time corresponding to the target media content under each matching dimension;

(2) and respectively determining the click rate ratio, the comment quantity ratio and the play duration ratio in the target media contents with the set number before sorting of the target media contents in the matching dimension based on the sum of the click rate, the sum of the comment quantity and the sum of the play duration corresponding to the target media contents in each matching dimension.

For each target media content in the set number of target media contents before sorting, firstly determining the matching dimension of the target media content with the search information, and then summing the click rates of the target media contents corresponding to the same matching dimension to obtain the sum of the click rates of the target media contents in each matching dimension in the set number of target media contents before sorting; summing the number of the comments of the target media contents corresponding to the same matching dimension to obtain the sum of the number of the comments of the target media contents under each matching dimension in the set number of the target media contents before sorting; and summing the playing time lengths of the target media contents corresponding to the same matching dimension to obtain the sum of the playing time lengths of the target media contents in each matching dimension in the set number of target media contents before sorting.

Further, the sum of click rates, the sum of comment numbers, and the sum of play durations of the target media contents in each matching dimension may be determined in a set number of target media contents before sorting, the sum of click rates, the sum of comment numbers, and the sum of play durations corresponding to the set number of target media contents before sorting may be determined, and then when the click rate occupation ratio of the target media contents in each matching dimension is determined, the sum of click rates of the target media contents in the matching dimension may be obtained by dividing the sum of click rates by the sum of click rates, and similarly, the comment number occupation ratio and the play duration occupation ratio may be obtained in the same manner.

S503, in the media content library, based on the number of the media contents matched with the search information in each matching dimension, determining the media contents matched with the search information in the matching dimension, and comparing the second number of the media contents matched with the search information in the media content library.

For example, the number of media contents matched with the search information in the media content library is specifically the sum of the number of media contents matched with the search information in each matching dimension, and when a second number ratio corresponding to the media contents matched with the search information in each matching dimension is determined in the media content library, the number of media contents matched with the search information in the matching dimension may be obtained by dividing the number of media contents matched with the search information in each matching dimension in the media content library by the sum of the number of media contents matched with the search information in each matching dimension in the media content library.

In addition, considering that in the media content library, when the order of the media content matched with the search information is larger in each matching dimension, before determining that the second number corresponding to each matching dimension is larger, the order of magnitude may be reduced in a logarithmic manner, for example, when the search information is "mango" and the order of magnitude of the number of the media content containing "mango" in the media title in the media content library is larger, the order of magnitude may be reduced in a logarithmic manner.

S504, aiming at each matching dimension, summing the first number ratio, the second number ratio and the user behavior data ratio corresponding to the matching dimension to obtain the ranking score weight corresponding to the target media content under the matching dimension.

For example, for a media title dimension, a first number ratio, a second number ratio and a user behavior data ratio corresponding to the media title dimension may be summed to obtain a ranking score weight corresponding to a target media content in the media title dimension, and a ranking score weight corresponding to a target media content in the music content dimension and a ranking score weight corresponding to a target media content in the user name dimension may also be obtained in the same manner.

Particularly, when the user behavior data includes the click rate, the number of comments, and the play duration of the target media content, the user behavior data ratio herein may include a click rate ratio, a comment number ratio, and a play duration ratio, so that for each matching dimension, a first number ratio, a second number ratio, a click rate ratio, a comment number ratio, and a play duration ratio corresponding to the matching dimension may be summed, thereby obtaining a ranking score weight corresponding to the target media content in the matching dimension.

In the embodiment of the disclosure, the ranking score weight corresponding to the target media content in each matching dimension is determined jointly by considering the first number ratio corresponding to the target media content in each matching dimension, the user behavior data ratio and the media content matched with the search information in the matching dimension and the second number ratio in the media content matched with the search information in the media content library, so that the ranking score weight corresponding to the target media content in each matching dimension can be accurately obtained by determining the ranking score weight from multiple angles, and the accurate display position can be determined subsequently.

Based on the same technical concept, an information pushing device corresponding to the method is further provided in the embodiment of the present disclosure, and as the principle of solving the problem of the device in the embodiment of the present disclosure is similar to that of the information pushing method in the embodiment of the present disclosure, the implementation of the device may refer to the implementation of the method, and repeated details are not repeated.

Referring to fig. 6, which is a schematic diagram of an information pushing apparatus 600 according to an embodiment of the present disclosure, the information pushing apparatus 600 includes:

an obtaining module 601, configured to obtain search information of a client; acquiring media contents matched with the search information according to multiple matching dimensions in a pre-established media content library to obtain multiple target media contents; acquiring user behavior data corresponding to each target media content in a plurality of target media contents, the correlation degree between each target media content and the search information, and acquiring the number of media contents matched with the search information in the media content library under various matching dimensions;

a determining module 602, configured to determine, based on the obtained user behavior data, the relevancy, and the number of the media contents, a corresponding display position of each target media content when displayed at the client;

the sending module 603 is configured to send the multiple target media contents and the display position corresponding to each target media content to the client, so that the client displays the target media contents based on the display position corresponding to each target media content.

In a possible implementation manner, the obtaining module 601 is specifically configured to:

in a pre-established media content library, acquiring a plurality of media contents matched with search information in various matching dimensions according to the characteristic information of each media content in various matching dimensions;

and extracting a set number of media contents from the acquired plurality of media contents as a plurality of target media contents according to the correlation degree between each media content and the search information.

In a possible implementation, the determining module 602 is specifically configured to:

determining a ranking score corresponding to each target media content based on user behavior data corresponding to each target media content in a plurality of target media contents and the correlation degree of the target media content and search information;

adjusting the initial display position based on the sequencing score corresponding to each target content, the user behavior data corresponding to the target media content, the matching dimension corresponding to the target media content and the number of the media contents, and determining the corresponding display position of the target media content when the target media content is displayed at the client.

In a possible implementation manner, the user behavior data corresponding to the target media content includes a click rate, a number of comments, and a play duration of the target media content, and the determining module 602 is specifically configured to:

determining a ranking score weight corresponding to the target media content under each matching dimension in the set number of target media contents before ranking based on user behavior data corresponding to each target content, the matching dimension corresponding to the target media content and the number of media contents matched with the search information under each matching dimension in the media content library;

determining user behavior data corresponding to the target media content in a set number of target media contents before sorting based on the user behavior data corresponding to each target media content and the matching dimension corresponding to the target media content;

and determining the ranking score weight corresponding to the target media content under each matching dimension based on the user behavior data and the number corresponding to the target media content under each matching dimension and the number of the media contents matched with the search information under each matching dimension in the media content library in the target media contents with the set number before ranking.

determining a first number ratio of a set number of target media contents of the matching dimension before sorting based on the number of the target media contents of each matching dimension;

determining the proportion of user behavior data in a set number of target media contents of the matching dimension before sequencing based on the user behavior data corresponding to the target media contents of each matching dimension;

determining, in a media content repository, media content matched with the search information in each matching dimension based on the number of media content matched with the search information in that matching dimension, a second number in the media content matched with the search information in the media content repository;

and respectively determining the click rate ratio, the comment quantity ratio and the play duration ratio in the target media contents with the set number before sorting of the target media contents in the matching dimension based on the sum of the click rate, the sum of the comment quantity and the sum of the play duration corresponding to the target media contents in each matching dimension.

Corresponding to the information pushing method in fig. 1, an embodiment of the present disclosure further provides an electronic device 700, as shown in fig. 7, which is a schematic structural diagram of the electronic device 700 provided in the embodiment of the present disclosure, and includes:

a processor 71, a memory 72, and a bus 73; the memory 72 is used for storing execution instructions and includes a memory 721 and an external memory 722; the memory 721 is also referred to as an internal memory, and is used for temporarily storing the operation data in the processor 71 and the data exchanged with the external memory 722 such as a hard disk, the processor 71 exchanges data with the external memory 722 through the memory 721, and when the electronic device 700 is operated, the processor 71 communicates with the memory 72 through the bus 73, so that the processor 71 executes the following instructions: acquiring search information of a client; in a pre-established media content library, acquiring media content matched with search information according to multiple matching dimensions to obtain multiple target media content; acquiring user behavior data corresponding to each target media content in a plurality of target media contents, the correlation degree between each target media content and search information, and acquiring the number of media contents matched with the search information in a media content library under various matching dimensions; determining a corresponding display position of each target media content when the target media content is displayed at the client based on the acquired user behavior data, the correlation and the number of the media contents; and sending the plurality of target media contents and the display position corresponding to each target media content to the client so that the client can display the target media contents based on the display position corresponding to each target media content.

The embodiments of the present disclosure also provide a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program performs the steps of the information pushing method in the foregoing method embodiments. The storage medium may be a volatile or non-volatile computer-readable storage medium.

The computer program product of the information push method provided in the embodiments of the present disclosure includes a computer-readable storage medium storing a program code, where instructions included in the program code may be used to execute the steps of the information push method in the embodiments of the method described above, which may be referred to in the embodiments of the method specifically, and are not described herein again.

The embodiments of the present disclosure also provide a computer program, which when executed by a processor implements any one of the methods of the foregoing embodiments. The computer program product may be embodied in hardware, software or a combination thereof. In an alternative embodiment, the computer program product is embodied in a computer storage medium, and in another alternative embodiment, the computer program product is embodied in a Software product, such as a Software Development Kit (SDK), or the like.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the apparatus described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. In the several embodiments provided in the present disclosure, it should be understood that the disclosed system, apparatus, and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present disclosure may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present disclosure may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present disclosure. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

Finally, it should be noted that: the above-mentioned embodiments are merely specific embodiments of the present disclosure, which are used for illustrating the technical solutions of the present disclosure and not for limiting the same, and the scope of the present disclosure is not limited thereto, and although the present disclosure is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive of the technical solutions described in the foregoing embodiments or equivalent technical features thereof within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present disclosure, and should be construed as being included therein. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.

Claims

1. An information pushing method, comprising:

acquiring search information of a client;

2. The information push method according to claim 1, wherein the obtaining of the media content matched with the search information in the pre-established media content library according to different matching dimensions to obtain a plurality of target media contents comprises:

3. The information pushing method according to claim 1, wherein the determining, based on the obtained user behavior data, the relevancy, and the number of the media contents, a corresponding display position of each target media content when being displayed at the client comprises:

4. The information pushing method according to claim 3, wherein the user behavior data corresponding to the target media content includes a click-through rate, a number of comments, and a playing time of the target media content, and the determining the ranking score corresponding to each target media content based on the user behavior data corresponding to each target media content in the plurality of target media contents and the correlation between the target media content and the search information includes:

5. The information pushing method according to claim 3, wherein the adjusting the initial display position based on the ranking score corresponding to each target content, the user behavior data corresponding to the target media content, the matching dimension corresponding to the target media content, and the number of the media content, and determining the corresponding display position of the target media content when the target media content is displayed at the client comprises:

6. The information pushing method according to claim 5, wherein the determining a ranking score weight corresponding to the target media content in each matching dimension based on the user behavior data corresponding to each target content, the matching dimension corresponding to the target media content, and the number of media contents matching the search information in each matching dimension in the media content library comprises:

7. The information pushing method according to claim 6, wherein the determining a ranking score weight corresponding to the target media content in each matching dimension based on the user behavior data and the number of the target media content in each matching dimension and the number of the media content matched with the search information in each matching dimension in the media content library comprises:

8. The information push method according to claim 7, wherein the user behavior data corresponding to the target media content includes a click-through rate, a number of comments, and a play duration of the target media content, and the determining, based on the user behavior data corresponding to the target media content in each matching dimension, a ratio of the user behavior data in a set number of target media contents of the target media content in the matching dimension before the sorting includes:

9. An information pushing apparatus, comprising:

10. An electronic device, comprising: processor, memory and bus, the memory stores machine readable instructions executable by the processor, the processor and the memory communicate through the bus when the electronic device runs, the machine readable instructions when executed by the processor perform the steps of the information pushing method according to any one of claims 1 to 8.

11. A computer-readable storage medium, having stored thereon a computer program for performing, when executed by a processor, the steps of the information pushing method according to any one of claims 1 to 8.