CN114780849B

CN114780849B - Content recommendation method, device, server and storage medium

Info

Publication number: CN114780849B
Application number: CN202210463994.5A
Authority: CN
Inventors: 刘飞; 姚可奇; 殷雨
Original assignee: Beijing Dajia Internet Information Technology Co Ltd
Current assignee: Beijing Dajia Internet Information Technology Co Ltd
Filing date: 2022-04-29
Publication date: 2024-07-02
Anticipated expiration: 2042-04-29

Abstract

The present disclosure relates to a content recommendation method, apparatus, server, storage medium and computer program product. The method comprises the following steps: determining an account location of a current account in response to a content acquisition request of the current account; screening second recommended content with the content position matched with the account position from the first recommended content; the first recommended content is content with a content type meeting preset recommended conditions, and the content position is represented by native information of a target object in the first recommended content; recommending the second recommended content to the current account. By adopting the method, the recommendation accuracy of the content can be improved.

Description

Content recommendation method, device, server and storage medium

Technical Field

The present disclosure relates to the field of internet technology, and in particular, to a content recommendation method, apparatus, server, storage medium, and computer program product.

Background

With the development of internet technology, a recommendation system recommends contents to an account according to account requirements.

In the related art, in the business scenario of the same city, the content with the same event occurrence position and account position is generally recommended to the account; but merely considering the event occurrence position may result in low recommendation accuracy of the content.

Disclosure of Invention

The present disclosure provides a content recommendation method, apparatus, server, storage medium, and computer program product to at least solve the problem of low content recommendation accuracy in the related art. The technical scheme of the present disclosure is as follows:

According to a first aspect of an embodiment of the present disclosure, there is provided a content recommendation method, including:

Determining an account location of a current account in response to a content acquisition request of the current account;

Screening second recommended content with the content position matched with the account position from the first recommended content; the first recommended content is content with a content type meeting preset recommended conditions, and the content position is represented by native information of a target object in the first recommended content;

Recommending the second recommended content to the current account.

In an exemplary embodiment, before screening the second recommended content whose content position matches the account position from the first recommended content, the method further includes:

acquiring the first recommended content;

Identifying native place information of a target object in the first recommended content;

and determining the native place information of the target object in the first recommended content as the content position matched with the first recommended content.

In an exemplary embodiment, the identifying the native information of the target object in the first recommended content includes:

Determining a target object in the first recommended content;

Identifying an object identifier of a target object in the first recommended content;

and inquiring the matching relation between the preset object identification and the native information to obtain the native information of the target object in the first recommended content.

In an exemplary embodiment, the content acquisition request is used to characterize an acquisition request for content associated with the account location and having a content type that satisfies the preset recommendation condition;

The recommending the second recommended content to the current account includes:

According to the content recommendation degree of the second recommended content, arranging the second recommended content to obtain the arranged second recommended content;

Recommending the arranged second recommended content to the current account.

In an exemplary embodiment, the content acquisition request is used to characterize an acquisition request for content associated with the account location;

Screening out third recommended content with content recommendation degree meeting preset recommendation degree from the second recommended content, and screening out fourth recommended content with content recommendation degree meeting the preset recommendation degree from the content associated with the account position;

Recommending the third recommended content and the fourth recommended content to the current account.

In an exemplary embodiment, the method further comprises:

Acquiring a content identifier of the content which is associated with the account position and the content recommendation degree of which meets the preset condition;

Arranging the content identifiers according to the sequence of the content recommendation degree from high to low to obtain a content identifier list matched with the account position;

updating the content identification list according to the content identification of the second recommended content to obtain an updated content identification list;

Recommending the updated content identification list to the current account.

In an exemplary embodiment, the method further comprises:

Adjusting the list name of the updated content identification list to be a target list name under the condition that the first N content identifications in the updated content identification list are the content identifications of the second recommended content; the target list name is a list name associated with the second recommended content, and N is a positive integer.

According to a second aspect of the embodiments of the present disclosure, there is provided a content recommendation apparatus including:

A location determination unit configured to perform determination of an account location of a current account in response to a content acquisition request of the current account;

a content screening unit configured to perform screening of second recommended content whose content position matches the account position from the first recommended content; the first recommended content is content with a content type meeting preset recommended conditions, and the content position is represented by native information of a target object in the first recommended content;

And a content recommending unit configured to perform recommending the second recommended content to the current account.

In an exemplary embodiment, the apparatus further comprises a location identification unit configured to perform acquiring the first recommended content; identifying native place information of a target object in the first recommended content; and determining the native place information of the target object in the first recommended content as the content position matched with the first recommended content.

In an exemplary embodiment, the location identifying unit is further configured to perform determining a target object in the first recommended content; identifying an object identifier of a target object in the first recommended content; and inquiring the matching relation between the preset object identification and the native information to obtain the native information of the target object in the first recommended content.

The content recommending unit is further configured to execute arrangement of the second recommended content according to the content recommendation degree of the second recommended content to obtain an arranged second recommended content; recommending the arranged second recommended content to the current account.

The content recommending unit is further configured to execute screening out third recommended content with content recommendation degree meeting preset recommendation degree from the second recommended content, and screening out fourth recommended content with content recommendation degree meeting the preset recommendation degree from the content associated with the account position; recommending the third recommended content and the fourth recommended content to the current account.

In an exemplary embodiment, the apparatus further includes a list recommendation unit configured to perform acquiring a content identification of a content associated with the account location, and the content recommendation degree satisfies a preset condition; arranging the content identifiers according to the sequence of the content recommendation degree from high to low to obtain a content identifier list matched with the account position; updating the content identification list according to the content identification of the second recommended content to obtain an updated content identification list; recommending the updated content identification list to the current account.

In an exemplary embodiment, the apparatus further includes a name adjustment unit configured to perform adjustment of a list name of the updated content identification list to a target list name in a case where a first N content identifications in the updated content identification list are content identifications of the second recommended content; the target list name is a list name associated with the second recommended content, and N is a positive integer.

According to a third aspect of embodiments of the present disclosure, there is provided a server comprising:

A processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement a content recommendation method as claimed in any one of the preceding claims.

According to a fourth aspect of embodiments of the present disclosure, there is provided a computer readable storage medium, which when executed by a processor of a server, causes the server to perform the content recommendation method as described in any one of the above.

According to a fifth aspect of embodiments of the present disclosure, there is provided a computer program product comprising instructions therein, which when executed by a processor of a server, enable the server to perform the content recommendation method as described in any one of the above.

The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects:

Determining an account location of the current account by responding to the content acquisition request of the current account; screening second recommended content with the content position matched with the account position from the first recommended content; the first recommended content is content with the content type meeting the preset recommended condition, and the content position is represented by the native information of the target object in the first recommended content; finally recommending the second recommended content to the current account; in this way, when content recommendation is performed, the content with the local information of the target object matched with the account position is screened out from the content with the content type meeting the preset recommendation condition and recommended to the current account, the content with the content type meeting the preset recommendation condition and the local information of the target object in the content are comprehensively considered, so that the content recommended to the current account is more accurate, the recommendation accuracy of the content is further improved, and the defect that the recommendation accuracy of the content is lower because only the content with the event occurrence position identical with the account position is recommended to the current account and the content with the local information of the target object matched with the account position is ignored is avoided.

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

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure and do not constitute an undue limitation on the disclosure.

Fig. 1 is a flowchart illustrating a content recommendation method according to an exemplary embodiment.

FIG. 2 is a flowchart illustrating steps for determining a content location to which first recommended content matches, according to an exemplary embodiment.

Fig. 3 is a flowchart illustrating another content recommendation method according to an exemplary embodiment.

Fig. 4 is a flow chart illustrating the association of olympic content with a same city according to an exemplary embodiment.

Fig. 5 is a flow chart illustrating a determination of a content list of the same city olympics according to an example embodiment.

FIG. 6 is a flowchart illustrating a determination of a co-city olympic-air list, according to an example embodiment.

Fig. 7 is a flow chart illustrating the acquisition of olympic area content according to an exemplary embodiment.

FIG. 8 is a flow chart illustrating recall of co-city Olympic content in accordance with an exemplary embodiment.

FIG. 9 is a flowchart illustrating the issuing of a co-city Olympic Games list, in accordance with an exemplary embodiment.

Fig. 10 is a block diagram illustrating a content recommendation device according to an exemplary embodiment.

Fig. 11 is a block diagram of a server, according to an example embodiment.

Detailed Description

In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the technical solutions of the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

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.

It should be further 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 presentation, analyzed data, etc.) related to the present disclosure are information and data authorized by the user or sufficiently authorized by each party.

FIG. 1 is a flowchart illustrating a content recommendation method, as shown in FIG. 1, for use in a server, according to an exemplary embodiment; it will be appreciated that the method may also be applied to a terminal, and may also be applied to a system comprising a terminal and a server, and implemented by interaction of the terminal and the server. In this exemplary embodiment, the method includes the steps of:

In step S110, an account location of the current account is determined in response to the content acquisition request of the current account.

The account refers to a registration account of an application program in the terminal, such as a registration account of a short video application program, a registration account of a video browsing program, and the like. The current account refers to an authorized account that needs processing analysis, and specifically refers to a recommended object of the content. The account location refers to a location or roaming location of the current account, such as a location city or roaming city of the current account.

The content acquisition request refers to an acquisition request for specific content, such as an acquisition request for content associated with an account location, an acquisition request for content associated with an account location and satisfying a content type, and the like, specifically refers to a co-city content acquisition request. It should be noted that, the content may refer to video, live broadcast, pictures, advertisements, news information, and the like, and the disclosure is not limited thereto.

Specifically, the server, in response to a content acquisition request of a current account, acquires an account location in the content acquisition request as an account location of the current account. For example, the server analyzes the content acquisition request to obtain a plurality of request information; and screening the account position from the plurality of request information to serve as the account position of the current account.

For example, if the account location in the content acquisition request of the current account is city a, the account location of the current account is city a.

In step S120, screening out a second recommended content whose content position matches the account position from the first recommended content; the first recommended content is content with a content type meeting preset recommendation conditions, and the content position is represented by the native information of the target object in the first recommended content.

The content type refers to a type corresponding to the content, and the preset recommendation condition refers to that the recommendation degree is larger than the preset recommendation degree. The content whose content type satisfies the preset recommendation condition refers to the content corresponding to the content type with the recommendation degree larger than the preset recommendation degree, and is used for representing popular content such as olympic games, world cup content, world tournament content and the like. It should be noted that the first recommended content includes a plurality of contents, and each content matches a corresponding content location.

Wherein, the target object refers to a key object in the first recommended content, such as a key athlete in the olympic games; the native place information of the target object refers to the native place corresponding to the target object, for example, the native place of the key athlete in the olympic games.

The second recommended content refers to the content with the same content position as the account position in the first recommended content. It should be noted that the second recommended content includes a plurality of contents, and the content position corresponding to each content is the same as the account position of the current account.

It should be noted that, when recommending content associated with an account location (as compared with urban content), in the prior art, recommending is performed by using an event occurrence location in the content, for example, if the event occurrence location in the content is the same as an account location of a current account, then recommending the content to the current account; the present disclosure recommends the content by using the through information corresponding to the target object in the content, for example, if the native information corresponding to the target object in the content is the same as the account position of the current account, the content is recommended to the current account.

Specifically, the server acquires native information of a target object in the first recommended content as a content position of the first recommended content; and screening the content with the content position matched with the account position from the first recommended content according to the content position to serve as second recommended content.

For example, the first recommended content includes content a, content B, and content c, the corresponding content locations are city a, and city B, respectively, and the current account location is city a, and the second recommended content is content a and content B.

In step S130, the second recommended content is recommended to the current account.

Specifically, the server recommends the second recommended content to the terminal corresponding to the current account, and the terminal displays the received second recommended content through the content display page for the current account to view, so that the current account can timely know the content associated with the target object with the same native information as the current account.

In the content recommendation method, the account position of the current account is determined by responding to the content acquisition request of the current account; screening second recommended content with the content position matched with the account position from the first recommended content; the first recommended content is content with the content type meeting the preset recommended condition, and the content position is represented by the native information of the target object in the first recommended content; finally recommending the second recommended content to the current account; in this way, when content recommendation is performed, the content with the local information of the target object matched with the account position is screened out from the content with the content type meeting the preset recommendation condition and recommended to the current account, the content with the content type meeting the preset recommendation condition and the local information of the target object in the content are comprehensively considered, so that the content recommended to the current account is more accurate, the recommendation accuracy of the content is further improved, and the defect that the recommendation accuracy of the content is lower because only the content with the event occurrence position identical with the account position is recommended to the current account and the content with the local information of the target object matched with the account position is ignored is avoided.

In an exemplary embodiment, the first recommended content includes content matching different content locations; in the step S120, screening the second recommended content whose content position matches the account position from the first recommended content specifically includes: screening out the content with the same content position as the account position from the content matched with different content positions; and determining the content with the same content position as the account position as second recommended content.

The content matching with the content location refers to a content set formed by content with the same native information of the target object, for example, olympic content matching with city a, and native information of key athletes in the olympic content is the same as city a.

The first recommended content includes a plurality of contents matched with different content positions, such as contents matched with city a, contents matched with city B, contents matched with city C, and the like. It should be noted that, the content matching each content location may be plural.

Specifically, a server acquires first recommended content in advance; identifying the native information of the target object in the first recommended content; determining the native information of the target object in the first recommended content as the content position matched with the first recommended content; in the first recommended content, content with the same content position is aggregated together to obtain content matched with different content positions; and screening out the content with the same content position as the account position of the current account from the content matched with the different content positions as second recommended content.

For example, for the olympic content, the server determines the native information of the key athlete in the olympic content as the content location matched by the olympic content, and then combines the olympic content with the same content location to obtain the olympic content matched with different content locations, such as the olympic content matched with city a, the olympic content matched with city B, and the like. Assuming that the account location of the current account is city B, the second recommended content is olympic content matching city B.

According to the technical scheme provided by the embodiment of the disclosure, the content with the same content position as the account position of the current account is screened out from the content matched with different content positions to be used as second recommended content recommended to the current account, wherein the content position is represented by native through information of a target object in the content; therefore, the content with the content type meeting the preset recommendation condition and the penetration information of the target object in the content are comprehensively considered, so that the determined recommended content is more accurate, and the accuracy of determining the recommended content is improved.

In an exemplary embodiment, as shown in fig. 2, before screening the second recommended content whose content position matches the account position from the first recommended content, the method further includes a step of determining the content position matched by the first recommended content, specifically including the following steps:

In step S210, a first recommended content is acquired.

In step S220, the native information of the target object in the first recommended content is identified.

In step S230, the native information of the target object in the first recommended content is determined as the content position to which the first recommended content matches.

Specifically, the server screens out content corresponding to a content type with recommendation degree larger than a preset recommendation degree from a content library storing contents with multiple content types as first recommended content; determining a target object in the first recommended content, and identifying native information of the target object in the first recommended content through a native information identification instruction; and determining the native information of the target object in the first recommended content as the content position matched with the first recommended content.

For example, the server obtains the olympic games content and identifies the native information of key athletes in the olympic games content; and determining the native information of the key athletes in the Olympic content as the content position matched with the Olympic content.

According to the technical scheme provided by the embodiment of the disclosure, through the penetration information of the target object in the first recommended content, the content position matched with the first recommended content is determined; therefore, the content position of the first recommended content is predetermined, so that the second recommended content with the content position matched with the account position of the current account can be quickly screened out from the first recommended content, and the determination efficiency of the second recommended content is improved. Meanwhile, when determining the content position of the first recommended content, the local information of the target object in the first recommended content is considered instead of the event occurrence position in the first recommended content, so that the determination accuracy of the second recommended content is improved.

In an exemplary embodiment, the step S220 identifies the native information of the target object in the first recommended content, and specifically includes: determining a target object in the first recommended content; identifying an object identifier of a target object in the first recommended content; and inquiring the matching relation between the preset object identification and the native information to obtain the native information of the target object in the first recommended content.

The object identification refers to unique identification information of a target object, and specifically refers to an object name, such as an athlete name.

The object identifiers and native information have a one-to-one matching relationship, and each object identifier is matched with corresponding native information, for example, the native information corresponding to the athlete U1 is city A, and the native information corresponding to the athlete U2 is city B.

Specifically, the server identifies the object in the first recommended content according to an image identification algorithm (such as a target detection algorithm); screening out the object with the highest association degree with the content from the objects, and taking the object as a target object in the first recommended content; extracting the face characteristics of the target object, and inquiring the matching relation between the preset face characteristics and the object identification according to the face characteristics of the target object to obtain the object identification of the target object; and inquiring the matching relation between the preset object identification and the through information according to the object identification of the target object to obtain the native information of the target object in the first recommended content.

For example, the olympic game content a includes a plurality of athletes, wherein the athlete U1 is a target athlete, the name of the athlete U1 is N1, the native information corresponding to N1 is city a, and the native information of the target athlete U1 in the olympic game content a is city a.

According to the technical scheme provided by the embodiment of the disclosure, the target object in the first recommended content is determined, and the native information of the target object in the first recommended content is identified, so that the subsequent determination of the native information of the target object in the first recommended content as the content position matched with the first recommended content is facilitated, and the accuracy of determining the content position of the content is improved.

In an exemplary embodiment, the content acquisition request is used to characterize an acquisition request for content associated with an account location and having a content type that meets a preset recommendation condition; step S130, recommending the second recommended content to the current account, specifically includes: according to the content recommendation degree of the second recommended content, arranging the second recommended content to obtain the arranged second recommended content; and recommending the arranged second recommended content to the current account.

The content recommendation degree is used for measuring the recommendation probability of the content, and the second recommendation content is generally arranged according to the sequence of the recommendation degree from high to low.

Specifically, the server extracts content characteristics of the second recommended content, and inputs the content characteristics of the second recommended content into a pre-trained content recommendation model (such as a fine-ranking model) to obtain the recommendation degree of the second recommended content; arranging the second recommended content according to the sequence of the recommendation degree from high to low to obtain the arranged second recommended content; recommending the arranged second recommended content to the terminal corresponding to the current account, and displaying the received arranged second recommended content through a content display page of the terminal, so that the current account can be conveniently checked.

For example, in the content browsing page in the same city, the current account selects "olympic area", the trigger terminal generates an acquisition request for olympic content associated with the account location (such as a positioning location) of the current account, and sends the acquisition request to the corresponding server; and the server screens out target Olympic content with the content position matched with the account position of the current account from the Olympic content library according to the acquisition request, arranges the target Olympic content and then sends the target Olympic content to the terminal, and the terminal displays the received target Olympic content.

According to the technical scheme provided by the embodiment of the disclosure, according to the acquisition request for the content which is associated with the account position and has the content type meeting the preset recommendation condition, the second recommended content of which the content position is the same as the account position of the current account is screened out from the first recommended content corresponding to the content type and recommended to the current account, so that the accurate pushing of the popular content in the same city scene is realized, and the recommendation accuracy of the content is improved.

In an exemplary embodiment, the content acquisition request is used to characterize an acquisition request for content associated with an account location; step S130, recommending the second recommended content to the current account, specifically includes: screening out third recommended content with content recommendation degree meeting preset recommendation degree from the second recommended content, and screening out fourth recommended content with content recommendation degree meeting preset recommendation degree from the content associated with the account position; and recommending the third recommended content and the fourth recommended content to the current account.

The content recommendation degree meets the preset recommendation degree, which means that the content recommendation degree is larger than the preset recommendation degree. The preset recommendation degree can be adjusted according to actual conditions, and the method is not particularly limited.

The third recommended content refers to content with content recommendation degree larger than preset recommendation degree in the second recommended content; the fourth recommended content is content with a content recommendation degree greater than a preset recommendation degree among the contents associated with the account position.

Wherein, the content associated with the account location refers to the content of which the event occurrence location is the same as the account location. The event occurrence location refers to an occurrence location of an event in the content, for example, the content a describes a certain event of the city a, and then the event occurrence location of the content a is the city a.

Specifically, the server screens out the content with the content recommendation degree larger than the preset recommendation degree from the second recommended content as a third recommended content; acquiring the content with the same event occurrence position as the account position from a content library as the content associated with the account position; screening out contents with the content recommendation degree larger than the preset recommendation degree from the contents associated with the account position, and taking the contents as fourth recommended contents; according to the content recommendation degree, the third recommended content and the fourth recommended content are arranged to obtain arranged recommended content, the arranged recommended content is recommended to the terminal corresponding to the current account, and the received arranged recommended content is displayed through the content display page of the terminal, so that the current account can be conveniently checked.

For example, assuming that the popular content is olympic content, in the content browsing page, the current account selects "same city content", the trigger terminal generates an acquisition request for the content associated with the account location of the current account, and sends the acquisition request to the corresponding server; the server screens out candidate Olympic content with the content position matched with the account position of the current account from the Olympic content library according to the acquisition request; and screening target Olympic content with content recommendation degree larger than preset recommendation degree from the candidate Olympic content. Meanwhile, the server screens candidate contents with the same event occurrence position and account position from the content library according to the acquisition request; screening target content with content recommendation degree larger than preset recommendation degree from candidate content; according to the content recommendation degree, the target Olympic content and the target content are arranged and then sent to the terminal, and the received target Olympic content and target content are displayed through the terminal.

According to the technical scheme provided by the embodiment of the disclosure, according to the acquisition request for the content associated with the account position, the third recommended content with the content recommendation degree meeting the preset recommendation degree is screened out from the second recommended content with the content position identical to the account position, the fourth recommended content with the content recommendation degree meeting the preset recommendation degree is screened out from the content with the content position identical to the account position, and finally the third recommended content and the fourth recommended content are recommended to the current account, so that the second recommended content with the content position identical to the account position and the content with the event position identical to the account position are comprehensively considered, the accurate pushing of the content is facilitated, and the recommendation accuracy of the content is improved.

In an exemplary embodiment, the content recommendation method provided in the present disclosure further includes: acquiring a content identifier of a content which is associated with the account position and has a content recommendation degree meeting a preset condition; arranging the content identifiers according to the sequence of the content recommendation degree from high to low to obtain a content identifier list matched with the account position; updating the content identification list according to the content identification of the second recommended content to obtain an updated content identification list; and recommending the updated content identification list to the current account.

Wherein, the content associated with the account location refers to the content of which the event occurrence location is the same as the account location. The content with the content recommendation degree satisfying the preset condition refers to the content with the content recommendation degree being larger than the preset recommendation degree.

Wherein each content is matched with a content identification. The content identifier refers to topic information, key information and the like of the content, and the current account can view the detailed information of the content by clicking the content identifier of the content.

Wherein, each account position is matched with a content identification list, such as the same city hot list corresponding to different cities; each content identification list comprises M content identifications which are arranged in the order of high content recommendation degree. M is a positive integer, and can be specifically adjusted according to actual conditions.

The content identifier list matched with the account position refers to a list formed by the first M content identifiers (such as the first 10 content identifiers and the first 15 content identifiers) in the content identifiers corresponding to the content with the screened content recommendation degree meeting the preset condition in the content associated with the account position.

Wherein the updated content identification list includes one or more of the content identifications of the second recommended content. For example, if the second recommended content includes content whose content recommendation degree satisfies the preset condition, the content identifiers of the content are added to the content identifier list matched with the account position, so as to obtain an updated content identifier list. In an actual scene, the updated content identification list is a list formed by the first M content identifications (such as the first 10 and the first 15) in the content identifications corresponding to the content with the screened content recommendation degree meeting the preset condition from the content and the second recommended content which are associated with the account position and have the content recommendation degree meeting the preset condition.

Specifically, the server obtains content associated with the account location from a content library; screening out the content with the content recommendation degree meeting the preset condition from the content associated with the account position; acquiring content identifiers of the content, and arranging the content identifiers according to the sequence of the content recommendation degree from high to low to obtain arranged content identifiers; screening out the first M content identifiers from the arranged content identifiers, and combining the first M content identifiers to obtain a content identifier list which is used as a content identifier list matched with the account position; under the condition that the second recommended content comprises content with content recommendation degree meeting the preset condition, arranging content identifiers in a content identifier list and content identifiers of the content with content recommendation degree meeting the preset condition in the sequence from high to low according to the content recommendation degree, and screening out the first M content identifiers from the arranged content identifiers to obtain an updated content identifier list; recommending the updated content identification list to the terminal corresponding to the current account, and displaying the received updated content identification list through the content display page of the terminal, so that the current account can be conveniently checked.

For example, the content identifier list matched with the account position includes a content identifier A1, a content identifier A2, a content identifier A3, a content identifier A4, a content identifier A5, a content identifier A6, a content identifier A7, a content identifier A8, a content identifier A9, and a content identifier a10, where content recommendation degrees corresponding to the content identifiers are all greater than a preset recommendation degree; the second recommended content is assumed to comprise content with content recommendation degree larger than preset recommendation degree, and content identifiers corresponding to the content are respectively B1, B2 and B3; the content recommendation degree corresponding to the content identifier B1 is between the content recommendation degree corresponding to the content identifier A2 and the content recommendation degree corresponding to the content identifier A3, the content recommendation degree corresponding to the content identifier B2 is between the content recommendation degree corresponding to the content identifier A4 and the content recommendation degree corresponding to the content identifier A5, the content recommendation degree corresponding to the content identifier B3 is between the content recommendation degree corresponding to the content identifier A6 and the content recommendation degree corresponding to the content identifier A7, and then the content identifier list is: content identifier A1, content identifier A2, content identifier B1, content identifier A3, content identifier A4, content identifier B2, content identifier A5, content identifier A6, content identifier B3, and content identifier A7.

According to the technical scheme provided by the embodiment of the disclosure, the content identification list matched with the account position is updated by utilizing the content identification of the second recommended content, the updated content identification list is obtained, and the updated content identification list is recommended to the current account, so that the purpose of recommending the content with the content recommendation degree meeting the preset condition to the current account is realized, and the recommendation accuracy of the content is improved.

In an exemplary embodiment, the content recommendation method provided in the present disclosure further includes: adjusting the list name of the updated content identification list to be a target list name under the condition that the first N content identifications in the updated content identification list are the content identifications of the second recommended content; the target list name is a list name associated with the second recommended content, and N is a positive integer.

Wherein N is less than M; such as n=3, m=10.

The list names refer to names corresponding to the updated content identification list, and are similar to a city hot list. The target list name refers to a list name associated with the second recommended content, such as an Olympic Games list.

For example, assuming that the first 3 contents of the updated list are olympic content or the first 3 contents of the updated list include olympic content, the name of the list is updated to "olympic list".

According to the technical scheme provided by the embodiment of the disclosure, under the condition that the first N content identifiers in the updated content identifier list are the content identifiers of the second recommended content, the list names of the updated content identifier list are adjusted to be the list names associated with the second recommended content, so that the aim of dynamically updating the list names of the content identifier list is fulfilled.

Fig. 3 is a flowchart illustrating another content recommendation method according to an exemplary embodiment, which is used in a server as shown in fig. 3, and includes the steps of:

In step S310, a first recommended content is acquired; the first recommended content is content with a content type meeting preset recommended conditions.

In step S320, a target object in the first recommended content is determined.

In step S330, the object identification of the target object in the first recommended content is identified.

In step S340, a matching relationship between the preset object identifier and the native information is queried to obtain native information of the target object in the first recommended content.

In step S350, the native information of the target object in the first recommended content is determined as the content position to which the first recommended content matches.

In step S360, the account location of the current account is determined in response to the content acquisition request of the current account.

In step S370, second recommended content whose content position matches the account position is screened out from the first recommended content.

In step S380, the second recommended content is recommended to the current account.

In the content recommendation method, when content recommendation is performed, content with the native information of the target object matched with the account position is screened out from the content with the content type meeting the preset recommendation condition and recommended to the current account, the content with the content type meeting the preset recommendation condition and the native information of the target object in the content are comprehensively considered, so that the content recommended to the current account is more accurate, the recommendation accuracy of the content is further improved, and the defect that the recommendation accuracy of the content is lower because only the content with the event occurrence position identical with the account position is recommended to the current account and the content with the native information of the target object matched with the account position is ignored is avoided.

In order to more clearly clarify the content recommendation method provided by the embodiments of the present disclosure, the content recommendation method will be specifically described in the following by using a specific embodiment. In one embodiment, taking olympic content as an example, the content recommendation method specifically includes 3 parts, namely olympic and co-city business association, co-city olympic content production and co-city olympic content consumption. The basic flow is as follows:

Step one: olympic is associated with the same city service. Referring to fig. 4, in general, a piece of video content includes time, place, person, event, etc. elements, an olympic video is typically a highlight moment such as training, competition, and capturing of a crown of an athlete, and an olympic video will include an athlete related to the video, and according to the native place of the athlete, the olympic video is associated with a city location or roaming, and is displayed in a business scene of the same city.

Step two: the same city olympic content production contains 2 parts, namely olympic video and same city olympic hot list. Referring to fig. 5, with respect to the olympic games, the content data of the olympic games produced by the same city end consumption operation is filtered out according to the configuration information (such as player name and native place of the player) of the national team; different levels and expiration times are set for Olympic content according to the content configuration information, and the Olympic content is stored in a Town Olympic content library (such as a MySQL database). Referring to fig. 6, first, creating a hotspot in the same-city hotspot operation background, and then screening out olympic content according to the province of the hotspot, and correlating the olympic content; when the Olympic hotspot penetrates out at the position 3 before the list, the list is named as an Olympic hotspot list.

Step three: the content consumption of the same city olympic games comprises 3 parts, namely the same city screening frame service, the same city olympic games content recall and the same city olympic hot list. For the same city screening frame service, referring to fig. 7, an "olympic area" screening item is added in the same city screening frame, and the user can select "olympic area" to screen olympic content related to a positioning city or a roaming city. For the same city olympic content recall, referring to fig. 8, the user enters the same city page, requests a recommendation server according to the user positioning or roaming city, and the recommendation server issues the corresponding olympic content to the user according to a certain strategy according to the city positioning, and renders a content page display and a label. Referring to fig. 9, for the co-city olympic board, the user enters the co-city page, and the recommendation server issues a co-city olympic board card according to the policy, if the user currently locates provinces or roams and includes a co-city olympic hotspot in the province olympic board, the co-city olympic board card display title is changed into co-city olympic.

In the content recommendation method, the following technical effects can be achieved: (1) The Olympic atmosphere in the same city service is created, the Olympic content consumption scene of the user is expanded, and the content recommendation accuracy is improved. (2) The scheme can be used as a general scheme for combining activities and city-sharing services, and is related to the positioning or roaming city of the city-sharing users through the places and the characters in the video content.

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.

It should be understood that the same/similar parts of the embodiments of the method described above in this specification may be referred to each other, and each embodiment focuses on differences from other embodiments, and references to descriptions of other method embodiments are only needed.

Based on the same inventive concept, the embodiment of the present disclosure also provides a content recommendation apparatus for implementing the above-mentioned related content recommendation method.

Fig. 10 is a block diagram illustrating a content recommendation device according to an exemplary embodiment. Referring to fig. 10, the apparatus includes a location determining unit 1010, a content filtering unit 1020, and a content recommending unit 1030.

The location determination unit 1010 is configured to perform determination of an account location of the current account in response to a content acquisition request of the current account.

A content screening unit 1020 configured to perform screening of second recommended content whose content position matches the account position from the first recommended content; the first recommended content is content with a content type meeting preset recommendation conditions, and the content position is represented by the native information of the target object in the first recommended content.

The content recommending unit 1030 is configured to perform recommending the second recommended content to the current account.

In an exemplary embodiment, the content recommendation device further includes a location identification unit configured to perform acquisition of the first recommended content; identifying the native information of the target object in the first recommended content; and determining the native information of the target object in the first recommended content as the content position matched with the first recommended content.

In an exemplary embodiment, the content acquisition request is used to characterize an acquisition request for content associated with an account location and having a content type that meets a preset recommendation condition;

The content recommending unit 1030 is further configured to perform ranking of the second recommended content according to the content recommendation degree of the second recommended content, to obtain a ranked second recommended content; and recommending the arranged second recommended content to the current account.

In an exemplary embodiment, the content acquisition request is used to characterize an acquisition request for content associated with an account location;

the content recommending unit 1030 is further configured to perform screening out a third recommended content whose content recommendation degree satisfies a preset recommendation degree from the second recommended content, and screening out a fourth recommended content whose content recommendation degree satisfies the preset recommendation degree from the content associated with the account position; and recommending the third recommended content and the fourth recommended content to the current account.

In an exemplary embodiment, the content recommendation device further includes a list recommendation unit configured to perform acquisition of content identification of content associated with the account location and having a content recommendation degree satisfying a preset condition; arranging the content identifiers according to the sequence of the content recommendation degree from high to low to obtain a content identifier list matched with the account position; updating the content identification list according to the content identification of the second recommended content to obtain an updated content identification list; and recommending the updated content identification list to the current account.

In an exemplary embodiment, the content recommendation device further includes a name adjustment unit configured to perform adjustment of a list name of the updated content identification list to a target list name in a case where the first N content identifications in the updated content identification list are content identifications of the second recommended content; the target list name is a list name associated with the second recommended content, and N is a positive integer.

The specific manner in which the various modules perform the operations in the apparatus of the above embodiments have been described in detail in connection with the embodiments of the method, and will not be described in detail herein.

The respective modules in the content recommendation apparatus described above may be implemented in whole or in part by software, hardware, and combinations 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.

Fig. 11 is a block diagram illustrating a server 1100 for performing a content recommendation method according to an exemplary embodiment. Referring to FIG. 11, a server 1100 includes a processing component 1120 that further includes one or more processors, and memory resources represented by memory 1122, for storing instructions, such as application programs, executable by the processing component 1120. An application program stored in memory 1122 may include one or more modules each corresponding to a set of instructions. Further, the processing component 1120 is configured to execute instructions to perform the above-described methods.

The server 1100 may further include: the power component 1124 is configured to perform power management of the server 1100, and the wired or wireless network interface 1126 is configured to connect the server 1100 to a network, and input output (I/O) interface 1128. The Server 1100 may operate based on an operating system stored in the memory 1122, such as Windows Server, mac OS X, unix, linux, freeBSD, or the like.

In an exemplary embodiment, a computer-readable storage medium is also provided that includes instructions, such as memory 1122 including instructions, that are executable by a processor of server 1100 to perform the above-described method. The storage medium may be a computer readable storage medium, which may be, for example, ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

In an exemplary embodiment, a computer program product is also provided, comprising instructions therein, executable by a processor of the server 1100 to perform the above-described method.

It should be noted that the descriptions of the foregoing apparatus, the server, the computer readable storage medium, the computer program product, and the like according to the method embodiments may further include other implementations, and specific implementation manners may refer to descriptions of related method embodiments, which are not described herein in detail.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any adaptations, uses, or adaptations of the disclosure following the general principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It is to be understood that the present disclosure is not limited to the precise arrangements and instrumentalities shown in the drawings, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A content recommendation method, comprising:

Recommending the second recommended content to the current account.

2. The method of claim 1, further comprising, prior to screening out a second recommended content from the first recommended content whose content location matches the account location:

acquiring the first recommended content;

3. The method of claim 2, wherein the identifying the native information of the target object in the first recommended content comprises:

Determining a target object in the first recommended content;

4. The method according to claim 1, wherein the content acquisition request is used to characterize an acquisition request for content associated with the account location and having a content type satisfying the preset recommendation condition;

Recommending the arranged second recommended content to the current account.

5. The method of claim 1, wherein the content acquisition request is used to characterize an acquisition request for content associated with the account location;

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

Recommending the updated content identification list to the current account.

7. The method of claim 6, wherein the method further comprises:

8. A content recommendation device, comprising:

9. The apparatus of claim 8, further comprising a location identification unit configured to perform acquiring the first recommended content; identifying native place information of a target object in the first recommended content; and determining the native place information of the target object in the first recommended content as the content position matched with the first recommended content.

10. The apparatus of claim 9, wherein the location identification unit is further configured to perform determining a target object in the first recommended content; identifying an object identifier of a target object in the first recommended content; and inquiring the matching relation between the preset object identification and the native information to obtain the native information of the target object in the first recommended content.

11. The apparatus of claim 8, wherein the content acquisition request is used to characterize an acquisition request for content associated with the account location and having a content type that satisfies the preset recommendation condition;

12. The apparatus of claim 8, wherein the content acquisition request is to characterize an acquisition request for content associated with the account location;

13. The apparatus according to claim 8, further comprising a list recommendation unit configured to perform acquisition of content identification of content associated with the account location and for which content recommendation degree satisfies a preset condition; arranging the content identifiers according to the sequence of the content recommendation degree from high to low to obtain a content identifier list matched with the account position; updating the content identification list according to the content identification of the second recommended content to obtain an updated content identification list; recommending the updated content identification list to the current account.

14. The apparatus according to claim 13, further comprising a name adjustment unit configured to perform adjustment of a list name of the updated content identification list to a target list name in a case where a first N content identifications in the updated content identification list are content identifications of the second recommended content; the target list name is a list name associated with the second recommended content, and N is a positive integer.

15. A server, comprising:

A processor;

a memory for storing the processor-executable instructions;

Wherein the processor is configured to execute the instructions to implement the content recommendation method of any one of claims 1 to 7.

16. A computer readable storage medium, characterized in that instructions in the computer readable storage medium, when executed by a processor of a server, enable the server to perform the content recommendation method according to any one of claims 1 to 7.

17. A computer program product comprising instructions which, when executed by a processor of a server, enable the server to perform the content recommendation method according to any one of claims 1 to 7.