CN111026969B - Content recommendation method and device, storage medium and server - Google Patents
Content recommendation method and device, storage medium and server Download PDFInfo
- Publication number
- CN111026969B CN111026969B CN201911310500.4A CN201911310500A CN111026969B CN 111026969 B CN111026969 B CN 111026969B CN 201911310500 A CN201911310500 A CN 201911310500A CN 111026969 B CN111026969 B CN 111026969B
- Authority
- CN
- China
- Prior art keywords
- content
- user
- interactive
- interaction
- users
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/43—Querying
- G06F16/435—Filtering based on additional data, e.g. user or group profiles
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The embodiment of the application discloses a content recommendation method and device, a storage medium and a server, which are applied to the technical field of information processing. The application server determines a plurality of corresponding contents according to the user content characteristics of the target user, acquires the interactive user characteristics of each content in the plurality of contents, compares the user attribute characteristics of the target user with the interactive user characteristics of each content, and finally determines the recommendation degree of each content according to the obtained multiple groups of comparison results so as to recommend the content. In this way, in the content recommendation process, not only the content characteristics of each content are considered, but also the interactive user characteristics interacted with each content are considered, and the corresponding content is recommended for the target user by combining the user attribute characteristics of the target user, so that the recommended content is more suitable for the target user due to more dimensionalities in the content recommendation process, and the user experience of the content recommendation is improved.
Description
Technical Field
The present application relates to the field of information processing technologies, and in particular, to a content recommendation method and apparatus, a storage medium, and a server.
Background
Many application systems (such as a news system or a live broadcast system) have a content recommendation function, specifically, a user can interact with content provided in the application system through an application terminal, such as comment, forwarding or praise on the content provided by the application system, and an application server can recommend corresponding types of content to the application terminal of each user according to interaction behaviors of the application terminal of each user and the content in the application system and by combining type labels of each content in the application system. For example, if an application terminal of a user generally reviews news of a sports type, an application server may provide the application terminal of the user with content of the sports type.
However, in the existing method for recommending content based on type tags, the calculated dimension is relatively single, so that the content recommended to the application terminal is not comprehensive enough.
Disclosure of Invention
The embodiment of the application provides a content recommendation method and device, a storage medium and a server, which realize content recommendation according to the characteristics of multiple dimensions of a target user.
An aspect of the present application provides a content recommendation method, including:
acquiring user content characteristics of a target user and acquiring user attribute characteristics of the target user; the user content features are used for representing the content in the application system interacted by the application terminal of the target user;
determining a corresponding plurality of contents according to the user content characteristics;
acquiring interactive user characteristics of each content in the plurality of contents;
comparing the user attribute characteristics with the interactive user characteristics of each content respectively to obtain a plurality of groups of comparison results;
and respectively determining the recommendation degree of each content according to the multiple groups of comparison results so as to recommend the content to the application terminal of the target user.
Another aspect of the embodiment of the present application provides a content recommendation apparatus, including:
the user acquisition unit is used for acquiring the user content characteristics of the target user and acquiring the user attribute characteristics of the target user; the user content features are used for representing the content in the application system interacted by the application terminal of the target user;
a content determining unit, configured to determine a plurality of corresponding contents according to the user content characteristics;
a content feature acquiring unit, configured to acquire an interactive user feature of each of the plurality of contents;
the comparison unit is used for comparing the user attribute characteristics with the interactive user characteristics of each content respectively to obtain a plurality of groups of comparison results;
and the recommending unit is used for respectively determining the recommending degree of each content according to the multiple groups of comparison results so as to recommend the content to the application terminal of the target user.
Another aspect of the embodiments of the present application provides a storage medium storing a plurality of instructions adapted to be loaded by a processor and to perform the content recommendation method according to the embodiments of the present application.
Another aspect of an embodiment of the present application provides a server, including a processor and a storage medium;
the storage medium is used for storing a plurality of instructions, and the instructions are used for being loaded by a processor and executing the content recommendation method according to the embodiment of the application; the processor is configured to implement each instruction of the plurality of instructions.
It can be seen that, in the method of this embodiment, the application server determines a plurality of corresponding contents according to the user content characteristics of the target user, and then obtains the interactive user characteristics of each of the plurality of contents, further compares the user attribute characteristics of the target user with the interactive user characteristics of each of the contents, and finally determines the recommendation degree of each of the contents according to the obtained plurality of sets of comparison results, so as to recommend the contents. In this way, in the content recommendation process, not only the content characteristics of each content are considered, but also the interactive user characteristics interacted with each content are considered, and the corresponding content is recommended for the target user by combining the user attribute characteristics of the target user, so that the recommended content is more suitable for the target user due to more dimensionalities in the content recommendation process, and the user experience of the content recommendation is improved.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the application, and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
Fig. 1 is a schematic diagram of a content recommendation method according to an embodiment of the present application;
FIG. 2 is a flow chart of a content recommendation method provided by an embodiment of the present application;
fig. 3a is a schematic diagram of a live home page displayed by a live terminal in an application embodiment of the present application;
FIG. 3b is a schematic diagram of a radio station content recommended by an application server displayed by a live terminal in an embodiment of the present application;
FIG. 4 is a schematic diagram of an interactive user feature and a content feature of a live server storing respective live content according to an embodiment of the present application;
FIG. 5 is a schematic diagram of live content recommendation performed by a live server in an embodiment of the present application;
fig. 6 is a schematic logic structure diagram of a content recommendation device according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of a server according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, 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 application described herein may be implemented, for example, in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The embodiment of the application provides a content recommendation method which is mainly applied to a scene shown in fig. 1, wherein the scene comprises an application terminal and an application server, and a user can enable the application terminal to initiate a content recommendation process to the application server by operating the application terminal, or the application server can actively initiate a content recommendation process for the application terminal of each user. In the embodiment of the application, the application server can realize intelligent recommendation of the content by the following steps:
acquiring user content characteristics of a target user, and acquiring user attribute characteristics of the target user, wherein the user content characteristics are used for representing content in an application system interacted by an application terminal of the target user; determining a corresponding plurality of contents according to the user content characteristics; acquiring interactive user characteristics of each content in the plurality of contents; comparing the user attribute characteristics with the interactive user characteristics of each content respectively to obtain a plurality of groups of comparison results; and respectively determining the recommendation degree of each content according to the multiple groups of comparison results so as to recommend the content to the application terminal of the target user.
The application terminal and the application server can be devices in any application system, such as a live broadcast system, a news system, a video system, a novel system, or the like. The content recommendation method in the embodiment of the application belongs to a specific application of cloud technology.
The Cloud technology (Cloud technology) refers to a hosting technology for integrating hardware, software, network and other series resources in a wide area network or a local area network to realize calculation, storage, processing and sharing of data, is a generic term of network technology, information technology, integration technology, management platform technology, application technology and the like applied based on a Cloud computing business mode, can form a resource pool, and is flexible and convenient as required. Cloud computing technology will become an important support, and background services of technical networking systems require a large amount of computing, storage resources, such as video websites, picture-like websites, and more portals. Along with the high development and application of the internet industry, each article possibly has an own identification mark in the future, the identification mark needs to be transmitted to a background system for logic processing, data with different levels can be processed separately, and various industry data needs strong system rear shield support and can be realized only through cloud computing.
The simplest cloud technology is already visible everywhere in network services, such as search engines, network mailboxes, etc., and a user can obtain a large amount of information only by inputting simple instructions; in the future, mobile devices such as mobile phones and the like can develop more application services through cloud computing technology; further, analysis of DNA structure, sequencing of gene maps, analysis of cancer cells, etc. can be easily achieved by this technique in the future.
In this way, in the content recommendation process, not only the content characteristics of each content are considered, but also the interactive user characteristics interacted with each content are considered, and the corresponding content is recommended for the target user by combining the user attribute characteristics of the target user, so that the recommended content is more suitable for the target user due to more dimensionalities in the content recommendation process, and the user experience of the content recommendation is improved.
The embodiment of the application provides a content recommendation method, which is mainly a method executed by an application server, and a flow chart is shown in fig. 2, and comprises the following steps:
step 101, obtaining user content characteristics of a target user, and obtaining user attribute characteristics of the target user, wherein the user content characteristics are used for representing content in an application system interacted by an application terminal of the target user.
It may be appreciated that in one case, the user may operate the application terminal, and the application terminal may initiate a content recommendation request to the application server according to the user operation information, where the content recommendation request is used to request the application server to recommend corresponding content to the application terminal of the target user, and the application server may initiate the flow of this embodiment after receiving the content recommendation request. In another case, the application server may directly initiate the flow of this embodiment according to a certain period, and recommend corresponding content to the application terminal of each user in the application system.
The user content features herein are used to represent attribute information of content interacted by the application terminal of the target user, such as content tags, for example, the user performs interaction such as praise, comment or forwarding on a piece of news of a sports type through the news terminal, and the user content features corresponding to the piece of news may include: sports labels, etc. Specifically, the application server may first obtain a plurality of interaction behavior records of the application terminal of the target user on the content in the application system within a period of time before the current moment, where each interaction behavior record in the plurality of interaction behavior records includes a content tag of the interaction content; and then counting the content labels in the interaction behavior records, and further determining the weight values corresponding to the content labels according to the counting result, wherein the user content characteristics comprise the weight values corresponding to the content labels.
When the application terminal interacts with a certain content, the application server may store an interaction behavior record, including a content tag of the interaction content, and may further include information such as interaction time and interaction type (such as interaction of forwarding or commenting), and an identifier of an interaction user, where the content tag may be information such as a type or name of the content. When the content labels are counted, the occurrence frequencies of the content labels corresponding to the content labels in a period of time before the current time can be counted, and then the weight values corresponding to the content labels are respectively determined according to the occurrence frequencies of the content labels, wherein the weight value of the content label with higher occurrence frequency can be a higher value.
The user attribute features refer to personal attributes of the target user, such as user age, user gender, region where the user is located, user occupation and the like, which are included in registration information of the target user, and when the target user registers in the application server through the application terminal, the registration information of the target user can be stored in the application server. The application server may extract the user attribute feature from the registration information of the target user when the user attribute feature is acquired.
Step 102, determining a plurality of corresponding contents according to the user content characteristics.
Specifically, if a plurality of content tags are included in the user content feature, the application server may determine contents corresponding to the plurality of content tags, respectively, from the locally stored contents, for example, the content tags are entertainment tags, the application server may determine a plurality of entertainment news corresponding to the entertainment tags, and the like.
The number of the determined contents may be any number, or may be determined according to the size of the display screen included in the application terminal of the target user, and if the size of the display screen of the application terminal is greater than a certain threshold, the number of the determined contents is greater than a certain value. Further, the application server may determine the number of content according to the weight value of each content tag in the user content feature, for example, the content tag with a larger weight value corresponds to a larger number of content and the content tag with a smaller weight value corresponds to a smaller number of content.
Step 103, obtaining the interactive user characteristics of each content in the plurality of contents.
Here, the interactive user feature of any content is used to represent attribute information of a user of an application terminal that interacts with any content, such as information of a user's sex or a user's age, for example, the user's sex of an application terminal that interacts with a certain news item (such as praise, comment or forward, etc.) is generally male, and the user's age is between 40 and 50 years, etc. Specifically, the application server may first obtain a plurality of interaction behavior records interacted with any content, where each interaction behavior record in the plurality of interaction behavior records includes attribute information of an interaction user; and then counting attribute information of the interactive users in the plurality of interactive behavior records to obtain distribution information of the interactive users in at least one dimension, wherein the interactive user characteristics of any content comprise the distribution information of the interactive users in at least one dimension.
When an application terminal of any user interacts with any piece of content, the application server may store an interaction behavior record, including attribute information of the interacting user, and may further include information such as content tag of the interacting content, interaction time and interaction type (such as forwarding or interaction of comments, etc.), where the attribute information of the interacting user may include attribute information such as user identifier, user age, user gender, user occupation or region where the user is located.
When attribute information of the interactive users is counted, the proportion of the interactive users in a plurality of age groups can be counted under the dimension of the ages of the users; the proportion of male interaction users to female interaction users under the dimension of the gender of the users can be counted; the proportion of interactive users in each region can be counted under the dimension of the region where the user is located; the proportion of interactive users in each professional field and the like can be counted in the dimension of the user profession.
It should be noted that, when the application server initiates the flow of this embodiment, the application server may obtain the interactive user characteristics of each content; the interactive user features of each content may also be obtained and stored in the application server before the process of the present embodiment is initiated, and when the application server initiates the process of the present embodiment, the interactive user features of each content are directly extracted from the local area.
And 104, respectively comparing the user attribute characteristics with the interactive user characteristics of each content to obtain a plurality of groups of comparison results.
Specifically, the application server may compare at least one personal attribute of the target user in the user attribute features obtained in the step 101 with distribution information of the interactive user in a corresponding dimension of any content, where the obtained set of comparison results includes: distribution information, namely distribution proportion, of at least one personal attribute of the target user in the user attribute characteristics under corresponding dimensions respectively.
For example, user attribute characteristics of the target user include: men, age 25, profession engineers, and the interactive user features of a content include: under the dimension of the gender of the user, the male interaction users account for 80 percent, and the female interaction users account for 20 percent, so that the distribution proportion of the personal attribute 'men' in the attribute characteristics of the users is 80 percent; in the dimension of the user age, the interactive user accounts for 30% between 20 and 30 years old, and the distribution proportion of personal attribute 'age 25' in the user attribute characteristics is 30%; in the dimension of the user occupation, the interactive users of the engineers occupy 20%, and the distribution proportion of the personal attribute of the user attribute feature, namely the occupation of the engineers, is 20%.
And 105, respectively determining the recommendation degree of each content according to the multiple groups of comparison results so as to recommend the content to the application terminal of the target user.
Specifically, when determining the recommendation degree of the corresponding content according to any set of comparison results, the application server may determine the weight value corresponding to at least one personal attribute according to the distribution information corresponding to at least one personal attribute in any set of comparison results; and then determining the recommendation degree of the corresponding content according to the calculation result of the weight value corresponding to the at least one personal attribute.
Further, since the user content feature obtained in the step 101 may include the weight values of a plurality of content tags, when determining the recommendation degree of a certain content, the application server needs to consider not only the weight value corresponding to the personal attribute but also the weight value of the content tag of the content, and specifically, the calculation result of the weight value corresponding to at least one personal attribute and the weight value of the content tag of the content is taken as the recommendation degree of the content.
For example, a set of comparison results for a certain content includes: the distribution proportion of the personal attribute 'men' is 80%, and the determined weight value is 80; the distribution proportion of the personal attribute 'age 25' is 30%, and the determined weight value is 30; the distribution proportion of the personal attribute "professional engineer" is 20%, and the determined weight value is 20, and the sum of the weight values is 80+30+20=130. Further, if the weight value of the content tag of the content is 18, the recommendation degree of the content is 130+18=148.
It should be further noted that, after the application server has recommended each content, the application server may recommend the content with a higher recommendation degree (for example, the recommendation degree is greater than a certain threshold value) to the application terminal of the target user, so that the user may interact with the recommended content through the application terminal, and after the application terminal receives the interaction information of the user and the recommended content, the interaction information is sent to the application server; and when the application server receives the interaction information of the application terminal and the recommended content, an interaction behavior record is recorded, wherein the interaction behavior record can comprise: attribute information of the interactive user, content tags of the interactive content, interaction time, interaction type (such as interaction of forwarding or comment and the like) and the like. In this way, the application server can conveniently use the interaction behavior record of each content to recommend the content.
It can be seen that, in the method of this embodiment, the application server determines a plurality of corresponding contents according to the user content characteristics of the target user, and then obtains the interactive user characteristics of each of the plurality of contents, further compares the user attribute characteristics of the target user with the interactive user characteristics of each of the contents, and finally determines the recommendation degree of each of the contents according to the obtained plurality of sets of comparison results, so as to recommend the contents. In this way, in the content recommendation process, not only the content characteristics of each content are considered, but also the interactive user characteristics interacted with each content are considered, and the corresponding content is recommended for the target user by combining the user attribute characteristics of the target user, so that the recommended content is more suitable for the target user due to more dimensionalities in the content recommendation process, and the user experience of the content recommendation is improved.
The content recommendation method in the present application is described below with a specific application example, and the method in this embodiment is specifically applied to a live broadcast application system, where the corresponding application terminal is a live broadcast terminal, the corresponding application server is a live broadcast server, and the recommended content is specifically live broadcast content or a hosting room.
As shown in fig. 3a, the live terminal may display multiple types of live content portals in a live home page, for example, types of radio stations, sound works or video works, and when a user clicks on a live content portal of a certain type (for example, a radio station type), the live terminal may initiate a recommendation of the live content of the type to the live server. When the live broadcast server receives a recommendation request for a certain type of live broadcast content, the recommendation degree of each content is obtained according to the method of the embodiment, and then the content with a larger recommendation degree is recommended to the live broadcast terminal to be displayed to the live broadcast terminal, as shown in fig. 3b, the live broadcast terminal displays a main broadcasting room of a radio station type recommended by the live broadcast server, and the method comprises the following steps: psychological stations for user a, music stations for user b, talk movie stations for user c, etc.
The content recommendation method executed by the live broadcast server of the embodiment mainly includes the following parts:
(1) As shown in fig. 4, the live broadcast server acquires and stores interactive user characteristics and content characteristics of each live broadcast content in the live broadcast system, and specifically includes:
step 201, for any direct broadcast content uploaded by any anchor user through a direct broadcast terminal, the application server stores content characteristics of the direct broadcast content, which may include: content tags, and identification of live users.
Step 202, when any interactive user interacts with any direct broadcast content through a direct broadcast terminal, the application server records an interaction behavior record, which may specifically include: attribute information of the interactive user, content tags of the interactive content, interaction time, interaction type (such as interaction of forwarding or comment and the like) and the like.
In step 203, the application server may count and store the interactive user features corresponding to any on-air content in a period of time, and may specifically count from multiple dimensions, in this embodiment, the dimensions of the user gender and the user age.
And under the dimension of the gender of the user, the application server records according to the interaction behavior of any direct broadcast content, and the distribution proportion of the male interaction user and the female interaction user is utilized. Further, in this embodiment, the application server may determine the discrimination weight according to the distribution ratio of the male interaction users and the female interaction users, for example, if the number of male interaction users is 80% greater than that of female interaction users, the discrimination weight is 80; the number of male interaction users is the same as that of female interaction users, and the judgment weight value is 0; the number of male interaction users is 80% less than that of female interaction users, and the discrimination weight value is female 80.
Under the dimension of the user age, the application server counts the distribution proportion of the interactive users in each age group according to the interactive behavior record of any one of the direct broadcast content, and can divide the interactive users according to the granularity of 5 years, such as the distribution proportion of the interactive users in the ages of 20 to 25 years, the distribution proportion of the interactive users in the ages of 25 to 30 years, and the like. Further, in this embodiment, the application server may determine the discrimination weight according to the distribution ratio of the interactive users in each age group, for example, if the distribution ratio of the interactive users between 20 and 25 years old is 60%, the discrimination weight is 60.
(2) As shown in fig. 5, when a live terminal of a certain user 1 initiates a content recommendation process, a live server may perform content recommendation according to the following steps, which specifically includes:
in step 301, the live server first obtains the user attribute features of the user 1, which may include personal attributes of multiple dimensions such as the user's gender, the user's age, and the like. Wherein user 1 is the target user.
In step 302, the live server obtains the user content characteristics of the live content interacted with by the live terminal of the user 1.
Specifically, when the live terminal of the user 1 interacts with a certain live content, the application server records an interaction behavior record, including: attribute information of the interactive user, content labels of the interactive content, interaction time, interaction type (such as interaction of forwarding or comment) and the like; the application server may obtain a plurality of interaction behavior records within a period of time before the current time, count the occurrence frequencies of a plurality of content tags, and determine weight values of the plurality of content tags according to the occurrence frequencies of the content tags, for example: singing 45, dance 24, etc., the frequency of occurrence of content tags described as "singing" is high, and the number of interactions of user 1 with live content of the singing type is high.
In step 303, the application server determines a plurality of corresponding live contents according to the plurality of content tags in the user content characteristics and the content tags in the content characteristics of each live content stored locally.
In step 304, the application server extracts the locally stored interactive user characteristics of each live content in the plurality of live contents determined in step 303.
In step 305, the application server compares the user attribute features of the user 1 obtained in step 301 with the interactive user features of each live broadcast content, so as to obtain multiple groups of comparison results, where each group of comparison results includes distribution information, i.e. distribution proportion, of multiple personal attributes in the user attribute features under corresponding dimensions in the interactive user features of any live broadcast content.
And 306, the application server respectively determines the weight value of each personal attribute according to the distribution proportion of the plurality of personal attributes in each group of comparison results under the corresponding dimension, and then calculates the recommendation degree of the corresponding live broadcast content according to the weight value of each personal attribute.
Taking the personal attribute as the user gender as an illustration, in the interactive user characteristics of a certain live broadcast content, the distribution proportion of male interactive users is 80% more than the distribution proportion of females in the user gender dimension, namely, the judgment weight value is male 80, if the user 1 is male, the weight value of the personal attribute 'male' of the user 1 is determined to be 80, and if the user 1 is female, the weight value of the personal attribute 'female' of the user 1 is determined to be-80. Further, since the weight values of the plurality of content tags are obtained in the above step 302, when determining the recommendation degree of a certain live content, the weight value a1 of the content tag of the live content may be added to the weight value of the personal attribute, such as a1+ (-80), and the obtained added value is used as the recommendation degree of the live content.
Taking the personal attribute as the age of the user as an illustration, the distribution proportion of the interactive users 20 to 25 years old in the user age dimension in the interactive user characteristics of a certain live broadcast content is 60 percent, namely the judgment weight value is 60, and if the user 1 is 22 years old, the weight value of the personal attribute '22 years old' of the user 1 is determined to be 60. Further, in the step 302, the weight value of the content tag of a live content may be obtained as a1, and the weight value of the personal attribute "female" of the user 1 is-80, so that when determining the final recommendation degree of a live content, the weight value a1 of the content tag of the live content may be added to the weight values of a plurality of personal attributes, that is, a1+ (-80) +60, and the obtained added value is used as the recommendation degree of the live content.
In step 307, the application server recommends a plurality of live broadcast contents with larger recommendation degree to the application terminal according to the recommendation degree of each live broadcast content.
Therefore, in the method of the embodiment, by analyzing the data of the interactive user of the live broadcast content, the application server can accurately obtain the live broadcast content which is suitable for the target user (i.e. the user 1) in the aspects of gender, age and the like, and recommends the live broadcast content to the live broadcast terminal, so that the user experience is improved.
The embodiment of the application also provides a content recommendation device, such as the application server, the structure schematic diagram of which is shown in fig. 6, and the content recommendation device specifically may include:
the user obtaining unit 10 is configured to obtain a user content feature of a target user, and obtain a user attribute feature of the target user, where the user content feature is used to represent content in an application system interacted with by an application terminal of the target user.
The user obtaining unit 10 is specifically configured to obtain a plurality of interaction behavior records of the application terminal on the content in the application system within a period of time before the current time when obtaining the user content characteristics; each of the plurality of interactive behavior records comprises a content tag of the interactive content; and counting the content labels in the interaction behavior records, determining the weight values corresponding to the content labels according to the counting result, wherein the user content characteristics comprise the weight values corresponding to the content labels.
Wherein if the result of the statistics comprises: when determining the weight values corresponding to the plurality of content tags according to the statistical result, the user obtaining unit 10 is specifically configured to determine the weight values corresponding to the plurality of content tags according to the occurrence frequencies of the plurality of content tags.
A content determining unit 11, configured to determine a plurality of corresponding contents according to the user content features acquired by the user acquiring unit 10.
A content feature acquiring unit 12 for acquiring the interactive user feature of each of the plurality of contents determined by the content determining unit 11.
The content feature acquiring unit 12 is specifically configured to acquire a plurality of interaction behavior records interacted with any one of the plurality of contents when acquiring an interaction user feature of the any one of the plurality of contents, where each interaction behavior record in the plurality of interaction behavior records includes attribute information of an interaction user; counting attribute information of the interactive users in the plurality of interactive behavior records to obtain distribution information of the interactive users in at least one dimension, wherein the interactive user characteristics of any content comprise: and the distribution information of the interactive users in at least one dimension.
The content feature obtaining unit 12 counts attribute information of the interactive users in the plurality of interactive behavior records, and is specifically used for counting proportions of the interactive users in a plurality of age groups in a dimension of the user age when obtaining distribution information of the interactive users in at least one dimension; or, counting the proportion of the male interaction user to the female interaction user under the dimension of the gender of the user; or, counting the proportion of interactive users in each region under the dimension of the region where the user is located; or, counting the proportion of interactive users in each professional field under the dimension of the user profession.
And a comparing unit 13, configured to compare the user attribute features acquired by the user acquiring unit 10 with the interactive user features of each content acquired by the content feature acquiring unit 12, respectively, to obtain multiple sets of comparison results.
And a recommending unit 14, configured to determine the recommendation degree of each content according to the multiple sets of comparison results obtained by the comparing unit 13, so as to recommend content to the application terminal of the target user.
Wherein if any set of comparison results includes: the recommendation unit 14 is specifically configured to determine, when determining the recommendation degree of the corresponding content according to the any one set of comparison results, a weight value corresponding to the at least one personal attribute according to the distribution information corresponding to the at least one personal attribute; and taking the calculation result of the weight value corresponding to the at least one personal attribute as the recommendation degree of the corresponding content.
Further, the above-mentioned recommending unit 14 is further configured to recommend content with a recommendation degree greater than a certain threshold to the application terminal of the target user, and the content recommending apparatus of this embodiment may further include: a recording unit 15, configured to store an interaction behavior record of the recommended content when receiving the interaction information of the application terminal and the content recommended by the recommending unit 14.
As can be seen, in the content recommendation device of the present embodiment, the content determining unit 11 determines a plurality of corresponding contents according to the user content characteristics of the target user, the content characteristic obtaining unit 12 obtains the interactive user characteristics of each of the plurality of contents, the comparing unit 13 compares the user attribute characteristics of the target user with the interactive user characteristics of each of the contents, and the recommending unit 14 determines the recommendation degree of each of the contents according to the obtained plurality of sets of comparison results, so as to recommend the contents. In this way, in the content recommendation process, not only the content characteristics of each content are considered, but also the interactive user characteristics interacted with each content are considered, and the corresponding content is recommended for the target user by combining the user attribute characteristics of the target user, so that the recommended content is more suitable for the target user due to more dimensionalities in the content recommendation process, and the user experience of the content recommendation is improved.
The embodiment of the present application further provides a server, whose structure schematic diagram is shown in fig. 7, where the terminal device may have a relatively large difference due to different configurations or performances, and may include one or more central processing units (central processing units, CPU) 20 (e.g., one or more processors) and a memory 21, and one or more storage media 22 (e.g., one or more mass storage devices) storing application programs 221 or data 222. Wherein the memory 21 and the storage medium 22 may be transitory or persistent. The program stored on the storage medium 22 may include one or more modules (not shown), each of which may include a series of instruction operations on a server. Still further, the central processor 20 may be arranged to communicate with the storage medium 22 and execute a series of instruction operations in the storage medium 22 on a server.
Specifically, the application program 221 stored in the storage medium 22 includes an application program for content recommendation, and the program may include the user acquisition unit 10, the content determination unit 11, the content feature acquisition unit 12, the comparison unit 13, the recommendation unit 14, and the recording unit 15 in the content recommendation apparatus described above, which will not be described here. Still further, the central processor 20 may be configured to communicate with the storage medium 22 and execute a series of operations corresponding to the application program of the content recommendation stored in the storage medium 22 on the server.
The server may also include one or more power supplies 23, one or more wired or wireless network interfaces 24, and/or one or more operating systems 223, such as Windows ServerTM, mac OS XTM, unixTM, linuxTM, freeBSDTM, or the like.
The steps performed by the application server described in the above method embodiment may be based on the structure of the server shown in fig. 7.
Embodiments of the present application also provide a storage medium storing a plurality of instructions adapted to be loaded by a processor and to perform a content recommendation method as performed by an application server as described above.
The embodiment of the application also provides a server, which comprises a processor and a storage medium;
the storage medium is used for storing a plurality of instructions for loading and executing the content recommendation method executed by the application server by the processor; the processor is configured to implement each instruction of the plurality of instructions.
Embodiments of the present application also provide a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the content recommendation method described above.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be implemented by a program to instruct related hardware, the program may be stored in a computer readable storage medium, and the storage medium may include: read Only Memory (ROM), random access memory RAM), magnetic or optical disks, and the like.
The content recommendation method, device, storage medium and server provided by the embodiment of the application are described in detail, and specific examples are applied to illustrate the principle and implementation of the application, and the description of the above embodiments is only used for helping to understand the method and core idea of the application; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present application, the present description should not be construed as limiting the present application in view of the above.
Claims (10)
1. A content recommendation method, comprising:
acquiring user content characteristics of a target user and acquiring user attribute characteristics of the target user; the user content features are used for representing the content in the application system interacted by the application terminal of the target user; the obtaining the user content characteristics of the target user specifically includes: acquiring a plurality of interactive behavior records of the application terminal on the content in the application system within a period of time before the current moment; each of the plurality of interactive behavior records comprises a content tag of the interactive content; counting content tags in the interaction behavior records, determining weight values corresponding to the content tags according to the counting result, wherein the user content features comprise the weight values corresponding to the content tags;
determining a corresponding plurality of contents according to the user content characteristics;
acquiring interactive user characteristics of each content in the plurality of contents;
comparing the user attribute characteristics with the interactive user characteristics of each content respectively to obtain a plurality of groups of comparison results;
and respectively determining the recommendation degree of each content according to the multiple groups of comparison results so as to recommend the content to the application terminal of the target user.
2. The method of claim 1, wherein the statistical result comprises: and determining the weight values corresponding to the content labels according to the statistical result if the occurrence frequencies corresponding to the content labels respectively in a period of time before the current moment, wherein the method specifically comprises the following steps:
and respectively determining the weight values corresponding to the content tags according to the occurrence frequencies of the content tags.
3. The method of claim 1, wherein obtaining the interactive user characteristics of any one of the plurality of content, specifically comprises:
acquiring a plurality of interaction behavior records interacted with any content, wherein each interaction behavior record in the plurality of interaction behavior records comprises attribute information of an interaction user;
counting attribute information of the interactive users in the plurality of interactive behavior records to obtain distribution information of the interactive users in at least one dimension, wherein the interactive user characteristics of any content comprise: and the distribution information of the interactive users in at least one dimension.
4. The method of claim 3, wherein the counting attribute information of the interactive users in the plurality of interaction behavior records to obtain distribution information of the interactive users in at least one dimension specifically comprises:
counting the proportion of interactive users in a plurality of age groups under the dimension of the age of the user; or alternatively, the first and second heat exchangers may be,
counting the proportion of male interaction users to female interaction users under the dimension of the gender of the users; or alternatively, the first and second heat exchangers may be,
counting the proportion of interactive users in each region under the dimension of the region where the user is located; or alternatively, the first and second heat exchangers may be,
and counting the proportion of interactive users in each professional field under the dimension of the user profession.
5. The method of any one of claims 1 to 4, wherein the interactive user features of any one of the content comprises: the distribution information of the interactive users in at least one dimension, and any set of comparison results comprise: the determining the recommendation degree of the corresponding content according to the any group of comparison results includes:
respectively determining weight values corresponding to the at least one personal attribute according to the distribution information corresponding to the at least one personal attribute;
and determining the recommendation degree of the corresponding content according to the calculation result of the weight value corresponding to the at least one personal attribute.
6. The method according to claim 5, wherein if the weight value of the content tag of the content in the user content feature, determining the recommendation degree of the corresponding content according to the calculation result of the weight value corresponding to the at least one personal attribute specifically includes:
and taking the weight value of the content label of the content and the calculation result of the weight value corresponding to the at least one personal attribute as the recommendation degree of the corresponding content.
7. The method of any one of claims 1 to 4, further comprising:
recommending the content with recommendation degree larger than a certain threshold to the application terminal of the target user;
and when the interaction information of the application terminal to the recommended content is received, storing an interaction behavior record of the recommended content.
8. A content recommendation device, comprising:
the user acquisition unit is used for acquiring the user content characteristics of the target user and acquiring the user attribute characteristics of the target user; the user content features are used for representing the content in the application system interacted by the application terminal of the target user; the obtaining the user content characteristics of the target user specifically includes: acquiring a plurality of interactive behavior records of the application terminal on the content in the application system within a period of time before the current moment; each of the plurality of interactive behavior records comprises a content tag of the interactive content; counting content tags in the interaction behavior records, determining weight values corresponding to the content tags according to the counting result, wherein the user content features comprise the weight values corresponding to the content tags;
a content determining unit, configured to determine a plurality of corresponding contents according to the user content characteristics;
a content feature acquiring unit, configured to acquire an interactive user feature of each of the plurality of contents;
the comparison unit is used for comparing the user attribute characteristics with the interactive user characteristics of each content respectively to obtain a plurality of groups of comparison results;
and the recommending unit is used for respectively determining the recommending degree of each content according to the multiple groups of comparison results so as to recommend the content to the application terminal of the target user.
9. A storage medium storing a plurality of instructions adapted to be loaded by a processor and to perform the content recommendation method according to any one of claims 1 to 7.
10. A server comprising a processor and a storage medium;
the storage medium storing a plurality of instructions for loading and executing by a processor the content recommendation method of any one of claims 1 to 7; the processor is configured to implement each instruction of the plurality of instructions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911310500.4A CN111026969B (en) | 2019-12-18 | 2019-12-18 | Content recommendation method and device, storage medium and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911310500.4A CN111026969B (en) | 2019-12-18 | 2019-12-18 | Content recommendation method and device, storage medium and server |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111026969A CN111026969A (en) | 2020-04-17 |
| CN111026969B true CN111026969B (en) | 2023-10-03 |
Family
ID=70209728
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911310500.4A Active CN111026969B (en) | 2019-12-18 | 2019-12-18 | Content recommendation method and device, storage medium and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111026969B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112165639B (en) * | 2020-09-23 | 2024-02-02 | 腾讯科技（深圳）有限公司 | Content distribution method, device, electronic equipment and storage medium |
| CN113055751B (en) * | 2021-03-19 | 2023-05-23 | 北京百度网讯科技有限公司 | Data processing method, device, electronic equipment and storage medium |
| CN114638649A (en) * | 2022-03-29 | 2022-06-17 | 金蝶征信有限公司 | Window pushing method, system and related device |
| CN115271891B (en) * | 2022-09-29 | 2022-12-30 | 深圳市人马互动科技有限公司 | Product recommendation method based on interactive novel and related device |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108829771A (en) * | 2018-05-29 | 2018-11-16 | 广州虎牙信息科技有限公司 | Main broadcaster's recommended method, device, computer storage medium and server |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105959374B (en) * | 2016-05-12 | 2019-05-03 | 腾讯科技（深圳）有限公司 | A kind of data recommendation method and its equipment |
-
2019
- 2019-12-18 CN CN201911310500.4A patent/CN111026969B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108829771A (en) * | 2018-05-29 | 2018-11-16 | 广州虎牙信息科技有限公司 | Main broadcaster's recommended method, device, computer storage medium and server |
Non-Patent Citations (2)
| Title |
|---|
| Fan Tang 等.《Friend Recommendation Based on the Similarity of Micro-blog User Model》.《2013 IEEE International Conference on Green Computing and Communications and IEEE Internet of Things and IEEE Cyber,Physical and Social Computing》.2013,全文. * |
| 张军.《基于大数据技术的有线电视节目推荐系统》.《电脑知识与技术》.2019,全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111026969A (en) | 2020-04-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111026969B (en) | Content recommendation method and device, storage medium and server | |
| US10454863B2 (en) | Data processing device and data processing method based on user emotion icon activity | |
| CN109325179B (en) | Content promotion method and device | |
| CN106326391B (en) | Multimedia resource recommendation method and device | |
| CN108269128B (en) | Advertisement putting method, device, equipment and storage medium | |
| CN107426328B (en) | Information pushing method and device | |
| EP2506522B1 (en) | Method and device for pushing data | |
| CN104537000B (en) | A kind of method and apparatus for pushed information | |
| CN108683952B (en) | Video content segment pushing method and device based on interactive video | |
| US20140095308A1 (en) | Advertisement distribution apparatus and advertisement distribution method | |
| CN103914550A (en) | Recommended content displaying method and recommended content displaying device | |
| CN102695121A (en) | Method and system for pushing friend information for user in social network | |
| CN114902702B (en) | Short message pushing method, device, server and storage medium | |
| CN110866183A (en) | Social interface recommendation method and device, electronic equipment and storage medium | |
| CN111722766A (en) | Multimedia resource display method and device | |
| CN111159553A (en) | Information pushing method and device, computer equipment and storage medium | |
| EP3026604A1 (en) | Device and method of providing an advertising service | |
| CN113343069B (en) | User information processing method, device, medium and electronic equipment | |
| CN113486211A (en) | Account identification method and device, electronic equipment, storage medium and program product | |
| CN114461893B (en) | Information recommendation method, related device, equipment and storage medium | |
| CN111954017B (en) | Live broadcast room searching method and device, server and storage medium | |
| CN113365090A (en) | Object recommendation method, object recommendation device, electronic equipment and readable storage medium | |
| CN112148962B (en) | Method and device for pushing information | |
| CN112561636A (en) | Recommendation method, recommendation device, terminal equipment and medium | |
| CN117196723A (en) | Advertisement space matching method, system, medium and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40021728 Country of ref document: HK |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |