CN117061796A - Film recommendation method, device, equipment and readable storage medium - Google Patents
Film recommendation method, device, equipment and readable storage medium Download PDFInfo
- Publication number
- CN117061796A CN117061796A CN202310954120.4A CN202310954120A CN117061796A CN 117061796 A CN117061796 A CN 117061796A CN 202310954120 A CN202310954120 A CN 202310954120A CN 117061796 A CN117061796 A CN 117061796A
- Authority
- CN
- China
- Prior art keywords
- film
- demand
- target user
- determining
- user
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000003860 storage Methods 0.000 title claims abstract description 19
- 238000011156 evaluation Methods 0.000 claims abstract description 39
- 230000004927 fusion Effects 0.000 claims description 9
- 238000007499 fusion processing Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 230000000977 initiatory effect Effects 0.000 claims description 3
- 230000001131 transforming effect Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000003993 interaction Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
- H04N21/25866—Management of end-user data
- H04N21/25891—Management of end-user data being end-user preferences
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/239—Interfacing the upstream path of the transmission network, e.g. prioritizing client content requests
- H04N21/2393—Interfacing the upstream path of the transmission network, e.g. prioritizing client content requests involving handling client requests
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/24—Monitoring of processes or resources, e.g. monitoring of server load, available bandwidth, upstream requests
- H04N21/2407—Monitoring of transmitted content, e.g. distribution time, number of downloads
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44204—Monitoring of content usage, e.g. the number of times a movie has been viewed, copied or the amount which has been watched
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/4508—Management of client data or end-user data
- H04N21/4532—Management of client data or end-user data involving end-user characteristics, e.g. viewer profile, preferences
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4667—Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/472—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content
- H04N21/47202—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content for requesting content on demand, e.g. video on demand
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Graphics (AREA)
- Computing Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses a film recommendation method, a device, equipment and a readable storage medium, and belongs to the technical field of computers. The method comprises the following steps: responding to a film on-demand request initiated by a target user, and acquiring historical on-demand data of the target user and candidate films corresponding to the target user; determining attribute information of a target triplet of the on-demand knowledge graph according to historical on-demand data of a target user and a pre-constructed on-demand knowledge graph; determining a plurality of preference characteristics of the target user according to the attribute information of the target triples; obtaining user preference evaluation values of the candidate films by inputting the preference characteristics and the candidate films into a film recommendation model; and sorting each candidate film according to the size of the user preference evaluation value, and determining the film recommended to the target user according to the sorting result. By the method, the instantaneity and the accuracy of the film recommendation result in a large-scale real-time recommendation scene can be ensured, and the user experience and satisfaction are improved.
Description
Technical Field
The embodiment of the application relates to the technical field of computers, in particular to a film recommendation method, a device, equipment and a readable storage medium.
Background
IPTV, also known as internet protocol television, is a video service built on top of an IP-based private broadband network, capable of providing high quality legacy television channel programming and video on demand content. Compared with the traditional television programs, the IPTV television has the advantages that not only can the same real-time online programs of the traditional television be watched in real time, but also programs which the user wants to watch can be searched for online watching through a data platform provided by a service provider. IPTV content recommendation is also video recommendation in nature, but IPTV users are large in volume, the user scale is usually tens of millions or hundreds of millions, and IPTV content sources are rich and varied, so that the content needs to be refreshed on a large screen in real time.
Most of the existing recommendation schemes are realized based on public data sets, the data sets are small in user scale, ideal recommendation effects are obtained by improving algorithm complexity, but large-scale recommendation scenes of billions of user scale and million film libraries cannot be applicable; in addition, under real-time recommendation, the existing scheme mostly extracts features in real time through distributed computing modes such as Hadoop, spark and the like, then inputs the features to a machine learning platform, recalls and sorts the features through a machine learning model, the scheme relates to transmission and interaction of cross-platform data, the data writing part of the machine learning platform is slower, and real-time recommendation cannot be achieved under a large-scale recommendation scene.
Disclosure of Invention
The embodiment of the application provides a film recommendation method, a film recommendation device, film recommendation equipment and a readable storage medium, which are used for at least solving the problem that the conventional recommendation scheme cannot be suitable for large-scale recommendation scenes.
In order to solve the technical problems, the application is realized as follows:
in a first aspect, an embodiment of the present application provides a film recommendation method, including:
responding to a film on-demand request initiated by a target user, and acquiring historical on-demand data of the target user and candidate films corresponding to the target user;
determining attribute information of a target triplet of the on-demand knowledge graph according to the historical on-demand data of the target user and a pre-constructed on-demand knowledge graph;
determining a plurality of preference characteristics of the target user according to the attribute information of the target triplet;
obtaining user preference evaluation values of the candidate films by inputting a plurality of preference characteristics and the candidate films into a film recommendation model;
and sorting each candidate film according to the size of the user preference evaluation value, and determining films recommended to the target user according to the sorting result.
In a second aspect, an embodiment of the present application provides a film recommendation apparatus, including:
the data acquisition module is used for responding to a film on-demand request initiated by a target user to acquire historical on-demand data of the target user and candidate films corresponding to the target user;
the information determining module is used for determining attribute information of a target triplet of the on-demand knowledge graph according to the historical on-demand data of the target user and the pre-constructed on-demand knowledge graph;
the feature determining module is used for determining a plurality of preference features of the target user according to the attribute information of the target triples;
the preference evaluation module is used for obtaining user preference evaluation values of the candidate films by inputting a plurality of preference characteristics and the candidate films into the film recommendation model;
and the film recommendation module is used for sequencing each candidate film according to the size of the user preference evaluation value, and determining films recommended to the target user according to the sequencing result.
In a third aspect, an embodiment of the present application provides an electronic device, including a processor and a memory, where the memory stores a program or instructions executable on the processor, the program or instructions implementing the steps of the method according to the first aspect, when executed by the processor.
In a fourth aspect, embodiments of the present application provide a readable storage medium having stored thereon a program or instructions which when executed by a processor perform the steps of the method as described in the first aspect above.
According to the film recommendation method provided by the embodiment of the application, in response to a film on-demand request initiated by a target user, historical on-demand data of the target user and candidate films corresponding to the target user are obtained; determining attribute information of a target triplet of the on-demand knowledge graph according to historical on-demand data of a target user and a pre-constructed on-demand knowledge graph; determining a plurality of preference characteristics of the target user according to the attribute information of the target triples; obtaining user preference evaluation values of the candidate films by inputting the preference characteristics and the candidate films into a film recommendation model; and sorting each candidate film according to the size of the user preference evaluation value, and determining the film recommended to the target user according to the sorting result.
Therefore, when a target user initiates a film on-demand request, the history on-demand data is stored and loaded through the constructed on-demand knowledge graph, the extraction and operation efficiency of preference characteristics of the target user can be improved, a plurality of preference characteristics of the target user and candidate films corresponding to the target user are further input into a film recommendation model, user preference evaluation values of the candidate films are obtained, film recommendation is carried out according to the user preference evaluation values, the influence of a multi-platform interaction process on the model recommendation effect can be avoided, the instantaneity and the accuracy of film recommendation results in a large-scale real-time recommendation scene are ensured, and accordingly the user experience and satisfaction are facilitated to be improved.
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 application as claimed.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.
Fig. 1 is a schematic flow chart of a film recommendation method according to an embodiment of the present application;
fig. 2 is a schematic diagram of a graph link structure of an on-demand knowledge graph according to an embodiment of the present application;
FIG. 3 is a schematic flow chart of a method for determining preference characteristics according to an embodiment of the present application;
FIGS. 4a-4c are schematic diagrams illustrating the structure of three types of acceptance modules with different dimension convolution kernel values according to embodiments of the present disclosure;
fig. 5 is a schematic structural diagram of a film recommendation device according to an embodiment of the present application;
fig. 6 shows a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the application. Rather, they are merely examples of apparatus and methods consistent with aspects of the application as detailed in the accompanying claims.
Fig. 1 is a schematic flow chart of a movie recommendation method according to an embodiment of the present application, where an execution subject of the method may be a terminal device or a server, where the terminal device may be a device such as a personal computer, or a mobile terminal device such as a mobile phone, a tablet computer, an IPTV television, or the like, and the terminal device may be a terminal device used by a user. The server may be an independent server or a server cluster formed by a plurality of servers, and the server may be a background server of a certain service, or may be a background server of a certain platform or application program (such as a movie recommendation platform, a video player, etc.), etc. The method can be used for recommending candidate movies corresponding to a target user in real time according to preference characteristics of the target user when the target user initiates a movie on-demand request, and in the embodiment of the application, an execution main body is taken as a server for explanation, and for the case of terminal equipment, the processing according to the following related content is omitted herein. As shown in the figure, the movie recommendation method 100 may include the steps of:
s101: and responding to a film on-demand request initiated by a target user, and acquiring historical on-demand data of the target user and candidate films corresponding to the target user.
In a specific implementation, when a film on-demand request initiated by a target user is obtained, historical on-demand data of the target user and a candidate film corresponding to the target user are obtained, where the historical on-demand data may be historical on-demand data of the target user within a preset time range, for example, on-demand data of the target user within a specific month; it may also be historical on-demand data within a preset time period, where the preset time period includes a time point when the film on-demand request is initiated, for example, on-demand data of a target user in the last month.
S102: and determining attribute information of a target triplet of the on-demand knowledge graph according to the historical on-demand data of the target user and the pre-constructed on-demand knowledge graph.
In the implementation, firstly, a pre-built on-demand knowledge graph is obtained, and from the traversal logic of a graph database and the data characteristics of a film recommendation scene, graph links of user-film content are built to unsupervised learn user preferences so as to complete analysis and mining of preference characteristics. And further determining the attribute information of the target triples of the on-demand knowledge graph according to the historical on-demand data of the target user. The target triples comprise user entities, movie entities, content entities and association relations among different entities.
In one possible implementation, the on-demand knowledge-graph may be constructed by:
taking the user entity as a central entity of the on-demand knowledge graph, and determining at least one film entity with a first association relationship with the central entity; and a content entity having a second association with each of the at least one movie entity;
and constructing the on-demand knowledge graph according to the user entity, the at least one film entity and the content entity.
In a specific implementation, as shown in fig. 2, a "user" is taken as a central entity of the on-demand knowledge graph, at least one film entity having a first association relationship with the central entity is determined, for example, the first association relationship is an on-demand relationship, film 1 on demand by the user, film 2 … … film N are determined, and content entities having a second association relationship with each film entity are determined, for example, the second association relationship may be other association relationships such as a affiliated relationship, an included relationship, and the like, a director to which each film belongs is determined, and a category of content, a director of the film, and the like of the film are determined. And constructing an on-demand knowledge graph according to the user entity, the at least one film entity and the content entity.
Wherein the attribute information comprises entity attribute information and relationship attribute information; the determining the attribute information of the target triplet of the on-demand knowledge graph comprises the following steps:
determining entity attribute information of each entity in the on-demand knowledge graph according to the historical on-demand data of the target user; determining relationship attribute information among different entities in the on-demand knowledge graph according to the number of content entities with the same category in the on-demand knowledge graph;
and determining the attribute information of the target triplet of the on-demand knowledge graph according to the entity attribute information and the relationship attribute information among different entities.
The history on-demand data comprises user on-demand information and media information, the user on-demand information comprises user identification ID, content name, channel category, on-demand time and other user on-demand behavior information, and the media information comprises information of directors, actors, types, mapping areas, mapping time and the like corresponding to the film.
In a specific implementation, according to user on-demand information and media information of a target user, entity attribute information of each entity in an on-demand knowledge graph is determined. In order to ensure the real-time performance of the recommendation system, the recommendation system can be in real-time butt joint with a graph database data loading component in a Kafka mode and the like to acquire user on-demand information, and the real-time creation and updating of the graph are completed; the media information data volume is relatively small, the map is imported through the file once for the first time, and then the map can be updated in real time in an API mode, so that the consistency of the film data of the target film database is ensured.
Further, the following policies may also be employed to determine attribute information for the target triplet:
let M denote all films on demand of target users, W i Representing a collection of movies seen by an ith person; v (V) i 、P i 、Q i Respectively represent W i A film category set, an actor set and a director set contained; v i 、p i 、q i Respectively represent V i 、P i 、Q i Specific elements of (3).
Let n vi 、n pi 、n qi Respectively representing the total number of occurrences of the ith category, actor and director in the film watching record, let n Vi 、n Pi 、n Qi Respectively representing the class of the ith personal viewing recordThe sum of the number of times of the album, the actor set and the director is known,
and n is Vi ＝∑ i∈R n vi ，n Pi ＝∑ i∈R n pi ，n Qi ＝∑ i∈R n qi 。
Based on the above calculation, the number distribution of directors, actors and categories accumulated in each film based on the history can be obtained, and the value range of each weight is changed into [0,1] in a standardized manner, and then:
the film category characteristic value of the ith user is a×n vx /n Vi ,x∈R；
The characteristic value of the movie actor of the ith user is b x n px /n Pi ,x∈R；
The film director characteristic value of the ith user is c qx /n Qi ,x∈R；
Wherein a, b, c are constants, are chosen from empirical values, and satisfy a+b+c=1.
S103: and determining a plurality of preference characteristics of the target user according to the attribute information of the target triplet.
And storing the category preference characteristics, the actor preference characteristics and the director preference characteristics in the form of relation attribute information, and fusing the category preference characteristics, the actor preference characteristics and the director preference characteristics with entity attribute information (such as user attribute information including on-demand days, on-demand times and the like and film attribute information including production time, film duration and the like) to complete the construction of the overall preference characteristics. Wherein the plurality of preference characteristics of the target user may be as shown in table 1:
TABLE 1
S104: and obtaining user preference evaluation values of the candidate films by inputting a plurality of preference characteristics and the candidate films into a film recommendation model.
The film recommendation model comprises a characteristic input layer, a characteristic fusion layer and an output layer; the obtaining the user preference evaluation value of the candidate film by inputting a plurality of preference characteristics and the candidate film into a film recommendation model comprises the following steps:
transforming, by the input layer, a plurality of the preference features into an input vector having a preset dimension;
inputting the input vector to a feature fusion layer for multi-scale feature fusion processing to obtain an output vector; the feature extraction layer is formed by combining a plurality of acceptance modules with convolution kernel branches with different dimensions according to a preset arrangement rule;
and the output layer determines a user preference evaluation value of the candidate film according to a similarity comparison result between the output vector and the feature vector corresponding to the candidate film.
The information module comprises a first information module, a second information module and a third information module, as shown in fig. 4a, wherein the first information module comprises one or more 1×1 and 3×3 convolution kernel branches; as shown in fig. 4b, the second indication module contains one or more 1×3, 3×1 convolution kernel branches; as shown in fig. 4c, the third indication module includes convolution kernel branches of 1×n, n×1, and 1×1, where n is the dimension of the input vector;
the step of inputting the input vector to a feature fusion layer for multi-scale feature fusion processing to obtain an output vector comprises the following steps:
and the input vector sequentially passes through the two first acceptance modules, the second acceptance module, the third acceptance module and the second acceptance module to be subjected to multi-scale feature fusion processing, so that an output vector is obtained. And scoring the candidate films corresponding to the target users according to the output vector to obtain user preference evaluation values of each candidate film.
S105: and sorting each candidate film according to the size of the user preference evaluation value, and determining films recommended to the target user according to the sorting result.
In an implementation, the structure of the movie recommendation model is shown in table 2:
TABLE 2
Determining a user preference evaluation value of each candidate film through a film recommendation model, sorting each candidate film according to the size of the user preference evaluation value, and determining films recommended to a target user according to sorting results, for example, recommending a preset number of films with top ranks to the target user, so that recommended content can accord with user preference, and user satisfaction is improved.
In a possible implementation manner, after determining the movies recommended to the target user according to the ranking result, the method further includes:
and updating the historical on-demand data of the target user according to the initiating time information corresponding to the film on-demand request.
In the implementation, the user updates the history on-demand data once every time when sending the on-demand request, so as to improve the accuracy of extracting the preference characteristics, thereby being beneficial to recommending the film content which better accords with the preference of the user.
In a possible implementation manner, after determining the movies recommended to the target user according to the ranking result, the method further includes:
converting the film content corresponding to the film into a preset format and then sending the film content to a play control server; and updating the content information of the film recommendation interface corresponding to the target user through the play control server.
In a specific implementation, a film on-demand request initiated by a target user can be received through an API mode, and recommended content is sent to a play control server in a preset format (such as JSON string) through the API mode, and the play control server updates content information of a film recommendation interface corresponding to the target user based on the JSON string.
The embodiment of the application provides a film recommendation method, which can realize the efficient storage and loading of historical video-on-demand data through a constructed video-on-demand knowledge graph when a target user initiates a video-on-demand request, improve the extraction and operation efficiency of the preference characteristics of the target user, further input a plurality of preference characteristics of the target user and candidate films corresponding to the target user into a film recommendation model to obtain user preference evaluation values of the candidate films, and perform film recommendation according to the user preference evaluation values, namely, the video-on-demand knowledge graph updates the preference characteristics of the target user in real time according to the video-on-demand request of the target user, and the film recommendation model performs film recommendation according to the preference characteristics, so that the influence of a multi-platform interaction process on the model recommendation effect can be avoided, and the real-time performance and accuracy of film recommendation results under a large-scale real-time recommendation scene are ensured, thereby being beneficial to improving the user experience and satisfaction.
Fig. 5 is a schematic structural diagram of a film recommendation device according to an embodiment of the present application, where the film recommendation device may implement all or part of the content in the embodiment shown in fig. 1, and the film recommendation device 500 includes:
the data obtaining module 510 is configured to obtain, in response to a film on-demand request initiated by a target user, historical on-demand data of the target user and a candidate film corresponding to the target user;
the information determining module 520 is configured to determine attribute information of a target triplet of the on-demand knowledge graph according to the historical on-demand data of the target user and a pre-constructed on-demand knowledge graph;
a feature determining module 530, configured to determine a plurality of preference features of the target user according to attribute information of the target triplet;
a preference evaluation module 540, configured to obtain a user preference evaluation value of the candidate movie by inputting a plurality of preference features and the candidate movie into a movie recommendation model;
and the movie recommendation module 550 is configured to rank each candidate movie according to the size of the user preference evaluation value, and determine a movie recommended to the target user according to the ranking result.
In a possible implementation manner, the information determining module 520 is configured to construct the on-demand knowledge-graph in the following manner:
taking the user entity as a central entity of the on-demand knowledge graph, and determining at least one film entity with a first association relationship with the central entity; and a content entity having a second association with each of the at least one movie entity;
and constructing the on-demand knowledge graph according to the user entity, the at least one film entity and the content entity.
In one possible implementation, the attribute information includes entity attribute information and relationship attribute information; the information determining module 520 is specifically configured to, when determining attribute information of the target triplet of the on-demand knowledge graph:
determining entity attribute information of each entity in the on-demand knowledge graph according to the historical on-demand data of the target user; determining relationship attribute information among different entities in the on-demand knowledge graph according to the number of content entities with the same category in the on-demand knowledge graph;
and determining the attribute information of the target triplet of the on-demand knowledge graph according to the entity attribute information and the relationship attribute information among different entities.
In one possible implementation manner, the film recommendation model comprises a feature input layer, a feature fusion layer and an output layer; the preference evaluation module 540 is specifically configured to, when configured to obtain the user preference evaluation value of the candidate movie by inputting a plurality of preference features and the candidate movie into a movie recommendation model:
transforming, by the input layer, a plurality of the preference features into an input vector having a preset dimension;
inputting the input vector to a feature fusion layer for multi-scale feature fusion processing to obtain an output vector; the feature extraction layer is formed by combining a plurality of acceptance modules with convolution kernel branches with different dimensions according to a preset arrangement rule;
and the output layer determines a user preference evaluation value of the candidate film according to a similarity comparison result between the output vector and the feature vector corresponding to the candidate film.
The method comprises the steps that an acceptance module comprises a first acceptance module, a second acceptance module and a third acceptance module, wherein the first acceptance module comprises one or more convolution kernel branches of 1×1 and 3×3, the second acceptance module comprises one or more convolution kernel branches of 1×3 and 3×1, and the third acceptance module comprises convolution kernel branches of 1×n, n×1 and 1×1, and n is the dimension of the input vector;
the step of inputting the input vector to a feature fusion layer for multi-scale feature fusion processing to obtain an output vector comprises the following steps:
and the input vector sequentially passes through the two first acceptance modules, the second acceptance module, the third acceptance module and the second acceptance module to be subjected to multi-scale feature fusion processing, so that the output vector is obtained.
In one possible implementation, the film recommendation device 500 further includes:
and the data updating module is used for updating the history on-demand data of the target user according to the initiating time information corresponding to the film on-demand request.
In one possible implementation, the film recommendation device 500 further includes:
the format conversion module is used for converting the film content corresponding to the film into a preset format and then sending the film content to the play control server; and updating the content information of the film recommendation interface corresponding to the target user through the play control server.
The embodiment of the application provides a film recommendation device which comprises a data acquisition module, an information determination module, a characteristic determination module, a preference evaluation module and a film recommendation module; responding to a film on-demand request initiated by a target user, and acquiring historical on-demand data of the target user and a candidate film corresponding to the target user through a data acquisition module; the information determining module determines attribute information of a target triplet of the on-demand knowledge graph according to the historical on-demand data of the target user and a pre-constructed on-demand knowledge graph; the feature determining module determines a plurality of preference features of the target user according to the attribute information of the target triplet; the preference evaluation module obtains user preference evaluation values of the candidate films by inputting a plurality of preference characteristics and the candidate films into a film recommendation model; and the film recommendation module ranks each candidate film according to the size of the user preference evaluation value, and determines films recommended to the target user according to the ranking result.
Therefore, when a target user initiates a film on-demand request, the history on-demand data is stored and loaded through the constructed on-demand knowledge graph, the extraction and operation efficiency of preference characteristics of the target user can be improved, a plurality of preference characteristics of the target user and candidate films corresponding to the target user are further input into a film recommendation model, user preference evaluation values of the candidate films are obtained, film recommendation is carried out according to the user preference evaluation values, the influence of a multi-platform interaction process on the model recommendation effect can be avoided, the instantaneity and the accuracy of film recommendation results in a large-scale real-time recommendation scene are ensured, and accordingly the user experience and satisfaction are facilitated to be improved.
Fig. 6 shows a schematic diagram of a hardware structure of an electronic device provided by an embodiment of the application, and referring to the figure, at a hardware level, the electronic device includes a processor, and optionally includes an internal bus, a network interface, and a memory. The Memory may include a Memory, such as a Random-Access Memory (RAM), and may further include a non-volatile Memory (non-volatile Memory), such as at least 1 disk Memory. Of course, the electronic device may also include hardware required for other services.
The processor, network interface, and memory may be interconnected by an internal bus, which may be an industry standard architecture (Industry Standard Architecture, ISA) bus, a peripheral component interconnect standard (Peripheral Component Interconnect, PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, among others. The buses may be classified as address buses, data buses, control buses, etc. For ease of illustration, only one bi-directional arrow is shown in the figure, but not only one bus or one type of bus.
And a memory for storing the program. In particular, the program may include program code including computer-operating instructions. The memory may include memory and non-volatile storage and provide instructions and data to the processor.
The processor reads the corresponding computer program from the nonvolatile memory into the memory and then runs to form a device for locating the target user on a logic level. A processor executing the program stored in the memory, and specifically executing: the method disclosed in the embodiment shown in fig. 1 and implementing the functions and advantages of the methods described in the foregoing method embodiments are not described herein.
The method disclosed in the embodiment of fig. 1 of the present application may be implemented in a processor or by a processor. The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or by instructions in the form of software. The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but also digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory, and the processor reads the information in the memory and, in combination with its hardware, performs the steps of the above method.
The computer device may also execute the methods described in the foregoing method embodiments, and implement the functions and beneficial effects of the methods described in the foregoing method embodiments, which are not described herein.
Of course, other implementations, such as a logic device or a combination of hardware and software, are not excluded from the electronic device of the present application, that is, the execution subject of the following processing flows is not limited to each logic unit, but may be hardware or a logic device.
The embodiment of the present application further provides a computer readable storage medium, where the computer readable storage medium stores one or more programs, where the one or more programs, when executed by an electronic device including a plurality of application programs, cause the electronic device to execute the method disclosed in the embodiment shown in fig. 1 and implement the functions and benefits of the methods described in the foregoing method embodiments, which are not described herein again.
The computer readable storage medium includes Read-Only Memory (ROM), random access Memory (Random Access Memory RAM), magnetic disk or optical disk, etc.
Further, embodiments of the present application also provide a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, implement the following flow: the method disclosed in the embodiment shown in fig. 1 and implementing the functions and advantages of the methods described in the foregoing method embodiments are not described herein.
In summary, the foregoing description is only of the preferred embodiments of the present application, and is not intended to limit the scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.
The system, apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. One typical implementation is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.
Claims (10)
1. A movie recommendation method, comprising:
responding to a film on-demand request initiated by a target user, and acquiring historical on-demand data of the target user and candidate films corresponding to the target user;
determining attribute information of a target triplet of the on-demand knowledge graph according to the historical on-demand data of the target user and a pre-constructed on-demand knowledge graph;
determining a plurality of preference characteristics of the target user according to the attribute information of the target triplet;
obtaining user preference evaluation values of the candidate films by inputting a plurality of preference characteristics and the candidate films into a film recommendation model;
and sorting each candidate film according to the size of the user preference evaluation value, and determining films recommended to the target user according to the sorting result.
2. The method of claim 1, wherein the on-demand knowledge-graph is constructed by:
taking the user entity as a central entity of the on-demand knowledge graph, and determining at least one film entity with a first association relationship with the central entity; and a content entity having a second association with each of the at least one movie entity;
and constructing the on-demand knowledge graph according to the user entity, the at least one film entity and the content entity.
3. The method of claim 2, wherein the attribute information includes entity attribute information and relationship attribute information; the determining the attribute information of the target triplet of the on-demand knowledge graph comprises the following steps:
determining entity attribute information of each entity in the on-demand knowledge graph according to the historical on-demand data of the target user; determining relationship attribute information among different entities in the on-demand knowledge graph according to the number of content entities with the same category in the on-demand knowledge graph;
and determining the attribute information of the target triplet of the on-demand knowledge graph according to the entity attribute information and the relationship attribute information among different entities.
4. The method of claim 1, wherein the movie recommendation model includes a feature input layer, a feature fusion layer, and an output layer; the obtaining the user preference evaluation value of the candidate film by inputting a plurality of preference characteristics and the candidate film into a film recommendation model comprises the following steps:
transforming, by the input layer, a plurality of the preference features into an input vector having a preset dimension;
inputting the input vector to a feature fusion layer for multi-scale feature fusion processing to obtain an output vector; the feature extraction layer is formed by combining a plurality of acceptance modules with convolution kernel branches with different dimensions according to a preset arrangement rule;
and the output layer determines a user preference evaluation value of the candidate film according to a similarity comparison result between the output vector and the feature vector corresponding to the candidate film.
5. The method of claim 4, wherein the indication module comprises a first indication module, a second indication module, and a third indication module, wherein the first indication module comprises one or more 1 x 1, 3 x 3 convolution kernel branches, the second indication module comprises one or more 1 x 3, 3 x 1 convolution kernel branches, and the third indication module comprises 1 x n, n x 1, 1 x 1 convolution kernel branches, n being the dimension of the input vector;
the step of inputting the input vector to a feature fusion layer for multi-scale feature fusion processing to obtain an output vector comprises the following steps:
and the input vector sequentially passes through the two first acceptance modules, the second acceptance module, the third acceptance module and the second acceptance module to be subjected to multi-scale feature fusion processing, so that the output vector is obtained.
6. The method according to claim 1, further comprising, after said determining a movie recommended to said target user based on the ranking result:
and updating the historical on-demand data of the target user according to the initiating time information corresponding to the film on-demand request.
7. The method according to claim 1, further comprising, after said determining a movie recommended to said target user based on the ranking result:
converting the film content corresponding to the film into a preset format and then sending the film content to a play control server; and updating the content information of the film recommendation interface corresponding to the target user through the play control server.
8. A movie recommendation device, characterized by comprising:
the data acquisition module is used for responding to a film on-demand request initiated by a target user to acquire historical on-demand data of the target user and candidate films corresponding to the target user;
the information determining module is used for determining attribute information of a target triplet of the on-demand knowledge graph according to the historical on-demand data of the target user and the pre-constructed on-demand knowledge graph;
the feature determining module is used for determining a plurality of preference features of the target user according to the attribute information of the target triples;
the preference evaluation module is used for obtaining user preference evaluation values of the candidate films by inputting a plurality of preference characteristics and the candidate films into the film recommendation model;
and the film recommendation module is used for sequencing each candidate film according to the size of the user preference evaluation value, and determining films recommended to the target user according to the sequencing result.
9. An electronic device comprising a processor and a memory storing a program or instructions executable on the processor, which when executed by the processor, implement the steps of the method of any one of claims 1 to 7.
10. A readable storage medium, characterized in that it stores thereon a program or instructions, which when executed by a processor, implement the steps of the method according to any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310954120.4A CN117061796A (en) | 2023-07-31 | 2023-07-31 | Film recommendation method, device, equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310954120.4A CN117061796A (en) | 2023-07-31 | 2023-07-31 | Film recommendation method, device, equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117061796A true CN117061796A (en) | 2023-11-14 |
Family
ID=88661764
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310954120.4A Pending CN117061796A (en) | 2023-07-31 | 2023-07-31 | Film recommendation method, device, equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117061796A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117956230A (en) * | 2024-03-26 | 2024-04-30 | 山东工程职业技术大学 | Fusion implementation method and system based on digital media on demand and digital resource downloading |
-
2023
- 2023-07-31 CN CN202310954120.4A patent/CN117061796A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117956230A (en) * | 2024-03-26 | 2024-04-30 | 山东工程职业技术大学 | Fusion implementation method and system based on digital media on demand and digital resource downloading |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109002488B (en) | Recommendation model training method and device based on meta-path context | |
| CA3007853C (en) | End-to-end deep collaborative filtering | |
| JP6855595B2 (en) | Using machine learning to recommend live stream content | |
| CN110139162B (en) | Media content sharing method and device, storage medium and electronic device | |
| US11017024B2 (en) | Media content rankings for discovery of novel content | |
| CN108829808B (en) | Page personalized sorting method and device and electronic equipment | |
| CN106326391B (en) | Multimedia resource recommendation method and device | |
| Rae et al. | Improving tag recommendation using social networks | |
| WO2017107453A1 (en) | Video content recommendation method, device, and system | |
| US10671670B2 (en) | Graph based content browsing and discovery | |
| CN108595493B (en) | Media content pushing method and device, storage medium and electronic device | |
| CN111258995B (en) | Data processing method, device, storage medium and equipment | |
| CN112052387B (en) | Content recommendation method, device and computer readable storage medium | |
| CN112507163B (en) | Duration prediction model training method, recommendation method, device, equipment and medium | |
| CN113873330B (en) | Video recommendation method and device, computer equipment and storage medium | |
| CN113254679B (en) | Multimedia resource recommendation method and device, electronic equipment and storage medium | |
| CN109255073B (en) | Personalized recommendation method and device and electronic equipment | |
| CN117061796A (en) | Film recommendation method, device, equipment and readable storage medium | |
| CN114357201B (en) | Audio-visual recommendation method and system based on information perception | |
| CN105956061B (en) | Method and device for determining similarity between users | |
| CN113515696A (en) | Recommendation method and device, electronic equipment and storage medium | |
| CN110569447B (en) | Network resource recommendation method and device and storage medium | |
| WO2018001223A1 (en) | Playlist recommending method and device | |
| CN111212304A (en) | Video recommendation method and server | |
| CN110996177B (en) | Video recommendation method, device and equipment for video-on-demand cinema |
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 |