CN114297417A

CN114297417A - Multimedia resource recommendation method and related device

Info

Publication number: CN114297417A
Application number: CN202111562839.0A
Authority: CN
Inventors: 廖一桥
Original assignee: Beijing Dajia Internet Information Technology Co Ltd
Current assignee: Beijing Dajia Internet Information Technology Co Ltd
Priority date: 2021-12-20
Filing date: 2021-12-20
Publication date: 2022-04-08

Abstract

The application discloses a multimedia resource recommendation method and a related device, which are used for solving the problems of complex operation, low efficiency and poor accuracy when multimedia resource recommendation is carried out in the related technology. According to the method and the device, the expected recommendation degrees of the users to different multimedia resource types are mined by adopting the recent historical behavior sequences of the users, and the higher the expected recommendation degree is, the more the users expect to acquire the multimedia resources of the type, so that the target historical behavior sequences of the users can be constructed based on the multimedia resource types expected to be acquired by the users, and the target historical behavior sequences are more focused on the recent interest of the users and the multimedia resource types expected to be acquired by the users in the recent period compared with the long-term behavior sequences of the related technology. In addition, in the recommendation method, the target historical behavior sequence does not need to be acquired for each resource type respectively, and the target historical behavior sequence is calculated once based on one request, so that compared with the prior art, the recommendation method can simplify operation and improve recommendation efficiency.

Description

Multimedia resource recommendation method and related device

Technical Field

The present application relates to the field of multimedia information processing technologies, and in particular, to a multimedia resource recommendation method and a related apparatus.

Background

In the training of the short video recommendation system model, more interesting content can be recommended to the user based on the information of the user interest points contained in the user historical behavior information, and the model has guiding significance for the learning of the model.

In the related technology, after acquiring multimedia resources to be recommended based on a user request, all historical behavior data of the user are used as input of a CTR (subscriber identity module) model based on retrieved user behavior, if candidate multimedia resources to be recommended comprise multiple types of multimedia resources, a GSU (general Search Unit) module is used for respectively generating corresponding long-term behavior sequences for each type of multimedia resources to be recommended as input of an ESU (exact Search Unit) module, then a deep learning model based on an attention mechanism is used for modeling the long-term behavior sequences to obtain evaluation scores of each candidate multimedia resource, and then ranking and recommending are carried out on each multimedia resource to be recommended based on the evaluation scores. The multimedia resource recommendation method in the related technology is complex in process, low in efficiency and poor in accuracy.

Disclosure of Invention

The application provides a multimedia resource recommendation method and a related device, which are used for solving the problems of complex operation, low efficiency and poor accuracy when multimedia resource recommendation is performed in the related technology.

In a first aspect, the present application provides a multimedia resource recommendation method, including:

responding to a multimedia resource recommendation request of a target account, and acquiring a recent history behavior sequence of the target account; historical behaviors in the recent historical behavior sequence represent operation behaviors of the target account for corresponding multimedia resources in a preset time period before the current time;

according to the recent historical behavior sequence, determining expected recommendation degrees of the target account on a plurality of multimedia resource types in a first multimedia resource type set respectively; the first multimedia resource type set is obtained based on multimedia resources corresponding to historical behaviors in the recent historical behavior sequence;

determining the interest multimedia resource types of the target account according to the expected recommendation degrees of the target account to a plurality of multimedia resource types in the first multimedia resource type set;

screening out target historical behaviors matched with the interest multimedia resource types from the full historical behavior sequence of the target account to obtain a target historical behavior sequence corresponding to the target account;

according to the target historical behavior sequence, determining the interest degree of the target account for the multimedia resources to be recommended, and determining the target multimedia resources in the multimedia resources to be recommended according to the interest degree; the target multimedia resource is used for recommending to the target account.

In a possible implementation manner, before determining, according to the recent past behavior sequence, desired recommendation degrees of the target account for a plurality of multimedia resource types in a first set of multimedia resource types, respectively, the method further includes:

acquiring multimedia resources corresponding to each historical behavior in the recent historical behavior sequence to obtain a first multimedia resource set;

classifying the first multimedia resource set to obtain a second multimedia resource type set;

determining the interest degree of the target account in each media resource type in a second multimedia resource type set;

and screening the multimedia resource types with the interest degrees lower than a preset interest degree threshold value from the second multimedia resource type set to obtain the first multimedia resource type set.

In a possible implementation manner, the determining, according to the recent past behavior sequence, desired recommendation degrees of the target account for a plurality of multimedia resource types in a first set of multimedia resource types respectively includes:

performing, for each multimedia resource type in the first set of multimedia resource types:

determining the number n of the multimedia resources of which the access time duration of the historical behaviors is higher than a time duration threshold in the multimedia resources included in the multimedia resource types; wherein n is a positive integer greater than or equal to 1;

and determining the expected recommendation degree of the target account for the multimedia resource type by adopting a relation that the expected recommendation degree is in direct proportion to the n and is in inverse proportion to the number of the multimedia resources included in the multimedia resource type.

In one possible implementation, the multimedia resource type includes multimedia resources including:

accessed multimedia resources belonging to the multimedia resource type in the multimedia resources corresponding to the historical behaviors of the recent historical behavior sequence;

and/or the presence of a gas in the gas,

and the associated multimedia resources of the accessed multimedia resources are the multimedia resources which are synchronously recommended to the target account when the accessed multimedia resources are recommended, and the number of the accessed multimedia resources and the total number of the associated multimedia resources are not higher than the upper limit of the number.

In a possible implementation manner, before determining, according to the target historical behavior sequence, a degree of interest of the target account in the multimedia resource to be recommended, the method further includes:

screening candidate multimedia resources belonging to the interest multimedia resource type from the multimedia resources to be recommended;

if the number of the candidate multimedia resources is lower than the preset number, screening the candidate multimedia resources from similar multimedia resource types of the interest multimedia resource type until the total number of the candidate multimedia resources screened finally is not lower than the preset number;

and screening the candidate multimedia resources screened finally to obtain the multimedia resources to be recommended which are finally used for determining the interest degree of the target account in the multimedia resources to be recommended.

In a possible implementation manner, if it is determined that the distribution of the expected recommendation degrees of the plurality of multimedia resource types satisfies a preset distribution, the step of determining the multimedia resource types of interest of the target account according to the expected recommendation degrees of the target account for the plurality of multimedia resource types is performed.

In a possible implementation manner, before determining the multimedia resource types of interest of the target account according to the expected recommendation degrees of the target account for a plurality of multimedia resource types, the method further includes:

if the expected recommendation degree distribution of the plurality of multimedia resource types does not meet the preset distribution, performing cluster analysis on the multimedia resource types in the first multimedia resource type set to obtain a new first multimedia resource type set, and returning to execute the step of determining the expected recommendation degrees of the target account on the plurality of multimedia resource types in the first multimedia resource type set respectively according to the recent historical behavior sequence.

In a possible implementation manner, the determining, according to the expected recommendation degrees of the target account for the plurality of multimedia resource types in the first set of multimedia resource types, an interest multimedia resource type of the target account specifically includes:

screening out a specified number of multimedia resource types as interest multimedia resource types of the target account according to the sequence of the expected recommendation degrees from high to low; alternatively, the first and second electrodes may be,

and screening out the multimedia resource types with the expected recommendation degrees higher than the expected recommendation degree threshold value as the interest multimedia resource types of the target account according to the sequence from high to low of the expected recommendation degrees.

In a possible implementation manner, the determining the interest level of the target account in each media resource type in the second set of multimedia resource types specifically includes:

determining the operating frequency of the target account for each multimedia resource type in a second set of multimedia resource types based on historical behaviors in the recent historical behavior sequence;

and determining the interestingness of each media resource type in the second multimedia resource type set based on the positive correlation between the interestingness and the operating frequency.

In one possible embodiment, the recent historical behavior sequence includes:

a specified number of historical behaviors of the target account within a preset time period before the current time;

and/or the presence of a gas in the gas,

historical behavior of the target account within a preset time period before the current time.

In a second aspect, the present application provides a multimedia resource recommendation apparatus, including:

the recent history behavior sequence acquisition module is configured to execute a multimedia resource recommendation request responding to a target account and acquire a recent history behavior sequence of the target account; historical behaviors in the recent historical behavior sequence represent operation behaviors of the target account for corresponding multimedia resources in a preset time period before the current time;

an expected recommendation degree determining module configured to execute determining, according to the recent historical behavior sequence, expected recommendation degrees of the target account for a plurality of multimedia resource types in a first multimedia resource type set respectively; the first multimedia resource type set is obtained based on multimedia resources corresponding to historical behaviors in the recent historical behavior sequence;

the interest multimedia resource type determining module is further configured to execute the determination of the interest multimedia resource type of the target account according to the expected recommendation degree of the target account to the plurality of multimedia resource types in the first multimedia resource type set respectively;

the target historical behavior screening module is configured to screen out target historical behaviors matched with the interest multimedia resource types from the full historical behavior sequences of the target accounts to obtain target historical behavior sequences corresponding to the target accounts;

the target multimedia resource determining module is further configured to execute the steps of determining the interest degree of the target account for the multimedia resources to be recommended according to the target historical behavior sequence, and determining the target multimedia resources in the multimedia resources to be recommended according to the interest degree; the target multimedia resource is used for recommending to the target account.

In a possible embodiment, the apparatus further comprises:

a first multimedia resource set obtaining module, configured to obtain multimedia resources corresponding to each historical behavior in the recent history behavior sequence to obtain a first multimedia resource set before the expected recommendation degree determining module determines, according to the recent history behavior sequence, the expected recommendation degrees of the target account for a plurality of multimedia resource types in the first multimedia resource type set respectively;

a classification module configured to perform classification on the first multimedia resource set to obtain a second multimedia resource type set;

an interestingness determination module configured to perform the determination of the interestingness of the target account for each media resource type in the second set of multimedia resource types;

and the first multimedia resource type set determining module is configured to screen multimedia resource types with the interestingness lower than a preset interestingness threshold value from the second multimedia resource type set to obtain the first multimedia resource type set.

In a possible implementation manner, the determining, according to the recent past historical behavior sequence, the expected recommendation degrees of the plurality of multimedia resource types in the first set of multimedia resource types by the target account is performed, and the expected recommendation degree determining module is specifically configured to perform:

and/or the presence of a gas in the gas,

In a possible embodiment, the apparatus further comprises:

the candidate multimedia resource screening module is configured to screen candidate multimedia resources belonging to the interest multimedia resource type from the multimedia resources to be recommended before the target multimedia resource determining module determines the interest degree of the target account for the multimedia resources to be recommended according to the target historical behavior sequence;

the resource supplementing module is configured to screen candidate multimedia resources from similar multimedia resource types of the interest multimedia resource types if the number of the candidate multimedia resources is lower than a preset number until the total number of the screened candidate multimedia resources is not lower than the preset number;

and the to-be-recommended multimedia resource determining module is configured to perform screening on the finally screened candidate multimedia resources to obtain the to-be-recommended multimedia resources which are finally used for determining the interest degree of the target account in the to-be-recommended multimedia resources.

In a possible embodiment, the apparatus further comprises:

and the expected recommendation degree distribution determining module is configured to determine that the expected recommendation degree distribution of the plurality of multimedia resource types meets a preset distribution before the interest multimedia resource type determining module executes the expected recommendation degrees of the plurality of multimedia resource types according to the target account and determines the interest multimedia resource type of the target account.

In a possible embodiment, the apparatus further comprises:

the clustering module is configured to perform clustering analysis on the multimedia resource types in the first multimedia resource type set to obtain a new first multimedia resource type set if the expected recommendation degree distribution determining module determines that the expected recommendation degree distribution of the multimedia resource types does not meet the preset distribution before the interest multimedia resource type determining module performs the expected recommendation degrees on the multimedia resource types according to the target account and determines the interest multimedia resource types of the target account;

and the iteration module is configured to execute the steps of determining the expected recommendation degrees of the target account on the plurality of multimedia resource types in the first multimedia resource type set respectively according to the recent historical behavior sequence after a new first multimedia resource type set is obtained.

In a possible implementation manner, the determining, according to the expected recommendation degrees of the target account for a plurality of multimedia resource types in the first set of multimedia resource types, an interest multimedia resource type of the target account is performed, and the interest multimedia resource type determining module is specifically configured to perform:

In a possible implementation manner, the determining the interest level of the target account in each media resource type in the second set of multimedia resource types is performed, and the interest level determining module is specifically configured to perform:

In one possible embodiment, the recent historical behavior sequence includes:

and/or the presence of a gas in the gas,

In a third aspect, the present application further provides an electronic device, including:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement any of the multimedia resource recommendation methods as provided in the first aspect of the present application.

In a fourth aspect, the present application further provides a computer-readable storage medium, where instructions, when executed by a processor of an electronic device, enable the electronic device to perform any multimedia resource recommendation method as provided in the first aspect of the present application.

In a fifth aspect, an embodiment of the present application provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the computer program implements any multimedia resource recommendation method as provided in the first aspect of the present application.

The technical scheme provided by the embodiment of the application at least has the following beneficial effects:

according to the method, the expected recommendation degree of the user to different multimedia resource types is mined by adopting the recent historical behavior sequence of the user, the higher the expected recommendation degree is, the more interesting the user is to the multimedia resources of the type, and the more expected the user is to acquire the multimedia resources of the type, so that the recent interest of the user and the interest degree of the user to each multimedia resource type can be mined by the method based on the recent historical behavior sequence of the user, then the target historical behavior sequence of the user is constructed based on the multimedia resource type expected to be acquired by the user, the target historical behavior sequence is more emphasized on the recent interest of the user and the multimedia resource type expected to be acquired by the user compared with the long-term behavior sequence of the related technology, and the accurate recommendation can be made for the user by describing the requirements of the user better based on the target historical behavior sequence of the method. In addition, in the method, the target historical behavior sequence does not need to be acquired for each multimedia resource type, and the target historical behavior sequence is calculated once based on one request, so that compared with the prior art, the method for recommending the multimedia resource can simplify the operation and improve the recommending efficiency.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the application. The objectives and other advantages of the application may be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments of the present application will be briefly described below, and it is obvious that the drawings described below are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a schematic view of an application scenario of a multimedia resource recommendation method according to an embodiment of the present application;

FIG. 2 is a schematic flowchart of a process for training a multimedia resource recommendation model according to an embodiment of the present application;

fig. 3 is a schematic flowchart of a multimedia resource recommendation method according to an embodiment of the present application;

FIG. 4 is a flowchart illustrating a method for determining a first set of multimedia resource types according to an embodiment of the present application;

fig. 5 is a flowchart illustrating a method for determining a desired recommendation level according to an embodiment of the present application;

fig. 6 is a flowchart illustrating a method for determining a multimedia resource to be recommended according to an embodiment of the present application;

fig. 7 is a block diagram of a multimedia resource recommendation device according to an embodiment of the present application;

fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

In order to make the technical solutions of the present application better understood by those of ordinary skill in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

In addition, it should be noted that in the technical solution of the present application, the acquisition, storage, use, processing, etc. of the data all conform to the relevant regulations of the national laws and regulations.

Hereinafter, some terms in the embodiments of the present application are explained to facilitate understanding by those skilled in the art.

(1) In the embodiments of the present application, the term "plurality" means two or more, and other terms are similar thereto.

(2) "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.

(3) A server serving the terminal, the contents of the service such as providing resources to the terminal, storing terminal data; the server is corresponding to the application program installed on the terminal and is matched with the application program on the terminal to run.

(4) The terminal device may refer to an APP (Application) of a software class, or may refer to a client. The system is provided with a visual display interface and can interact with a target account; is corresponding to the server, and provides local service for the client. For software applications, except some applications that are only run locally, the software applications are generally installed on a common client terminal and need to be run in cooperation with a server terminal. After the development of the internet, more common application programs include short video applications, email clients for receiving and sending emails, and clients for instant messaging, for example. For such applications, a corresponding server and a corresponding service program are required in the network to provide corresponding services, such as database services, configuration parameter services, and the like, so that a specific communication connection needs to be established between the client terminal and the server terminal to ensure the normal operation of the application program.

In the related technology, after acquiring multimedia resources to be recommended based on a user request, all historical behavior data of the user are used as input of a CTR (subscriber identity module) model based on retrieved user behavior, if candidate multimedia resources to be recommended comprise multiple types of multimedia resources, a GSU (general Search Unit) module is used for respectively generating corresponding long-term behavior sequences for each type of multimedia resources to be recommended as input of an ESU (exact Search Unit) module, then a deep learning model based on an attention mechanism is used for modeling the long-term behavior sequences to obtain evaluation scores of each candidate multimedia resource, and then ranking and recommending are carried out on each multimedia resource to be recommended based on the evaluation scores.

Therefore, in the related art, for one request of a user, a long-term behavior sequence needs to be generated based on all historical behaviors of the user and all resources to be recommended. However, there may be several hundreds or even thousands of candidate videos in the resource to be recommended corresponding to one user request, so that the process of constructing the long-term behavior sequence may need to be executed several hundreds or thousands of times for one user request, and each time a long-term behavior sequence is constructed, the GSU module needs to execute once for each candidate video, which results in high frequency of related technology requests. Therefore, the process of constructing the long-term behavior sequence by the related art is complex and inefficient, and further the recommendation process is complex, inefficient and poor in accuracy.

In addition, the long-term behavior sequence generated by adopting all the historical behaviors of the user in the related technology emphasizes the long-term historical interest of the user, so that the resources screened based on the long-term historical interest are often the resources which are liked by the user in the past, but the currently liked resources cannot be met, and the current requirements which are recommended to the user cannot be met.

In view of this, the present application provides a multimedia resource recommendation method and a related apparatus, so as to solve the problems of complex operation, low efficiency and poor accuracy when performing multimedia resource recommendation in the related art.

The inventive concept of the present application can be summarized as follows: the method comprises the steps of firstly responding to a multimedia resource recommendation request of a target account, obtaining a recent history behavior sequence of the target account, and then determining expected recommendation degrees of the target account on a plurality of multimedia resource types in a first multimedia resource type set according to the recent history behavior sequence; meanwhile, according to the expected recommendation degrees of the target account to a plurality of multimedia resource types in the first multimedia resource type set, the interest multimedia resource type of the target account is determined; screening out target historical behaviors matched with the interest multimedia resource types from the full historical behavior sequence of the target account to obtain a target historical behavior sequence corresponding to the target account; finally, according to the target historical behavior sequence, the interest degree of the target account for the multimedia resources to be recommended is determined, the target multimedia resources in the multimedia resources to be recommended are determined according to the interest degree, the target multimedia resources are recommended to the target account, therefore, the expected recommendation degrees of different multimedia resource types by the user are mined by adopting the recent historical behavior sequence of the user, the higher the expected recommendation degree is, the more the user is interested in the multimedia resources of the type, and the more the user is expected to acquire the multimedia resources of the type, so that the recent interest of the user and the interest degree of the user in each multimedia resource type can be mined by the method based on the recent historical behavior sequence of the user, and then the target historical behavior sequence of the user is constructed based on the multimedia resource type expected to be acquired by the user, so that the target historical behavior sequence is more important than the long-term behavior sequence of the related technology than the recent interest of the user And the type of multimedia resources expected to be obtained by the user in the near future, and the target historical behavior sequence based on the application can better describe the requirements of the user and make accurate recommendation for the user. In addition, in the method, the target historical behavior sequence does not need to be acquired for each multimedia resource type, and the target historical behavior sequence is calculated once based on one request, so that compared with the prior art, the method for recommending the multimedia resource can simplify the operation and improve the recommending efficiency.

After introducing the design concept of the embodiment of the present application, some simple descriptions are provided below for application scenarios to which the technical solution of the embodiment of the present application can be applied, and it should be noted that the application scenarios described below are only used for describing the embodiment of the present application and are not limited. In specific implementation, the technical scheme provided by the embodiment of the application can be flexibly applied according to actual needs.

Fig. 1 is a schematic view of an application scenario of a multimedia resource recommendation method according to an embodiment of the present application. The application scenario includes a plurality of terminal devices 101 (including terminal device 101-1, terminal device 101-2, … … terminal device 101-n), and further includes server 102. The terminal device 101 and the server 102 are connected through a wireless or wired network, and the server 102 provides multimedia resources for the terminal device 101 to display.

The terminal device 101 includes, but is not limited to, a desktop computer, a mobile phone, a mobile computer, a tablet computer, a media player, a smart wearable device, a smart television, and other electronic devices.

The server 102 may be a server, a server cluster composed of several servers, or a cloud computing center. The server 102 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a network service, cloud communication, middleware service, a domain name service, a security service, a CDN, a big data and artificial intelligence platform, and the like.

Of course, the method provided in the embodiment of the present application is not limited to the application scenario shown in fig. 1, and may also be used in other possible application scenarios, and the embodiment of the present application is not limited. The functions that can be implemented by each device in the application scenario shown in fig. 1 will be described in the following method embodiments, and will not be described in detail herein.

To further illustrate the technical solutions provided by the embodiments of the present application, the following detailed description is made with reference to the accompanying drawings and the detailed description. Although the embodiments of the present application provide the method operation steps as shown in the following embodiments or figures, more or less operation steps may be included in the method based on the conventional or non-inventive labor. In steps where no necessary causal relationship exists logically, the order of execution of the steps is not limited to that provided by the embodiments of the present application.

It should be noted that the resource recommendation method provided by the present application is applicable to any network resource, such as short videos, long videos, network elements, commodities, and other scenes that need to recommend the network resource. In addition, the user information required for realizing resource recommendation is available through user authorization permission.

Some brief descriptions are provided below for a training procedure of a multimedia resource recommendation model to which the technical solution of the embodiment of the present application is applicable, so as to facilitate understanding of the technical solution provided by the embodiment of the present application by those skilled in the art.

Referring to fig. 2, a schematic flowchart of a multimedia resource recommendation model training process provided in an embodiment of the present application includes the following steps:

in step 201, training data is obtained to construct a training sample of a multimedia resource recommendation model (i.e., the user behavior interest CTR model described above).

In some embodiments, the training sample of the multimedia resource recommendation model includes target account features, multimedia resource features, context features, and target account behaviors on the sample, such as praise, concern, long-time viewing of the sample, and the training sample further includes a target historical behavior sequence of the user. The target historical behavior sequence in the present application is constructed based on the recent historical behavior sequence of the user (which will be described later herein).

The target account characteristics may be a target account ID, a device ID, or other characteristics that can represent target account information, such as target account interest, target account age, and the like. The target account feature may also be a sequence of averaged summed target account behaviors, such as a sequence of averaged most recently viewed multimedia asset IDs. The target account characteristic may also be a target account behavior sequence, for example, a target account history viewing multimedia resource ID sequence, a target account history viewing multimedia resource author ID sequence, a target account history viewing multimedia resource duration sequence from the current time, and other behavior sequences, which may be set according to an actual use situation, and the present application embodiment does not limit this.

The multimedia resource feature may be a multimedia resource ID, or other features capable of representing multimedia resource information, such as multimedia resource age, multimedia resource category, and the like, and may be set according to an actual use condition, which is not limited in this embodiment of the present application.

In step 202, the structure and parameters of the ESU in the multimedia resource recommendation model are adjusted based on the training samples, i.e., the ESU module is trained. Here, it can be embodied that the target historical behavior sequence obtained in step 201 is modeled based on an attention mechanism.

In step 203, training of the GSU module in the multimedia resource recommendation model is performed, thereby obtaining a trained GSU module and an ESU module.

In step 204, multimedia resource recommendation is performed based on the trained multimedia resource model.

The method for recommending the multimedia resource is mainly based on the process of training the multimedia resource recommendation model, the expected recommendation degrees of the user to different multimedia resource types are mined by adopting the recent historical behavior sequence of the user, the multimedia resource types which are interested by the user in the recent time are obtained according to the expected recommendation degrees of the user to the different multimedia resource types, and therefore the sample historical behavior sequence of the user is obtained, namely the training sample in the step 201 is obtained. And after obtaining the training samples, training the multimedia asset recommendation model using step 202 and step 203. The multimedia resource recommendation method provided by the application mainly comprises the steps of obtaining a target historical behavior sequence of a user by using the same method as the method for obtaining the sample historical behavior sequence, and inputting the target historical behavior sequence into a trained multimedia resource recommendation model, so that the target multimedia resource is obtained and recommended to the user.

Referring to fig. 3, a flowchart of a multimedia resource recommendation method provided in an embodiment of the present application is schematically shown. As shown in fig. 3, the method may be implemented as the following steps:

in step 301, in response to a multimedia resource recommendation request of a target account, obtaining a recent history behavior sequence of the target account; and the historical behaviors in the recent historical behavior sequence represent the operation behaviors of the target account for the corresponding multimedia resources in a preset time period before the current time.

For example, the preset time period is set to be 10 minutes, the historical behaviors in the recent historical behavior sequence represent the operation behaviors of the target account on the corresponding multimedia resources within 10 minutes before the current time, for example, the recent historical behavior sequence includes the viewing time or the number of praise times of each multimedia resource within 10 minutes.

In some embodiments, the multimedia resource recommendation request may be a refresh operation of the target account on the multimedia resource, or may be a search operation of the target account on the multimedia resource, which is not specifically limited in this application.

In some embodiments, the target account may include a unique identifier of the target account, such as a target account ID, and may further include a device ID, which may be set according to an actual use situation, and this is not limited in this embodiment of the present application.

In some embodiments, in response to a multimedia resource recommendation request of a target account, resources in a multimedia resource library are screened through steps of vector recall, rough arrangement and the like, and finally, multimedia resources to be recommended are obtained. The number of the multimedia resources to be recommended is large, for example, the number of the multimedia resources to be recommended can generally exceed about 1000.

In some embodiments, the recent historical sequence of behaviors includes: a specified number of historical behaviors of the target account within a preset time period before the current time; and/or historical behavior of the target account within a preset time period before the current time. For example: taking the multimedia resource as a video as an example, the recent history behavior sequence may include a video ID sequence of the last 50 videos watched by the target account, a video author ID sequence of the last 50 videos watched by the target account, a video duration sequence of the last 50 videos watched by the target account, a length sequence of the last 50 videos watched by the target account from the current time, and the like, and may also include a video ID sequence of videos watched within the last 10 minutes watched by the target account, or the number of times of approval for the videos watched within the last 10 minutes by the target account.

Therefore, a reliable range can be determined for the recent history behavior series acquired by the multimedia resource recommendation request based on the target account by setting a time period or a specified number, and the processing amount of the history behavior can be reduced by limiting the number while acquiring the history behavior, and the recent preference of the user can also be reflected.

In response to the multimedia resource recommendation request of the target account, the step of obtaining the recent history behavior sequence of the target account needs to obtain information of the target account, so in the application, any information of the target account is obtained after authorization and approval.

In step 302, according to the recent history behavior sequence, determining expected recommendation degrees of the target account to a plurality of multimedia resource types in the first multimedia resource type set respectively; the first multimedia resource type set is obtained based on the multimedia resources corresponding to the historical behaviors in the recent historical behavior sequence.

Wherein, the desired recommendation level refers to a level at which the interest of the target account in a certain multimedia resource type is not satisfied.

In a possible implementation manner, it may take a long time to determine the expected recommendation degrees of all multimedia resource types in the recent action sequence, so that it is inefficient to determine the expected recommendation degrees, and therefore, in order to improve the efficiency of determining the expected recommendation degrees, in this embodiment of the application, before determining the expected recommendation degrees of the target accounts respectively for a plurality of multimedia resource types in the first multimedia resource type set according to the recent historical action sequence, the range of the multimedia resource types may be narrowed, and specifically, the steps shown in fig. 4 may be performed:

in step 401, multimedia resources corresponding to each historical behavior in the recent historical behavior sequence are obtained, and a first multimedia resource set is obtained.

In step 402, the first set of multimedia resources is categorized to obtain a second set of multimedia resource types.

In step 403, the interest level of the target account in each media asset type in the second set of multimedia asset types is determined.

In a possible implementation manner, in this embodiment of the present application, determining the interest level of the target account in each media resource type in the second multimedia resource type set may specifically be implemented as: firstly, determining the operating frequency of a target account on each multimedia resource type in a second multimedia resource type set based on the historical behaviors in the recent historical behavior sequence; and then determining the interestingness of each media resource type in the second multimedia resource type set based on the positive correlation between the interestingness and the operating frequency.

Illustratively, according to the historical behaviors in the recent historical behavior sequence, it is determined that the multimedia resource types included in the second set of multimedia resource types include game-type videos, food-type videos, advertisement-type videos, and sales-type videos, wherein the recommended game-type videos include 20, food-type videos include 15, advertisement-type foods include 3, and sales-type videos, the number of times of approval of the target account for the game-type videos is 10, the number of times of approval of the food-type videos is 15, the number of times of approval of the advertisement-type videos is 0, and the number of times of approval of the sales-type videos is 1, the operating frequency of the target account for the game-type videos is 0.5, the operating frequency of the food-type videos is 1, the operating frequency of the advertisement-type foods is 0, and the operating frequency of the sales-type videos is 0.2, because the interest degree is positively correlated with the operating frequency, that is, the operating frequency is higher, the higher the interest degree of the corresponding multimedia resource type is, the higher the interest degree of the target account on the game video is determined to be 0.5, the interest degree on the food video is 1, the interest degree on the advertisement food is 0, and the interest degree on the sales video is 0.2.

Therefore, the interest degree of each multimedia resource type is determined according to the operation frequency of each type of multimedia resource in the recent historical behavior sequence, the interest degree of the user on different types of multimedia resources can be mined from the user behavior, and the interest of the user on different types of resources can be accurately measured.

In step 404, a multimedia resource type with an interest level lower than a predetermined interest level threshold is filtered from the second multimedia resource type set to obtain a first multimedia resource type set.

Illustratively, the threshold value of interest degree is set to be 0.5, in the above example, the interest degree of the target account in the game video is 0.5, the interest degree in the gourmet video is 1, the interest degree in the advertisement food is 0, and the interest degree in the sales video is 0.2, then the multimedia resource types with interest degree lower than 0.5 in the second multimedia resource type set can be filtered out, so as to obtain the game video and the gourmet video, and the game video and the gourmet video are used as the multimedia resource types in the first multimedia resource type set.

Therefore, the multimedia resource types higher than the interest threshold can be screened out by presetting the interest threshold, so that the range of the multimedia resource types can be narrowed, and the efficiency of determining the expected recommendation degree of the target account to a plurality of multimedia resource types in the first multimedia resource type set can be improved.

In a possible implementation manner, after determining the first set of multimedia resource types, it is required to determine, according to a recent history behavior sequence of the target account, desired recommendation degrees of the target account for a plurality of multimedia resource types in the first set of multimedia resource types, in this embodiment, the steps shown in fig. 5 may be performed for each multimedia resource type in the first set of multimedia resource types, respectively:

in step 501, determining the number n of multimedia resources with the access time length of the historical behavior higher than a time length threshold in the multimedia resources included in the multimedia resource types; wherein n is a positive integer greater than or equal to 1.

In a possible implementation manner, the multimedia resources included in the multimedia resource types in the embodiment of the present application specifically include: the accessed multimedia resources belonging to the multimedia resource type in the multimedia resources corresponding to the historical behaviors of the recent historical behavior sequence are adopted, so that the multimedia resources provided by the user historical behaviors are operated, namely the accessed multimedia resources can better represent the resources in which the user is interested.

In another embodiment, the multimedia resource included in the multimedia resource type may also be an associated multimedia resource of the aforementioned accessed multimedia resources, the associated multimedia resource is a multimedia resource that is synchronously recommended to the target account when the accessed multimedia resource is recommended, and the number of the accessed multimedia resources and the total number of the associated multimedia resources are not higher than the upper limit of the number. That is, when the types of the accessed multimedia resources are insufficient, the associated multimedia resources recommended synchronously can be adopted for supplement so as to expand the number of the multimedia resources, and the sufficient number of multimedia resources are ensured to be used as a support to improve the recommendation efficiency when the subsequent recommendation is performed based on the multimedia resources.

In step 502, the expected recommendation degree of the target account for the multimedia resource type is determined according to a relationship that the expected recommendation degree is in direct proportion to n and in inverse proportion to the number of the multimedia resources included in the multimedia resource type.

In a possible implementation manner, the first set of multimedia resource types includes a plurality of multimedia resource types, and therefore, calculating the corresponding expected recommendation degree for each multimedia resource type can count historical behaviors in a recent behavior sequence of the target account, distinguish the historical behaviors of the target account for each multimedia resource type into positive samples and negative samples, and calculate the expected recommendation degree of the target account for each multimedia resource type in a calculation manner of positive sample number/(positive sample number + negative sample number). The higher the positive sample proportion is, the higher the expected recommendation degree of the target account to the corresponding multimedia resource type is, and the greater the demand of the target account to the multimedia resource type is.

Illustratively, if the multimedia resource types in the first set of multimedia resource types include game videos and food videos, 10 game videos and 5 food videos are recommended to the target account in the near future, only 6 game videos and 1 food video are accessed by the target account in the near future, and the access time length of 1 video in the game videos is higher than the duration threshold value and the access time length of 1 video in the food videos is higher than the duration threshold value.

The first assumption is that the multimedia resources included in the multimedia resource type include accessed multimedia resources belonging to the multimedia resource type in the multimedia resources corresponding to the recent historical behavior of the historical behavior sequence, the number of the multimedia resources of the game video is 6, that is, the total sample number is 6, the number of the positive samples is 1, the number of the negative samples is 5, the calculated expected recommendation degree is 0.2, the number of the multimedia resources of the gourmet video is 1, that is, the total sample number is 1, the number of the positive samples is 1, the number of the negative samples is 0, the calculated expected recommendation degree is 1, and obviously, the expected recommendation degree of the target account for the multimedia resource type of the gourmet video is higher.

The second assumption is that the multimedia resources included in the multimedia resource type include accessed multimedia resources belonging to the multimedia resource type and associated multimedia resources of the accessed multimedia resources in the multimedia resources corresponding to the history behavior of the recent history behavior sequence. The number of multimedia resources of the game-like video is 10, that is, the total sample number is 10, the number of positive samples is 1, the number of negative samples is 9, and the calculated expected recommendation degree is 0.1, while the number of multimedia resources of the gourmet-like video is 5, that is, the total sample number is 5, the number of positive samples is 1, the number of negative samples is 4, and the calculated expected recommendation degree is 0.2, and obviously, the expected recommendation degree of the target account for the type of multimedia resources of the gourmet-like video is higher.

Therefore, the expected recommendation degree of the target account for each multimedia resource type in the first multimedia resource type set is determined through the method, which type of multimedia resource is expected by the user in the multimedia resources recommended to the user can be mined, and the recommendation accuracy is improved.

Therefore, the degree that the interest of each multimedia resource type of the target account is not met can be determined according to the expected recommendation degree of the target account to the plurality of multimedia resource types in the first multimedia resource type set, the recommended multimedia resource types are guaranteed to be in accordance with the recently interested multimedia resource types of the target account, and the problem of interest change of the target account in target historical behavior sequence modeling is solved.

In step 303, the interested multimedia resource types of the target account are determined according to the expected recommendation degrees of the target account to the plurality of multimedia resource types in the first set of multimedia resource types.

In a possible implementation manner, there may be no outstanding expected recommendation degree of the target account for a certain multimedia resource type, that is, there is no outstanding interest, which indicates that the expected recommendation degree of the most expected multimedia resource type and the least expected multimedia resource type of the target account are equal, so before determining the interest multimedia resource type of the target account according to the expected recommendation degrees of the target account for a plurality of multimedia resource types in the first multimedia resource type set, it is further required to determine that the expected recommendation degree distribution of the plurality of multimedia resource types satisfies the preset distribution, that is, it is determined that there is outstanding interest in the embodiment of the present application.

The preset distribution can be represented by using the difference between the expected recommendation degrees, a difference threshold can be set, and if the difference between the expected recommendation degrees of the multiple multimedia resource types is greater than the difference threshold, the expected recommendation degree distribution of the multiple multimedia resource types meets the preset distribution. The distribution condition can also be expressed as distribution concentration or distribution dispersion, a concentration threshold or a dispersion threshold is set, and if the expected recommendation degree distribution of the multiple multimedia resource types is greater than the concentration threshold or the expected recommendation degree distribution of the multiple multimedia resource types is less than the dispersion threshold, the expected recommendation degree distribution of the multiple multimedia resource types meets the preset distribution.

In a possible implementation manner, if it is determined that the expected recommendation degree distribution of the plurality of multimedia resource types meets the preset distribution, which indicates that the expected recommendation degree of the target account for at least one multimedia resource type is greater than the expected recommendation degrees of the other multimedia resource types, a step of determining the interested multimedia resource type of the target account according to the expected recommendation degrees of the target account for the plurality of multimedia resource types is performed.

Therefore, the expected recommendation degree of the multimedia resource type can be determined to meet the requirement of determining the interest multimedia resource type of the target account by setting the preset distribution, and the interest multimedia resource type of the target account can be determined better.

In a possible implementation manner, if it is determined that the expected recommendation degree distribution of the plurality of multimedia resource types does not satisfy the preset distribution, which indicates that there may be no expected recommendation degree of the target account for a certain multimedia resource type, performing cluster analysis on the multimedia resource types in the first multimedia resource type set to obtain a new first multimedia resource type set, and returning to execute the step of determining the expected recommendation degrees of the target account for the plurality of multimedia resource types in the first multimedia resource type set respectively according to the recent historical behavior sequence. For example, if the expected recommendation degrees of 1000 multimedia resource types do not meet the preset distribution, performing cluster analysis on the 1000 multimedia resource types, changing the clustered multimedia resource types into 100 multimedia resource types, and determining the expected recommendation degrees of the multimedia resource types based on the 100 multimedia resource types, thereby screening out a plurality of multimedia resource types as the interested multimedia resource types of the target account.

In one possible implementation, the cluster analysis may merge multimedia resource types with adjacent desired recommendation degrees into one multimedia resource type based on a tree structure of hierarchical clusters.

Therefore, by clustering and analyzing the multimedia resource types which do not meet the preset distribution, the subdivision degree of the multimedia resource types can be reduced, the distribution of the multimedia resource types in the recent behavior sequence is concentrated as much as possible, the expected recommendation degree difference of different multimedia resource types is large as much as possible, the expected recommendation degree of the multimedia resource types can be calculated better, and the interested multimedia resource types of the target account can be determined better according to the expected recommendation degree of the multimedia resource types.

In a possible implementation manner, after the expected recommendation degree of the target account for each multimedia resource type in the first multimedia resource type set is determined, in the embodiment of the application, a specified number of multimedia resource types can be screened out as the interest multimedia resource types of the target account according to the sequence from high to low of the expected recommendation degree; or screening out the multimedia resource types with the expected recommendation degrees higher than the expected recommendation degree threshold value as the interest multimedia resource types of the target account according to the sequence from high to low of the expected recommendation degrees.

For example, 100 multimedia resource types may be ranked from high to low according to respective expected recommendation degrees, the specified number of interest multimedia resource types is set to be 10, and then the top 10 multimedia resource types in the ranking are selected as the interest multimedia resource types of the target account. The expected recommendation degree threshold value can also be set to be 0.6, and the multimedia resource type with the expected recommendation degree greater than or equal to the expected recommendation degree threshold value 0.6 is selected as the interest multimedia resource type of the target account.

Therefore, the interested multimedia resource types of the target account can be screened out through a method of sequencing or setting a threshold value, the method can screen out the multimedia resource types which are interested by the user, and the screening method is simple, efficient and easy to implement.

In step 304, a target historical behavior matched with the interest multimedia resource type is screened from the full historical behavior sequence of the target account, and a target historical behavior sequence corresponding to the target account is obtained.

The full-volume historical behavior sequence comprises all behavior sequences of target accounts since the target account registration application, and the sequence length of different target accounts is different and can be between hundreds and hundreds of thousands. The full-amount historical behavior sequence may include ID sequences of all the access multimedia resources of the target account, ID sequences of all the authors of all the access multimedia resources of the target account, duration sequences of all the access multimedia resources of the target account, and a sequence of the current duration of all the access multimedia resources of the target account, which may be set according to an actual use situation, and is not limited in the embodiments of the present application.

In a possible implementation manner, a corresponding behavior sequence may be obtained from the full-volume historical behavior sequence of the target account according to the interest multimedia resource type of the target account obtained in step 303, so as to construct a new target historical behavior sequence.

In step 305, according to the target historical behavior sequence, determining the interest degree of the target account for the multimedia resources to be recommended, and determining the target multimedia resources in the multimedia resources to be recommended according to the interest degree; the target multimedia resource is used for recommending to the target account.

In a possible implementation manner, before determining the interest degree of the target account in the multimedia resource to be recommended according to the target historical behavior sequence, in this embodiment of the present application, the multimedia resource to be recommended of the interest degree of the target account in the multimedia resource to be recommended may also be determined, and specifically, the steps shown in fig. 6 may be performed:

in step 601, candidate multimedia resources belonging to the interest multimedia resource type are screened out from the multimedia resources to be recommended.

In step 602, if the number of the candidate multimedia resources is less than the preset number, the candidate multimedia resources are screened from the similar multimedia resource types of the interest multimedia resource type until the total number of the candidate multimedia resources screened finally is not less than the preset number.

In a possible implementation manner, a plurality of candidate multimedia resources corresponding to the interest multimedia resource type may be obtained by screening from the multimedia resource library based on the interest multimedia resource type of the target account obtained in step 303. The plurality of candidate multimedia assets may be new to old multimedia assets or may be the most popular multimedia assets. When the number of the multimedia resources obtained by screening in the multimedia resource library does not meet the preset number, the requirement can be relaxed, and the multimedia resources corresponding to other multimedia resource types closest to the interest multimedia resource type are screened until the number of the multimedia resources obtained by screening meets the preset number. The preset number may be thousands or tens of thousands, and may be set according to actual conditions, which is not limited in the embodiments of the present application.

In step 603, the candidate multimedia resources finally screened are screened to obtain the multimedia resources to be recommended, which are finally used for determining the interest degree of the multimedia resources to be recommended by the target account.

In a possible implementation manner, the candidate multimedia resources screened in step 602 are used as a recall source, and funnel-type screening is performed through the steps of coarse arrangement, fine arrangement and the like, and finally, the multimedia resources to be recommended are screened. The number of the screened multimedia resources to be recommended is about 1000 generally, and the multimedia resources to be recommended can be set according to actual conditions, and the method is not limited in the embodiment of the application.

Therefore, the multimedia resources corresponding to the type of the interest multimedia resources which are most expected to be recommended by the target account can be sufficiently supplied, and the problem of insufficient supply of the multimedia resources which are interested by the target account can be solved.

In a possible implementation manner, the interest degree of the target account for the multimedia resources to be recommended is determined according to the target historical behavior sequence, in the embodiment of the application, the target historical behavior sequence may be adopted to sort the multimedia resources to be recommended to obtain the recommendation sequence of the multimedia resources to be recommended, and the more advanced the recommendation sequence is, the greater the interest degree of the target account for the multimedia resources to be recommended is.

For example, the sample historical behavior sequence may be first taken by using a method of taking to a target historical behavior sequence, and the sample historical behavior sequence may be modeled based on a transform (machine translation Attention mechanism) or Multi-head Attention mechanism, for example, a vector including multimedia resource features and other features of a target item may be used as a query (query condition), and the sample historical behavior sequence may be used as a key and a value (value) in an Attention mechanism manner based on QKV (query-key-value). The feature is spliced with other features and then the estimated output of the corresponding target item can be obtained through an MLP (Multi-Layer Perception). And then training the multimedia resource recommendation model, namely predicting the scores of the behaviors of the target account to-be-recommended multimedia resource samples, inputting the models by using the target account characteristics, the multimedia resource characteristics, the context characteristics and the sample historical behavior sequence, and predicting the scores of the behaviors of the target account to-be-recommended multimedia resource samples, such as the probability of praise, concern and long-time viewing of the to-be-recommended multimedia resource samples. And updating parameters of the multimedia resource recommendation model based on the estimated scores of the behaviors of the multimedia resource samples to be recommended by the target accounts and the actual behavior calculation loss functions of the target accounts in the neural network training samples. And finally, combining the estimated scores of the various behaviors of the output target account multimedia resource sample to be recommended by using the trained multimedia resource recommendation model based on an ensemble sort formula to obtain the recommendation sequence of the multimedia resource to be recommended, and finally determining the interest degree of the target account multimedia resource to be recommended.

In one possible implementation mode, a target multimedia resource in the multimedia resources to be recommended is determined according to the interest degree; the target multimedia resource is used for recommending to the target account. According to the recommendation sequence of the multimedia resources to be recommended, the multimedia resources to be recommended with the front recommendation sequence can be recommended to the target account, namely the multimedia resources to be recommended with the larger interest degree of the multimedia resources to be recommended by the target account are recommended to the target account.

Based on the foregoing description, in the embodiment of the present application, first, in response to a multimedia resource recommendation request of a target account, a recent history behavior sequence of the target account is obtained, and then, according to the recent history behavior sequence, expected recommendation degrees of the target account on a plurality of multimedia resource types in a first multimedia resource type set are determined; meanwhile, according to the expected recommendation degrees of the target account to a plurality of multimedia resource types in the first multimedia resource type set, the interest multimedia resource type of the target account is determined; screening out target historical behaviors matched with the interest multimedia resource types from the full historical behavior sequence of the target account to obtain a target historical behavior sequence corresponding to the target account; and finally, according to the target historical behavior sequence, determining the interest degree of the target account for the multimedia resources to be recommended, determining the target multimedia resources in the multimedia resources to be recommended according to the interest degree, and recommending the target multimedia resources to the target account.

Therefore, the expected recommendation degrees of the users to different multimedia resource types are mined by adopting the recent historical behavior sequence of the users, the higher the expected recommendation degree is, the more the users are interested in the multimedia resources of the type, and the more the users are expected to acquire the multimedia resources of the type, so that the recent interest of the users and the interest degree of the users to each multimedia resource type can be mined by the application based on the recent historical behavior sequence of the users, then the target historical behavior sequence of the users is constructed based on the multimedia resource types expected to be acquired by the users, the target historical behavior sequence is more emphasized on the recent interest of the users and the multimedia resource types expected to be acquired by the users in comparison with the long-term behavior sequence of the related technology, and the accurate recommendation can be made for the users by better describing the requirements of the users based on the target historical behavior sequence of the application. In addition, in the method, the target historical behavior sequence does not need to be acquired for each multimedia resource type, and the target historical behavior sequence is calculated once based on one request, so that compared with the prior art, the method for recommending the multimedia resource can simplify the operation and improve the recommending efficiency.

The embodiment of the application also provides a multimedia resource recommendation device based on the same inventive concept. Fig. 7 is a block diagram of an apparatus for recommending multimedia resources according to an embodiment of the present application, and referring to fig. 7, the apparatus includes: a recent history behavior sequence obtaining module 701, an expected recommendation degree determining module 702, an interest multimedia resource type determining module 703, a target history behavior screening module 704 and a target multimedia resource determining module 705, wherein:

a recent history behavior sequence obtaining module 701 configured to execute a multimedia resource recommendation request in response to a target account, and obtain a recent history behavior sequence of the target account; historical behaviors in the recent historical behavior sequence represent operation behaviors of the target account for corresponding multimedia resources in a preset time period before the current time;

an expected recommendation degree determining module 702 configured to perform determining, according to the recent past behavior sequence, expected recommendation degrees of the target account for a plurality of multimedia resource types in a first set of multimedia resource types, respectively; the first multimedia resource type set is obtained based on multimedia resources corresponding to historical behaviors in the recent historical behavior sequence;

an interest multimedia resource type determining module 703, further configured to perform determining an interest multimedia resource type of the target account according to expected recommendation degrees of the target account for a plurality of multimedia resource types in the first multimedia resource type set, respectively;

a target historical behavior screening module 704 configured to perform screening of a target historical behavior matched with the interest multimedia resource type from the full historical behavior sequence of the target account, so as to obtain a target historical behavior sequence corresponding to the target account;

the target multimedia resource determining module 705 is further configured to execute determining the interest degree of the target account for the multimedia resources to be recommended according to the target historical behavior sequence, and determining the target multimedia resources in the multimedia resources to be recommended according to the interest degree; the target multimedia resource is used for recommending to the target account.

In a possible embodiment, the apparatus further comprises:

a first multimedia resource set obtaining module, configured to obtain multimedia resources corresponding to each historical behavior in the recent history behavior sequence to obtain a first multimedia resource set before the expected recommendation degree determining module 702 determines, according to the recent history behavior sequence, expected recommendation degrees of the target account for multiple multimedia resource types in the first multimedia resource type set, respectively;

In a possible implementation manner, the determining, according to the recent past historical behavior sequence, the expected recommendation degrees of the plurality of multimedia resource types in the first set of multimedia resource types by the target account is performed, and the expected recommendation degree determining module 702 is specifically configured to perform:

and/or the presence of a gas in the gas,

In a possible embodiment, the apparatus further comprises:

a candidate multimedia resource screening module configured to perform screening of candidate multimedia resources belonging to the interest multimedia resource type from the to-be-recommended multimedia resources before the target multimedia resource determining module 705 performs determining the interest degree of the target account to the to-be-recommended multimedia resources according to the target historical behavior sequence;

In a possible embodiment, the apparatus further comprises:

an expected recommendation degree distribution determining module configured to determine that the expected recommendation degree distribution of the plurality of multimedia resource types satisfies a preset distribution before the interest multimedia resource type determining module 703 executes the expected recommendation degrees of the plurality of multimedia resource types according to the target account and determines the interest multimedia resource type of the target account.

In a possible embodiment, the apparatus further comprises:

a clustering module, configured to perform, before the interest multimedia resource type determining module 703 performs the expected recommendation degrees to the plurality of multimedia resource types according to the target account, and determines the interest multimedia resource type of the target account, if the expected recommendation degree distribution determining module determines that the expected recommendation degree distribution of the plurality of multimedia resource types does not satisfy the preset distribution, performing cluster analysis on the multimedia resource types in the first multimedia resource type set to obtain a new first multimedia resource type set;

In a possible implementation manner, the determining, according to the expected recommendation degrees of the target account for a plurality of multimedia resource types in the first set of multimedia resource types, an interest multimedia resource type of the target account is performed, and the interest multimedia resource type determining module 703 is specifically configured to perform:

In one possible embodiment, the recent historical behavior sequence includes:

and/or the presence of a gas in the gas,

The multimedia resource recommendation device and the multimedia resource recommendation method provided by the embodiment of the application adopt the same inventive concept, can obtain the same beneficial effects, and are not repeated herein.

After introducing the multimedia resource recommendation method and apparatus according to the exemplary embodiment of the present application, an electronic device of the multimedia resource recommendation method according to the embodiment of the present application is introduced next.

As will be appreciated by one skilled in the art, aspects of the present application may be embodied as a system, method or program product. Accordingly, various aspects of the present application may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" system.

In some possible implementations, an electronic device according to the present application may include at least one processor, and at least one memory. Wherein the memory stores program code which, when executed by the processor, causes the processor to perform the multimedia resource recommendation method according to various exemplary embodiments of the present application described above in this specification. For example, the processor may perform steps as in a multimedia resource recommendation method.

An electronic device 800 according to this embodiment of the application is described below with reference to fig. 8. The electronic device 800 shown in fig. 8 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.

As shown in fig. 8, the electronic device 800 is represented in the form of a general electronic device. The components of the electronic device 800 may include, but are not limited to: the at least one processor 801, the at least one memory 802, and a bus 803 that couples various system components including the memory 802 and the processor 801.

Bus 803 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a processor, or a local bus using any of a variety of bus architectures.

The memory 802 may include readable media in the form of volatile memory, such as Random Access Memory (RAM)8021 and/or cache memory 8022, and may further include Read Only Memory (ROM) 8023.

Memory 802 may also include a program/utility 8025 having a set (at least one) of program modules 8024, such program modules 8024 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.

The electronic device 800 may also communicate with one or more external devices 804 (e.g., keyboard, pointing device, etc.), with one or more devices that enable a user to interact with the electronic device 800, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 800 to communicate with one or more other electronic devices. Such communication may be through input/output (I/O) interfaces 805. Also, the electronic device 800 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the internet) via the network adapter 806. As shown, the network adapter 806 communicates with other modules for the electronic device 800 over the bus 803. It should be understood that although not shown in the figures, other hardware and/or software modules may be used in conjunction with electronic device 800, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.

In an exemplary embodiment, a computer-readable storage medium comprising instructions, such as the memory 802 comprising instructions, executable by the processor 801 to perform the multimedia resource recommendation method described above is also provided. Alternatively, the storage medium may be a non-transitory computer readable storage medium, which may be, for example, a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

In an exemplary embodiment, there is also provided a computer program product comprising a computer program which, when executed by the processor 801, implements any of the methods of multimedia asset recommendation methods as provided herein.

In an exemplary embodiment, aspects of a multimedia resource recommendation method provided in the present application may also be implemented in the form of a program product, which includes program code for causing a computer device to perform the steps of the multimedia resource recommendation method according to various exemplary embodiments of the present application described above in this specification when the program product runs on the computer device.

The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

The program product for the multimedia resource recommendation method of the embodiments of the present application may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on an electronic device. However, the program product of the present application is not limited thereto, and in this document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

A readable signal medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for carrying out operations of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the consumer electronic device, partly on the consumer electronic device, as a stand-alone software package, partly on the consumer electronic device and partly on a remote electronic device, or entirely on the remote electronic device or server. In the case of remote electronic devices, the remote electronic devices may be connected to the consumer electronic device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external electronic device (e.g., through the internet using an internet service provider).

It should be noted that although several units or sub-units of the apparatus are mentioned in the above detailed description, such division is merely exemplary and not mandatory. Indeed, the features and functions of two or more units described above may be embodied in one unit, according to embodiments of the application. Conversely, the features and functions of one unit described above may be further divided into embodiments by a plurality of units.

Further, while the operations of the methods of the present application are depicted in the drawings in a particular order, this does not require or imply that these operations must be performed in this particular order, or that all of the illustrated operations must be performed, to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable image scaling apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable image scaling apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable image scaling apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable image scaling device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer implemented process such that the instructions which execute on the computer or other programmable device provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

While the preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all alterations and modifications as fall within the scope of the application.

It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.

Claims

1. A method for recommending multimedia resources, the method comprising:

2. The method according to claim 1, wherein the determining, according to the recent past historical behavior sequence, the expected recommendation degrees of the target account for the plurality of multimedia resource types in the first set of multimedia resource types respectively comprises:

3. The method of claim 1, wherein before determining the interest level of the target account in the multimedia resource to be recommended according to the target historical behavior sequence, the method further comprises:

4. The method of claim 1, wherein if it is determined that the distribution of the expected recommendation degrees for the plurality of multimedia resource types satisfies a preset distribution, the step of determining the multimedia resource types of interest of the target account according to the expected recommendation degrees for the plurality of multimedia resource types by the target account is performed.

5. The method of claim 4, wherein before determining the multimedia resource types of interest to the target account according to the desired recommendation levels of the target account for the plurality of multimedia resource types, the method further comprises:

6. The method according to any one of claims 1 to 5, wherein the determining the interest multimedia resource type of the target account according to the expected recommendation degree of the target account for a plurality of multimedia resource types in the first set of multimedia resource types respectively comprises:

7. An apparatus for recommending multimedia resources, the apparatus comprising:

8. An electronic device, comprising:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the multimedia resource recommendation method of any of claims 1-6.

9. A computer-readable storage medium, wherein instructions in the computer-readable storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the multimedia asset recommendation method of any of claims 1-6.

10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, carries out the method of multimedia resource recommendation according to any of claims 1-6.