WO2018192272A1

WO2018192272A1 - Multimedia resource recommendation method and apparatus

Info

Publication number: WO2018192272A1
Application number: PCT/CN2018/070028
Authority: WO
Inventors: 刘荣; 赵磊; 单明辉; 王建宇; 潘柏宇; 项青
Original assignee: 优酷信息技术（北京）有限公司
Priority date: 2017-04-17
Filing date: 2018-01-02
Publication date: 2018-10-25
Also published as: CN108733684A; TW201840197A; TWI678922B

Abstract

A multimedia resource recommendation method and apparatus. The method comprises: determining various multimedia resources associated with a target user (S11); determining categories corresponding to the multimedia resources associated with the target user (S12); sorting the categories according to the number of multimedia resources, belonging to each of the categories, in the multimedia resources associated with the target user and the degree of interest of the target user for each of the multimedia resources in each of the categories (S13); and recommending the sorted categories to the target user (S14). The method can reduce the time spent by a user to find the category of a multimedia resource that he/she wants to watch, thereby reducing the time spent by the user to find the multimedia resource that he/she wants to watch, improving the recommendation efficiency of the multimedia resource, and improving the user experience.

Description

Method and device for recommending multimedia resources

cross reference

The present application claims the priority of the Japanese Patent Application No.

Technical field

The present disclosure relates to the field of multimedia technologies, and in particular, to a method and an apparatus for recommending multimedia resources.

Background technique

In the era of the Internet, especially in the era of mobile Internet, how to provide users with timely and valuable information is a hot spot for many Internet companies. In recent years, with the development of machine learning systems, the recommendation system has begun to support personalized recommendation strategies. The personalized recommendation strategy needs to be differentiated according to the actual usage of different users.

The operator of a video site or video application categorizes the video in a video site or video application to guide the user in selecting the category of interest. For example, the home page of a video site may include categories such as selections, episodes, variety shows, and movies. By showing the user the category of the video, it is possible to direct the user directly into the category of interest. In the related art, the number of categories displayed for the user is large, and the order of the categories displayed for each user is the same, so that the user needs to spend more time to find the category of interest, and the user experience is poor.

Summary of the invention

In view of this, the present disclosure proposes a method and an apparatus for recommending multimedia resources to solve the problem that the user needs to spend more time in the related art to find the category of the multimedia resources that are of interest.

According to an aspect of the present disclosure, a method for recommending a multimedia resource is provided, including:

Determining various multimedia resources associated with the target user;

Determining a category corresponding to each multimedia resource associated with the target user;

Sorting each category according to the number of multimedia resources belonging to each category among the multimedia resources associated with the target user, and the degree of interest of the target user for each multimedia resource in each category;

The sorted categories are recommended to the target users.

In a possible implementation manner, the method further includes:

Determining the degree of interest of the target user for each multimedia resource according to a time interval between the time point of the target user interacting with each multimedia resource and the current time, wherein the interest degree is negatively correlated with the time interval.

In a possible implementation, the interest rate of the target user to each multimedia resource is determined according to a time interval between a time point of the target user interacting with each multimedia resource and a current time, including:

Using the formula 1 to determine the degree of interest g(u, v _ij ) of the target user u for the multimedia resource v _ij in the category c _i ;

Where d is the attenuation coefficient, 0 < d < 1,

A time interval between a time point at which the target user u interacts with the multimedia resource v _ij and a current time.

In a possible implementation manner, according to the quantity of multimedia resources belonging to each category among the multimedia resources associated with the target user, and the interest degree of the target user to each multimedia resource in each category, each category Sort, including:

Calculating a score of each category for the target user according to the number of multimedia resources belonging to each category among the multimedia resources associated with the target user, and the degree of interest of the target user for each multimedia resource in each category;

Each category is sorted in order of highest to lowest scores for the target users for each category.

In a possible implementation manner, each category is calculated according to the number of multimedia resources belonging to each category among the multimedia resources associated with the target user, and the interest degree of the target user to each multimedia resource in each category. The score for the target user includes:

Using the formula 2, the score s(u, c _i ) of the category c _i for the target user u is determined;

Where h(u,c _i ) represents the first parameter, h(u,c _i ) is positively correlated with n, 0<h(u,c _i )<n, and n represents the multimedia associated with the target user u The number of multimedia resources belonging to the category c _i in the resource, g(u, v _ij ) represents the degree of interest of the target user u for the multimedia resource v _ij , and v _ij represents the j-th multimedia resource in the category c _i .

In a possible implementation manner, the first parameter is determined by using Equation 3;

h(u,c _i )=ln n is Equation 3.

In a possible implementation manner, determining respective multimedia resources associated with the target user includes:

Determining at least one of the following as a multimedia resource associated with the target user: a multimedia resource clicked by the target user, a multimedia resource searched by the target user, a multimedia resource viewed by the target user, the target user point The multimedia resource, the multimedia resource of the target user comment, the multimedia resource of the target user publishing the barrage, the multimedia resource shared by the target user, the multimedia resource of the target user, and the multimedia subscribed by the target user Resources.

According to another aspect of the present disclosure, a device for recommending a multimedia resource is provided, including:

a first determining module, configured to determine respective multimedia resources associated with the target user;

a second determining module, configured to determine a category corresponding to each multimedia resource associated with the target user;

a sorting module, configured to sort each category according to a quantity of multimedia resources belonging to each category among the multimedia resources associated with the target user, and an interest degree of the target user to each multimedia resource in each category;

A recommendation module is used to recommend the sorted categories to the target user.

In a possible implementation, the device further includes:

a third determining module, configured to determine, according to a time interval between a time point of the target user interacting with each multimedia resource and a current time, an interest degree of the target user to each multimedia resource, where the interest degree is The time intervals are negatively correlated.

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

Where d is the attenuation coefficient, 0 < d < 1,

In a possible implementation manner, the ordering module includes:

a calculation submodule, configured to calculate, according to the number of multimedia resources belonging to each category among the multimedia resources associated with the target user, and the interest degree of the target user to each multimedia resource in each category, calculate each category for the The score of the target user;

A sorting sub-module for sorting each category according to a high-to-low score of the respective categories for the target users.

In a possible implementation manner, the calculation submodule is used to:

h(u,c _i )=ln n is Equation 3.

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

According to another aspect of the present disclosure, a recommendation device for a multimedia resource is provided, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to perform the above method.

According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium that enables a terminal and/or a server to execute when instructions in the storage medium are executed by a processor of a terminal and/or a server The above method.

The method and apparatus for recommending multimedia resources according to aspects of the present disclosure are based on the number of multimedia resources belonging to each category among the multimedia resources associated with the target user, and the degree of interest of the target user for each multimedia resource in each category, for each category Sorting and recommending the sorted categories to the target users, thereby reducing the time taken by the user to find the category of multimedia resources that he wants to watch, thereby reducing the time it takes for the user to find the multimedia resources that he wants to watch. Improve the recommendation efficiency of multimedia resources and improve the user experience.

Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments.

DRAWINGS

The accompanying drawings, which are incorporated in FIG

FIG. 1 illustrates a flow chart of a method of recommending a multimedia resource according to an embodiment of the present disclosure.

FIG. 2 illustrates an exemplary flowchart of a method of recommending a multimedia resource according to an embodiment of the present disclosure.

FIG. 3 illustrates an exemplary flowchart of a method S13 of recommending a multimedia resource according to an embodiment of the present disclosure.

FIG. 4 illustrates a block diagram of a recommendation device for a multimedia resource according to an embodiment of the present disclosure.

FIG. 5 illustrates an exemplary block diagram of a recommendation device for a multimedia resource according to an embodiment of the present disclosure.

FIG. 6 is a block diagram of an apparatus 1900 for recommending multimedia resources, according to an exemplary embodiment.

detailed description

Various exemplary embodiments, features, and aspects of the present disclosure are described in detail below with reference to the drawings. The same reference numerals in the drawings denote the same or similar elements. Although the various aspects of the embodiments are illustrated in the drawings, the drawings are not necessarily drawn to scale unless otherwise indicated.

The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustrative." Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or preferred.

In addition, numerous specific details are set forth in the Detailed Description of the <RTIgt; Those skilled in the art will appreciate that the present disclosure may be practiced without some specific details. In some instances, methods, means, components, and circuits that are well known to those skilled in the art are not described in detail.

FIG. 1 illustrates a flow chart of a method of recommending a multimedia resource according to an embodiment of the present disclosure. The method can be applied to a server, which is not limited herein. As shown in FIG. 1, the method includes steps S11 to S14.

In step S11, respective multimedia resources associated with the target user are determined.

As an example of the present embodiment, each multimedia resource associated with the target user may be determined upon receiving a request from the target user to obtain a category list of multimedia resources.

In a possible implementation, determining each multimedia resource associated with the target user may include: determining at least one of the following as a multimedia resource associated with the target user: a multimedia resource clicked by the target user, and a target user search Multimedia resources, multimedia resources viewed by target users, multimedia resources praised by target users, multimedia resources of target user comments, multimedia resources of target users publishing bullets, multimedia resources shared by target users, multimedia resources of target users, and target users Subscribe to multimedia resources.

In a possible implementation manner, determining each multimedia resource associated with the target user may be: determining respective multimedia resources associated with the target user in the first time period. As an example of the implementation, at least one of the following may be determined as a multimedia resource associated with the target user in the first time period: the multimedia resource that the target user clicks in the first time period, and the target user in the first time period The multimedia resource searched within, the multimedia resource that the target user views in the first time period, the multimedia resource that the target user likes in the first time period, the multimedia resource that the target user comments in the first time period, and the target user are in the first The multimedia resources of the barrage are published in a period of time, the multimedia resources shared by the target user in the first time period, the multimedia resources collected by the target user in the first time period, and the multimedia resources subscribed by the target user in the first time period. For example, the starting time point of the first time period may be separated from the current time point by a first time, and the ending time point of the first time period may be the current time point. The first duration may be one week or one month, and is not limited herein. By determining each multimedia resource associated with the target user in the first time period, the target user may be recommended for the multimedia resource according to the short-term interest of the target user.

As an example of the embodiment, the interaction behavior of the target user for the multimedia resource on the mobile application may be recorded, and each multimedia resource associated with the target user is determined according to the interaction behavior of the target user on the mobile application for the multimedia resource. The interaction behavior may include at least one of the following: a click behavior, a search behavior, a viewing behavior, a praise behavior, a comment behavior, a publication barrage behavior, a sharing behavior, a collection behavior, and a subscription behavior.

In step S12, categories corresponding to respective multimedia resources associated with the target user are determined.

As an example of the present embodiment, the category of the secondary navigation corresponding to each multimedia resource associated with the target user may be determined. For example, the variety is a category of navigation, and the category of secondary navigation under the first level navigation may include mainland variety, Hong Kong and Taiwan variety, Korean variety, American variety and network variety. For another example, the episode is another category of navigation, and the category of the second-level navigation under the first-level navigation may include costume dramas, martial arts dramas, police dramas, military dramas, mythological dramas, science fiction gatherings. , funny dramas, idol dramas, suspense dramas, historical dramas, children's dramas, rural dramas, urban dramas, family dramas, romance dramas and fashion dramas.

As an example of the embodiment, the category corresponding to the multimedia resource may be determined according to the title and/or the label of the multimedia resource.

As another example of the embodiment, the category corresponding to the multimedia resource may be determined by means of manual marking.

In step S13, each category is sorted according to the number of multimedia resources belonging to each category among the multimedia resources associated with the target user, and the degree of interest of the target user for each multimedia resource in each category.

As an example of this embodiment, the ranking of a category for a target user is positively correlated with the number of multimedia resources associated with the target user in the category. For example, the greater the number of multimedia resources associated with a target user in category A, the higher the ranking of category A for the target user.

As an example of the embodiment, the ranking of a certain category for the target user is positively correlated with the degree of interest of the target user for each multimedia resource in the category. For example, the higher the interest of the target user for each multimedia resource in category B, the higher the ranking of category B for the target user.

In step S14, the sorted respective categories are recommended to the target user.

As an example of the present embodiment, a category list may be generated based on the sorted respective categories, and the category list is recommended to the target user. For example, a list of categories of videos can be presented to a target user in a video website or video application.

The embodiment can reduce the time taken by the user to find the category of the multimedia resource that is desired to be viewed, thereby reducing the time taken by the user to find the multimedia resource that is desired to be viewed, improving the recommendation efficiency of the multimedia resource, and improving the user experience.

FIG. 2 illustrates an exemplary flowchart of a method of recommending a multimedia resource according to an embodiment of the present disclosure. As shown in FIG. 2, the method includes steps S21 to S25.

In step S21, respective multimedia resources associated with the target user are determined.

For the step S21, refer to the description of step S11 above.

In step S22, categories corresponding to respective multimedia resources associated with the target user are determined.

For the step S22, refer to the description of step S12 above.

In step S23, the interest degree of the target user to each multimedia resource is determined according to the time interval between the time point of the target user interacting with each multimedia resource and the current time, wherein the interest degree is negatively correlated with the time interval.

As an example of the embodiment, the longer the time interval between the time point of the target user viewing the first multimedia resource and the current time, the smaller the interest rate of the target user on the first multimedia resource is; the target user views The shorter the time interval between the time point of the first multimedia resource and the current time, the greater the degree of interest of the target user to the first multimedia resource. The first multimedia resource is any one of the multimedia resources associated with the target user.

In step S24, each category is sorted according to the number of multimedia resources belonging to each category among the multimedia resources associated with the target user, and the degree of interest of the target user for each multimedia resource in each category.

Here, the description of step S13 above is referred to step S24.

In step S25, the sorted respective categories are recommended to the target user.

Wherein, refer to the description of step S14 above for step S25.

In a possible implementation manner, determining the interest degree of the target user to each multimedia resource according to the time interval between the time point of the target user interacting with each multimedia resource and the current time may include: determining the target user by using Equation 1: u the degree of interest g(u,v _ij ) to the multimedia resource v _ij in the category c _i ;

Where d is the attenuation coefficient, 0 < d < 1,

Indicates the time interval between the time point at which the target user u interacts with the multimedia resource v _ij and the current time.

For example, d can be 0.9.

Can be in hours. For example, the interaction behavior of the target user for the second multimedia resource is a viewing behavior, and the time interval between the time point when the target user views the second multimedia resource and the current time is 2 hours, and the target user is the second largest The interest level of media resources is equal to 0.9 ² =0.81. The second multimedia resource may represent any one of the multimedia resources associated with the target user.

FIG. 3 illustrates an exemplary flowchart of a method S13 of recommending a multimedia resource according to an embodiment of the present disclosure. As shown in FIG. 3, sorting each category according to the number of multimedia resources belonging to each category among the multimedia resources associated with the target user, and the degree of interest of the target user for each multimedia resource in each category may include:

In step S31, the scores of the respective categories for the target users are calculated according to the number of multimedia resources belonging to each category among the multimedia resources associated with the target user, and the degree of interest of the target users for the respective multimedia resources in the respective categories.

In this example, the score of a category for a target user is positively correlated with the number of multimedia resources associated with the target user in the category, and is positively correlated with the degree of interest of the target user for each multimedia resource in the category.

In step S32, the respective categories are sorted in descending order of the scores of the respective users for the respective categories.

In a possible implementation manner, calculating, according to the number of multimedia resources belonging to each category among the multimedia resources associated with the target user, and the interest degree of the target user to each multimedia resource in each category, calculating each category for the target user The score may include: determining, by using Equation 2, the score s(u, c _i ) of the category c _i for the target user u;

Where h(u,c _i ) represents the first parameter, h(u,c _i ) is positively correlated with n, 0<h(u,c _i )<n, and n represents the multimedia resource associated with the target user u The number of multimedia resources belonging to the category c _i , g(u, v _ij ) represents the degree of interest of the target user u to the multimedia resource v _ij , and v _ij represents the j-th multimedia resource in the category c _i .

In this implementation, by setting h(u, c _i ) to be positively correlated with n and 0<h(u, c _i )<n, the influence of the outlier can be removed, and the score of the determined category c _i for the target user u can be improved. The accuracy of s(u,c _i ).

In a possible implementation manner, the first parameter may be determined by using Equation 3;

h(u,c _i )=ln n is Equation 3.

For example, the number of multimedia resources belonging to category c ₂ among the multimedia resources associated with the target user is 100, and the first parameter of category c ₂ for the target user is approximately equal to 4.6.

It should be noted that although the first parameter is determined in the above manner by using Equation 3 as an example, those skilled in the art can understand that the present disclosure is not limited thereto. In fact, a person skilled in the art can flexibly set the determining manner of the first parameter according to the actual application scenario, as long as the first parameter h(u, c _i ) is positively correlated with n, and 0<h(u, c _i )<n Just fine.

FIG. 4 illustrates a block diagram of a recommendation device for a multimedia resource according to an embodiment of the present disclosure. As shown in FIG. 4, the apparatus includes: a first determining module 41, configured to determine respective multimedia resources associated with a target user; and a second determining module 42, configured to determine, corresponding to each multimedia resource associated with the target user, a sorting module 43, configured to: according to the number of multimedia resources belonging to each category among the multimedia resources associated with the target user, and the degree of interest of the target user for each multimedia resource in each category, for each category Sorting; a recommendation module 44 for recommending the sorted categories to the target user.

FIG. 5 illustrates an exemplary block diagram of a recommendation device for a multimedia resource according to an embodiment of the present disclosure. As shown in Figure 5:

In a possible implementation manner, the device further includes: a third determining module 45, configured to determine the target according to a time interval between a time point at which the target user interacts with each multimedia resource and a current time The user's interest in each multimedia resource, wherein the degree of interest is negatively correlated with the time interval.

In a possible implementation manner, the third determining module 45 is configured to: determine, by using Equation 1, the degree of interest g(u, v _ij ) of the target user u to the multimedia resource v _ij in the category c _i ;

Where d is the attenuation coefficient, 0 < d < 1,

In a possible implementation manner, the sorting module 43 includes: a calculating submodule 431, configured to use, according to a quantity of multimedia resources belonging to each category among the multimedia resources associated with the target user, and the target user pair a degree of interest of each multimedia resource in each category, calculating a score of each category for the target user; a sorting sub-module 432, configured to perform each category according to a high-to-low score of each category for the target user Sort.

In a possible implementation manner, the calculating sub-module 431 is configured to: determine, by using Equation 2, a score s(u, c _i ) of the category c _i for the target user u;

h(u,c _i )=ln n is Equation 3.

In a possible implementation, the first determining module 41 is configured to: determine at least one of the following as a multimedia resource associated with the target user: the multimedia resource clicked by the target user, the target user The searched multimedia resource, the multimedia resource viewed by the target user, the multimedia resource that the target user likes, the multimedia resource of the target user comment, the multimedia resource of the target user publishing the bullet, and the shared by the target user a multimedia resource, a multimedia resource of the target user, and a multimedia resource subscribed by the target user.

FIG. 6 is a block diagram of an apparatus 1900 for recommending multimedia resources, according to an exemplary embodiment. For example, device 1900 can be provided as a server. Referring to Figure 6, apparatus 1900 includes a processing component 1922 that further includes one or more processors, and memory resources represented by memory 1932 for storing instructions executable by processing component 1922, such as an application. An application stored in memory 1932 can include one or more modules each corresponding to a set of instructions. Additionally, processing component 1922 is configured to execute instructions to perform the methods described above.

Apparatus 1900 can also include a power supply component 1926 configured to perform power management of apparatus 1900, a wired or wireless network interface 1950 configured to connect apparatus 1900 to the network, and an input/output (I/O) interface 1958. Device 1900 can operate based on an operating system stored in memory 1932, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, or the like.

In an exemplary embodiment, there is also provided a non-transitory computer readable storage medium comprising instructions, such as a memory 1932 comprising instructions executable by processing component 1922 of apparatus 1900 to perform the above method.

The present disclosure can be a system, method, and/or computer program product. The computer program product can comprise a computer readable storage medium having computer readable program instructions embodied thereon for causing a processor to implement various aspects of the present disclosure.

The computer readable storage medium can be a tangible device that can hold and store the instructions used by the instruction execution device. The computer readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (non-exhaustive list) of computer readable storage media include: portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM) Or flash memory), static random access memory (SRAM), portable compact disk read only memory (CD-ROM), digital versatile disk (DVD), memory stick, floppy disk, mechanical encoding device, for example, with instructions stored thereon A raised structure in the hole card or groove, and any suitable combination of the above. A computer readable storage medium as used herein is not to be interpreted as a transient signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (eg, a light pulse through a fiber optic cable), or through a wire The electrical signal transmitted.

The computer readable program instructions described herein can be downloaded from a computer readable storage medium to various computing/processing devices or downloaded to an external computer or external storage device over a network, such as the Internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and/or edge servers. A network adapter card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium in each computing/processing device .

Computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine related instructions, microcode, firmware instructions, state setting data, or in one or more programming languages. Source code or object code written in any combination, including object oriented programming languages such as Smalltalk, C++, etc., as well as conventional procedural programming languages such as the "C" language or similar programming languages. The computer readable program instructions can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer, partly on the remote computer, or entirely on the remote computer or server. carried out. In the case of a remote computer, the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or wide area network (WAN), or can be connected to an external computer (eg, using an Internet service provider to access the Internet) connection). In some embodiments, the customized electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), can be customized by utilizing state information of computer readable program instructions. Computer readable program instructions are executed to implement various aspects of the present disclosure.

Aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus, and computer program products according to embodiments of the present disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowcharts and/or block diagrams can be implemented by computer readable program instructions.

The computer readable program instructions can be provided to a general purpose computer, a special purpose computer, or a processor of other programmable data processing apparatus to produce a machine such that when executed by a processor of a computer or other programmable data processing apparatus Means for implementing the functions/acts specified in one or more of the blocks of the flowcharts and/or block diagrams. The computer readable program instructions can also be stored in a computer readable storage medium that causes the computer, programmable data processing device, and/or other device to operate in a particular manner, such that the computer readable medium storing the instructions includes An article of manufacture that includes instructions for implementing various aspects of the functions/acts recited in one or more of the flowcharts.

The computer readable program instructions can also be loaded onto a computer, other programmable data processing device, or other device to perform a series of operational steps on a computer, other programmable data processing device or other device to produce a computer-implemented process. Thus, instructions executed on a computer, other programmable data processing apparatus, or other device implement the functions/acts recited in one or more of the flowcharts and/or block diagrams.

The flowchart and block diagrams in the Figures illustrate the architecture, functionality and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a portion of an instruction that includes one or more components for implementing the specified logical functions. Executable instructions. In some alternative implementations, the functions noted in the blocks may also occur in a different order than those illustrated in the drawings. For example, two consecutive blocks may be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending upon the functionality involved. It is also noted that each block of the block diagrams and/or flowcharts, and combinations of blocks in the block diagrams and/or flowcharts, can be implemented in a dedicated hardware-based system that performs the specified function or function. Or it can be implemented by a combination of dedicated hardware and computer instructions.

The embodiments of the present disclosure have been described above, and the foregoing description is illustrative, not limiting, and not limited to the disclosed embodiments. Numerous modifications and changes will be apparent to those skilled in the art without departing from the scope of the invention. The choice of terms used herein is intended to best explain the principles, practical applications, or technical improvements of the techniques in the <RTIgt; </ RTI> <RTIgt; </ RTI> <RTIgt; </ RTI> <RTIgt;

Claims

A method for recommending a multimedia resource, comprising:

Determining various multimedia resources associated with the target user;

Determining a category corresponding to each multimedia resource associated with the target user;

Sorting each category according to the number of multimedia resources belonging to each category among the multimedia resources associated with the target user, and the degree of interest of the target user for each multimedia resource in each category;

The sorted categories are recommended to the target users.
The method of claim 1 further comprising:

Determining the degree of interest of the target user for each multimedia resource according to a time interval between the time point of the target user interacting with each multimedia resource and the current time, wherein the interest degree is negatively correlated with the time interval.
The method according to claim 2, wherein the interest rate of the target user for each multimedia resource is determined according to a time interval between a time point at which the target user interacts with each multimedia resource and a current time, including :

Using the formula 1 to determine the degree of interest g(u, v ij ) of the target user u for the multimedia resource v ij in the category c i ;

Where d is the attenuation coefficient, 0 < d < 1,
A time interval between a time point at which the target user u interacts with the multimedia resource v ij and a current time.
The method according to any one of claims 1 to 3, characterized in that, according to the number of multimedia resources belonging to each category among the multimedia resources associated with the target user, and the target users in each category The interest level of each multimedia resource, sorting each category, including:

Calculating a score of each category for the target user according to the number of multimedia resources belonging to each category among the multimedia resources associated with the target user, and the degree of interest of the target user for each multimedia resource in each category;

Each category is sorted in order of highest to lowest scores for the target users for each category.
The method according to claim 4, wherein the number of multimedia resources belonging to each category among the multimedia resources associated with the target user, and the degree of interest of the target user for each multimedia resource in each category , calculating the scores of each category for the target user, including:

Using the formula 2, the score s(u, c i ) of the category c i for the target user u is determined;

Where h(u,c i ) represents the first parameter, h(u,c i ) is positively correlated with n, 0<h(u,c i )<n, and n represents the multimedia associated with the target user u The number of multimedia resources belonging to the category c i in the resource, g(u, v ij ) represents the degree of interest of the target user u for the multimedia resource v ij , and v ij represents the j-th multimedia resource in the category c i .
The method according to claim 5, wherein the first parameter is determined by using Equation 3;

h(u,c i )=ln n is Equation 3.
The method of claim 1, wherein determining respective multimedia resources associated with the target user comprises:

Determining at least one of the following as a multimedia resource associated with the target user: a multimedia resource clicked by the target user, a multimedia resource searched by the target user, a multimedia resource viewed by the target user, the target user point The multimedia resource, the multimedia resource of the target user comment, the multimedia resource of the target user publishing the barrage, the multimedia resource shared by the target user, the multimedia resource of the target user, and the multimedia subscribed by the target user Resources.
A device for recommending multimedia resources, comprising:

a first determining module, configured to determine respective multimedia resources associated with the target user;

a second determining module, configured to determine a category corresponding to each multimedia resource associated with the target user;

a sorting module, configured to sort each category according to a quantity of multimedia resources belonging to each category among the multimedia resources associated with the target user, and an interest degree of the target user to each multimedia resource in each category;

A recommendation module is used to recommend the sorted categories to the target user.
The device according to claim 8, wherein the device further comprises:

a third determining module, configured to determine, according to a time interval between a time point of the target user interacting with each multimedia resource and a current time, an interest degree of the target user to each multimedia resource, where the interest degree is The time intervals are negatively correlated.
The apparatus according to claim 9, wherein said third determining module is configured to:

Using the formula 1 to determine the degree of interest g(u, v ij ) of the target user u for the multimedia resource v ij in the category c i ;

Where d is the attenuation coefficient, 0 < d < 1,
A time interval between a time point at which the target user u interacts with the multimedia resource v ij and a current time.
The apparatus according to any one of claims 8 to 10, wherein the ordering module comprises:

a calculation submodule, configured to calculate, according to the number of multimedia resources belonging to each category among the multimedia resources associated with the target user, and the interest degree of the target user to each multimedia resource in each category, calculate each category for the The score of the target user;

A sorting sub-module for sorting each category according to a high-to-low score of the respective categories for the target users.
The apparatus of claim 11 wherein said computing sub-module is for:

Using the formula 2, the score s(u, c i ) of the category c i for the target user u is determined;

Where h(u,c i ) represents the first parameter, h(u,c i ) is positively correlated with n, 0<h(u,c i )<n, and n represents the multimedia associated with the target user u The number of multimedia resources belonging to the category c i in the resource, g(u, v ij ) represents the degree of interest of the target user u for the multimedia resource v ij , and v ij represents the j-th multimedia resource in the category c i .
The apparatus according to claim 12, wherein said first parameter is determined using Equation 3;

h(u,c i )=ln n is Equation 3.
The apparatus according to claim 8, wherein said first determining module is configured to:

Determining at least one of the following as a multimedia resource associated with the target user: a multimedia resource clicked by the target user, a multimedia resource searched by the target user, a multimedia resource viewed by the target user, the target user point The multimedia resource, the multimedia resource of the target user comment, the multimedia resource of the target user publishing the barrage, the multimedia resource shared by the target user, the multimedia resource of the target user, and the multimedia subscribed by the target user Resources.
A device for recommending multimedia resources, comprising:

processor;

a memory for storing processor executable instructions;

Wherein the processor is configured to:

Determining various multimedia resources associated with the target user;

Determining a category corresponding to each multimedia resource associated with the target user;

Sorting each category according to the number of multimedia resources belonging to each category among the multimedia resources associated with the target user, and the degree of interest of the target user for each multimedia resource in each category;

The sorted categories are recommended to the target users.