CN113609332A

CN113609332A - Method, system and device for recommending video live broadcast resources

Info

Publication number: CN113609332A
Application number: CN202110917459.8A
Authority: CN
Inventors: 杨洪新; 汤殷琦
Original assignee: Shanghai Zhongyuan Network Co ltd
Current assignee: Shanghai Zhongyuan Network Co ltd
Priority date: 2021-08-11
Filing date: 2021-08-11
Publication date: 2021-11-05
Anticipated expiration: 2041-08-11
Also published as: CN113609332B

Abstract

The embodiment of the invention provides a method, a system and a device for recommending video live broadcast resources, wherein the method comprises the following steps: receiving a video live broadcast resource request sent by a target client; inquiring each video live broadcast resource corresponding to the target client in a pre-recorded corresponding relation between the client and the video live broadcast resource to serve as a first video live broadcast resource; wherein, the corresponding relation is as follows: determining similarity between the user characteristics of a user logging in a client and the resource characteristics of the video live broadcast resources; recommending the live video resources to the target client based on the arrangement sequence of the first live video resources in the corresponding relationship. The method provided by the embodiment of the application can provide personalized recommendation for the user and can reduce the recommendation time delay.

Description

Method, system and device for recommending video live broadcast resources

Technical Field

The invention relates to the technical field of internet, in particular to a method, a system and a device for recommending video live broadcast resources.

Background

With the rapid development of internet technology, the amount of data in a network has increased explosively. It is difficult for users to find out the content really interested by themselves facing a lot of data, and it is also difficult for content providers to accurately push the content of good quality to interested users.

In the related art, for a live scene, a currently popular video live resource (i.e., an anchor) can be recommended to a user. However, recommendation is performed to the user only based on popular live video resources, and personalized requirements of the user cannot be met.

Disclosure of Invention

The embodiment of the invention aims to provide a method, a system and a device for recommending video live broadcast resources, which can provide personalized recommendation for users and can reduce the recommendation time delay. The specific technical scheme is as follows:

in a first aspect of the present invention, a method for recommending a live video resource is provided, where the method includes:

receiving a video live broadcast resource request sent by a target client;

inquiring each video live broadcast resource corresponding to the target client in a pre-recorded corresponding relation between the client and the video live broadcast resource to serve as a first video live broadcast resource; wherein, the corresponding relation is as follows: determining similarity between the user characteristics of a user logging in a client and the resource characteristics of the video live broadcast resources;

recommending the live video resources to the target client based on the arrangement sequence of the first live video resources in the corresponding relationship.

Optionally, if the target client does not exist in the corresponding relationship, recommending the video live broadcast resource to the target client based on a preset video live broadcast resource.

Optionally, after the video live broadcast resources are pushed to the target client based on the arrangement order of the first video live broadcast resources in the corresponding relationship, the method further includes:

when the preset time is reached, after the last recommendation is determined, logging in the video live broadcast resource browsed by the target user of the target client as a second video live broadcast resource;

determining a video live broadcast resource associated with the second video live broadcast resource as a third video live broadcast resource;

sequencing the third video live broadcast resources based on the similarity between the resource characteristics of the third video live broadcast resources and the user characteristics of the target user to obtain a sequencing result;

and updating the video live broadcast resources corresponding to the target client in the corresponding relationship according to the sequencing result.

Optionally, the method is applied to a resource recommendation server in a resource recommendation system, where the resource recommendation system further includes a resource ranking server;

the method for sequencing the third video live broadcast resource based on the resource characteristics of the third video live broadcast resource to obtain a sequencing result comprises the following steps:

and sending the resource characteristics of the third video live broadcast resource to the resource sequencing server, so that the resource sequencing server sequences the third video live broadcast resource based on the similarity between the resource characteristics of the third video live broadcast resource and the user characteristics of the target user to obtain a sequencing result, and sending the sequencing result to the resource recommendation server.

Optionally, the sorting the third video live broadcast resource based on the similarity between the resource characteristic of the third video live broadcast resource and the user characteristic of the target user to obtain a sorting result includes:

for each third video live broadcast resource, inputting the resource characteristics of the third video live broadcast resource and the user characteristics of the target user into a pre-trained browsing prediction network model to obtain the probability of the target user browsing the third video live broadcast resource, wherein the probability is used as the similarity between the resource characteristics of the third video live broadcast resource and the user characteristics of the target user; the browsing prediction network model is obtained by training based on a preset training sample; the preset training sample comprises user characteristics of a sample user and resource characteristics of a video live broadcast resource browsed by the sample user;

and sequencing the third video live broadcast resources according to the sequence of the corresponding similarity from large to small to obtain a sequencing result.

Optionally, after determining the last recommendation, logging in a video live broadcast resource browsed by the user of the target client, and taking the video live broadcast resource as a second video live broadcast resource, the method further includes:

and aiming at each second video live broadcast resource, taking the resource characteristics of the second video live broadcast resource and the user characteristics of the target user as training data, and adjusting the model parameters of the browsing prediction network model to update the browsing prediction network model.

In a second aspect of the present invention, a method for recommending live video resources is provided, where the method is applied to a resource sequencing server in a resource recommendation system, the resource recommendation system further includes a resource recommendation server, and the method includes:

receiving resource characteristics of a third video live broadcast resource sent by the resource recommendation server; wherein the third video live resource is associated with a second video live resource; the second video live broadcast resource is determined by the resource recommendation server at a preset moment, and after last recommendation, the target user who logs in the target client browses the video live broadcast resource;

and sending the sequencing result to the resource recommendation server so that the resource recommendation server records the corresponding relation between the target client and the sequencing result, and recommending the live video resource to the target client based on the corresponding relation when receiving the live video resource request sent by the target client.

In a third aspect of the present invention, there is also provided a system for recommending live video resources, where the system includes:

the video live broadcast resource recommendation system comprises a target client and a resource recommendation server, wherein:

the client is used for sending a video live broadcast resource request to the resource recommendation server;

the resource recommendation server is used for receiving a video live broadcast resource request sent by a client, and inquiring each video live broadcast resource corresponding to the target client in a pre-recorded corresponding relationship between the client and the video live broadcast resource to serve as a first video live broadcast resource; wherein, the corresponding relation is as follows: determining similarity between the user characteristics of a user logging in a client and the resource characteristics of the video live broadcast resources; recommending the live video resources to the target client based on the arrangement sequence of the first live video resources in the corresponding relationship.

Optionally, the resource recommendation server is further configured to recommend the live video resource to the target client based on a preset live video resource if the target client does not exist in the corresponding relationship.

Optionally, the resource recommendation server is further configured to, after pushing the live video resources to the target client based on the arrangement order of the first live video resources in the corresponding relationship, determine resource characteristics of a third live video resource associated with a second live video resource that has been browsed by the target user who logs in the target client after last recommendation is determined;

Optionally, the video live broadcast resource recommendation system further includes a resource sorting server;

the resource recommendation server is further configured to send the resource characteristics of the third video live broadcast resource to the resource sorting server;

and the resource sequencing server is used for sequencing the third video live broadcast resource based on the similarity between the resource characteristics of the third video live broadcast resource and the user characteristics of the target user to obtain a sequencing result, and sending the sequencing result to the resource recommendation server.

Optionally, the resource sequencing server is configured to, for each third video live broadcast resource, input a resource feature of the third video live broadcast resource and a user feature of the target user into a pre-trained browsing prediction network model, to obtain a probability that the target user browses the third video live broadcast resource, where the probability is used as a similarity between the resource feature of the third video live broadcast resource and the user feature of the target user; the browsing prediction network model is obtained by training based on a preset training sample; the preset training sample comprises user characteristics of a sample user and resource characteristics of a video live broadcast resource browsed by the sample user;

Optionally, the video live broadcast resource recommendation system further includes a resource acquisition server;

the resource acquisition server is used for determining second video live broadcast resources browsed by the user of the target client after last recommendation according to the browsing behavior data of the target user sent by the target client;

storing the resource characteristics of the third video live broadcast resource to a first preset storage space;

and the resource recommendation server is used for acquiring the resource characteristics of the third video live broadcast resource from the first preset storage space.

Optionally, the resource sequencing server is further configured to obtain the browsing prediction network model from a second preset storage space;

and the resource acquisition server is further configured to, for each second video live broadcast resource, use the resource characteristics of the second video live broadcast resource and the user characteristics of the target user as training data to update the model parameters of the browsing prediction network model in the second preset storage space.

In a fourth aspect of the present invention, there is also provided a live video resource recommendation apparatus, where the apparatus includes:

the information receiving module is used for receiving a video live broadcast resource request sent by a target client;

the first video live broadcast resource query module is used for querying each video live broadcast resource corresponding to the target client in the pre-recorded corresponding relation between the client and the video live broadcast resources as a first video live broadcast resource; wherein, the corresponding relation is as follows: determining similarity between the user characteristics of a user logging in a client and the resource characteristics of the video live broadcast resources;

and the video live broadcast resource recommending module recommends the video live broadcast resources to the target client based on the arrangement sequence of the first video live broadcast resources in the corresponding relation.

Optionally, the video live broadcast resource recommending module is further configured to recommend the video live broadcast resource to the target client based on a preset video live broadcast resource if the target client does not exist in the corresponding relationship.

Optionally, the apparatus further comprises:

the second video live broadcast resource determining module is used for determining video live broadcast resources browsed by a user logging in the target client after last recommendation when the preset time is reached and taking the video live broadcast resources as second video live broadcast resources;

a third video live broadcast resource determining module, configured to determine a video live broadcast resource associated with the second video live broadcast resource as a third video live broadcast resource;

the sorting module is used for sorting the third video live broadcast resources based on the similarity between the resource characteristics of the third video live broadcast resources and the user characteristics of the target user to obtain a sorting result;

and the video live broadcast resource updating module is used for updating the video live broadcast resources corresponding to the target client in the corresponding relationship according to the sequencing result.

Optionally, the apparatus is applied to a resource recommendation server in a resource recommendation system, where the resource recommendation system further includes a resource ranking server;

the sequencing module is further configured to send the resource characteristics of the third video live broadcast resource to the resource sequencing server, so that the resource sequencing server sequences the third video live broadcast resource based on the similarity between the resource characteristics of the third video live broadcast resource and the user characteristics of the target user to obtain a sequencing result, and sends the sequencing result to the resource recommendation server.

Optionally, the sorting module is specifically configured to, for each third video live broadcast resource, input a resource feature of the third video live broadcast resource and a user feature of the target user into a pre-trained browsing prediction network model, to obtain a probability that the target user browses the third video live broadcast resource, where the probability is used as a similarity between the resource feature of the third video live broadcast resource and the user feature of the target user; the browsing prediction network model is obtained by training based on a preset training sample; the preset training sample comprises user characteristics of a sample user and resource characteristics of a video live broadcast resource browsed by the sample user; and sequencing the third video live broadcast resources according to the sequence of the corresponding similarity from large to small to obtain a sequencing result.

Optionally, the apparatus further comprises:

and the browsing prediction network model updating module is used for taking the resource characteristics of the second video live broadcast resources and the user characteristics of the target user as training data for each second video live broadcast resource, and adjusting the model parameters of the browsing prediction network model so as to update the browsing prediction network model.

In a fifth aspect of the present invention, there is also provided a live video resource recommendation apparatus, where the apparatus is applied to a resource sorting server in a resource recommendation system, the resource recommendation system further includes a resource recommendation server, and the apparatus includes:

the resource characteristic receiving module is used for receiving the resource characteristics of the third video live broadcast resource sent by the resource recommendation server; wherein the third video live resource is associated with a second video live resource; the second video live broadcast resource is determined by the resource recommendation server at a preset moment, and after last recommendation, the target user who logs in the target client browses the video live broadcast resource;

and the sequencing result sending module is used for sending the sequencing result to the resource recommendation server so that the resource recommendation server records the corresponding relation between the target client and the sequencing result, and recommending the live video resource to the target client based on the corresponding relation when receiving the live video resource request sent by the target client.

Optionally, the sorting module is specifically configured to, for each third video live broadcast resource, input the resource characteristics of the third video live broadcast resource and the user characteristics of the target user into a pre-trained browsing prediction network model, to obtain a probability that the target user browses the third video live broadcast resource, where the probability is used as a similarity between the resource characteristics of the third video live broadcast resource and the user characteristics of the target user; the browsing prediction network model is obtained by training based on a preset training sample; the preset training sample comprises user characteristics of a sample user and resource characteristics of a video live broadcast resource browsed by the sample user; and sequencing the third video live broadcast resources according to the sequence of the corresponding similarity from large to small to obtain a sequencing result.

In another aspect of the present invention, there is also provided an electronic device, including a processor, a communication interface, a memory and a communication bus, where the processor, the communication interface, and the memory complete communication with each other through the communication bus;

a memory for storing a computer program;

and the processor is used for realizing any video live broadcast resource recommendation method when executing the program stored in the memory.

In yet another aspect of the present invention, there is also provided a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and when executed by a processor, the computer program implements any one of the above methods for recommending a live video resource.

In yet another aspect of the present invention, there is also provided a computer program product containing instructions, which when run on a computer, causes the computer to execute any one of the above-mentioned methods for recommending a live video resource.

By adopting the video live broadcast resource recommendation method provided by the embodiment of the invention, a video live broadcast resource request sent by a target client is received; inquiring each video live broadcast resource corresponding to the target client in a pre-recorded corresponding relation between the client and the video live broadcast resource to serve as a first video live broadcast resource; wherein, the corresponding relation is as follows: determining similarity between the user characteristics of a user logging in a client and the resource characteristics of the video live broadcast resources; and recommending the live video resources to the target client based on the arrangement sequence of the first live video resources in the corresponding relationship.

The video live broadcast resource recommended to the target client is determined based on the user characteristics of the user who logs in the client and the similarity between the video live broadcast resource and the resource characteristics, so that the method provided by the embodiment of the application can provide personalized recommendation for the user. In addition, the method of the embodiment of the invention can predetermine the video live broadcast resource corresponding to the client, correspondingly, when the video live broadcast resource request is received, the video live broadcast resource is directly recommended to the client, and the recommendation time delay can be reduced.

Of course, not all advantages described above need to be achieved at the same time in the practice of any one product or method of the present application.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below.

Fig. 1 is a flowchart of a video live broadcast resource recommendation method in an embodiment of the present invention;

fig. 2 is a flowchart of another video live broadcast resource recommendation method in an embodiment of the present invention;

fig. 3 is a flowchart of another video live broadcast resource recommendation method in an embodiment of the present invention;

fig. 4 is a flowchart of another video live broadcast resource recommendation method in an embodiment of the present invention;

fig. 5 is a flowchart of another video live broadcast resource recommendation method in an embodiment of the present invention;

fig. 6 is a flowchart of a video live broadcast resource recommendation method in an embodiment of the present invention;

fig. 7 is a flowchart of another video live broadcast resource recommendation method according to an embodiment of the present invention;

fig. 8 is a structural diagram of a video live broadcast resource recommendation system in an embodiment of the present invention;

fig. 9 is a schematic diagram illustrating a principle of recommending a live video resource according to an embodiment of the present invention;

fig. 10 is a structural diagram of a live video resource recommendation device according to an embodiment of the present invention;

fig. 11 is a structural diagram of a live video resource recommendation device according to an embodiment of the present invention;

fig. 12 is a schematic structural diagram of an electronic device according to an embodiment of the present invention;

fig. 13 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

In the related art, a current popular video live broadcast resource can be recommended to a user for a live broadcast scene. However, recommendation is performed to the user only based on the popular live video resource, which cannot meet the personalized requirements of the user, and the user experience is not good.

In order to solve the above problem, the present invention provides a live video resource recommendation method, which can be applied to a server (hereinafter referred to as a target server).

Referring to fig. 1, fig. 1 is a flowchart of a video live broadcast resource recommendation method provided by an embodiment of the present invention, including:

s101: and receiving a video live broadcast resource request sent by a target client.

S102: and inquiring each video live broadcast resource corresponding to the target client in the pre-recorded corresponding relation between the client and the video live broadcast resource to serve as a first video live broadcast resource.

Wherein, the corresponding relation is as follows: and determining the similarity between the user characteristics of the user logging in the client and the resource characteristics of the video live broadcast resources.

S103: and recommending the live video resources to the target client based on the arrangement sequence of the first live video resources in the corresponding relationship.

The video live broadcast resource recommended to the target client is determined based on the similarity between the user characteristics of the user who logs in the client and the resource characteristics of the video live broadcast resource, so that the method provided by the embodiment of the application can provide personalized recommendation for the user. In addition, the method of the embodiment of the invention can predetermine the video live broadcast resource corresponding to the client, correspondingly, when the video live broadcast resource request is received, the video live broadcast resource is directly recommended to the client, and the recommendation time delay can be reduced.

The video live broadcast resources mentioned in the embodiments of the present invention correspond to anchor broadcasts, that is, one video live broadcast resource may represent one anchor broadcast.

In step S101, the target client may be an application installed in an intelligent device such as a mobile phone and a computer and used for browsing live video resources.

When detecting that a target user logs in, a target client sends a video live broadcast resource request to a target server; or when the target user refreshes the video live broadcast recommendation page of the target client, the target client sends a video live broadcast resource request to the recommendation server; or, when the target user is watching the live broadcast, the target client sends a video live broadcast resource request to the recommendation server at regular time.

In step S102, the target server may determine in advance a correspondence between the client and the live video resource, and the correspondence may exist locally, where the correspondence may be in various forms. For example, the video live broadcast resource recommendation system allocates an individual storage space for each client in the database, and records the video live broadcast resource corresponding to the client in the corresponding relationship in the storage space; or, the recommendation system allocates a shared storage space in the database, and stores the corresponding relation between each client and the video live broadcast resource in the shared storage space.

In addition, the target server may also set a storage duration for the above correspondence, and the storage duration may be set empirically, such as setting the storage duration to 6 hours, 24 hours, and so on. When the offline duration of the target user from the target client reaches the storage duration, the corresponding relation between the target user and the corresponding video live broadcast resource can be deleted.

In an implementation manner, the corresponding relationship may be a corresponding relationship between an identifier of the client and an identifier of the live video resource, the identifier of the live video resource may be a live broadcast room address of a corresponding anchor, and the identifier of the client may be an account of a user who logs in the client.

The user characteristics of the user may include: personal information and/or browsing behavior information of the user. Wherein the personal information may include at least one of: age, gender, physical location of the user, type of video live asset of interest. The browsing behavior information may include at least one of: the time length of the user watching the recommended live video resources and the comment content of the user aiming at the watched live video resources.

The resource characteristics of the live video resource may include anchor characteristics, offline characteristics, and real-time characteristics of the corresponding anchor. Wherein the anchor feature may include at least one of: age, sex, type of anchor. The offline features may include at least one of: the behavior of the anchor historical live broadcast and the index parameters of the anchor historical live broadcast. The act of anchor history live may include at least one of: once singing, once dancing, once playing games. The anchor's live room history index parameters may include at least one of: the average duration of the historical live broadcast, the average online number of the historical live broadcast and the average praise number of the historical live broadcast. The real-time features may include at least one of: the current state of the anchor and the current index parameters of the live broadcast room of the anchor. The current state of the anchor may include at least one of: singing, dancing, playing. The current index parameters of the live room of the anchor may include at least one of: the current live broadcast time length, the current online number of people and the current praise number.

In step S103, in one manner, the target server may recommend the first live video resource to the target client directly.

In another mode, the target server may further filter the first video live broadcast resource, for example, remove a video live broadcast resource that has been recommended to the target client before and/or a video live broadcast resource corresponding to a currently offline anchor, and recommend the filtered video live broadcast resource to the target client.

In one embodiment, referring to fig. 2, on the basis of fig. 1, after S101, the method may further include the steps of:

s104: and if the target client does not exist in the corresponding relation, recommending the video live broadcast resources to the target client based on the preset video live broadcast resources.

When a target user logs in a target client for the first time to watch live broadcasting, the target server does not record the corresponding relation between the target client and the video live broadcasting resource. Or, when the time that the target user has been offline exceeds the storage duration of the corresponding relationship, the target server deletes the corresponding relationship between the target client and the video live broadcast resource, so that the target client does not exist in the corresponding relationship. At this time, the video live broadcast resource cannot be recommended to the target client based on the corresponding relationship.

The preset video live broadcast resource can be a video live broadcast resource with the largest number of online people currently, or can also be a video live broadcast resource with the largest number of praise currently, or can also be a video live broadcast resource with the largest number of gifts currently received.

In addition, the target server can update the video live broadcast resource corresponding to the target client in the corresponding relation based on the browsing behavior of the user.

In one embodiment, referring to fig. 3, on the basis of fig. 2, after S103, the method may further include the steps of:

s105: and when the preset moment is reached, determining that the video live broadcast resource browsed by the user of the target client is logged in after the last recommendation, and taking the video live broadcast resource as a second video live broadcast resource.

S106: and determining the video live broadcast resource associated with the second video live broadcast resource as a third video live broadcast resource.

S107: and sequencing the third video live broadcast resources based on the similarity between the resource characteristics of the third video live broadcast resources and the user characteristics of the target user to obtain a sequencing result.

S108: and updating the video live broadcast resources corresponding to the target client in the corresponding relationship according to the sequencing result.

In the embodiment of the present invention, the target server may update the corresponding relationship according to a preset period. That is to say, when a time corresponding to the preset period (that is, a preset time) is reached, the target server may determine browsing behavior data of the target user after last recommendation, and determine the third video live broadcast resource based on the browsing behavior, so as to update the video live broadcast resource corresponding to the target client according to the third video live broadcast resource.

It can be understood that, if the video live broadcast resource is recommended to the target client based on the arrangement order of the first video live broadcast resource in the corresponding relationship last time, the determining of the second video live broadcast resource includes: and logging in the video live broadcast resources browsed by the target user of the target client in the first video live broadcast resources. If the video live broadcast resource is recommended to the target client based on the preset video live broadcast resource at the last time, the determined second video live broadcast resource comprises: and in the preset video live broadcast resources, logging in the video live broadcast resources browsed by the target user of the target client.

In step S105, in an implementation manner, after the target server recommends the video live broadcast resource to the target client, the target client may obtain browsing behavior data of the target user for the recommended video live broadcast resource. For example, browsing behavior data may include: and identifying the video live broadcast resources which have been browsed by the target user.

Then, the target client may add the browsing behavior data to a preset message queue, and correspondingly, the target server may obtain the browsing behavior data from the preset message queue to determine a third video live broadcast resource. The preset message queue may be a kafka message queue.

In step S106, the target server may determine, from other live video resources, a live video resource having at least one same resource feature as the second live video resource as a third live video resource. Or, the target server may also determine, as a third video live broadcast resource, a video live broadcast resource corresponding to another anchor that the anchor concerns corresponding to the second video live broadcast resource. Or, the target server may also determine, as a third video live broadcast resource, a video live broadcast resource corresponding to another anchor of the anchor corresponding to the second video live broadcast resource that has been paid attention to.

In step S107, the target server may calculate a similarity between each third video live broadcast resource and the target user, and rank the third video live broadcast resources according to the similarity.

In one implementation, for each third video live broadcast resource, a feature vector corresponding to a resource feature of the third video live broadcast resource and a feature vector corresponding to a user feature of the target user may be determined, and then, a similarity between the two feature vectors may be calculated as a similarity between the target user and the third video live broadcast resource.

In another implementation, the similarity between the target user and each third video live broadcast resource may also be calculated based on a pre-trained network model.

In step S108, the target server may determine that the video live broadcast resource corresponding to the target client in the corresponding relationship is a third video live broadcast resource after sorting, so as to update the corresponding relationship. Or, the video live broadcast resources corresponding to the target client in the corresponding relationship may be determined as the top preset number of video live broadcast resources in the sequenced third video live broadcast resources, so as to update the corresponding relationship.

In one embodiment, the method may be applied to a resource recommendation server (i.e., the target server) in a resource recommendation system, and the resource recommendation system may further include a resource ranking server.

Therefore, the target server can send the resource characteristics of the third video live broadcast resource to the resource sorting server, and the resource sorting server can sort the third video live broadcast resource.

The method for the resource sorting server to sort the third live video resource may refer to the method for the target server to sort the third live video resource in step S107.

In one implementation, the resource recommendation server may be a server corresponding to a near-line layer of the recommendation system, for example, the resource recommendation server may be a cloud server deployed with a container, and the near-line layer is deployed in the container. Additionally, the resource ranking server may be a physical server.

Based on the framework, the third video live broadcast resources are sequenced through the physical server, the service load of the near line layer can be reduced, the speed of the near line layer for responding to the video live broadcast resource request of the user is increased, and the time delay is reduced.

In addition, the near line layer is arranged in a cloud container, and flexible arrangement of the near line layer can be achieved. When a new function needs to be added to the near-line layer, the new function can be quickly on-line.

In one implementation, the Resource ranking server may register a service in the zookeeper, become a provider of the ranking service, and write a URL (Uniform Resource Locator) address of the Resource ranking server, so that the Resource recommendation server may subscribe to the ranking service in the zookeeper. And the resource recommendation server sends the micro-service request containing the identifier of the third video live broadcast resource to the resource sorting server through the URL address of the resource sorting server. Further, the resource sorting server may sort the third live video resource. Correspondingly, the resource recommendation server can subscribe the services registered in the zookeeper by the resource sequencing server in the zookeeper to become consumers of the sequencing services, and writes the URL addresses of the consumers in the zookeeper so that the resource sequencing server returns the sequencing result of the third video live broadcast resource to the resource recommendation server through the URL address of the resource recommendation server after obtaining the sequencing result of the third video live broadcast resource.

In one embodiment, referring to fig. 4, on the basis of fig. 3, step S107 may include:

s1071: and aiming at each third video live broadcast resource, inputting the resource characteristics of the third video live broadcast resource and the user characteristics of the target user into a pre-trained browsing prediction network model to obtain the probability of the target user browsing the third video live broadcast resource, wherein the probability is used as the similarity between the resource characteristics of the third video live broadcast resource and the user characteristics of the target user.

The browsing prediction network model is obtained by training based on a preset training sample. The preset training sample comprises the user characteristics of the sample user and the resource characteristics of the video live broadcast resources browsed by the sample user.

S1072: and sequencing the third video live broadcast resources according to the sequence of the corresponding similarity from large to small to obtain a sequencing result.

Wherein the browsing prediction network model can be set by a technician according to experience and business requirements. For example, the browsing prediction network model may be an LR (Logistic Regression) model, a GBDT (iterative Decision Tree) model, a GBDT-FM (iterative Decision Tree-Factorization) model, or a Deep (Deep ordering) model.

In one embodiment, referring to fig. 5, on the basis of fig. 4, after step S105, the method may further include the steps of:

s109: and aiming at each second video live broadcast resource, taking the resource characteristics of the second video live broadcast resource and the user characteristics of the target user as training data, and adjusting the model parameters of the browsing prediction network model to update the browsing prediction network model.

In the embodiment of the present invention, the target server may update the browsing prediction network model to improve the accuracy of the browsing prediction network model.

In one implementation, the target server may input the resource characteristics of the second video live broadcast resource and the user characteristics of the target user into a browsing prediction network model to obtain a prediction probability of the target user for the second video live broadcast resource, and calculate a loss function value between the prediction probability and a tag of the target user for the second video live broadcast resource. Further, model parameters of the browsing prediction network model are adjusted based on the loss function value. The tag of the target user for the second video live broadcast resource may indicate whether the target user browses the second video live broadcast resource.

In another mode, the target server combines every two resource features of the second video live broadcast resource to obtain a high-order combination feature of the second video live broadcast resource, and/or combines every two user features of the target user to obtain a high-order combination feature of the target user.

And the target server inputs the resource characteristics of the second video live broadcast resource, the high-order combination characteristics of the second video live broadcast resource, the user characteristics of the target user and the high-order combination characteristics of the target user as training data into a browsing prediction network model to obtain the prediction probability of the target user for the second video live broadcast resource, and calculates the loss function value between the prediction probability and the label of the target user for the second video live broadcast resource. Further, model parameters of the browsing prediction network model are adjusted based on the loss function value. The tag of the target user for the second video live broadcast resource may indicate whether the target user browses the second video live broadcast resource.

It can be understood that, the above-mentioned process of updating the browsing prediction network model, that is, the process of training the browsing prediction network model again, is based on the resource characteristics of the second video live broadcast resource and the user characteristics of the target user.

Therefore, in the process of training the browsing prediction network model based on the preset training sample, the browsing prediction network model can be updated by referring to the resource characteristics based on the second video live broadcast resource and the user characteristics of the target user.

Based on the same inventive concept, the embodiment of the invention provides a live video resource recommendation method, which can also be applied to a resource sequencing server in a resource recommendation system, wherein the resource recommendation system further comprises a resource recommendation server. Referring to fig. 6, the method may include the steps of:

s601: and receiving resource characteristics of the third video live broadcast resource sent by the resource recommendation server.

Wherein the third video live resource is associated with the second video live resource; the second video live broadcast resource is determined by the resource recommendation server at a preset moment, and after last recommendation, the target user who logs in the target client browses the video live broadcast resource.

S602: and sequencing the third video live broadcast resources based on the similarity between the resource characteristics of the third video live broadcast resources and the user characteristics of the target user to obtain a sequencing result.

S603: and sending the sequencing result to a resource recommendation server so that the resource recommendation server updates the corresponding relation, and recommending the video live broadcast resource to the target client based on the updated corresponding relation when receiving the video live broadcast resource request sent by the target client.

The method for recommending the live video resources to the target client by the resource sequencing server is based on the user characteristics of the user logging in the client and the similarity determination between the user characteristics of the live video resources, and therefore the method provided by the embodiment of the application can realize personalized recommendation for the user. In addition, the method of the embodiment of the invention can predetermine the video live broadcast resource corresponding to the client, correspondingly, when the video live broadcast resource request is received, the video live broadcast resource is directly recommended to the client, and the recommendation time delay can be reduced.

S602 may refer to the process of the target server sorting the third video live broadcast resources in step S107.

In one embodiment, referring to fig. 7, on the basis of fig. 6, step S602 may include:

s6021: and aiming at each third video live broadcast resource, inputting the resource characteristics of the third video live broadcast resource and the user characteristics of the target user into a pre-trained browsing prediction network model to obtain the probability of the target user browsing the third video live broadcast resource, wherein the probability is used as the similarity between the resource characteristics of the third video live broadcast resource and the user characteristics of the target user.

The browsing prediction network model is obtained by training based on a preset training sample; the preset training sample comprises the user characteristics of the sample user and the resource characteristics of the video live broadcast resources browsed by the sample user.

S6022: and sequencing the third video live broadcast resources according to the sequence of the corresponding similarity from large to small to obtain a sequencing result.

Steps S6021-S6022 may be referred to the description of steps S1071-S1072 described above.

Based on the same inventive concept, an embodiment of the present invention further provides a live video resource recommendation system, see fig. 8, where fig. 8 is a structural diagram of a live video resource recommendation system provided in an embodiment of the present application, and the structural diagram includes:

the client 801 is configured to send a video live broadcast resource request to the resource recommendation server.

The resource recommendation server 802 is configured to receive a video live broadcast resource request sent by a client, and query, in a pre-recorded correspondence between the client and a video live broadcast resource, each video live broadcast resource corresponding to a target client as a first video live broadcast resource.

Wherein, the corresponding relation is as follows: determining similarity between the user characteristics of a user logging in a client and the resource characteristics of the video live broadcast resources; and recommending the live video resources to the target client based on the arrangement sequence of the first live video resources in the corresponding relationship.

In an embodiment, the resource recommendation server 802 is further configured to recommend the live video resource to the target client based on a preset live video resource if the target client does not exist in the corresponding relationship.

In one embodiment, the resource recommendation server 802 is further configured to, after pushing the live video resources to the target client based on the arrangement order of the first live video resources in the corresponding relationship, determine resource characteristics of a third live video resource associated with a second live video resource that has been browsed by the target user who logs in the target client after last recommendation; sequencing the third video live broadcast resources based on the similarity between the resource characteristics of the third video live broadcast resources and the user characteristics of the target user to obtain a sequencing result; and updating the video live broadcast resources corresponding to the target client in the corresponding relationship according to the sequencing result.

In one embodiment, the resource recommendation server 802 is further configured to send the resource characteristics of the third live video resource to the resource ranking server.

And the resource sequencing server 803 is configured to sequence the third video live broadcast resource based on the similarity between the resource characteristics of the third video live broadcast resource and the user characteristics of the target user to obtain a sequencing result, and send the sequencing result to the resource recommendation server.

In an embodiment, the resource sorting server 803 is specifically configured to, for each third video live broadcast resource, input the resource characteristics of the third video live broadcast resource and the user characteristics of the target user into a pre-trained browsing prediction network model, to obtain a probability that the target user browses the third video live broadcast resource, where the probability is used as a similarity between the resource characteristics of the third video live broadcast resource and the user characteristics of the target user; the browsing prediction network model is obtained by training based on a preset training sample; presetting a training sample containing user characteristics of a sample user and resource characteristics of a video live broadcast resource browsed by the sample user; and sequencing the third video live broadcast resources according to the sequence of the corresponding similarity from large to small to obtain a sequencing result.

In an embodiment, the resource obtaining server 804 is configured to determine, according to browsing behavior data of a target user sent by a target client, a second video live broadcast resource that is browsed by the user of the target client in the first video live broadcast resource; determining a video live broadcast resource associated with the second video live broadcast resource as a third video live broadcast resource; and storing the resource characteristics of the third video live broadcast resource to a first preset storage space.

The resource recommendation server 802 is further configured to obtain resource characteristics of a third video live broadcast resource from the first preset storage space.

In the embodiment of the present invention, the resource obtaining server 804 receives browsing behavior data sent by the target client, analyzes the browsing behavior data, determines a second video live broadcast resource browsed by the user of the target client after the last recommendation, determines a video live broadcast resource associated with the second video live broadcast resource through a resource feature of the second video live broadcast resource, and stores the resource feature of the third video live broadcast resource to the first preset storage space.

In one implementation, the target client may add the browsing behavior data to a preset message queue, and correspondingly, the target server may obtain the browsing behavior data from the preset message queue to determine a third video live broadcast resource. The preset message queue may be a kafka message queue.

In an embodiment, the resource sorting server 803 is further configured to obtain the browsing prediction network model from a second preset storage space.

The resource obtaining server 804 is further configured to, for each second video live broadcast resource, use the resource characteristics of the second video live broadcast resource and the user characteristics of the target user as training data to update the model parameters of the browsing prediction network model in the second preset storage space.

In this embodiment of the present invention, the resource obtaining server 804 is configured to update the browsing prediction network model.

In one implementation, the target client may send browsing behavior data to the resource acquisition server 804, where the browsing behavior data may further include user characteristics of the user.

The resource obtaining server 804 may update the browsing prediction network model stored in the second preset storage space based on the identifier of the live video resource in the browsing behavior data and the user characteristics of the user, so that the resource sorting server 803 may obtain the updated browsing prediction network model from the second preset storage space.

Referring to fig. 9, fig. 9 is a schematic diagram illustrating a principle of recommending a live video resource according to an embodiment of the present invention. In fig. 9, the APP back end corresponds to the target client, the cloud container deploys a Nearline near-line layer, which indicates that a server corresponding to the near-line layer of the recommendation system is deployed in a container of the cloud server, and the server corresponding to the near-line layer corresponds to the resource recommendation server. And the physical machine deployment predictor sequencing module represents that the resource sequencing module is deployed on the physical machine, and the sequencing module corresponds to the resource sequencing server.

Couchbase (database) personalized cache index, which represents a storage index of a personalized cache stored in Couchbase. And the personalized cache corresponds to the video live broadcast resources in the corresponding relation. And the storage index of the personalized cache is used for searching the video live broadcast resources in the corresponding relation in Couchbase. And the non-personalized cache index represents a storage index of a non-personalized cache stored in the Couchbase, the non-personalized cache corresponds to the pre-stored live video resource, and the storage index of the non-personalized cache is used for searching the pre-stored live video resource in the Couchbase.

The APP backend sends a query request, i.e., a video live broadcast resource request, to the near-line layer. And after receiving the resource request, the near line layer inquires the index. That is, the above correspondence is queried, the live video resource is preset, and a query result is returned, that is, the queried live video resource is returned.

The APP back end can obtain user behavior data, and the user behavior data can contain video live broadcast resources browsed by a target user who logs in a target client.

And the APP rear end generates a user behavior pingback message according to the user behavior data and adds the user behavior pingback message to the Kafka message queue. The proximity layer can construct a personalized cache index according to the Kafka message queue.

The algorithmic engineering babel (translator) task is performed by the resource acquisition server. The algorithm engineering is applied to the resource acquisition server, and the second video live broadcast resource browsed by the target user can be determined according to the user behavior pingback message in the Kafka message queue.

The Hive table is used for recording each currently existing video live broadcast resource, and each video live broadcast resource may include an identifier of each video live broadcast resource and an anchor characteristic of an anchor corresponding to each video live broadcast resource. The Bl Hive table (boolean value honeycomb table) is used for recording each current existing video live broadcast resource, and corresponds to the offline characteristics and the real-time characteristics of the anchor.

And searching and determining the anchor recall source reverse arrangement in the Hive table according to the anchor characteristics of the anchor corresponding to the second video live broadcast resource through algorithm engineering, wherein the anchor recall source reverse arrangement corresponds to the third video live broadcast resource. The algorithm engineering uses a base tool, and can translate the anchor recast source reverse format into a key-value (key value pair) format and store the key-value format into the Couchbase, wherein the key can be one anchor feature in anchor features corresponding to the anchor of the second video live broadcast resource, and the value can be the associated video live broadcast resource queried by using the resource features.

Algorithm engineering looks up offline features in the Bl Hive table that determine each anchor in the anchor recall source reverse. The algorithm engineering uses a base tool to translate the format of the searched offline feature forward row into a key-value format to be stored in Couchbase, wherein the key can call the anchor in the source reverse row for the anchor, and the value can be the offline feature corresponding to the anchor. The offline features are arranged by adopting a forward index, namely the offline features are arranged according to each anchor. Algorithm engineering uses a flight tool, Batch (Batch) outputs in a Bl Hive table, real-time characteristics of each anchor in the anchor recall source reverse row are determined, and the real-time characteristics are stored in Couchbase.

And searching the anchor characteristic corresponding to the anchor of the second video live broadcast resource in the Hive table, searching the offline characteristic and the real-time characteristic corresponding to the anchor of the second video live broadcast resource in the Bl Hive table, and using the anchor characteristic, the offline characteristic and the real-time characteristic corresponding to the anchor of the second video live broadcast resource as the resource characteristic of the second video live broadcast resource. The algorithm engineering searches the user characteristics of the target user logging in the APP in the Hive table, and translates the searched resource characteristics and the user characteristics into key-value by using a band tool. The key-value of the resource feature may be a video live broadcast resource in the second video live broadcast resource, and the value may be a resource feature corresponding to the video live broadcast resource. The key-value of the user characteristic may be a client identifier, and the value may be a user characteristic of a user corresponding to the client. The algorithm engineering may also update the model file stored in the Couchbase, that is, update the browsing prediction network model, with the translated resource features and the corresponding user features as sample data. The model file may include model files of GBDT, GBDT-FM models.

MicroAPI call: GBDT/GBDT-FM, indicate that the near-line layer packs the anchor characteristics, the off-line characteristics and the real-time characteristics of the anchor recalling the source loaded from the database into a micro API call (micro service request), and sends the micro service request to the sequencing module. The sorting module may scan Couchbase periodically (e.g., every 5min) to obtain the model file generated by the above algorithm engineering, and load the model file into the cache. When the sequencing module receives a micro-service request from a near-line layer, based on a browsing prediction network model represented by the model file, target user characteristics, anchor characteristics of an anchor recall source, offline characteristics and real-time characteristic input in the micro-service request are processed so as to sequence the anchor recall source, obtain a sequencing result and return the sequencing result to the near-line layer. And after receiving the sorting result, the near line layer deletes the personalized cache index of the target user in the database, and takes the sorting result as a new personalized cache construction index and stores the index into the database.

The near-line layer can also acquire live video resources of the hot anchor from MySQL (relational database management system), and store the live video resources of the hot anchor as non-personalized cache in a Couchbase database.

The pressure test is carried out based on the video live broadcast resource recommendation method provided by the embodiment of the invention, in the test process, the number of video live broadcast resources is 3000, 6 recalls are adopted, namely, 6 types of resource characteristics are determined according to the second video live broadcast resource, and the video live broadcast resource containing at least one type of resource characteristics in the 6 types of resource characteristics is determined to be used as a third video live broadcast resource. In addition, the number of tested users is 200 ten thousand, and QPS (Query Per Second, Query rate Per Second) is: 5000-8000, and obtaining the test result shown in the table (1).

Watch (1)

User ratio	Recommendation latency
		50％	35ms
90％	37ms
		95％	41ms
99％	49ms

In table (1), the recommendation delay of 50% of all users does not exceed 35 ms, the recommendation delay of 90% of all users does not exceed 37 ms, the recommendation delay of 95% of all users does not exceed 41 ms, and the recommendation delay of 99% of all users does not exceed 49 ms, so that the recommendation delay is maintained at a small value by the method of the embodiment of the present invention.

Based on the same inventive concept, an embodiment of the present invention further provides a live video resource recommendation device, referring to fig. 10, where fig. 10 is a structural diagram of a live video resource recommendation device provided in an embodiment of the present application, including:

an information receiving module 1001, configured to receive a video live broadcast resource request sent by a target client;

a first video live broadcast resource query module 1002, configured to query, in a pre-recorded correspondence between a client and a video live broadcast resource, each video live broadcast resource corresponding to a target client as a first video live broadcast resource; wherein, the corresponding relation is as follows: determining similarity between the user characteristics of a user logging in a client and the resource characteristics of the video live broadcast resources;

and the video live broadcast resource recommending module 1003 is configured to recommend the video live broadcast resources to the target client based on the arrangement sequence of the first video live broadcast resources in the corresponding relationship.

In an embodiment, the live video resource recommending module 1003 is further configured to recommend a live video resource to the target client based on a preset live video resource if the target client does not exist in the corresponding relationship.

And the second video live broadcast resource determining module is used for determining the video live broadcast resource browsed by the user logging in the target client side in the first video live broadcast resource as the second video live broadcast resource when the preset time is reached.

And the third video live broadcast resource determining module is used for determining the video live broadcast resource associated with the second video live broadcast resource as the third video live broadcast resource.

And the sequencing module is used for sequencing the third video live broadcast resources based on the similarity between the resource characteristics of the third video live broadcast resources and the user characteristics of the target user to obtain a sequencing result.

In an embodiment, the sorting module is further configured to send the resource characteristics of the third video live broadcast resource to the resource sorting server, so that the resource sorting server sorts the third video live broadcast resource based on the similarity between the resource characteristics of the third video live broadcast resource and the user characteristics of the target user to obtain a sorting result, and sends the sorting result to the resource recommendation server.

In one embodiment, the sorting module is specifically configured to, for each third video live broadcast resource, input a resource feature of the third video live broadcast resource and a user feature of the target user into a pre-trained browsing prediction network model to obtain a probability that the target user browses the third video live broadcast resource, where the probability is used as a similarity between the resource feature of the third video live broadcast resource and the user feature of the target user; the browsing prediction network model is obtained by training based on a preset training sample; presetting a training sample containing user characteristics of a sample user and resource characteristics of a video live broadcast resource browsed by the sample user; and sequencing the third video live broadcast resources according to the sequence of the corresponding similarity from large to small to obtain a sequencing result.

And the browsing prediction network model updating module is used for taking the resource characteristics of the second video live broadcast resources and the user characteristics of the target user as training data aiming at each second video live broadcast resource, and adjusting the model parameters of the browsing prediction network model so as to update the browsing prediction network model.

Based on the same inventive concept, the embodiment of the invention also provides a video live broadcast resource recommendation device. Referring to fig. 11, fig. 11 is a structural diagram of a live video resource recommendation device according to an embodiment of the present application, including:

a resource feature receiving module 1101, configured to receive a resource feature of a third video live broadcast resource sent by a resource recommendation server; wherein the third video live resource is associated with the second video live resource; the second video live broadcast resource is determined by the resource recommendation server at a preset moment, and logs in a video live broadcast resource browsed by a target user of a target client in a first video live broadcast resource corresponding to the target client in a pre-recorded corresponding relation;

the sorting module 1102 is configured to sort the third video live broadcast resources based on the similarity between the resource characteristics of the third video live broadcast resources and the user characteristics of the target user to obtain a sorting result;

the sorting result sending module 1103 is configured to send a sorting result to the resource recommendation server, so that the resource recommendation server records a correspondence between the target client and the sorting result, and when a video live broadcast resource request sent by the target client is received, recommends a video live broadcast resource to the target client based on the correspondence. The sorting module 1102 is specifically configured to, for each third video live broadcast resource, input the resource characteristics of the third video live broadcast resource and the user characteristics of the target user into a pre-trained browsing prediction network model to obtain a probability that the target user browses the third video live broadcast resource, where the probability is used as a similarity between the resource characteristics of the third video live broadcast resource and the user characteristics of the target user; the browsing prediction network model is obtained by training based on a preset training sample; presetting a training sample containing user characteristics of a sample user and resource characteristics of a video live broadcast resource browsed by the sample user;

An embodiment of the present invention further provides an electronic device, as shown in fig. 12, including a processor 1201, a communication interface 1202, a memory 1203, and a communication bus 1204, where the processor 1201, the communication interface 1202, and the memory 1203 complete mutual communication through the communication bus 1204,

a memory 1203 for storing a computer program;

the processor 1201 is configured to implement the following steps when executing the program stored in the memory 1203:

receiving a video live broadcast resource request sent by a target client;

An embodiment of the present invention further provides an electronic device, as shown in fig. 13, including a processor 1301, a communication interface 1302, a memory 1303, and a communication bus 1304, where the processor 1301, the communication interface 1302, and the memory 1303 complete mutual communication through the communication bus 1304,

a memory 1303 for storing a computer program;

the processor 1301 is configured to implement the following steps when executing the program stored in the memory 1303:

The communication bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.

The communication interface is used for communication between the electronic equipment and other equipment.

The Memory may include a Random Access Memory (RAM) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.

The Processor may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the device can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component.

In another embodiment of the present invention, a computer-readable storage medium is further provided, where a computer program is stored in the computer-readable storage medium, and when executed by a processor, the computer program implements the video live resource recommendation method in any of the above embodiments.

In another embodiment of the present invention, there is also provided a computer program product containing instructions, which when run on a computer, causes the computer to execute the method for recommending a live video resource as described in any of the above embodiments.

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.

It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the apparatus, the system, the electronic device, the computer-readable storage medium, and the computer program product, since they are substantially similar to the method embodiments, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiments.

The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.

Claims

1. A method for recommending live video resources is characterized by comprising the following steps:

receiving a video live broadcast resource request sent by a target client;

2. The method of claim 1, wherein after receiving the request for the live video resource sent by the target client, the method further comprises:

and if the target client does not exist in the corresponding relation, recommending the live video resources to the target client based on preset live video resources.

3. The method of claim 1, wherein after pushing the live video resource to the target client based on the arrangement order of the first live video resource in the corresponding relationship, the method further comprises:

4. The method according to claim 3, wherein the method is applied to a resource recommendation server in a resource recommendation system, the resource recommendation system further comprising a resource ranking server;

5. The method according to claim 3 or 4, wherein the sorting the third video live broadcast resource based on the similarity between the resource characteristic of the third video live broadcast resource and the user characteristic of the target user to obtain a sorting result comprises:

6. The method of claim 5, wherein after determining the last recommendation, logging in a live video resource viewed by the user of the target client as a second live video resource, the method further comprises:

7. A live video resource recommendation method is applied to a resource sequencing server in a resource recommendation system, the resource recommendation system further comprises a resource recommendation server, and the method comprises the following steps:

8. The method according to claim 7, wherein the sorting the third video live broadcast resource based on the similarity between the resource characteristic of the third video live broadcast resource and the user characteristic of the target user to obtain a sorting result comprises:

9. The video live broadcast resource recommendation system is characterized by comprising a target client and a resource recommendation server, wherein:

10. A live video resource recommendation apparatus, the apparatus comprising:

and the video live broadcast resource recommending module is used for recommending the video live broadcast resources to the target client based on the arrangement sequence of the first video live broadcast resources in the corresponding relation.

11. The live video resource recommendation device is applied to a resource sequencing server in a resource recommendation system, the resource recommendation system further comprises a resource recommendation server, and the device comprises:

12. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing mutual communication by the memory through the communication bus;

a memory for storing a computer program;

a processor for implementing the method steps of any one of claims 1-6, or 7-8 when executing a program stored in a memory.

13. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method steps of any one of claims 1 to 6, or 7 to 8.