CN110929086A

CN110929086A - Audio and video recommendation method and device and storage medium

Info

Publication number: CN110929086A
Application number: CN201911330723.7A
Authority: CN
Inventors: 艾立超
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Shenzhen Yayue Technology Co ltd
Priority date: 2019-12-20
Filing date: 2019-12-20
Publication date: 2020-03-27

Abstract

The embodiment of the application provides an audio and video recommendation method, an audio and video recommendation device and a storage medium, wherein the method comprises the following steps: acquiring user behavior data of a user from a playing terminal; determining a target interest type corresponding to the user behavior data; determining a target audio and video set according to the target interest type, wherein the target audio and video set comprises at least one audio and video matched with the target interest type, and each audio and video corresponds to audio and video description information; acquiring similarity between the user behavior data and audio and video description information of each audio and video in the target audio and video set; and determining a target audio and video according to the similarity and a preset threshold, and recommending the target audio and video to the playing terminal. The scheme can improve the accuracy of personalized recommendation of the audio and video.

Description

Audio and video recommendation method and device and storage medium

Technical Field

The embodiment of the application relates to the technical field of internet, in particular to an audio and video recommendation method, an audio and video recommendation device and a storage medium.

Background

At present, the smart television or the smart box is widely applied to watching the online watching of the audio and video. For an operator who provides an internet television (Over The Top, OTT) or an audio/video resource for an intelligent television or an intelligent box, personalized recommendation or differentiated operation can be performed according to The interest of a user in order to improve The audience rating of audio/video and optimize audio/video services. For example, the audio and video is recommended based on the watching history of the user, that is, the interest and hobbies of the user when watching the audio and video content are analyzed by recording the watching history of the user within a period of time, and then the audio and video content similar to the theme is recommended to the user. The method can continuously analyze and correct the interests and hobbies of the user in the audio and video background according to the watching history of the user, thereby realizing the accuracy correction of the audio and video recommended content. Or, content pushing based on the audio and video playing amount and popularity in the background media asset library, namely counting the audio and video content playing data, acquiring all user watching records in a period of time, finding out the audio and video which the user likes to watch from all the user watching records, and organizing the audio and video content into a ranking list to be pushed to the user. The audios and videos in the leaderboard may represent hobby interests of most users.

In the research and practice process of the prior art, the inventor of the embodiment of the application finds that recommending audios and videos based on the user viewing history depends on the viewing history accuracy of a large number of users, namely, the user clicks. But for most users, their viewing history is often a popular movie that the audio visual application (App) recommends to them to list in the top. In addition, when the number of viewing histories of the user is small, a more accurate recommendation sample cannot be generated. Although recommending audios and videos based on the audio and video playing quantity and the popularity can represent the interests and hobbies of most users, for each audio and video user, the interests of the user are not necessarily met, and therefore the recommendation accuracy is not high.

Disclosure of Invention

The embodiment of the application provides an audio and video recommendation method, an audio and video recommendation device and a storage medium, which can improve the accuracy of personalized audio and video recommendation.

In one aspect, an embodiment of the present application provides an audio and video recommendation method, where the method includes:

acquiring user behavior data of a user from a playing terminal, wherein the user behavior data come from a user terminal in communication connection with the playing terminal;

determining a target interest type corresponding to the user behavior data;

determining a target audio and video set according to the target interest type, wherein the target audio and video set comprises at least one audio and video matched with the target interest type;

acquiring similarity between the user behavior data and audio and video description information of each audio and video in the target audio and video set;

and determining a target audio and video according to the similarity and a preset threshold, and recommending the target audio and video to the playing terminal.

In one possible design, the recommending the target audio/video to the play terminal includes:

sending recommendation information to the user terminal, and sending the target audio and video to the playing terminal after receiving a playing instruction for selecting the target audio and video from the user terminal; the recommendation information is used for indicating the target audio and video recommended to the user;

or sending recommendation information to the user terminal so that the playing terminal plays the locally stored target audio and video according to the playing instruction after receiving the playing instruction for selecting the target audio and video from the user terminal; the recommendation information is used for indicating the target audio and video recommended to the user.

In a possible design, the recommending the target audio/video to the play terminal includes one of:

sending recommendation information to the playing terminal, and sending the target audio and video to the playing terminal after receiving a playing instruction from the user from the playing terminal; the recommendation information is used for indicating the target audio and video recommended to the user;

or sending recommendation information to the playing terminal so that the playing terminal plays the locally stored target audio and video according to the playing instruction after receiving the playing instruction from the user; the recommendation information is used for indicating the target audio and video recommended to the user.

In one possible design, the obtaining user behavior data of the user includes:

sending an authorization request to the user terminal, so that the authorization request is used for requesting the user to authorize and collect the user behavior data;

after receiving confirmation information returned by the user terminal based on the authorization request, sending an acquisition request to the user terminal, wherein the acquisition request is used for requesting to acquire the current user behavior data of the user;

and updating the user behavior data corresponding to the user identification according to the user identification of the user.

In one possible design, the user behavior data includes at least one of:

user interest distribution, user subscription information, user biological clock distribution, or user mobility data;

the recommendation information includes at least one of:

the target audio and video description information, the target audio and video playing link or the target audio and video epitome.

In a possible design, before determining the target audio/video according to the similarity and a preset threshold, the method further includes:

determining target recommendation time, wherein the target recommendation time comprises the acquisition time of the user behavior data, the current time and the playing time of recommended audios and videos;

the determining the target audio and video according to the similarity and the preset threshold comprises the following steps:

determining candidate audios and videos with similarity higher than the preset threshold value from the target audio and video set;

and determining the target audio and video from the candidate audio and video according to the target interest type and the target recommendation time.

In one possible design, the determining the target audio/video from the candidate audio/videos according to the target interest type and the target recommendation time includes:

determining user interest distribution of the user according to the user behavior data, wherein the user interest distribution is distributed according to a biological clock of the user;

and determining a target audio and video which accords with the biological clock distribution of the user according to the interest distribution of the user, the target interest type and the target recommendation time.

In one possible design, after determining the target audio-video that conforms to the user's biological clock distribution, the method further includes:

and generating a recommendation strategy for the target audio and video which accords with the biological clock distribution according to the target recommendation time, wherein the recommendation strategy comprises a recommendation time interval of each target audio and video and a recommendation mode of each target audio and video.

In one possible design, the method further includes:

acquiring current time;

determining a target recommendation time interval to which the current time belongs;

and determining the audio and video to be recommended corresponding to the target recommendation time interval and the target recommendation mode of the audio and video to be recommended from the target audio and video set according to the target recommendation time interval and the recommendation strategy.

In one possible design, the user behavior data includes the user subscription information; the method further comprises the following steps:

acquiring current time and an audio and video database updated by the current time;

updating a target audio and video set of the user according to the user subscription information;

determining a target audio/video matched with the user subscription information from the updated target audio/video set of the user;

and recommending the target audio and video matched with the user subscription information to the playing terminal.

In one possible design, the user behavior data includes a user interest distribution; the method further comprises the following steps:

acquiring a current hot topic;

according to the hot topics and the user interest distribution, determining a target audio and video matched with the user interest distribution from the target audio and video set;

and recommending the target audio and video matched with the user interest distribution to the playing terminal.

In one possible design, the recommendation information is stored on a blockchain node.

In another aspect, an embodiment of the present application provides an audio and video recommendation device, which has a function of implementing the audio and video recommendation method provided in the foregoing first aspect. The functions can be realized by hardware, and the functions can also be realized by executing corresponding software by hardware. The hardware or software includes one or more modules corresponding to the above functions, which may be software and/or hardware.

In one possible design, the audio-visual recommendation device includes:

the system comprises a receiving and sending module, a processing module and a processing module, wherein the receiving and sending module is used for acquiring user behavior data of a user from a playing terminal, and the user behavior data come from a user terminal in communication connection with the playing terminal;

the processing module is used for determining a target interest type corresponding to the user behavior data acquired by the transceiving module; determining a target audio and video set according to the target interest type, wherein the target audio and video set comprises at least one audio and video matched with the target interest type; acquiring similarity between the user behavior data and audio and video description information of each audio and video in the target audio and video set; determining a target audio/video according to the similarity and a preset threshold;

the transceiver module is further configured to recommend the target audio and video to the play terminal.

In one possible design, the transceiver module is specifically configured to perform one of:

In one possible design, the transceiver module is further configured to:

the processing module is further configured to update the user behavior data received by the transceiver module to the user behavior data corresponding to the user identifier according to the user identifier of the user.

In one possible design, the user behavior data includes at least one of:

the recommendation information includes at least one of:

In a possible design, before determining the target audio/video according to the similarity and a preset threshold, the processing module is further configured to:

In one possible design, the processing module is specifically configured to:

In one possible design, after the processing module determines the target audio/video that conforms to the user's biological clock distribution, the processing module is further configured to:

In one possible design, after the processing module generates the recommendation policy, the processing module is further configured to:

acquiring current time;

In one possible design, the user behavior data includes the user subscription information; the processing module is further configured to:

acquiring the current time and an audio and video database updated by the current time through the transceiver module;

and recommending the target audio and video matched with the user subscription information to the playing terminal through the transceiving module.

In one possible design, the user behavior data includes a user interest distribution; the processing module is further configured to:

acquiring a current hot topic through the transceiver module;

and recommending the target audio and video matched with the user interest distribution to the playing terminal through the transceiving module.

A further aspect of the embodiments of the present application provides a computer device, which includes at least one connected processor, a memory and a transceiver, wherein the memory is used for storing a computer program, and the processor is used for calling the computer program in the memory to execute the method of the first aspect.

Yet another aspect of the embodiments of the present application provides a computer-readable storage medium, which includes instructions that, when executed on a computer, cause the computer to perform the method of the first aspect.

Compared with the related art, in the scheme provided by the embodiment of the application, since the user behavior data is acquired from the playing terminal in communication connection with the user terminal, the playing terminal is more familiar with the real user behavior data of the user, and the playing terminal is specially used for serving the user, after the user behavior data is reported to the server, the user can be understood more, and the playing terminal is specially used for performing individual personalized service and management on the user from the playing terminal, instead of relying on a uniform recommendation scheme. Therefore, when at least one target audio and video set matched with the target interest type is determined according to the target interest type corresponding to the user behavior data, more accurate target audio and video can be acquired and recommended to the user, and therefore the accuracy of personalized audio and video recommendation can be improved.

Drawings

FIG. 1a is a block diagram of a recommendation system in an embodiment of the present application;

fig. 1b is a schematic flowchart illustrating a process of establishing a bluetooth connection between the smart television and the smart band in the embodiment of the present application;

fig. 2 is a schematic flowchart of an audio and video recommendation method in an embodiment of the present application;

FIG. 3a is a schematic diagram of a user interest distribution in an embodiment of the present application;

FIG. 3b is a diagram illustrating a user sending a user subscription message in various ways according to an embodiment of the present application;

FIG. 4a is a schematic diagram of a recommended strategy in an embodiment of the present application;

fig. 4b is a schematic diagram of recommending audios and videos in the embodiment of the present application;

fig. 4c is a schematic diagram of recommending audios and videos in the embodiment of the present application;

FIG. 5 is a schematic diagram of an architecture of a distributed system in an embodiment of the present application;

fig. 6 is a schematic structural diagram of an audio and video recommendation device in an embodiment of the present application;

fig. 7 is a schematic structural diagram of a computer device for executing an audio and video recommendation method in an embodiment of the present application;

fig. 8 is a schematic structural diagram of a server for executing an audio and video recommendation method in an embodiment of the present application.

Detailed Description

The terms "target audio-video" and the like in the description and claims of the embodiments of the application and the drawings are used for distinguishing similar objects and not necessarily for describing a particular sequence or order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprise" and "have," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or modules is not necessarily limited to those steps or modules expressly listed, but may include other steps or modules not expressly listed or inherent to such process, method, article, or apparatus, such that the division of modules presented in the present application is merely a logical division and may be implemented in a practical application in a different manner, such that multiple modules may be combined or integrated into another system or some features may be omitted or not implemented, and such that couplings or direct couplings or communicative connections shown or discussed may be through interfaces, indirect couplings or communicative connections between modules may be electrical or the like, the embodiments of the present application are not limited. Moreover, the modules or sub-modules described as separate components may or may not be physically separated, may or may not be physical modules, or may be distributed in a plurality of circuit modules, and some or all of the modules may be selected according to actual needs to achieve the purpose of the embodiments of the present application.

The embodiment of the application provides an audio and video recommendation method, an audio and video recommendation device and a storage medium, which can be used on a server side, wherein the server side can be used for analyzing user behavior data and then recommending audio and video to a user based on the user behavior data, so that high-precision personalized recommendation is realized. In some embodiments, as shown in fig. 1a, a schematic diagram of a framework of a recommendation system for implementing an audio and video recommendation method, the recommendation system includes a user terminal 1, a play terminal 2, and a server 3. The details will be described below.

The user terminal 1 is responsible for collecting and reporting user behavior data, and the user terminal 1 can be wearable devices such as a smart watch, a smart bracelet and smart glasses, and can also be terminals such as a mobile phone and a personal computer. The user terminal 1 may include a near-field communication (NFC) module, a bluetooth module, or a near-field communication module, such as a wireless personal area network (ZigBee) module.

The playing terminal 2 is used for playing the audio and video from the server 3, and the playing terminal 2 can comprise an intelligent television, a personal computer, a projector, a mobile phone and other intelligent terminals. The playing terminal 2 includes a connection module 21 and a playing client 22. The connection module 21 is used for communication connection and data interaction with the user terminal 1, for example, the connection module is a module that connects and transmits data through a bluetooth/ZigBee protocol or the like. The playing client 22 refers to a software application provided in the playing terminal 2, and the playing client 22 may be used to display or play audio and video content received by the user terminal 1 from the server 3 or the user terminal 1. The playback client 22 may be a software application such as an audiovisual client or a browser client, for example, the playback client may be an audiovisual App. The user can operate through the playing client 22 to perform communication interaction with the server 3. The playing terminal 2 can also collect user behavior data and report the user behavior data to the server 3. In some embodiments, the playing client 22 may also refer to an audio client, a video client, or a client having both audio and video functions, which is not limited in this application.

The server 3 is used for providing audio and video resources for the user terminal 1, and the server 3 comprises a recommending module 31, an analyzing module 32 and an audio and video library 33. The recommending module 21 is configured to receive the user behavior data transmitted by the analyzing module 32, and push the audio and video to the playing client 22. The analysis module 32 is responsible for data modeling and processing analysis of the user behavior data sent from the playback client 22. The audiovisual library 33 is used to provide audiovisual resources to the recommendation module 31.

In the embodiment of the application, the user terminal 1, the playing terminal 2 and the server 3 can be in communication connection with each other, the user terminal 1 can also be in communication connection with only the playing terminal 2 or the server 3, and the user terminal 1 can be in communication connection with the playing terminal through a local area network and a near field communication mode, and can also be in remote communication connection. The embodiment of the present application does not limit the communication connection manner and communication connection between the user terminal 1, the playback terminal 2, and the server 3. Taking the connection module as an example through a bluetooth module, the user terminal 1 (e.g., smart band) and the play terminal 2 (e.g., smart tv) establish a communication connection through the bluetooth module. Fig. 1b is a schematic flow chart of establishing a bluetooth connection between the smart television and the smart band. Specifically, the process of establishing the bluetooth connection includes the following operations:

101. and after receiving the instruction input by the user, the intelligent television starts the Bluetooth.

102. And the intelligent television sends a device connection request and searches for Bluetooth devices within the effective distance.

103. After receiving an instruction input by a user, the intelligent bracelet starts Bluetooth, searches Bluetooth equipment in an effective distance, and processes the equipment connection request after searching the equipment connection request sent by the intelligent television.

104. And the intelligent bracelet sends hardware data of the intelligent bracelet to the intelligent television.

105. After the smart television receives the hardware data of the conveying bracelet, the smart television requests the smart bracelet to establish Bluetooth connection.

106. After the smart band receives the instruction that the user confirms to select the Bluetooth connection (i.e. the user confirms to be connected with the smart device through Bluetooth).

107. And the intelligent bracelet sends a connection confirmation message to the intelligent television.

108. The Bluetooth connection is established with intelligent bracelet to the smart TV.

The embodiment of the application mainly provides the following technical scheme:

after the user terminal 1, the playing terminal 2 and the server 3 are in communication connection with each other, the playing client 22 based on the user terminal 1 and the playing terminal 2 collects user behavior data, the server 3 analyzes the user behavior data, and finally, based on the user behavior data and the audio and video database 33, the interested target audio and video of the user is recommended for the user.

Referring to fig. 2, an audio and video recommendation method provided by an embodiment of the present application is described below, where the method may be performed by a server or a play terminal, or may be performed by both the server and the play terminal. The examples of the present application are not limited thereto. The embodiment corresponding to fig. 2 is described by taking an example of a method for executing audio and video recommendation by a server, and the embodiment of the present application includes:

201. and acquiring user behavior data of the user from the playing terminal.

The user behavior data may come from a user terminal in communication connection with the play terminal, or may come from the play terminal (for example, from a user's daily search record, an audio/video play record, or the like). The user behavior data comprises at least one of:

user interest distribution, user subscription information, user biological clock distribution, or user mobility data.

The user interest distribution refers to the distribution characteristics of at least one interest point of the user, and as shown in fig. 3a, the user a includes basketball, fantasy movie, swimming, and artificial intelligence. In some embodiments, in order to intuitively reflect the degrees of different points of interest of the user, and facilitate to recommend audios and videos matched with the points of interest to the user with pertinence and accuracy, the different points of interest of the user may be quantized, for example, the degrees of the different points of interest of the user are quantized into interest values. For example, Ua represents the interest value of a user in a certain interest point, and a represents the name of the interest point. For example with U_swimIndicating the user's interest in swimming this point of interest. The embodiment of the application does not limit the user interest distribution mode and the acquisition channel.

The user subscription information refers to audio and video recommendation information or keywords subscribed by a user on a user terminal or a playing terminal. For example, the user subscription information is: audio and video associated with a soccer league; or, the user subscription information is: the three players are in the latest dynamic state; or, the user subscription information is: basketball games. The user can update the user subscription information irregularly or periodically, including updating modes such as adding, deleting, replacing or modifying. The embodiment of the application does not limit the subscription mode, the subscription frequency and the subscription channel of the user subscription information. For example, as shown in fig. 3b, the user sends the user subscription information to the server in a video App, smart tv, personal computer, and short message manner of the mobile phone.

The user biological clock distribution refers to a periodic distribution characteristic which is formed by the movement of the user due to the habit of the user and accords with a certain time law. For example, the user's motion follows a regular time-structured sequence, representing the intrinsic rhythmicity of the user while performing an activity. For example, the user is in good mental state at 7-8 points, 21: 00-12: and 00 is mental state fatigue time. Such as sleep data, a deep sleep period, and a light sleep period. Accessible intelligence bracelet is gathered and is obtained, and this application embodiment does not do the restriction to the acquisition mode and the acquisition channel of user's biological clock distribution.

The user mobility data refers to the motion state of the user, such as the walking speed, the heartbeat speed, the heart rate and other motion states. In the embodiment of the application, the user mobility data is that the user behavior data comes from a user terminal in communication connection with the play terminal.

In some embodiments, the obtaining the user behavior data of the user from the playback terminal includes:

It can be understood that, after receiving the confirmation information of the user, a user folder may be created for the user, where the user folder is used to store user behavior data of the user, and the user behavior data may form a mapping relationship with the user identifier for storage, or may be stored in a user image manner, which is not limited in this embodiment of the present application. After receiving the user behavior data, the user behavior data can be bound with the user identifier (i.e., an updating process) to ensure that the user behavior data stored on the server side is the latest data and is more comprehensive. For example, the user has performed different-dimension authorization on different apps in the user terminal, for example, the App1 is authorized to read the web access record, the input method input record, and the like of the user, the App2 is authorized to read the speaking voice, the web search record, and the like of the user, and the App3 is authorized to read the position information, the consumption information, the audio/video playing record of the App1, and the like of the user. After receiving the user behavior data from the user terminal, the server can classify or update the user behavior data to the user identifier locally and uniformly and store the user behavior data.

On one hand, the acquired user behavior data are all known by the user and authorized by the user, so that the fact that the privacy of the user is maliciously acquired under an unknown condition can be avoided; on the other hand, the user behavior data are acquired from a plurality of different channels, and the user behavior data acquired from each channel have emphasis points or are different, so that the user behavior data can be acquired more comprehensively through the different channels, more comprehensive basis is provided for the subsequent analysis of the interest points of the user, and the accuracy of recommending the target audio/video is ensured. In addition, the user behavior data acquired from different channels can be uniformly classified, so that the user behavior data of the same user can be managed more efficiently, and the cost for respectively managing the user behavior data of single or few dimensions is saved.

202. And determining a target interest type corresponding to the user behavior data.

The target interest type refers to a type to which the interest point in the user behavior data belongs, for example, swimming is included in the user behavior data, and then it can be determined that swimming is a target interest type of the user. The user behavior data may include at least one interest point of the user, and thus, the target interest type may include at least one target interest type, which is not limited in the embodiments of the present application.

203. And determining a target audio and video set according to the target interest type.

The target audio and video set comprises at least one audio and video matched with the target interest type, and each audio and video corresponds to audio and video description information. The audio-video description information may be referred to as an audio-video attribute, for example, if the audio-video library includes a plurality of sports audio-video, audio-video a may be set to a surfing attribute, audio-video B may be set to a swimming attribute, and audio-video C may be set to a basketball attribute. For example, without repeated description, the attributes or categories of the content included in each audio/video in the audio/video library may be divided in advance, so as to facilitate rapid determination of the target audio/video set. The dimension number related to the target audio/video set is not limited in the embodiment of the application.

It should be noted that the audio and video in the embodiment of the present application includes at least one of audio and video, and the embodiment of the present application is not limited to this.

204. And acquiring the similarity between the user behavior data and the audio and video description information of each audio and video in the target audio and video set.

In some embodiments, the similarity may be implemented by cosine similarity, euclidean distance, or the like, and the similarity may also be replaced by a matching degree, which is not limited in the embodiment of the present application. Taking cosine similarity as an example, the similarity can be calculated in the following manner:

wherein Ua represents the interest value of the user U in the interest point a, for example, Ua represents the interest value of the user in the sport of "swimming", that is, the value corresponding to "swimming" in the user behavior data;

va indicates whether the interest point a is included in the video V, for example, Va indicates whether "swimming" is included in the video V, that is, Va indicates whether a value corresponding to "swimming" in the user behavior data is included in the video V.

In this embodiment, the closer the cosine similarity value is to 1, the closer the recommended video V is to the interest point of the user.

205. And determining a target audio and video according to the similarity and a preset threshold, and recommending the target audio and video to the playing terminal.

Wherein, the target audio-video can be 1 or at least two audio-videos. When the number of the at least two videos is at least two, the at least two videos may be presented according to the user interest distribution shown in fig. 3a, for example, the videos may be randomly arranged, or may be arranged according to the size sequence of the interest values, which is not limited in the embodiment of the present application. The target audio and video can be presented in a list, set and other ways, and the presentation way of the target audio and video is not limited in the embodiment of the application. In this application, the target audio and video may refer to audio, video, or data including both audio and video, which is not limited in this application.

In some embodiments, the recommending the target audio and video to the play terminal includes one of:

In some embodiments, the recommendation information includes at least one of:

The audio and video description information can include information such as the field type, the subject abstract, the related person and the producer of the target audio and video.

The playing link refers to address information which can enter a playing interface of the target audio/video by clicking a network address.

The audio/video epitome is an outline of the target audio/video formed by clipping and synthesizing the wonderful segments in the target audio/video.

Therefore, the embodiment provides multiple channels for recommending the target audio and video, the user can be guaranteed to acquire the latest target audio and video in real time, and the target audio and video is not missed by the user due to a single recommendation channel.

In consideration of more factors influencing the determination of the target audio and video, in order to further improve the accuracy of recommending the target audio and video to the user, the embodiments of the present application are introduced from the following angles:

(1) recommending target audio and video based on target recommendation time

In some embodiments, before determining the target audio/video according to the similarity and a preset threshold, the method further includes:

a. and determining target recommendation time, wherein the target recommendation time comprises the acquisition time of the user behavior data, the current time and the playing time of the recommended audio and video.

For example, the acquisition time may be 12 o ' clock, the current time may be 14 o ' clock, and the playing time may be 12 o ' clock and half clock.

b. Determining candidate audios and videos with similarity higher than the preset threshold value from the target audio and video set; and determining the target audio and video from the candidate audio and video according to the target interest type and the target recommendation time.

In some embodiments, the determining the target audio/video from the candidate audio/videos according to the target interest type and the target recommendation time includes:

For example, if the user is morning and the interest point is health preserving, morning exercise audios and videos such as Taijiquan are recommended; and if the interest point is health maintenance at night, recommending the recorded audio and video of the medicated wine for foot bath.

Therefore, the real requirements of the users at different time stages can be met through real-time dynamic adjustment, and the users can be guided to form habits.

(2) Recommending target audio and video based on recommendation strategy

In some embodiments, a preset recommendation strategy may be adopted to determine the target audio-video, specifically. After determining a target audio-video that conforms to the user's biological clock profile, the method further comprises:

and generating a recommendation strategy for the target audio and video which accords with the user biological clock distribution according to the target recommendation time, wherein the recommendation strategy comprises a recommendation time interval of each target audio and video and a recommendation mode of each target audio and video.

For example, user a wakes up at 7 points a day, goes to lunch break at 12 points a day, and goes to a muscle relaxed state at 18 points a day. User A is accustomed to doing sports at 7 o ' clock and watching entertainment videos between 12 o ' clock and 12 o ' clock, accustomed to running between 18 o ' clock and 19 o ' clock and accustomed to watching ball game videos between 20 o ' clock and 23 o ' clock. Then, as shown in FIG. 4a, the recommendation policy may include: music a with a rhythmic feeling is recommended in half at 7, entertainment video a distributed by free media is recommended in half at 12 to 12, bright music b is recommended at 18 to 19, and a football match is recommended at 20 to 23. The recommendation mode may be an App push notification message, a short message, a telephone, a mail, and the like, which is not limited in the embodiment of the present application.

Therefore, the recommendation strategy can pre-arrange the target audios and videos to be recommended by the user at different time stages, so that the recommendation efficiency can be improved, the calculation resources occupied by temporarily calculating the target audios and videos to be recommended when different time points are needed are avoided, on one hand, the recommendation speed is improved, on the other hand, the concurrence condition of calculating the target audios and videos at the same time point is reduced, and the performance of the server is improved.

In some embodiments, the recommendation strategy may be implemented by a model or a knowledge graph. The recommendation policy may also be referred to as a recommendation list, a recommendation rule, a recommendation queue, or the like, and the name or the expression of the recommendation policy is not limited in the embodiment of the present application. When the recommendation strategy is executed, a timer, a thread and the like can be introduced, and the recommendation strategy can be dynamically adjusted, for example, adjusted according to updated user behavior data; or adjusting according to the updated audio and video; or according to the updated user behavior data and the updated audio and video. The embodiment of the application does not limit the way and the trigger mechanism for dynamically adjusting the recommendation strategy.

(3) Recommending target audio and video based on recommendation strategy and current time

In some embodiments, after generating the recommendation policy, the method further comprises:

acquiring current time;

according to the target recommendation time interval and the recommendation strategy, determining the audio and video to be recommended corresponding to the target recommendation time interval and a target recommendation mode of the audio and video to be recommended from the target audio and video set;

correspondingly, the recommendation information is sent to the user terminal according to the target recommendation mode.

For example, in the morning, the App automatically dials a phone call or makes a ringtone (only the right of the user terminal is obtained) recommendation; for example, in the working time of a working day, audio and video (for example, learning audio and video related to work, such as PPT skill, legal case analysis and the like) is recommended to a user through subscription modes such as App messages, short messages, telephones, mails and the like. For example, as shown in fig. 4b, the current time is 20: 15, the ratio of 20: 15 during an event in a certain football match, the relevant football highlight audio-video or live link may be recommended to the user according to the recommendation strategy as shown in fig. 4 a.

Therefore, the effectiveness of recommending the audio and video can be improved by setting different recommending modes at different time periods.

(4) Recommending target audio and video based on user subscription information

In some embodiments, the user behavior data includes the user subscription information; the method further comprises the following steps:

Therefore, the current time is obtained based on the user subscription information, and once an event meeting the user subscription occurs at the current time and a target audio/video meeting the user subscription information exists, the target audio/video is recommended to the user. Therefore, the newly acquired audio and video can be recommended to the user in the first time, the recommendation delay is reduced, the user behavior data does not need to be updated, the user portrait is reestablished, and the latest audio and video can be recommended to the user.

(5) Recommending target audio/video based on user interest distribution and hot topics

In some embodiments, the user behavior data includes a user interest distribution, the method further comprising:

acquiring a current hot topic;

The hot topics can be obtained through heat calculation, and the embodiment of the application does not limit the hot topics.

As shown in fig. 4c, (1) in fig. 4c is a schematic diagram of user interest distribution of the user at each of the 4 points of interest of basketball, movie, swimming, and artificial intelligence, and (2) in fig. 4c is a schematic diagram of ranking of the current hot topics. In (2) in fig. 4c, the hot topic top4 is once: the 50 th basketball tournament cup, the gold week program, the badminton semi-finals, and the 6 th generation domestic robot. Although the popularity of the prime week program and the badminton semi-finals is higher, the two hot topics are not matched with the user interest distribution, that is, the two hot topics are not the interest points of the user, then according to the user interest distribution shown in (1) in fig. 4c and the hot topic ranking shown in (2) in fig. 4c, it can be obtained that the 50 th basketball tournament cup and the 6 th generation household robot issue are both matched with the user interest distribution, and then, the audios and videos corresponding to the two hot topics issued by the 50 th basketball tournament cup and the 6 th generation household robot can be recommended to the user.

Therefore, the target audio and video is recommended to the user based on the current hot topics and the user interest distribution, the latest and interesting audio and video can be provided like the user, the pertinence is stronger, and the recommendation effectiveness is improved.

In the embodiment of the application, the user behavior data is acquired from the playing terminal in communication connection with the user terminal, so that the playing terminal is more familiar with the real user behavior data of the user, and the playing terminal is specially used for serving the user, so that after the user behavior data is reported to the server, the server can understand the user more, and the server is specially used for performing individual personalized service and management on the user from the playing terminal instead of relying on a uniform recommendation scheme. Therefore, when at least one target audio and video set matched with the target interest type is determined according to the target interest type corresponding to the user behavior data, more accurate target audio and video can be acquired and recommended to the user, and therefore the accuracy of personalized audio and video recommendation can be improved.

Optionally, in some embodiments of the present application, the target audio/video and the recommendation information may be stored in a blockchain node. The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism and an encryption algorithm. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product services layer, and an application services layer.

The block chain underlying platform can comprise processing modules such as user management, basic service, intelligent contract and operation monitoring. The user management module is responsible for identity information management of all blockchain participants, and comprises public and private key generation maintenance (account management), key management, user real identity and blockchain address corresponding relation maintenance (authority management) and the like, and under the authorization condition, the user management module supervises and audits the transaction condition of certain real identities and provides rule configuration (wind control audit) of risk control; the basic service module is deployed on all block chain node equipment and used for verifying the validity of the service request, recording the service request to storage after consensus on the valid request is completed, for a new service request, the basic service firstly performs interface adaptation analysis and authentication processing (interface adaptation), then encrypts service information (consensus management) through a consensus algorithm, transmits the service information to a shared account (network communication) completely and consistently after encryption, and performs recording and storage; the intelligent contract module is responsible for registering and issuing contracts, triggering the contracts and executing the contracts, developers can define contract logics through a certain programming language, issue the contract logics to a block chain (contract registration), call keys or other event triggering and executing according to the logics of contract clauses, complete the contract logics and simultaneously provide the function of upgrading and canceling the contracts; the operation monitoring module is mainly responsible for deployment, configuration modification, contract setting, cloud adaptation in the product release process and visual output of real-time states in product operation, such as: alarm, monitoring network conditions, monitoring node equipment health status, and the like.

The device (also referred to as a server) for executing the audio/video recommendation method in the embodiment of the present application may be a node in a blockchain system. The audio/video recommendation device in the embodiment of the present application may be a node in a blockchain system as shown in fig. 5.

Any technical feature mentioned in the embodiment corresponding to any one of fig. 1a to 5 is also applicable to the embodiment corresponding to fig. 6 to 8 in the embodiment of the present application, and the details of the subsequent similarities are not repeated.

In the above description, an audio and video recommendation method in the embodiment of the present application is described, and apparatuses for executing the audio and video recommendation method are respectively described below.

Referring to fig. 6, a schematic structural diagram of an audio/video recommendation apparatus 60 shown in fig. 6 is applicable to analyzing interest in user behavior data and recommending interesting audio/video to a user. The audio/video recommendation device 60 in the embodiment of the present application can implement the steps of the audio/video recommendation method executed in the embodiment corresponding to any one of fig. 1a to fig. 5. The functions realized by the audio and video recommendation device can be realized by hardware, and can also be realized by executing corresponding software by hardware. The hardware or software includes one or more modules corresponding to the above functions, which may be software and/or hardware. The audio/video recommendation device 60 may include a processing module 601 and a transceiver module 602, and the processing module 601 and the transceiver module 602 may refer to operations executed in an embodiment corresponding to any one of fig. 1a to fig. 5, which are not described herein again. For example, the processing module 601 may be configured to control operations of the transceiver module 602, such as obtaining user behavior data, sending recommendation information, and sending a target audio/video.

In some embodiments, the transceiver module 602 may be configured to obtain user behavior data of a user from a playback terminal, where the user behavior data is from a user terminal communicatively connected to the playback terminal;

the processing module 601 may be configured to determine a target interest type corresponding to the user behavior data acquired by the transceiver module 602; determining a target audio and video set according to the target interest type, wherein the target audio and video set comprises at least one audio and video matched with the target interest type; acquiring similarity between the user behavior data and audio and video description information of each audio and video in the target audio and video set; determining a target audio/video according to the similarity and a preset threshold;

the transceiver module 602 is further configured to recommend the target audio and video to the play terminal.

In some embodiments, the transceiver module 602 is specifically configured to perform one of the following:

In some embodiments, the transceiver module 602 is further configured to:

the processing module 601 is further configured to update the user behavior data received by the transceiver module 602 to the user behavior data corresponding to the user identifier according to the user identifier of the user.

In some embodiments, the user behavior data includes at least one of:

the recommendation information includes at least one of:

In some embodiments, before determining the target audio/video according to the similarity and a preset threshold, the processing module 601 is further configured to:

In some embodiments, the processing module 601 is specifically configured to:

In some embodiments, after the processing module 601 determines the target audio and video conforming to the user's biological clock distribution, it is further configured to:

In some embodiments, after the processing module 601 generates the recommendation policy, it is further configured to:

acquiring current time;

In some embodiments, the user behavior data includes the user subscription information; the processing module 601 is further configured to:

acquiring the current time and an audio and video database updated by the current time through the transceiver module 602;

and recommending the target audio and video matched with the user subscription information to the playing terminal through the transceiver module 602.

In some embodiments, the user behavior data includes a user interest distribution; the processing module 601 is further configured to:

obtaining a current hot topic through the transceiver module 602;

and recommending the target audio and video matched with the user interest distribution to the playing terminal through the transceiver module 602.

The audio/video recommendation apparatus 60 in the embodiment of the present application is described above from the perspective of a modular functional entity, and the electronic device (for example, a play terminal or a server) that executes the audio/video recommendation method in the embodiment of the present application is described below from the perspective of hardware processing. The device 60 shown in fig. 6 may have a structure as shown in fig. 7, when the device 60 shown in fig. 6 has a structure as shown in fig. 7, the processor and the transceiver in fig. 7 can implement the same or similar functions of the processing module 601 and the transceiver module 602 provided in the device embodiment corresponding to the device 60, and the central storage in fig. 7 stores a computer program that the processor needs to call when executing the above-mentioned audio-video recommendation method. In the embodiment of this application, an entity device corresponding to the transceiver module 602 in the embodiment shown in fig. 6 may be a transceiver, an input/output unit, or an input/output interface, and an entity device corresponding to the processing module 601 may be a processor.

Fig. 8 is a schematic diagram of a server 820, which may have a relatively large difference due to different configurations or performances, and includes one or more central processing units 822 (e.g., one or more processors) and a memory 832, and one or more storage media 830 (e.g., one or more mass storage devices) for storing applications 842 or data 844. Memory 832 and storage medium 830 may be, among other things, transient or persistent storage. The program stored in the storage medium 830 may include one or more modules (not shown), each of which may include a series of instruction operations for the server. Still further, a central processor 822 may be provided in communication with the storage medium 830 for executing a series of instruction operations in the storage medium 830 on the server 820.

The Server 820 may also include one or more power supplies 826, one or more wired or wireless network interfaces 850, one or more input-output interfaces 858, and/or one or more operating systems 841, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc.

The steps performed by the server in the above embodiments may be based on the structure of the server 820 shown in fig. 8. For example, the steps performed by the apparatus 50 shown in fig. 8 in the above-described embodiment may be based on the server structure shown in fig. 8. For example, the processor 822, by calling instructions in the memory 832, performs the following operations:

acquiring user behavior data of a user from a playing terminal through the input/output interface 757, wherein the user behavior data comes from a user terminal in communication connection with the playing terminal;

determining a target interest type corresponding to the user behavior data; determining a target audio and video set according to the target interest type, wherein the target audio and video set comprises at least one audio and video matched with the target interest type; acquiring similarity between the user behavior data and audio and video description information of each audio and video in the target audio and video set; determining a target audio/video according to the similarity and a preset threshold;

and recommending the target audio and video to the playing terminal through the input and output interface 757.

In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system, the apparatus and the module described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the several embodiments provided in the embodiments of the present application, it should be understood that the disclosed system, apparatus, and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical division, and in actual implementation, there may be other divisions, for example, multiple modules or components may be combined or integrated into another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or modules, and may be in an electrical, mechanical or other form.

The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.

In addition, functional modules in the embodiments of the present application may be integrated into one processing module, or each module may exist alone physically, or two or more modules are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may be stored in a computer readable storage medium.

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. The procedures or functions described in accordance with the embodiments of the present application are generated in whole or in part when the computer program is loaded and executed on a computer. 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 a computer can store or a data storage device, such as a server, a data center, etc., that is integrated with one or more 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.

The technical solutions provided by the embodiments of the present application are introduced in detail, and the principles and implementations of the embodiments of the present application are explained by applying specific examples in the embodiments of the present application, and the descriptions of the embodiments are only used to help understanding the method and core ideas of the embodiments of the present application; meanwhile, for a person skilled in the art, according to the idea of the embodiment of the present application, there may be a change in the specific implementation and application scope, and in summary, the content of the present specification should not be construed as a limitation to the embodiment of the present application.

Claims

1. An audio-video recommendation method, characterized in that the method comprises:

determining a target interest type corresponding to the user behavior data;

2. The method according to claim 1, wherein the recommending the target audio and video to the play terminal comprises:

3. The method according to claim 1, wherein the recommending the target audio and video to the play terminal comprises:

4. The method according to claim 1, wherein the obtaining user behavior data of the user from the play terminal comprises:

5. The method according to claim 1, wherein before determining the target audio/video according to the similarity and a preset threshold, the method further comprises:

6. The method according to claim 5, wherein the determining the target audio-video from the candidate audio-videos according to the target interest type and the target recommendation time comprises:

7. The method of claim 6, wherein after determining the target audio-video that conforms to the user's biological clock profile, the method further comprises:

8. The method of claim 7, further comprising:

acquiring current time;

9. The method of claim 1, wherein the user behavior data comprises the user subscription information; the method further comprises the following steps:

10. The method of claim 1, wherein the user behavior data comprises a user interest distribution; the method further comprises the following steps:

acquiring a current hot topic;

11. A method according to claim 2 or 3, characterized in that the recommendation information is stored on a blockchain node.

12. An audio-visual recommendation device, characterized in that the audio-visual recommendation device comprises:

the receiving and sending module is used for acquiring user behavior data of a user from the playing terminal, wherein the user behavior data come from a user terminal in communication connection with the playing terminal;

the processing module is used for determining a target interest type corresponding to the user behavior data acquired by the transceiver module; determining a target audio and video set according to the target interest type, wherein the target audio and video set comprises at least one audio and video matched with the target interest type; acquiring similarity between the user behavior data and audio and video description information of each audio and video in the target audio and video set; determining a target audio/video according to the similarity and a preset threshold;

the transceiver module is also used for the playing terminal to recommend the target audio and video.

13. A computer device, characterized in that the computer device comprises:

at least one processor, memory, and transceiver;

wherein the memory is for storing a computer program and the processor is for calling the computer program stored in the memory to perform the method of any one of claims 1-11.

14. A computer-readable storage medium comprising instructions which, when executed on a computer, cause the computer to perform the method of any one of claims 1-11.