CN114866818B - Video recommendation method, device, computer equipment and storage medium - Google Patents
Video recommendation method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN114866818B CN114866818B CN202210693360.9A CN202210693360A CN114866818B CN 114866818 B CN114866818 B CN 114866818B CN 202210693360 A CN202210693360 A CN 202210693360A CN 114866818 B CN114866818 B CN 114866818B
- Authority
- CN
- China
- Prior art keywords
- video
- user
- information
- user demand
- demand
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000011156 evaluation Methods 0.000 claims abstract description 146
- 230000006399 behavior Effects 0.000 claims description 76
- 230000002159 abnormal effect Effects 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 9
- 230000011218 segmentation Effects 0.000 claims description 7
- 238000005516 engineering process Methods 0.000 abstract description 13
- 238000013473 artificial intelligence Methods 0.000 abstract description 7
- 238000004458 analytical method Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 229920000642 polymer Polymers 0.000 description 3
- 238000006116 polymerization reaction Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44213—Monitoring of end-user related data
- H04N21/44222—Analytics of user selections, e.g. selection of programs or purchase activity
- H04N21/44224—Monitoring of user activity on external systems, e.g. Internet browsing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/475—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data
- H04N21/4756—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data for rating content, e.g. scoring a recommended movie
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/475—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data
- H04N21/4758—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data for providing answers, e.g. voting
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Social Psychology (AREA)
- Computing Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the application belongs to the field of artificial intelligence, and relates to a video recommendation method, a device, computer equipment and a storage medium, wherein the method comprises the following steps: acquiring video browsing behavior data of a user; generating user demand assessment information according to the video browsing behavior data, wherein the user demand assessment information comprises user demand questions and corresponding demand assessment values and answer definitions thereof; when video recommendation is determined to be required to be performed on the user according to the user demand evaluation information, calculating a matching value of the user demand evaluation information and video tags of all candidate videos; and selecting the candidate video as a recommended video according to the matching value, and pushing the recommended video to the user. In addition, the application also relates to a blockchain technology, and video browsing behavior data can be stored in the blockchain. The video recommendation method and device improve accuracy of video recommendation.
Description
Technical Field
The present application relates to the field of artificial intelligence technologies, and in particular, to a video recommendation method, apparatus, computer device, and storage medium.
Background
With the development of computer and internet technologies, live broadcast and short video have also been rapidly developed. The media forms of live broadcast and short video can enable users to easily acquire information, so that service parties often utilize live broadcast and short video to conduct product propaganda and recommendation.
Live broadcast is also one type of video, and a service side generally recommends a video related to a product to a user, so that product promotion and recommendation are realized. However, current video recommendation techniques typically make recommendations based on the browsing habits of the user. Some types of commodities are complex, the information quantity is large, the information needed to be known by the user is large, video recommendation is carried out according to browsing habits, and video needed by the user is often difficult to recommend.
Disclosure of Invention
The embodiment of the application aims to provide a video recommendation method, a video recommendation device, computer equipment and a storage medium, so as to solve the problem of low video recommendation accuracy.
In order to solve the above technical problems, the embodiment of the present application provides a video recommendation method, which adopts the following technical scheme:
acquiring video browsing behavior data of a user;
Generating user demand evaluation information according to the video browsing behavior data, wherein the user demand evaluation information comprises user demand questions, corresponding demand evaluation values and answer definitions;
When the video recommendation needs to be carried out on the user according to the user demand assessment information, calculating a matching value of the user demand assessment information and video tags of candidate videos;
And selecting candidate videos as recommended videos according to the matching values, and pushing the recommended videos to the user.
In order to solve the above technical problems, the embodiment of the present application further provides a video recommendation device, which adopts the following technical scheme:
The data acquisition module is used for acquiring video browsing behavior data of a user;
The evaluation generation module is used for generating user demand evaluation information according to the video browsing behavior data, wherein the user demand evaluation information comprises user demand questions, corresponding demand evaluation values and answer definitions;
the matching calculation module is used for calculating the matching value of the user demand evaluation information and the video label of each candidate video when the video recommendation needs to be carried out on the user according to the user demand evaluation information;
and the video pushing module is used for selecting candidate videos as recommended videos according to the matching values and pushing the recommended videos to the user.
In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical schemes:
acquiring video browsing behavior data of a user;
Generating user demand evaluation information according to the video browsing behavior data, wherein the user demand evaluation information comprises user demand questions, corresponding demand evaluation values and answer definitions;
When the video recommendation needs to be carried out on the user according to the user demand assessment information, calculating a matching value of the user demand assessment information and video tags of candidate videos;
And selecting candidate videos as recommended videos according to the matching values, and pushing the recommended videos to the user.
In order to solve the above technical problems, an embodiment of the present application further provides a computer readable storage medium, which adopts the following technical schemes:
acquiring video browsing behavior data of a user;
Generating user demand evaluation information according to the video browsing behavior data, wherein the user demand evaluation information comprises user demand questions, corresponding demand evaluation values and answer definitions;
When the video recommendation needs to be carried out on the user according to the user demand assessment information, calculating a matching value of the user demand assessment information and video tags of candidate videos;
And selecting candidate videos as recommended videos according to the matching values, and pushing the recommended videos to the user.
Compared with the prior art, the embodiment of the application has the following main beneficial effects: acquiring video browsing behavior data, wherein the video browsing behavior data records various behaviors of a user when watching video, and the user behaviors can be analyzed according to the video browsing behavior data to generate user demand evaluation information; the user demand evaluation information comprises a user demand question, a corresponding demand evaluation value and answer definition, wherein the demand evaluation value indicates the interest degree of the user on the question, and the answer definition indicates the knowledge degree of the user on the answer of the question; according to the user demand assessment information, the user demand can be analyzed, and whether video recommendation is to be carried out on the user or not is determined; if so, calculating the matching value of the user demand evaluation information and the video label of each candidate video, wherein the matching value indicates the relevance between the user demand problem and the candidate video, selecting the candidate video related to the user demand problem according to the matching value and pushing the candidate video to the user, thereby realizing accurate pushing according to the user demand and improving the accuracy of video recommendation.
Drawings
In order to more clearly illustrate the solution of the present application, a brief description will be given below of the drawings required for the description of the embodiments of the present application, it being apparent that the drawings in the following description are some embodiments of the present application, and that other drawings may be obtained from these drawings without the exercise of inventive effort for a person of ordinary skill in the art.
FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;
FIG. 2 is a flow chart of one embodiment of a video recommendation method according to the present application;
FIG. 3 is a schematic diagram of an embodiment of a video recommendation device according to the present application;
FIG. 4 is a schematic structural diagram of one embodiment of a computer device in accordance with the present application.
Detailed Description
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the applications herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having" and any variations thereof in the description of the application and the claims and the description of the drawings above are intended to cover a non-exclusive inclusion. The terms first, second and the like in the description and in the claims or in the above-described figures, are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
In order to make the person skilled in the art better understand the solution of the present application, the technical solution of the embodiment of the present application will be clearly and completely described below with reference to the accompanying drawings.
As shown in fig. 1, a system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium to provide communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
The user may interact with the server 105 via the network 104 using the terminal devices 101, 102, 103 to receive or send messages or the like. Various communication client applications, such as a web browser application, a shopping class application, a search class application, an instant messaging tool, a mailbox client, social platform software, etc., may be installed on the terminal devices 101, 102, 103.
The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablet computers, electronic book readers, MP3 players (Moving Picture Experts Group Audio Layer III, dynamic video expert compression standard audio plane 3), MP4 (Moving Picture Experts Group Audio Layer IV, dynamic video expert compression standard audio plane 4) players, laptop and desktop computers, and the like.
The server 105 may be a server providing various services, such as a background server providing support for pages displayed on the terminal devices 101, 102, 103.
It should be noted that, the video recommendation method provided in the embodiment of the present application is generally executed by a server, and accordingly, the video recommendation device is generally disposed in the server.
It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
With continued reference to fig. 2, a flow chart of one embodiment of a video recommendation method in accordance with the present application is shown. The video recommendation method comprises the following steps:
step S201, obtaining video browsing behavior data of a user.
In this embodiment, the electronic device (e.g., the server shown in fig. 1) on which the video recommendation method operates may communicate with the terminal through a wired connection or a wireless connection. It should be noted that the wireless connection may include, but is not limited to, 3G/4G/5G connection, wiFi connection, bluetooth connection, wiMAX connection, zigbee connection, UWB (ultra wideband) connection, and other now known or later developed wireless connection.
Specifically, the method comprises the steps of firstly obtaining video browsing behavior data and recommending videos based on the video browsing behavior data. The video browsing behavior data can be behavior data left by a user browsing videos (including live videos and short videos) on a certain platform; the video browsing behavior data may also include video recording information of the video browsed by the user, the video recording information about the video itself, such as video tags, video contents, and the like.
It should be emphasized that, to further ensure the privacy and security of the video browsing behavior data, the video browsing behavior data may also be stored in a node of a blockchain.
The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The blockchain (Blockchain), essentially a de-centralized database, is a string of data blocks that are generated in association using cryptographic methods, each of which contains information from a batch of network transactions for verifying the validity (anti-counterfeit) of its information and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.
Step S202, user demand assessment information is generated according to the video browsing behavior data, wherein the user demand assessment information comprises user demand questions, corresponding demand assessment values and answer definitions.
Specifically, the video browsing behavior data records related behaviors of a user when browsing videos, for example, a problem posed by the user when watching live or short videos, wherein the problem posed by the user is the performance of a certain requirement (such as the requirement on the videos and the requirement on products related to the videos) of the user, and accordingly the user requirement problem can be extracted.
Meanwhile, the demand evaluation value and the answer definition can be calculated according to the video browsing behavior data. The demand evaluation value evaluates the degree of demand of the user, and when it is evaluated that the user is interested in the problem, the demand evaluation value is higher. The answer definition is used for evaluating whether the answer of the user to the user demand question is clear or not, and when the answer of the user to the question is evaluated to be clear, the answer definition is higher.
The user demand questions, the demand evaluation values, and the answer definitions are user demand evaluation information extracted from the video browsing behavior data.
Further, the step S202 may include: extracting user demand problems based on user search information and user comment information in the video browsing behavior data; calculating a requirement evaluation value and answer definition corresponding to a user requirement problem according to time information and video recording information corresponding to user search information and user comment information; and determining the user demand questions, the demand evaluation values and the answer definition as user demand evaluation information.
Specifically, the video browsing behavior data records user search information and user comment information of a user on a video platform. The user search information may be information left by the user searching on the video platform, for example, the user may search on the video platform for "how high the XX car consumes fuel" and "how high the XX insurance product pays" which may be used as the user search information. The user comment information may be comment information left by the user when watching a video, for example, when the user watches a live broadcast of a certain insurance product, a comment "XX insurance product premium" is left. According to the user search information and the user comment information, the user demand problem can be extracted.
The user search information and the user comment information also have corresponding time information, for example, each time the user leaves comments on the video platform, the corresponding time can be recorded. When the user is determined to generate the same user demand question for a plurality of times according to the time information, the user is shown to try to acquire an answer for one question for a plurality of times, the user can be judged to have higher demands for the question, and a higher demand evaluation value can be added. The video on the video platform is provided with video recording information, the video recording information can record the content of the video in different time periods, and according to the time information of the user for giving questions and the video recording information, whether the user obtains answer information related to the questions required by the user through the video can be judged, so that whether the answer of the user to the questions is clear is judged, and accordingly, the answer definition can be given.
The user demand questions, the demand evaluation values and the answer definition are the user demand evaluation information extracted from the video browsing behavior data.
In one embodiment, a user may praise or collect video comments while watching a video, which may also be extracted as a user demand problem when the video comments contain a problem. User demand questions extracted based on the praise or collection behavior may also give a demand evaluation value and answer clarity.
In one embodiment, the demand evaluation value and the answer sharpness may be determined according to a preset rule, for example, the demand evaluation value is given according to the number of times the user has posed the user demand problem; or the video browsing behavior data can be input into the neural network model to obtain the requirement evaluation value and the answer definition.
In this embodiment, a user demand problem is determined according to user search information and user comment information, and a demand evaluation value and answer definition corresponding to the user demand problem are determined according to time information and video recording information, so as to obtain user demand evaluation information for evaluating and analyzing user demands.
In step S203, when it is determined that video recommendation is required to be performed to the user according to the user demand evaluation information, a matching value between the user demand evaluation information and the video tag of each candidate video is calculated.
Specifically, for the user demand problem in the user demand evaluation information, if the demand evaluation value is high and the answer definition is low, video recommendation can be made to the user to help the user solve the user demand problem through the recommended video.
The video platform pre-exists a plurality of candidate videos, and the candidate videos have video labels, wherein the video labels are used for describing the candidate videos, such as content, types and the like of the candidate videos.
The matching value of the user demand assessment information and each candidate video can be calculated, and the matching value represents the relevance of the user demand problem in the user demand assessment information and each candidate video in a digital form.
Further, the step of calculating the matching value between the user requirement evaluation information and the video tag of each candidate video may include: acquiring video tags of candidate videos; respectively carrying out word segmentation processing on the user demand problem and the video tag in the user demand evaluation information to obtain a plurality of sub words; and calculating the matching value of the user demand evaluation information and each video tag according to the obtained subword.
Specifically, video tags of candidate videos are obtained, the lengths of the video tags are different and can be longer or shorter, and word segmentation processing can be carried out on the video tags to obtain a plurality of sub words; and then word segmentation processing is carried out on the user demand problem to obtain a plurality of sub words. And calculating the matching value of the user demand problem in the user demand evaluation information and each video tag according to the obtained subword.
In one embodiment, the match value is expressed as:；
wherein, For user demand problem,/>Is a video tag,/>The concept of the degree of polymerization, which represents the degree of polymerization of user demand problems and video labels, originally comes from the chemical field, is an index for measuring the molecular size of polymers. Taking the number of the repeated units as a reference, namely the average value of the number of the repeated units contained in a polymer macromolecular chain is expressed as n; based on the number of structural units, i.e. the number of individual structural units contained in the macromolecular chain of the polymer. In the present application, the degree of polymerization may be an average value of the number of identical or similar subwords. /(I)Representing the number of identical subwords in the user demand questions and video tags,/>Indicating the user demand problem and the number of total subwords in the video tag.
In one embodiment, the user demand questions and video tags may be converted into vectors and then used as matching values for the user demand questions and video tags by calculating cosine similarities between the vectors.
In this embodiment, the video tag and the user demand problem are segmented to obtain a plurality of words, and a matching value is calculated according to the subwords, so as to obtain the matching degree of the user demand problem and each candidate video.
Further, the step of obtaining the video tag of each candidate video includes: for each candidate video, acquiring a short label which is added in advance to the candidate video; obtaining video voice of a candidate video, and performing voice recognition on the video voice to obtain a voice recognition result; obtaining a video screenshot of a candidate video, and carrying out image recognition on the video screenshot to obtain an image recognition result; constructing a long label of the candidate video according to the voice recognition result and the image recognition result; and generating video labels of the candidate videos according to the short labels and the long labels.
Specifically, the video tag of each candidate video includes a short tag that can be used to describe the candidate video in a shorter text, and a long tag that can be used to describe the candidate video in a longer text.
The short label can be added in advance, for example, when a user uploads the video to the video platform, the short label of the video can be set by the user, or the video is identified by the video platform, and the short label is added.
The candidate video has video voice, and voice recognition is carried out on the video voice to obtain a voice recognition result; the candidate video can be captured to obtain a video capture, the video capture can contain explanatory information such as subtitles, and the like, and the image recognition is carried out on the video capture to obtain an image recognition result. The voice recognition result and the image recognition result are detailed descriptions of video contents of the candidate video, a long label can be constructed according to the voice recognition result and the image recognition result, and then the short label and the long label are spliced together to obtain the video label of the candidate video.
In this embodiment, a short tag of a candidate video is obtained, then voice recognition is performed on video voice of the candidate video, image recognition is performed on a video screenshot, and a long video is constructed according to a video result, so that a video tag for explaining the candidate video in detail is obtained according to the short tag and the long tag.
And S204, selecting the candidate videos as recommended videos according to the matching values, and pushing the recommended videos to the user.
Specifically, selecting a candidate video with a higher matching value as a recommended video, for example, comparing the calculated matching value with a preset matching threshold value, and selecting a candidate video with a matching value larger than the matching threshold value as the recommended video; or sorting the matching values from big to small, and selecting the candidate video ranked in the top N bits as the recommended video.
When the user is detected to log in the video platform, the recommended video can be recommended to the user, so that video recommendation is completed. For example, because the product to be recommended has complex functions, more information needs to be introduced, a plurality of different short videos can be produced based on the production mode of the current short video, and the product is introduced from different layers. After a user browses some short videos or live videos, generating video browsing behavior data, extracting a user demand problem 'XX insurance amount' from the video browsing behavior data, calculating a matching value according to the demand problem and video labels of candidate videos, selecting short videos related to the special introduction XX insurance amount, and recommending the short videos to the user, so that the confusion of the user is solved. The products to be recommended may be various products, and in one embodiment, the products to be recommended may be products in the financial, insurance fields.
In one embodiment, when the calculated matching values are smaller than the preset matching threshold, it indicates that there is no candidate video matching with the user demand problem, and operation indication information can be generated according to the user demand problem and pushed to related staff to remind the making of new videos.
In this embodiment, video browsing behavior data is obtained, the video browsing behavior data records various behaviors of a user when watching a video, and user behaviors can be analyzed according to the video browsing behavior data to generate user demand evaluation information; the user demand evaluation information comprises a user demand question, a corresponding demand evaluation value and answer definition, wherein the demand evaluation value indicates the interest degree of the user on the question, and the answer definition indicates the knowledge degree of the user on the answer of the question; according to the user demand assessment information, the user demand can be analyzed, and whether video recommendation is to be carried out on the user or not is determined; if so, calculating the matching value of the user demand evaluation information and the video label of each candidate video, wherein the matching value indicates the relevance between the user demand problem and the candidate video, selecting the candidate video related to the user demand problem according to the matching value and pushing the candidate video to the user, thereby realizing accurate pushing according to the user demand and improving the accuracy of video recommendation.
Further, after the step S204, the method may further include: acquiring push feedback data of a user aiming at a recommended video; updating user demand assessment information of a user based on push feedback data; determining the user type of the user according to the user demand evaluation information; and when the user belongs to a preset user type, pushing the candidate product corresponding to the recommended video to the user.
Specifically, after pushing the recommended video related to the user demand problem to the user, the user can watch the recommended video, and the behavior data generated in this process is recorded as push feedback data.
And updating the user demand assessment information according to the push feedback data. For example, when the user is detected to finish watching the recommended video, the answer definition in the user demand assessment information may be increased. Meanwhile, the purchase evaluation value of the user on the product can be determined according to the user demand evaluation information, the purchase evaluation value measures the possible purchase degree of the user on the product, and the user type can be classification of the user according to the purchase evaluation value. When the user type belongs to a preset user type (namely, the user type with higher purchase possibility for the product), pushing the candidate product corresponding to the recommended video to the user; for example, a purchase page of the candidate product is pushed to the user.
In one embodiment, based on the user demand evaluation information, the purchase evaluation value of the user may be determined by a preset rule, for example, the purchase evaluation value is calculated according to the demand evaluation value and the answer definition, and the higher the demand evaluation value, the higher the answer definition, the higher the purchase evaluation value. Or inputting the user demand evaluation information or the video browsing behavior data into a model built based on the neural network, and outputting the purchase evaluation value of the user through the model.
In the embodiment, the user demand evaluation information is updated according to the pushing feedback information, and when the user has higher purchase possibility for the candidate product according to the user demand evaluation information, the candidate product is pushed to the user, so that the product recommendation based on the user behavior analysis is realized, and the accuracy of the product recommendation is improved.
Further, after the step of obtaining the push feedback data of the user for the recommended video, the method may further include: acquiring the playing completion position of the recommended video from the push feedback data; acquiring an answer position of a recommended video; when the playing completion position is smaller than the answer position, marking the push of the recommended video as abnormal push; when the abnormal pushing quantity is detected to be larger than a preset quantity threshold, video early warning information of the recommended video is generated.
Specifically, when the user views the recommended video, the user may exit from viewing the video at a certain time point, for example, after the video viewing is finished, or exit from viewing the video in the middle of the video, where the user exits from viewing the video is the playing completion position.
The recommended video has answer information of the user demand questions, and the position of the answer information is the answer position. In one embodiment, the completion location and answer location may be time information, e.g., time information contains minutes and seconds, to locate the completion location and answer location. Comparing the size of the complete playing position with the size of the answer position, if the complete playing position is smaller than the answer position, indicating that the user exits the recommended video watching before watching the answer information, and marking the current pushing as abnormal pushing when the video pushing action does not obtain a substantial effect.
If the pushing quantity of abnormal pushing generated by the recommended video is detected to be larger than a preset quantity threshold, the recommended video has lower effect on solving the problem of user demand, and video early warning information can be generated. The video early warning information is sent to the relevant staff member so that the relevant staff member can reproduce the video to improve the video quality.
In this embodiment, when the completion position is smaller than the answer position, the push is marked as abnormal push; when the pushing quantity of abnormal pushing is larger than a preset quantity threshold, generating video early warning information representing poor video quality so as to adjust videos in time and improve the probability of obtaining answer information by a user through the videos.
Further, the video recommendation method may further include: and stopping the video recommendation process when the video recommendation of the user is not required according to the user demand evaluation information or when the user is detected to be a risk user.
Specifically, when the user is determined to have no interest in the candidate product related to the video or the user has known about the problem related to the product according to the user demand evaluation information, the video recommendation process can be stopped without performing video recommendation on the user; or the video recommendation process may also be stopped when it is detected that the user is a risk user. The risk user may be that the account of the user is detected to have abnormal use, or the user is a blacklist user.
In this embodiment, when it is determined that video recommendation is not required for the user according to the user demand evaluation information, or when it is detected that the user is a risk user, the video recommendation process is stopped, so as to reduce consumption of computing resources.
In one embodiment, the server stores the user demand assessment information via three storage areas, e.g., three tables. The first table is used for storing user demand questions and related information thereof, including user identification (i.e. user ID for uniquely identifying a certain user), a demand evaluation value, a live question time (time point when the user puts forward the user demand questions in live broadcast), whether to answer in live broadcast (identify whether to answer the user demand questions by anchor in live broadcast), a live answer time (time point when the anchor answers the user demand questions in live broadcast), a video identification (video ID for uniquely identifying a certain video) of a recommended video, an answer position (position of answer information in the recommended video) of the recommended video, a complete broadcast position of the recommended video, whether to acquire answers by the recommended video, answer definition, purchase evaluation value, and whether to end the video recommendation process. Wherein, whether to obtain the answer through the recommended video and whether to end the video recommendation process can be stored in a form of 0-1, and the other fields can be stored in a form of percentage values. The information in the first storage area may be from video browsing behavior data as well as push feedback data.
The second storage area is used for storing a fluctuation factor of each field in the first storage area, and the fields in the first storage area can be increased or decreased in value according to the fluctuation factor. The fluctuation factor can be set manually according to the business requirements, for example, the fluctuation factor can be set to 10%.
The third storage area is used for storing the generated operation indication information. The application can analyze the video browsing behavior data, such as inputting the video browsing behavior data into a model built based on a neural network for analysis, and recording the operation abnormality; for example, according to the matching value, the recommended video cannot be matched, or the user has a higher requirement evaluation value, the anchor answers the user requirement problem in live broadcast, but the user still has frequent searching or questioning actions on the user requirement. The operation indication information is sent to relevant staff for analysis.
The demand evaluation value can be obtained according to the user portrait, wherein the user portrait comprises the searching information of the number of times of searching the questions, the number of times of asking the questions and each time after the user watches the video, which are extracted from the video browsing behavior data; wherein, the more the searching times and the questioning times are, the more the value of the demand evaluation value is increased according to the fluctuation factor. If the time interval of a user asking questions for multiple questions before a host answers the questions in the video watching process is longer, the demand evaluation value is larger; the larger the demand evaluation value is, the higher the priority of performing the corresponding video push is. Meanwhile, the demand evaluation value is reduced by a certain percentage at intervals with the lapse of time. In live broadcast, if the host answers the problem, but the requirement evaluation value of a plurality of users for a certain user requirement problem is still higher, a running record can be generated, data errors are displayed, and the running record is recorded in a third storage area.
In live broadcast, video and voice can be converted into characters, and the converted characters are matched with the user demand problem. If the matching is followed by determining that the anchor has solved the user demand problem in the live broadcast, corresponding values of "whether to solve in the live broadcast" and "live broadcast solution time" are determined. The live quiz time, whether to answer in live, and the live answer time may be used to determine the demand assessment value and answer clarity.
After the first storage area is updated according to the push feedback data, if the playing position is smaller than the answer position, the user is not informed of seeing the answer in the recommended video, and the answer definition is not improved. The video platform can continuously push recommended videos containing answer information at the moment, if more clients exist, video early warning information is generated, and the quality of questions is suggested to be improved or the answer position is advanced.
The answer definition can be calculated according to the complete playing position and the demand evaluation value, and the higher the number of the complete playing position is, the gradually decreasing demand evaluation value along with time is, so that the higher the answer definition is indicated by the user.
The purchase evaluation value may be analyzed based on the demand evaluation value, the answer sharpness, and user portraits of the video, favorites, comments, viewing time, etc., and may decrease gradually over time.
After the user gets the answer and does not watch the video for a period of time, the video recommendation process can be set to be 1; or when the video platform detects that the user is a risk client, the field value is set to 1.
The data in the three storage areas can be asynchronously and independently operated by one service after the watching is finished; in order to ensure the operation efficiency, a certain amount of clients can be operated by using multiple threads for the first time, and the subsequent updated data can be automatically calculated and updated at preset time (for example, the time when the number of visitors is small).
The application can identify whether the user comment information is effective or not through natural language processing, detect the user demand problem and identify whether the user puts forward the same user demand problem at other time points or not. If the user has posed the same user-required question at other time points and answer information is not obtained, the answer definition is reduced. The video platform can search users with the same condition, and if the number of the users is large, operation indication information is generated to prompt that the video quality containing corresponding answers is insufficient, replacement is suggested, or the information transmitted by the anchor is unclear.
In live broadcast, if the host answers the user demand questions, the user responds to the questions, continuously watches live broadcast, the demand evaluation value rises, the purchase evaluation value also rises, and the answer definition also improves.
If the fact that the user does not respond to the answer of the anchor in live broadcast is identified, or the anchor does not answer the problem of the user and the demand evaluation value continues to rise, the answer definition is unchanged, and relevant videos are recommended to the user according to the video tags.
If the related candidate videos cannot be found according to the matching values, generating operation indication information, prompting that the videos related to the user demand problems cannot be found, and suggesting to update the videos.
If the finishing position is larger than the answer position, increasing the answer definition according to the fluctuation factor; if the playing position is smaller than the answer position, the answer definition is not improved, the demand evaluation value continues to rise, the video pushing is marked as abnormal pushing, and when the number of the pushing of the abnormal pushing is detected to be larger than a preset number threshold, video early warning information is generated and stored in a third storage area.
In addition, whether the user pays attention to the user demand problem or not can be judged by data such as the back browse amount of the user, the video replay times, the replay position (the viewing position when the user watches the video again) and the like, if so, the demand evaluation value is promoted, and the purchase evaluation value is promoted.
The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Wherein artificial intelligence (ARTIFICIAL INTELLIGENCE, AI) is the theory, method, technique, and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend, and expand human intelligence, sense the environment, acquire knowledge, and use knowledge to obtain optimal results.
Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by computer readable instructions stored in a computer readable storage medium that, when executed, may comprise the steps of the embodiments of the methods described above. The storage medium may be a nonvolatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a random access Memory (Random Access Memory, RAM).
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.
With further reference to fig. 3, as an implementation of the method shown in fig. 2, the present application provides an embodiment of a video recommendation apparatus, where the embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 2, and the apparatus is particularly applicable to various electronic devices.
As shown in fig. 3, the video recommendation apparatus 300 according to the present embodiment includes: a data acquisition module 301, an evaluation generation module 302, a matching calculation module 303, and a video pushing module 304, wherein:
the data acquisition module 301 is configured to acquire video browsing behavior data of a user.
The evaluation generating module 302 is configured to generate user requirement evaluation information according to the video browsing behavior data, where the user requirement evaluation information includes a user requirement question, a requirement evaluation value corresponding to the user requirement question, and answer definition.
And the matching calculation module 303 is configured to calculate a matching value between the user requirement evaluation information and the video tag of each candidate video when it is determined that video recommendation is required to be performed on the user according to the user requirement evaluation information.
The video pushing module 304 is configured to select the candidate video as the recommended video according to the matching value, and push the recommended video to the user.
In this embodiment, video browsing behavior data is obtained, the video browsing behavior data records various behaviors of a user when watching a video, and user behaviors can be analyzed according to the video browsing behavior data to generate user demand evaluation information; the user demand evaluation information comprises a user demand question, a corresponding demand evaluation value and answer definition, wherein the demand evaluation value indicates the interest degree of the user on the question, and the answer definition indicates the knowledge degree of the user on the answer of the question; according to the user demand assessment information, the user demand can be analyzed, and whether video recommendation is to be carried out on the user or not is determined; if so, calculating the matching value of the user demand evaluation information and the video label of each candidate video, wherein the matching value indicates the relevance between the user demand problem and the candidate video, selecting the candidate video related to the user demand problem according to the matching value and pushing the candidate video to the user, thereby realizing accurate pushing according to the user demand and improving the accuracy of video recommendation.
In some alternative implementations of the present embodiment, the evaluation generation module 302 may include: a problem extraction sub-module, a calculation sub-module, and an evaluation determination sub-module, wherein:
And the problem extraction sub-module is used for extracting user demand problems based on the user search information and the user comment information in the video browsing behavior data.
And the computing sub-module is used for computing the demand evaluation value and the answer definition corresponding to the user demand problem according to the time information and the video recording information corresponding to the user search information and the user comment information.
And the evaluation determination submodule is used for determining the user demand questions, the demand evaluation values and the answer definition as user demand evaluation information.
In this embodiment, a user demand problem is determined according to user search information and user comment information, and a demand evaluation value and answer definition corresponding to the user demand problem are determined according to time information and video recording information, so as to obtain user demand evaluation information for evaluating and analyzing user demands.
In some alternative implementations of the present embodiment, the matching calculation module 303 may include: the label obtains sub-module, segmentation sub-module and matches calculation sub-module, wherein:
and the label acquisition sub-module is used for acquiring the video labels of the candidate videos.
And the word segmentation sub-module is used for respectively carrying out word segmentation processing on the user demand problem and the video tag in the user demand evaluation information to obtain a plurality of sub-words.
And the matching calculation sub-module is used for calculating the matching value of the user demand evaluation information and each video tag according to the obtained subword.
In this embodiment, the video tag and the user demand problem are segmented to obtain a plurality of words, and a matching value is calculated according to the subwords, so as to obtain the matching degree of the user demand problem and each candidate video.
In some optional implementations of this embodiment, the tag acquisition sub-module may include: short label acquisition unit, speech recognition unit, image recognition unit, long label construction unit and label generation unit, wherein:
and the short label acquisition unit is used for acquiring the short labels which are added in advance to the candidate videos for each candidate video.
The voice recognition unit is used for acquiring video voice of the candidate video and performing voice recognition on the video voice to obtain a voice recognition result.
The image recognition unit is used for acquiring the video screenshot of the candidate video and carrying out image recognition on the video screenshot to obtain an image recognition result.
And the long label construction unit is used for constructing long labels of candidate videos according to the voice recognition result and the image recognition result.
And the label generating unit is used for generating video labels of the candidate videos according to the short labels and the long labels.
In this embodiment, a short tag of a candidate video is obtained, then voice recognition is performed on video voice of the candidate video, image recognition is performed on a video screenshot, and a long video is constructed according to a video result, so that a video tag for explaining the candidate video in detail is obtained according to the short tag and the long tag.
In some optional implementations of the present embodiment, the video recommendation apparatus 300 may further include: the device comprises a feedback acquisition module, an evaluation updating module, a type determining module and a product pushing module, wherein:
the feedback acquisition module is used for acquiring push feedback data of the user aiming at the recommended video.
And the evaluation updating module is used for updating the user demand evaluation information of the user based on the push feedback data.
And the type determining module is used for determining the user type of the user according to the user demand evaluation information.
And the product pushing module is used for pushing the candidate products corresponding to the recommended video to the user when the user belongs to the preset user type.
In the embodiment, the user demand evaluation information is updated according to the pushing feedback information, and when the user has higher purchase possibility for the candidate product according to the user demand evaluation information, the candidate product is pushed to the user, so that the product recommendation based on the user behavior analysis is realized, and the accuracy of the product recommendation is improved.
In some optional implementations of the present embodiment, the video recommendation apparatus 300 may further include: the system comprises a complete broadcast position acquisition module, an answer position acquisition module, an abnormal push marking module and an early warning information generation module, wherein:
And the complete broadcasting position acquisition module is used for acquiring the complete broadcasting position of the recommended video from the push feedback data.
And the answer position acquisition module is used for acquiring the answer position of the recommended video.
And the abnormal pushing marking module is used for marking the pushing of the recommended video as abnormal pushing when the playing completion position is smaller than the answer position.
The early warning information generation module is used for generating video early warning information of the recommended video when the pushing quantity of the abnormal pushing is detected to be larger than a preset quantity threshold value.
In this embodiment, when the completion position is smaller than the answer position, the push is marked as abnormal push; when the pushing quantity of abnormal pushing is larger than a preset quantity threshold, generating video early warning information representing poor video quality so as to adjust videos in time and improve the probability of obtaining answer information by a user through the videos.
In some optional implementations of the present embodiment, the video recommendation apparatus 300 may further include: and the process stopping module is used for stopping the video recommendation process when the video recommendation of the user is not required according to the user demand evaluation information or when the user is detected to be a risk user.
In this embodiment, when it is determined that video recommendation is not required for the user according to the user demand evaluation information, or when it is detected that the user is a risk user, the video recommendation process is stopped, so as to reduce consumption of computing resources.
In order to solve the technical problems, the embodiment of the application also provides computer equipment. Referring specifically to fig. 4, fig. 4 is a basic structural block diagram of a computer device according to the present embodiment.
The computer device 4 comprises a memory 41, a processor 42, a network interface 43 communicatively connected to each other via a system bus. It should be noted that only computer device 4 having components 41-43 is shown in the figures, but it should be understood that not all of the illustrated components are required to be implemented and that more or fewer components may be implemented instead. It will be appreciated by those skilled in the art that the computer device herein is a device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction, and its hardware includes, but is not limited to, a microprocessor, an Application SPECIFIC INTEGRATED Circuit (ASIC), a Programmable gate array (Field-Programmable GATE ARRAY, FPGA), a digital Processor (DIGITAL SIGNAL Processor, DSP), an embedded device, and the like.
The computer equipment can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing equipment. The computer equipment can perform man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch pad or voice control equipment and the like.
The memory 41 includes at least one type of readable storage medium including flash memory, hard disk, multimedia card, card memory (e.g., SD or DX memory, etc.), random Access Memory (RAM), static Random Access Memory (SRAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), programmable Read Only Memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the storage 41 may be an internal storage unit of the computer device 4, such as a hard disk or a memory of the computer device 4. In other embodiments, the memory 41 may also be an external storage device of the computer device 4, such as a plug-in hard disk, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD) or the like, which are provided on the computer device 4. Of course, the memory 41 may also comprise both an internal memory unit of the computer device 4 and an external memory device. In this embodiment, the memory 41 is typically used to store an operating system and various application software installed on the computer device 4, such as computer readable instructions of a video recommendation method. Further, the memory 41 may be used to temporarily store various types of data that have been output or are to be output.
The processor 42 may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 42 is typically used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is configured to execute computer readable instructions stored in the memory 41 or process data, such as computer readable instructions for executing the video recommendation method.
The network interface 43 may comprise a wireless network interface or a wired network interface, which network interface 43 is typically used for establishing a communication connection between the computer device 4 and other electronic devices.
The computer device provided in the present embodiment may perform the video recommendation method described above. The video recommendation method may be the video recommendation method of each of the above embodiments.
In this embodiment, video browsing behavior data is obtained, the video browsing behavior data records various behaviors of a user when watching a video, and user behaviors can be analyzed according to the video browsing behavior data to generate user demand evaluation information; the user demand evaluation information comprises a user demand question, a corresponding demand evaluation value and answer definition, wherein the demand evaluation value indicates the interest degree of the user on the question, and the answer definition indicates the knowledge degree of the user on the answer of the question; according to the user demand assessment information, the user demand can be analyzed, and whether video recommendation is to be carried out on the user or not is determined; if so, calculating the matching value of the user demand evaluation information and the video label of each candidate video, wherein the matching value indicates the relevance between the user demand problem and the candidate video, selecting the candidate video related to the user demand problem according to the matching value and pushing the candidate video to the user, thereby realizing accurate pushing according to the user demand and improving the accuracy of video recommendation.
The present application also provides another embodiment, namely, a computer-readable storage medium storing computer-readable instructions executable by at least one processor to cause the at least one processor to perform the steps of the video recommendation method as described above.
In this embodiment, video browsing behavior data is obtained, the video browsing behavior data records various behaviors of a user when watching a video, and user behaviors can be analyzed according to the video browsing behavior data to generate user demand evaluation information; the user demand evaluation information comprises a user demand question, a corresponding demand evaluation value and answer definition, wherein the demand evaluation value indicates the interest degree of the user on the question, and the answer definition indicates the knowledge degree of the user on the answer of the question; according to the user demand assessment information, the user demand can be analyzed, and whether video recommendation is to be carried out on the user or not is determined; if so, calculating the matching value of the user demand evaluation information and the video label of each candidate video, wherein the matching value indicates the relevance between the user demand problem and the candidate video, selecting the candidate video related to the user demand problem according to the matching value and pushing the candidate video to the user, thereby realizing accurate pushing according to the user demand and improving the accuracy of video recommendation.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method according to the embodiments of the present application.
It is apparent that the above-described embodiments are only some embodiments of the present application, but not all embodiments, and the preferred embodiments of the present application are shown in the drawings, which do not limit the scope of the patent claims. This application may be embodied in many different forms, but rather, embodiments are provided in order to provide a thorough and complete understanding of the present disclosure. Although the application has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described in the foregoing description, or equivalents may be substituted for elements thereof. All equivalent structures made by the content of the specification and the drawings of the application are directly or indirectly applied to other related technical fields, and are also within the scope of the application.
Claims (9)
1. A video recommendation method, comprising the steps of:
acquiring video browsing behavior data of a user, wherein the video browsing behavior data is behavior data generated by live broadcasting and short video browsing of the user;
Generating user demand evaluation information according to the video browsing behavior data, wherein the user demand evaluation information comprises user demand questions, corresponding demand evaluation values and answer definitions;
When the video recommendation needs to be carried out on the user according to the user demand assessment information, calculating a matching value of the user demand assessment information and video tags of candidate videos, wherein if the demand assessment value is higher and the answer definition is lower, the video recommendation needs to be carried out on the user;
selecting candidate videos as recommended videos according to the matching values, and pushing the recommended videos to the user;
The step of generating user demand assessment information according to the video browsing behavior data comprises the following steps:
extracting user demand problems based on user search information and user comment information in the video browsing behavior data;
Calculating a demand evaluation value and answer definition corresponding to the user demand problem according to the time information and video recording information corresponding to the user search information and the user comment information, wherein the video recording information records the content of the video in different time periods;
and determining the user demand questions, the demand evaluation values and the answer definition as user demand evaluation information.
2. The video recommendation method according to claim 1, wherein the step of calculating a matching value of the user demand assessment information and video tags of respective candidate videos comprises:
Acquiring video tags of candidate videos;
Performing word segmentation processing on the user demand problem in the user demand assessment information and the video tag respectively to obtain a plurality of sub words;
And calculating the matching value of the user demand assessment information and each video tag according to the obtained subword.
3. The video recommendation method according to claim 1, wherein the step of acquiring video tags of each candidate video comprises:
for each candidate video, acquiring a short label which is added in advance to the candidate video;
Acquiring video voices of the candidate videos, and performing voice recognition on the video voices to obtain voice recognition results;
obtaining a video screenshot of the candidate video, and carrying out image recognition on the video screenshot to obtain an image recognition result;
Constructing a long label of the candidate video according to the voice recognition result and the image recognition result;
and generating video labels of the candidate videos according to the short labels and the long labels.
4. The video recommendation method according to claim 1, further comprising, after the step of selecting a candidate video as a recommended video based on the matching value and pushing the recommended video to the user:
Acquiring push feedback data of a user aiming at the recommended video;
updating user demand assessment information of the user based on the push feedback data;
determining the user type of the user according to the user demand assessment information;
And when the user belongs to a preset user type, pushing the candidate product corresponding to the recommended video to the user.
5. The video recommendation method according to claim 4, further comprising, after the step of acquiring push feedback data of a user for the recommended video:
Acquiring the playing completion position of the recommended video from the push feedback data;
acquiring an answer position of the recommended video;
when the playing completion position is smaller than the answer position, marking the push of the recommended video as abnormal push;
And when the abnormal pushing quantity is detected to be larger than a preset quantity threshold, generating video early warning information of the recommended video.
6. The video recommendation method according to claim 1, wherein the method further comprises:
and stopping the video recommendation process when the video recommendation of the user is not required according to the user demand evaluation information or when the user is detected to be a risk user.
7. A video recommendation device, comprising:
The data acquisition module is used for acquiring video browsing behavior data of a user, wherein the video browsing behavior data is behavior data generated by live broadcasting and short video browsing of the user;
The evaluation generation module is used for generating user demand evaluation information according to the video browsing behavior data, wherein the user demand evaluation information comprises user demand questions, corresponding demand evaluation values and answer definitions;
The matching calculation module is used for calculating a matching value of the user demand evaluation information and the video label of each candidate video when the video recommendation needs to be carried out on the user according to the user demand evaluation information, wherein if the demand evaluation value is higher and the answer definition is lower, the video recommendation needs to be carried out on the user;
the video pushing module is used for selecting candidate videos as recommended videos according to the matching values and pushing the recommended videos to the user;
the generating user demand assessment information according to the video browsing behavior data comprises the following steps:
extracting user demand problems based on user search information and user comment information in the video browsing behavior data;
Calculating a demand evaluation value and answer definition corresponding to the user demand problem according to the time information and video recording information corresponding to the user search information and the user comment information, wherein the video recording information records the content of the video in different time periods;
and determining the user demand questions, the demand evaluation values and the answer definition as user demand evaluation information.
8. A computer device comprising a memory having stored therein computer readable instructions which when executed by a processor implement the steps of the video recommendation method of any of claims 1 to 6.
9. A computer readable storage medium having stored thereon computer readable instructions which when executed by a processor implement the steps of the video recommendation method according to any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210693360.9A CN114866818B (en) | 2022-06-17 | 2022-06-17 | Video recommendation method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210693360.9A CN114866818B (en) | 2022-06-17 | 2022-06-17 | Video recommendation method, device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114866818A CN114866818A (en) | 2022-08-05 |
| CN114866818B true CN114866818B (en) | 2024-04-26 |
Family
ID=82625607
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210693360.9A Active CN114866818B (en) | 2022-06-17 | 2022-06-17 | Video recommendation method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114866818B (en) |
Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105959736A (en) * | 2016-04-29 | 2016-09-21 | 广东小天才科技有限公司 | Recommendation method and device for tutoring video |
| CN106878819A (en) * | 2017-01-20 | 2017-06-20 | 合网络技术（北京）有限公司 | The method, system and device of information exchange in a kind of network direct broadcasting |
| WO2017107453A1 (en) * | 2015-12-23 | 2017-06-29 | 乐视控股（北京）有限公司 | Video content recommendation method, device, and system |
| CN107423326A (en) * | 2017-04-11 | 2017-12-01 | 广州亿码科技有限公司 | A kind of recommendation and result queries method and system based on answer-mode |
| WO2018023665A1 (en) * | 2016-08-05 | 2018-02-08 | 吴晓敏 | Data acquisition method for video recommendation technology and video recommendation system |
| CN107888950A (en) * | 2017-11-09 | 2018-04-06 | 福州瑞芯微电子股份有限公司 | A kind of method and system for recommending video |
| CN109727092A (en) * | 2018-12-15 | 2019-05-07 | 深圳壹账通智能科技有限公司 | Products Show method, apparatus, computer equipment and storage medium based on AI |
| CN110310169A (en) * | 2019-05-22 | 2019-10-08 | 深圳壹账通智能科技有限公司 | Information-pushing method, device, equipment and medium based on interest value |
| CN110430477A (en) * | 2019-08-12 | 2019-11-08 | 广州华多网络科技有限公司 | Recommended method, device, computer equipment and the storage medium of live content |
| CN110781376A (en) * | 2019-08-30 | 2020-02-11 | 腾讯科技（深圳）有限公司 | Information recommendation method, device, equipment and storage medium |
| CN111276020A (en) * | 2020-03-23 | 2020-06-12 | 广东工业大学 | Question-answer interaction system and method for online education platform |
| CN111782943A (en) * | 2020-06-24 | 2020-10-16 | 中国平安财产保险股份有限公司 | Information recommendation method, device, equipment and medium based on historical data record |
| CN111836106A (en) * | 2020-07-29 | 2020-10-27 | 深圳市睿策者科技有限公司 | Online video playing monitoring processing method and device, computer and storage medium |
| CN112040338A (en) * | 2020-07-31 | 2020-12-04 | 中国建设银行股份有限公司 | Video playing cheating detection method and device and electronic equipment |
| CN112115299A (en) * | 2020-09-17 | 2020-12-22 | 北京百度网讯科技有限公司 | Video searching method and device, recommendation method, electronic device and storage medium |
| CN112351288A (en) * | 2019-08-07 | 2021-02-09 | 阿里巴巴集团控股有限公司 | Live broadcast information processing method, device, server, terminal and storage medium |
| CN112348549A (en) * | 2020-09-16 | 2021-02-09 | 广州阿凡提电子科技有限公司 | Advertisement operation method, intelligent terminal and storage device |
| KR20210025422A (en) * | 2019-08-27 | 2021-03-09 | 주식회사 앱플러 | Method for recommending goods based on multiple video stream using video interaction choices |
| CN113254712A (en) * | 2021-05-12 | 2021-08-13 | 北京百度网讯科技有限公司 | Video matching method, video processing device, electronic equipment and medium |
| CN113747249A (en) * | 2021-07-30 | 2021-12-03 | 北京达佳互联信息技术有限公司 | Live broadcast problem processing method and device and electronic equipment |
| CN114095738A (en) * | 2020-07-30 | 2022-02-25 | 京东方科技集团股份有限公司 | Video and live broadcast processing method, live broadcast system, electronic device, terminal and medium |
| CN114430490A (en) * | 2022-01-20 | 2022-05-03 | 阿里巴巴（中国）有限公司 | Live question and answer and interface display method and computer storage medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140030688A1 (en) * | 2012-07-25 | 2014-01-30 | Armitage Sheffield, Llc | Systems, methods and program products for collecting and displaying query responses over a data network |
| US20180348878A1 (en) * | 2017-06-05 | 2018-12-06 | Ethan Koplowitz | Service Provider to Customer Gateway System |
| US10616625B2 (en) * | 2018-05-21 | 2020-04-07 | Hulu, LLC | Reinforcement learning network for recommendation system in video delivery system |
-
2022
- 2022-06-17 CN CN202210693360.9A patent/CN114866818B/en active Active
Patent Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017107453A1 (en) * | 2015-12-23 | 2017-06-29 | 乐视控股（北京）有限公司 | Video content recommendation method, device, and system |
| CN105959736A (en) * | 2016-04-29 | 2016-09-21 | 广东小天才科技有限公司 | Recommendation method and device for tutoring video |
| WO2018023665A1 (en) * | 2016-08-05 | 2018-02-08 | 吴晓敏 | Data acquisition method for video recommendation technology and video recommendation system |
| CN106878819A (en) * | 2017-01-20 | 2017-06-20 | 合网络技术（北京）有限公司 | The method, system and device of information exchange in a kind of network direct broadcasting |
| CN107423326A (en) * | 2017-04-11 | 2017-12-01 | 广州亿码科技有限公司 | A kind of recommendation and result queries method and system based on answer-mode |
| CN107888950A (en) * | 2017-11-09 | 2018-04-06 | 福州瑞芯微电子股份有限公司 | A kind of method and system for recommending video |
| CN109727092A (en) * | 2018-12-15 | 2019-05-07 | 深圳壹账通智能科技有限公司 | Products Show method, apparatus, computer equipment and storage medium based on AI |
| CN110310169A (en) * | 2019-05-22 | 2019-10-08 | 深圳壹账通智能科技有限公司 | Information-pushing method, device, equipment and medium based on interest value |
| CN112351288A (en) * | 2019-08-07 | 2021-02-09 | 阿里巴巴集团控股有限公司 | Live broadcast information processing method, device, server, terminal and storage medium |
| CN110430477A (en) * | 2019-08-12 | 2019-11-08 | 广州华多网络科技有限公司 | Recommended method, device, computer equipment and the storage medium of live content |
| KR20210025422A (en) * | 2019-08-27 | 2021-03-09 | 주식회사 앱플러 | Method for recommending goods based on multiple video stream using video interaction choices |
| CN110781376A (en) * | 2019-08-30 | 2020-02-11 | 腾讯科技（深圳）有限公司 | Information recommendation method, device, equipment and storage medium |
| CN111276020A (en) * | 2020-03-23 | 2020-06-12 | 广东工业大学 | Question-answer interaction system and method for online education platform |
| CN111782943A (en) * | 2020-06-24 | 2020-10-16 | 中国平安财产保险股份有限公司 | Information recommendation method, device, equipment and medium based on historical data record |
| CN111836106A (en) * | 2020-07-29 | 2020-10-27 | 深圳市睿策者科技有限公司 | Online video playing monitoring processing method and device, computer and storage medium |
| CN114095738A (en) * | 2020-07-30 | 2022-02-25 | 京东方科技集团股份有限公司 | Video and live broadcast processing method, live broadcast system, electronic device, terminal and medium |
| CN112040338A (en) * | 2020-07-31 | 2020-12-04 | 中国建设银行股份有限公司 | Video playing cheating detection method and device and electronic equipment |
| CN112348549A (en) * | 2020-09-16 | 2021-02-09 | 广州阿凡提电子科技有限公司 | Advertisement operation method, intelligent terminal and storage device |
| CN112115299A (en) * | 2020-09-17 | 2020-12-22 | 北京百度网讯科技有限公司 | Video searching method and device, recommendation method, electronic device and storage medium |
| CN113254712A (en) * | 2021-05-12 | 2021-08-13 | 北京百度网讯科技有限公司 | Video matching method, video processing device, electronic equipment and medium |
| CN113747249A (en) * | 2021-07-30 | 2021-12-03 | 北京达佳互联信息技术有限公司 | Live broadcast problem processing method and device and electronic equipment |
| CN114430490A (en) * | 2022-01-20 | 2022-05-03 | 阿里巴巴（中国）有限公司 | Live question and answer and interface display method and computer storage medium |
Non-Patent Citations (2)
| Title |
|---|
| Yonghe Zhang ; Weichen Jia ; Chunying Zhu ; Ying Song. EVOV: A video recommendation system to support sustainable vocabulary learning.《2015 IEEE International Conference on Teaching, Assessment, and Learning for Engineering (TALE)》.2015,全文. * |
| 基于用户行为与内容综合分析评估的视频推荐方法研究;杨箭;;电子技术与软件工程;20160701(第13期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114866818A (en) | 2022-08-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112632385B (en) | Course recommendation method, course recommendation device, computer equipment and medium | |
| CN111444428A (en) | Information recommendation method and device based on artificial intelligence, electronic equipment and storage medium | |
| CN114648392B (en) | Product recommendation method and device based on user portrait, electronic equipment and medium | |
| CN113220734A (en) | Course recommendation method and device, computer equipment and storage medium | |
| CN116821475B (en) | Video recommendation method and device based on client data and computer equipment | |
| CN113590945A (en) | Book recommendation method and device based on user borrowing behavior-interest prediction | |
| WO2024148918A1 (en) | Method and apparatus for training cross-domain recommendation model, and device, medium and product | |
| CN112507141B (en) | Investigation task generation method, investigation task generation device, computer equipment and storage medium | |
| CN117314586A (en) | Product recommendation method, device, computer equipment and storage medium | |
| CN117234505A (en) | Interactive page generation method, device, equipment and storage medium thereof | |
| CN117194779A (en) | Marketing system optimization method, device and equipment based on artificial intelligence | |
| CN116703515A (en) | Recommendation method and device based on artificial intelligence, computer equipment and storage medium | |
| CN111127057B (en) | Multi-dimensional user portrait recovery method | |
| CN116701593A (en) | Chinese question-answering model training method based on GraphQL and related equipment thereof | |
| CN114866818B (en) | Video recommendation method, device, computer equipment and storage medium | |
| CN112084408B (en) | List data screening method, device, computer equipment and storage medium | |
| CN116166858A (en) | Information recommendation method, device, equipment and storage medium based on artificial intelligence | |
| CN112035740B (en) | Project use time length prediction method, device, equipment and storage medium | |
| CN112069807A (en) | Text data theme extraction method and device, computer equipment and storage medium | |
| CN113792549B (en) | User intention recognition method, device, computer equipment and storage medium | |
| CN116957685A (en) | Advertisement recommendation method, device, equipment and medium | |
| CN116542779A (en) | Product recommendation method, device, equipment and storage medium based on artificial intelligence | |
| CN116757771A (en) | Scheme recommendation method, device, equipment and storage medium based on artificial intelligence | |
| CN117493563A (en) | Session intention analysis method, device, equipment and storage medium thereof | |
| CN116843935A (en) | Material data clustering method and related device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |