CN113095884B - Television member user recommendation method and system based on user feedback - Google Patents
Television member user recommendation method and system based on user feedback Download PDFInfo
- Publication number
- CN113095884B CN113095884B CN202110431728.XA CN202110431728A CN113095884B CN 113095884 B CN113095884 B CN 113095884B CN 202110431728 A CN202110431728 A CN 202110431728A CN 113095884 B CN113095884 B CN 113095884B
- Authority
- CN
- China
- Prior art keywords
- user
- users
- seed
- interest
- vector
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Economics (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Game Theory and Decision Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention belongs to the field of signal processing, and provides a television member user recommendation method and system based on user feedback. The method comprises the steps of obtaining payment behavior information in a historical set time period, marking users with payment behaviors in the historical set time period as seed users, and marking users without payment behaviors as candidate users; extracting and depicting user interest according to video playing behaviors of a user to obtain a user interest expression vector, splicing the user interest expression vector with a user portrait, and obtaining a user embedded expression vector through a full connection layer; clustering the seed users to obtain a plurality of seed user groups, representing the average vector of each seed user group as a corresponding user group vector, calculating the similarity between the candidate users and the seed user groups, selecting the users with the similarity exceeding a set threshold value from the candidate users as expansion users, and recommending the members.
Description
Technical Field
The invention belongs to the field of signal processing, and particularly relates to a television member user recommendation method and system based on user feedback.
Background
The statements in this section merely provide background information related to the present disclosure and may not constitute prior art.
In the current large video networks and platforms, such as network platforms like Youku and Aiqiyi, there are abundant video resources including TV plays, movies, fantasy, etc., and these videos are provided for the users of the platforms to watch. The website platform launches member package service aiming at the videos, the package contains a plurality of videos, and the videos can be watched after the user pays for purchasing the package. Moreover, the income of the member package accounts for a large proportion of the income of the current video website, so that the platform income can be increased and the user experience can be improved by finding users who may buy the member package from non-member users.
The inventor finds that behavior feedback such as subsequent playing history is still related to member recommendation tasks after a user purchases a package in a television member user expansion/recommendation scene, however, existing television member user potential prediction or recommendation does not consider television member user behavior feedback information, and therefore the precision of a television member user potential prediction result and the accuracy of a recommendation user becoming a television member are reduced.
Disclosure of Invention
In order to solve the technical problems in the background art, the invention provides a television member user recommendation method and system based on user feedback, which can accurately depict the representation of the part of users by continuously recording the subsequent watching operation information of the users after the users purchase member packages, so as to improve the performance of the member user expansion method.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention provides a television member user recommendation method based on user feedback.
A television member user recommendation method based on user feedback comprises the following steps:
acquiring payment behavior information in a historical set time period, marking users who have payment behaviors in the historical set time period as seed users, and marking users who have not payment behaviors as candidate users;
extracting and depicting user interest according to video playing behaviors of a user to obtain a user interest expression vector, splicing the user interest expression vector with a user portrait, and obtaining a user embedded expression vector through a full connection layer;
clustering the seed users to obtain a plurality of seed user groups, representing the average vector of each seed user group as a corresponding user group vector, calculating the similarity between the candidate users and the seed user groups, selecting the users with the similarity exceeding a set threshold value from the candidate users as expansion users, and recommending the members.
As an embodiment, for a seed user, the process of representing the user interest representation vector is as follows:
acquiring a play history sequence in a time period set by a seed user;
dividing the play history sequence into a front play sequence and a rear play sequence according to the payment time of the seed user for placing the order;
respectively extracting an extensive film watching interest vector before a user purchases a member package and a film watching interest vector related to the package after the user purchases the member package from the front playing sequence and the rear playing sequence;
and carrying out interest enhancement extraction on the wide viewing interests before purchase by using the viewing interests related to the package to obtain the final interest expression vector of the user.
As one embodiment, a bidirectional GRU module is used for pre-play sequences to extract a broad viewing interest vector before a user purchases a member package.
As one embodiment, the self-attention module is used for the post-play sequence to extract the viewing interest vector associated with the package after the user purchases the member package.
As one embodiment, for the candidate seed user, the user interest expression vector is a user history extensive viewing interest expression vector.
As one implementation mode, the expression process of the user history wide viewing interest expression vector is as follows:
acquiring a play history sequence in a time period set by a candidate seed user;
and extracting historical extensive viewing interests of the user from the pre-playing sequence to obtain a historical extensive viewing interest expression vector of the user.
As an embodiment, a bidirectional GRU module is used to extract historical broad viewing interests of the user for pre-play sequences.
A second aspect of the invention provides a television member user recommendation system based on user feedback.
A television member user recommendation system based on user feedback, comprising:
the system comprises a user dividing module, a data processing module and a data processing module, wherein the user dividing module is used for acquiring payment behavior information in a historical set time period, marking users who have payment behaviors in the historical set time period as seed users and marking users who have not payment behaviors as candidate users;
the user vector representation module is used for extracting and depicting user interest according to video playing behaviors of a user to obtain a user interest representation vector, then splicing the user interest representation vector with a user portrait, and obtaining a user embedded representation vector through a full connection layer;
and the user expansion recommending module is used for clustering the seed users to obtain a plurality of seed user groups, the average vector of each seed user group is used as the corresponding user group vector to represent, the similarity between the candidate users and the seed user groups is calculated, and the users with the similarity exceeding a set threshold value are selected from the candidate users to be used as expansion users and member recommendation is carried out.
A third aspect of the invention provides a computer-readable storage medium.
A computer-readable storage medium, on which a computer program is stored, which when executed by a processor, performs the steps in the method for recommending television member users based on user feedback as described above.
A fourth aspect of the invention provides a computer apparatus.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor when executing the program implementing the steps in the user feedback based television member user recommendation method as described above.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides a television member user expansion method based on user feedback, which continuously records the subsequent watching operation after a user purchases a member package, and uses the information to further accurately depict the representation of the part of the user, thereby more accurately representing the interest representation of the user to the package and improving the performance of the member user expansion method.
Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
FIG. 1 is a model framework diagram of a television member user recommendation method based on user feedback according to an embodiment of the present invention;
FIG. 2 is a flow chart of a television member user recommendation method based on user feedback according to an embodiment of the present invention;
fig. 3 is a user division processing diagram of the embodiment of the present invention.
Detailed Description
The invention is further described with reference to the following figures and examples.
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. 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 invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
Example one
Referring to fig. 1 and fig. 2, a television member user recommendation method based on user feedback according to this embodiment specifically includes the following steps:
step 1: and acquiring the information of the payment behaviors in the historical set time period, marking the users with the payment behaviors in the historical set time period as seed users, and marking the users without the payment behaviors as candidate users.
For ease of description, a week is used for the scale. And acquiring the purchasing data information of the member package in the past one week to obtain a user id list of successfully purchasing the package and the corresponding ordering time.
And marking the users who purchase the member packages as seed users, and marking the users who do not purchase the member packages as candidate users.
The users who successfully purchased the package are the seed users, while the current non-member users are the candidate users, and the extended users are selected from the candidate users, as shown in fig. 3.
Step 2: and extracting and depicting user interest according to the video playing behavior of the user to obtain a user interest expression vector, splicing the user interest expression vector with the user portrait, and obtaining a user embedded expression vector through a full connection layer.
For seed user representation learning:
in step 211, a play history sequence in a user history time period (for example, one month in the past) is obtained.
In the embodiment, the play history of each user in a month before the current time is selected, and the play history includes video id and play time information.
Step 212, the play history sequence is divided into a pre-play sequence and a post-play sequence according to the payment time of the seed user.
And dividing the play history record into play history sequences before and after purchase according to the order placing time of the seed user in the order information, and obtaining the embedded expression e of the corresponding video.
Step 213, extracting the wide viewing interest vector of the user before purchasing the member package by using the bidirectional GRU module aiming at the pre-playing sequence; the self-attention module is used for the post-play sequence to extract the viewing interest vectors of the user that are more relevant to the package after purchasing the member package.
For the play-before-purchase history sequence, a bidirectional GRU model is used, video embedding representation is carried out, meanwhile, the change situation of the video in the past and in the future is considered, a play-before-purchase video embedding representation matrix PS is obtained, and the GRU calculation formula is as follows:
wherein r is t Is a reset gate, z t It is the update of the door that is,is a candidate activation function, h t Is an activation function, e t Is the input embedding vector at the t-th position in the sequence, σ isThe function is activated. Obtaining a bi-directional representationAnd PS = [ h ] 1 ,h 2 ,...]。
For the post-purchase play history sequence, extracting the interest distribution of the user after purchasing the set of videos by using a self-attention model to obtain a post-purchase video embedded representation AS, wherein the corresponding calculation formula is AS follows:
Q=W Q E,K=W K E,V=W V E
AS=avgpoolng(Att)
wherein E is a post-playback sequence embedding matrix, W is a parameter matrix, d K For the dimension size of K, avgpoling () is an average pooling operation.
And 214, performing interest enhancement extraction on the obtained film watching interests related to the package to the wide film watching interests before purchase to obtain the final interest expression vector of the user.
Embedding and representing PS and AS based on the obtained before and after purchase, using an activation unit to carry out interest enhancement representation on the PS by the AS, correcting the interest distribution before purchase to obtain the real interest vector IP of the user for the package, wherein the corresponding calculation formula is AS follows:
and step 215, splicing the user interest expression vector and the user portrait, and obtaining a final user embedded expression vector UI through a full connection layer.
UI=[IP,UP]
In this case, UP represents a user image.
And calculating a loss function by using the watching conditions of the videos which are currently hot played in the user playing history. The popular film to be viewed is marked with label 1, otherwise, the calculation is 0,loss as follows:
where X represents the set of hot-cast videos we have selected, y i E {0,1} is the corresponding label.
For candidate user representation learning, the partial computation manner is the same as the seed user representation corresponding partial learning computation manner.
Step 221, obtaining the play history sequence in the user history time period (for example, the past month). The calculation method is the same as above.
Step 222, using the bidirectional GRU module for the pre-play sequence to extract the historical broad viewing interest PS of the user. The calculation method is the same as above.
And 223, splicing the user historical wide viewing interest expression vector with the user portrait, and obtaining a final user embedded expression vector UI through a full connection layer: UI = [ PS, UP ].
And step 3: clustering the seed users to obtain a plurality of seed user groups, representing the average vector of each seed user group as a corresponding user group vector, calculating the similarity between the candidate users and the seed user groups, and selecting the users with the similarity exceeding a set threshold value from the candidate users as the expansion users and recommending the members.
In specific implementation, for seed users, a K-means method is used for clustering seed user groups to obtain K users [ G ] of different interest groups 1 ,G 2 ,...,G K ]。
[G 1 ,G 2 ,..,G K ]=K-means(Ul 1 ,UI 2 ,..,UI n )
Wherein K is a hyper-parameter, n is the number of seed users, and G represents a seed user group.
For each user population, their average vector is calculated as the user population vector representation GE.
GE=avgpooling(UI),for UIinG
For each candidate user, calculating the similarity with the user group vector as the attribution score scorei of the user and each seed user group.
score i =cosine(UI c ,GE i )
Therein, UI c Embedded representation vectors representing candidate users, GE i A population vector representation representing a seed user population i.
The group with the highest score is selected as the user's home group, and the score is the user's expansion score.
And selecting the users with the scores higher than the set threshold value as the extension users.
And (3) calculating a loss function, namely calculating model loss by adopting a binary cross entropy loss function, wherein the calculation mode is as follows:
wherein D represents a training set, x and y represent user interest embedding vectors and corresponding label values respectively, namely whether a user is an extended user or not, and p (x) is a user extension part to predict whether the user is an extended user or not, namely whether the user can purchase packages in the future week or not.
Through the analysis of the actual scene user data, after a user buys a package, the playing ratio of the user to the video in the package is increased by a large extent, and the average playing ratio of the video in the package is increased by about 20% before and after the package is bought by the part of users who buy the package, and the amount of high-ratio users is obviously increased. According to the television member user recommendation method based on user feedback, after a user purchases a member package, the user continuously records the subsequent watching operation, and the information is used for further and accurately depicting the representation of the part of the user, so that the interest representation of the user on the package is more accurately represented, and the performance of the member user expansion method is improved.
Example two
The embodiment provides a television member user recommendation system based on user feedback, which specifically comprises the following modules:
the user dividing module is used for acquiring the information of the payment behaviors in the historical set time period, marking the users with the payment behaviors in the historical set time period as seed users, and marking the users without the payment behaviors as candidate users;
the user vector representation module is used for extracting and depicting user interest according to video playing behaviors of a user to obtain a user interest representation vector, then splicing the user interest representation vector with a user portrait and obtaining a user embedded representation vector through a full connection layer;
and the user expansion recommendation module is used for clustering the seed users to obtain a plurality of seed user groups, the average vector of each seed user group is used as the corresponding user group vector to represent, the similarity between the candidate users and the seed user groups is calculated, and the users with the similarity exceeding a set threshold value are selected from the candidate users to be used as expansion users and member recommendation is carried out.
It should be noted that, each module in the television member user recommendation system based on user feedback in the embodiment corresponds to each step in the television member user recommendation method based on user feedback in the first embodiment one by one, and the specific implementation process is the same, which is not described herein again.
EXAMPLE III
The present embodiment provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor, implements the steps in the television member user recommendation method based on user feedback as described above.
Example four
The embodiment provides a computer device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the steps of the television member user recommendation method based on user feedback.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (9)
1. A television member user recommendation method based on user feedback is characterized by comprising the following steps:
acquiring payment behavior information in a historical set time period, marking users who have payment behaviors in the historical set time period as seed users, and marking users who have not payment behaviors as candidate users;
extracting and depicting user interest according to video playing behaviors of a user to obtain a user interest expression vector, splicing the user interest expression vector with a user portrait, and obtaining a user embedded expression vector through a full connection layer;
clustering seed users to obtain a plurality of seed user groups, representing the average vector of each seed user group as a corresponding user group vector, calculating the similarity between candidate users and the seed user groups, selecting the users with the similarity exceeding a set threshold value from the candidate users as expansion users, and recommending members;
for the seed user, the expression process of the user interest expression vector is as follows:
acquiring a play history sequence in a time period set by a seed user;
dividing the play history sequence into a front play sequence and a rear play sequence according to the payment time of the seed user for placing the order;
respectively extracting an extensive film watching interest vector before a user purchases a member package and a film watching interest vector related to the package after the user purchases the member package from the front playing sequence and the rear playing sequence;
and carrying out interest enhancement extraction on the wide viewing interests before purchase by using the viewing interests related to the package to obtain the final interest expression vector of the user.
2. The method of claim 1, wherein a bi-directional GRU module is used for pre-play sequences to extract a broad viewing interest vector from the user prior to purchasing the member package.
3. The method of claim 1, wherein a self-attention module is used for the post-play sequence to extract a viewing interest vector associated with the package after the user purchases the member package.
4. The method as claimed in claim 1, wherein the user interest expression vector is a user history broad viewing interest expression vector for the candidate seed user.
5. The method as claimed in claim 4, wherein the step of representing the historical broad viewing interest expression vector comprises the steps of:
acquiring a play history sequence in a time period set by a candidate seed user;
and extracting historical extensive viewing interests of the user from the pre-playing sequence to obtain a historical extensive viewing interest expression vector of the user.
6. The method of claim 5, wherein the bidirectional GRU module is used for pre-play sequences to extract historical broad viewing interests of the user.
7. A television member user recommendation system based on user feedback, comprising:
the system comprises a user dividing module, a data processing module and a data processing module, wherein the user dividing module is used for acquiring payment behavior information in a historical set time period, marking users who have payment behaviors in the historical set time period as seed users and marking users who have not payment behaviors as candidate users;
the user vector representation module is used for extracting and depicting user interest according to video playing behaviors of a user to obtain a user interest representation vector, then splicing the user interest representation vector with a user portrait, and obtaining a user embedded representation vector through a full connection layer;
the user expansion recommendation module is used for clustering the seed users to obtain a plurality of seed user groups, the average vector of each seed user group is used as the corresponding user group vector to represent, the similarity between the candidate users and the seed user groups is calculated, and the users with the similarity exceeding a set threshold value are selected from the candidate users to be used as expansion users and member recommendation is carried out;
for the seed user, the expression process of the user interest expression vector is as follows:
acquiring a play history sequence in a time period set by a seed user;
dividing the play history sequence into a front play sequence and a rear play sequence according to the payment time of the seed user for placing the order;
respectively extracting a wide film watching interest vector before a user purchases a member package and a film watching interest vector related to the package after the user purchases the member package from the front playing sequence and the back playing sequence;
and carrying out interest enhancement extraction on the wide viewing interests before purchase by using the viewing interests related to the package to obtain the final interest expression vector of the user.
8. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for television member user recommendation based on user feedback according to any one of claims 1-6.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program performs the steps of the method for television member user recommendation based on user feedback as claimed in any one of claims 1-6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110431728.XA CN113095884B (en) | 2021-04-21 | 2021-04-21 | Television member user recommendation method and system based on user feedback |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110431728.XA CN113095884B (en) | 2021-04-21 | 2021-04-21 | Television member user recommendation method and system based on user feedback |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113095884A CN113095884A (en) | 2021-07-09 |
CN113095884B true CN113095884B (en) | 2022-12-06 |
Family
ID=76679034
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110431728.XA Active CN113095884B (en) | 2021-04-21 | 2021-04-21 | Television member user recommendation method and system based on user feedback |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113095884B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116934389B (en) * | 2023-06-12 | 2024-02-23 | 嘉兴华数广电网络有限公司 | Digital television value ticket card management system based on cloud computing and cross-platform technology |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103714139A (en) * | 2013-12-20 | 2014-04-09 | 华南理工大学 | Parallel data mining method for identifying a mass of mobile client bases |
CN110348930A (en) * | 2018-04-08 | 2019-10-18 | 阿里巴巴集团控股有限公司 | Business object data processing method, the recommended method of business object information and device |
CN111461841A (en) * | 2020-04-07 | 2020-07-28 | 腾讯云计算(北京)有限责任公司 | Article recommendation method, device, server and storage medium |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109214616B (en) * | 2017-06-29 | 2023-04-07 | 上海寒武纪信息科技有限公司 | Information processing device, system and method |
CN108596705A (en) * | 2018-03-23 | 2018-09-28 | 郑州大学西亚斯国际学院 | A kind of commodity suitable for e-commerce recommend method and system with information classification |
CN109710805B (en) * | 2018-12-13 | 2022-03-04 | 百度在线网络技术(北京)有限公司 | Video interaction method and device based on interest cluster |
-
2021
- 2021-04-21 CN CN202110431728.XA patent/CN113095884B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103714139A (en) * | 2013-12-20 | 2014-04-09 | 华南理工大学 | Parallel data mining method for identifying a mass of mobile client bases |
CN110348930A (en) * | 2018-04-08 | 2019-10-18 | 阿里巴巴集团控股有限公司 | Business object data processing method, the recommended method of business object information and device |
CN111461841A (en) * | 2020-04-07 | 2020-07-28 | 腾讯云计算(北京)有限责任公司 | Article recommendation method, device, server and storage medium |
Non-Patent Citations (4)
Title |
---|
AE-UPCP: Seeking Potential Membership Users by Audience Expansion Combining User Preference with Consumption Pattern;Xiaokang Xu .etc;《Database Systems for Advanced Applications 2021》;20210406;p392-399 * |
Buying or Browsing? : Predicting Real-time Purchasing Intent using Att ention-based Deep Network with Multiple Behavior;Long Guo .etc;《KDD ’19》;20190808;全文 * |
Deep Interest Evolution Network for Click-Through Rate Prediction;Guorui Zhou .etc;《Association for the Advancement of Artificial》;20181116;全文 * |
MISS: A Multi-user Identification Network for Shared-Account Session-Aware Recommendation;Xinyu Wen .etc;《Database Systems for Advanced Applications 2021》;20210406;全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN113095884A (en) | 2021-07-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109145784B (en) | Method and apparatus for processing video | |
CN106326391B (en) | Multimedia resource recommendation method and device | |
CN111754267B (en) | Data processing method and system based on block chain | |
KR102203253B1 (en) | Rating augmentation and item recommendation method and system based on generative adversarial networks | |
CN110232403A (en) | A kind of Tag Estimation method, apparatus, electronic equipment and medium | |
TW201340690A (en) | Video recommendation system and method thereof | |
CN109598527A (en) | Analysis of advertising results method and device | |
CN106682953B (en) | Advertisement pushing method and pushing device | |
US20230353828A1 (en) | Model-based data processing method and apparatus | |
CN105308636A (en) | Apparatus and method for providing virtual advertisement | |
US20150310498A1 (en) | Computer-Implemented Systems and Methods for Generating Media Content Recommendations for Subsequent Works | |
CN115100717B (en) | Training method of feature extraction model, and recognition method and device of cartoon object | |
CN112232546A (en) | Recommendation probability estimation method and device, electronic equipment and storage medium | |
CN113095884B (en) | Television member user recommendation method and system based on user feedback | |
CN104967690A (en) | Information push method and device | |
CN111046230A (en) | Content recommendation method and device, electronic equipment and storable medium | |
CN110704728A (en) | Information recommendation method and device, electronic equipment and storage medium | |
CN115119014A (en) | Video processing method, and training method and device of frame insertion quantity model | |
CN117909586A (en) | Content recommendation method, device, electronic equipment and storage medium | |
CN113095883A (en) | Video payment user prediction method and system based on deep cross attention network | |
CN108769831A (en) | The generation method and device of video advance notice | |
CN116261009B (en) | Video detection method, device, equipment and medium for intelligently converting video audience | |
US20220358405A1 (en) | System and Method for Generating Artificial Intelligence Driven Insights | |
CN116028708A (en) | Training method and device for recommendation model | |
CN113240004B (en) | Video information determining method, device, electronic equipment and storage medium |
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 |