CN108243357A - A kind of video recommendation method and device - Google Patents
A kind of video recommendation method and device Download PDFInfo
- Publication number
- CN108243357A CN108243357A CN201810072044.3A CN201810072044A CN108243357A CN 108243357 A CN108243357 A CN 108243357A CN 201810072044 A CN201810072044 A CN 201810072044A CN 108243357 A CN108243357 A CN 108243357A
- Authority
- CN
- China
- Prior art keywords
- video
- user
- feature
- sample data
- scoring
- 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.)
- Pending
Links
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]
- H04N21/40—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]
- H04N21/20—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]
- H04N21/20—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
- H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
- H04N21/25866—Management of end-user data
- H04N21/25891—Management of end-user data being end-user preferences
-
- 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
- H04N21/4667—Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Graphics (AREA)
- Computing Systems (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of video recommendation method and device, including：According to user characteristics and the interest preference model of video features training user；After the initial recommendation video of target user is obtained, according to preset user interest preference model, the scoring of video is recommended in prediction, and according to the scoring for recommending video, obtains the preferred video of target user, and the preferred video is recommended target user.When recommending as a result, video, user characteristics and video features are further contemplated so that the video specific aim recommended for user is stronger.
Description
Technical field
The present invention relates to video recommendations field more particularly to a kind of video recommendation methods and device.
Background technology
Video website or video APP would generally be supplied to the thousands of video content of user to be watched for user, also,
Can all there be the emerging video of substantial amounts by video daily.In face of so huge information content, in order to make user fast
Speed finds interested video, enhances user experience, and video recommendations technology is come into being.
In the prior art, the mode of generally use collaboration filtering recommends video, and the mode of filtering is cooperateed with not examine
Consider the feature of user and the feature of video, obtained recommendation video genre is various, not strong for the specific aim of user.
Invention content
In view of this, an embodiment of the present invention provides a kind of video recommendation method and devices, solve and obtain in the prior art
The problem of recommendation video genre arrived is various, and specific aim is poor.
The invention discloses a kind of video recommendation method, including：
Obtain the initial recommendation video of target user；
According to preset user interest preference model, the scoring for recommending video is predicted；The user interest preference mould
Type obtains after being trained by preset method to positive sample data and negative sample data；The positive sample data include
The video features of user characteristics and the participation video of the user；The negative sample data include user characteristics and the user not
Participate in the video features of video；
According to the scoring for recommending video, the preferred video of the target user is determined；
The preferred video is sent to the target user.
Optionally, it further includes：
According to the user-Video Events, the feature of user and the spy of video that the user-Video Events include are extracted
Sign；
Positive sample is generated according to the feature of participation video of user in the user video event and the feature of the user
Data；
According in the user-Video Events, the feature for having neither part nor lot in video of the user and the feature of the user are given birth to
Into negative sample data；
The positive sample data and the negative sample data are trained using preset method, it is inclined to obtain user interest
Good model, so that the user interest preference model scores to video according to the feature of user and the feature of video.
Optionally, the preset method includes：GBDT iteration decision Tree algorithms.
Optionally, which is characterized in that
The user characteristics include：Age, gender, region；
The video features include：Video type, video tab.
Optionally, it is described to obtain the preliminary recommendation video of target user, including：
Obtain user-Video Events；
According to user-Video Events, the similar users of target user are calculated；
According to the similar users of the target user, the initial recommendation video of the target user is generated.
Optionally, it is described according to user-Video Events, the similar users of target user are calculated, including：
Obtain the scoring of the video of each user；
User-video matrix is built according to the scoring of the video of each user；
Based on Similarity Algorithm, according to the user-video matrix, the similar users of the target user are calculated.
Optionally, it is described according to preset user interest preference model, predict the scoring for recommending video, including：
Extract the user characteristics of the target user；
The user characteristics of the target user and the recommendation video are input in the user interest preference model,
To predict the scoring for recommending video.
The embodiment of the invention also discloses a kind of video recommendations device, including：
Acquiring unit, for obtaining the initial recommendation video of target user；
Predicting unit, for according to preset user preferences modeling, predicting the scoring for recommending video；The user is emerging
Interesting preference pattern is by preset method to being obtained after positive sample data and the training of negative sample data；The positive sample data
Including：The video features of user characteristics and the participation video of the user；The negative sample data include user characteristics and described
User has neither part nor lot in the video features of video；
Determination unit, for according to the scoring for recommending video, determining the preferred video of the target user；
Transmitting element, for the preferred video to be sent to the target user.
Optionally, it further includes：
Extraction unit, for according to the user-Video Events, extracting the user's that the user-Video Events include
The feature of feature and video；
First generation unit, for according to the feature of the participation video of user and the user in the user video event
Feature generation positive sample data；
Second generation unit, for according in the user-Video Events, the feature for having neither part nor lot in video of the user and
The feature generation negative sample data of the user；
Training unit, for being trained using preset method to the positive sample data and the negative sample data,
Obtain user interest preference model so that the user interest preference model according to the feature of user and the feature of video to video
It scores.
10th, the apparatus according to claim 1, which is characterized in that the acquiring unit, including：
First obtains subelement, for obtaining user-Video Events；
Computation subunit, for according to user-Video Events, calculating the similar users of target user；
Subelement is generated, for the similar users according to the target user, generates the initial recommendation of the target user
Video.
An embodiment of the present invention provides a kind of video recommendation method and device, including：According to user characteristics and video features
The interest preference model of training user；It is inclined according to preset user interest after the initial recommendation video of target user is obtained
The scoring of video is recommended in good model, prediction, and according to the scoring for recommending video, obtains the preferred video of target user, and
The preferred video is recommended into target user.When recommending as a result, video, further contemplate user characteristics and video is special
Sign so that the video specific aim recommended for user is stronger.
Description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The embodiment of invention, for those of ordinary skill in the art, without creative efforts, can also basis
The attached drawing of offer obtains other attached drawings.
Fig. 1 shows a kind of flow diagram of video recommendation method provided in an embodiment of the present invention；
Fig. 2 shows a kind of flow signals of training method of user interest preference model provided in an embodiment of the present invention
Figure；
Fig. 3 shows a kind of structure diagram of video recommendations device provided in an embodiment of the present invention.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present invention, the technical solution in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other without making creative work
Embodiment shall fall within the protection scope of the present invention.
With reference to figure 1, a kind of flow diagram of video recommendation method provided in an embodiment of the present invention is shown, in this implementation
In example, this method includes：
S101：Obtain the initial recommendation video of target user；
Wherein, it is relevant with target user to recommend video, can recommend the video of target user.
In the present embodiment, the acquisition modes of initial recommendation video can be including a variety of, in the present embodiment, without limit
It is fixed.For example, following steps 1 may be used) to the mode of step 3)：
1) user-Video Events are obtained；
2) according to user-Video Events, the similar users of target user are calculated；
3) according to the similar users of the target user, the initial recommendation video of the target user is generated.
According to the similar users of the target user, the initial recommendation video of the target user is generated；Wherein, user-
Video Events include user information and video information, wherein, video information includes：Video type, video tab and video
Score information.Wherein, the score information of video can represent user to video interested degree, such as：Video-see, video
Collection and video download correspond to different scorings.
In the present embodiment, can the similar users of target user be calculated according to the scoring of video in user-Video Events,
Can specifically it include：
Obtain the scoring of the video of each user；
User-video matrix is built according to the scoring of the video of each user；
Based on Similarity Algorithm, according to the user-video matrix, the similar users of the target user are calculated.
It illustrates：User-video matrix is as shown in table 1 below, and wherein User1 ... Userm is user id,
Item1 ... Itemn are video id, and Rmn represents scoring of the user to different video, according to the user-video matrix, Yi Jixiang
Like property algorithm, it may be determined that go out the similar users of target user.
Table 1
| Item1 | … | Itemk | … | Itemn | |
| User1 | R1,1 | … | R1, k | … | R1, n |
| … | … | … | … | … | … |
| Userk | RK, 1 | … | Rk, k | … | RK, n |
| … | … | … | … | … | … |
| Userm | RM, 1 | … | RM, k | … | RM, n |
In the present embodiment, after obtaining similar users, it can be generated according to the participation video with similar users and recommend video,
The participation video of middle similar users can be with the related video of similar users, such as can include：Similar users viewing, under
The video for carrying or collecting.Wherein, recommend video that can include：With in the related video of similar users, with target user
Not related video.Wherein, can include with the not related video of user：What user did not watched, and downloaded and do not collected
Video.
102：According to preset user interest preference model, the scoring for recommending video is predicted；The user interest is inclined
Good model obtains after being trained by preset method to positive sample data and negative sample data；The positive sample data
The video features of participation video including user characteristics and the user；The negative sample data include user characteristics and the use
Family has neither part nor lot in the video features of video；
In the present embodiment, the initial recommendation video of obtained target user is not special in view of user characteristics and video
Sign, for obtained recommendation video than wide, specific aim is poor, can be according to user spy in order to improve the specific aim for recommending video
The trained user interest preference model of video features of seeking peace, screens initial video, specifically, S102 includes：
Extract the feature of the target user and the feature for recommending video；
By the feature of the target user and the feature for recommending video, it is input to the user interest preference model
In, to predict the scoring for recommending video.
In the present embodiment, trained user interest preference model can predict the video with certain features be directed to
The scoring of the user of certain features as a result, according to user characteristics and video features, can predict the scoring of video.
Wherein, it for the training process of user interest preference model, can be described in detail in embodiment two, this implementation
In example, repeat no more.
S103：According to the scoring for recommending video, the preferred video of the target user is obtained；
In the present embodiment, after obtaining recommending the scoring of video, it can be obtained according to preset any of which
The preferred video of target user, such as the preferred video of target user can be obtained by following embodiment, specifically, packet
It includes：
Embodiment one：The recommendation video of preset fraction threshold value will be more than in the scoring, as the target user's
Preferred video；
Embodiment two：
According to the scoring for recommending video, the recommendation video is ranked up；
According to ranking results, the preferred video of the target user is obtained.
For example, it may be preferred video of the earlier recommendation video as target user that will sort.
S104：The preferred video is sent to the target user.
In the present embodiment, it can obtained according to user characteristics and the interest preference model of video features training user
After the initial recommendation video of target user, according to preset user interest preference model, the scoring of video is recommended in prediction, and
According to the scoring for recommending video, the preferred video of target user is obtained, and the preferred video is recommended into target user.As a result,
When recommending video, user characteristics and video features are further contemplated so that the video specific aim for user's recommendation is more
By force.
Embodiment two：
With reference to figure 2, a kind of stream of the training clothes method of user interest preference model provided in an embodiment of the present invention is shown
Journey schematic diagram, in the present embodiment, this method includes：
S201：According to the user-Video Events, extract the feature for the user that the user-Video Events include and regard
The feature of frequency；
In the present embodiment, according to user-Video Events, the feature of the user extracted can include：Age, gender,
Domain etc.；The feature of video can include：Video type, video tab viewing number, viewing duration etc..Wherein, for user spy
It seeks peace the information of character property in video features, the form that can be converted to vector or number is indicated, such as：For user
Region in feature can pass through the different region of digital representation；For the video tab in video features, vector can be passed through
Form represent different video tab.
S202：It is generated according to the feature of participation video of user in the user-Video Events and the feature of the user
Positive sample data；
In the present embodiment, the participation video of user can be understood as with the related video of user, can represent that user sees
The video seen, collect or downloaded.
Wherein, the score information of video is not included in positive sample data or the scoring of video can be set to 0.
S203：It is given birth to according to the feature of the non-participating video of user in the user-Video Events and the feature of the user
Into negative sample data；
In the present embodiment, the non-participating video of user can be understood as with the not related video of user, such as：User is not
Viewing, collection and the video do not downloaded.
For example, as shown in table 2 below, wherein, front two row data sample is positive sample data, last column data sample
For negative sample data, wherein, user-age represents the age of user, and user-sex represents the gender of user, and user-area is represented
The region of user, this three parts represent user characteristics；Video-type represents video type, and video-tag represents video tab,
Behavior-type represents the ID of video, number of behavior-count video-sees etc..
Table 2
S204：The positive sample data and the negative sample data are trained using preset method, obtain user
Interest preference model, so that the user interest preference model predicts commenting for video according to the feature of user and the feature of video
Point；
In the present embodiment, positive sample data and negative sample data can be trained by any training method,
In the present embodiment, without limiting.
Preferably, GBDT (English full name can be passed through：Gradient Boosting Decision Tree, Chinese are complete
Claim：Gradient promotes decision tree) algorithm, positive sample data and negative sample data are trained.
By above introduction it is found that positive sample data can represent the interested video of user, negative sample data can be with
Represent the uninterested video of user.By being trained to a large amount of positive sample data and negative sample data, use can be predicted
Family is to the interest level of some video, you can to predict that video is directed to the scoring of some user.
It, can be with by the user interest preference model after positive sample data and the training of negative sample data in the present embodiment
It predicts the scoring of video, and then the video of recommendation can further be screened, obtain more targeted recommendation video.
With reference to figure 3, a kind of structure diagram of video recommendations device provided in an embodiment of the present invention is shown, in this implementation
In example, which includes：
Acquiring unit 301, for obtaining the initial recommendation video of target user；
Predicting unit 302, for according to preset user preferences modeling, predicting the scoring for recommending video；The use
Family interest preference model is by preset method to being obtained after positive sample data and the training of negative sample data；The positive sample
Data include：The video features of user characteristics and the participation video of the user；The negative sample data include user characteristics and
The user has neither part nor lot in the video features of video；
Determination unit 303, for according to the scoring for recommending video, determining the preferred video of the target user；
Transmitting element 304, for the preferred video to be sent to the target user.
Optionally, it further includes：
Extraction unit, for according to the user-Video Events, extracting the user's that the user-Video Events include
The feature of feature and video；
First generation unit, for according to the feature of the participation video of user and the user in the user video event
Feature generation positive sample data；
Second generation unit, for according in the user-Video Events, the feature for having neither part nor lot in video of the user and
The feature generation negative sample data of the user；
Training unit, for being trained using preset method to the positive sample data and the negative sample data,
Obtain user interest preference model so that the user interest preference model according to the feature of user and the feature of video to video
It scores.
Optionally, the preset method includes：GBDT iteration decision Tree algorithms.Optionally,
The user characteristics include：Age, gender, region；
The video features include：Video type, video tab.
Optionally, the acquiring unit, including：
First obtains subelement, for obtaining user-Video Events；
First computation subunit, for according to user-Video Events, calculating the similar users of target user；
Subelement is generated, for the similar users according to the target user, generates the initial recommendation of the target user
Video.
Optionally, computing unit, including：
Second obtains subelement, for obtaining the scoring of the video of each user；
Subelement is built, user-video matrix is built for the scoring of the video according to each user；
Second computation subunit for being based on Similarity Algorithm, according to the user-video matrix, calculates the target
The similar users of user.
Optionally, the predicting unit, including：
Subelement is extracted, for extracting the user characteristics of the target user；
Subelement is predicted, for by the user characteristics of the target user and the recommendation video, being input to the user
In interest preference model, to predict the scoring for recommending video.
Device through this embodiment when recommending video, further contemplates user characteristics and video features, makes
It obtains stronger for the video specific aim of user's recommendation.
It should be noted that each embodiment in this specification is described by the way of progressive, each embodiment weight
Point explanation is all difference from other examples, and just to refer each other for identical similar part between each embodiment.
The foregoing description of the disclosed embodiments enables professional and technical personnel in the field to realize or use the present invention.
A variety of modifications of these embodiments will be apparent for those skilled in the art, it is as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, it is of the invention
The embodiments shown herein is not intended to be limited to, and is to fit to and the principles and novel features disclosed herein phase one
The most wide range caused.
Claims (10)
1. a kind of video recommendation method, which is characterized in that including：
Obtain the initial recommendation video of target user；
According to preset user interest preference model, the scoring for recommending video is predicted；The user interest preference model is
It is obtained after being trained by preset method to positive sample data and negative sample data；The positive sample data include user
The video features of the participation video of feature and the user；The negative sample data include user characteristics and the user has neither part nor lot in
The video features of video；
According to the scoring for recommending video, the preferred video of the target user is determined；
The preferred video is sent to the target user.
2. it according to the method described in claim 1, it is characterized in that, further includes：
According to the user-Video Events, the feature of user and the feature of video that the user-Video Events include are extracted；
Positive sample data are generated according to the feature of participation video of user in the user video event and the feature of the user；
According in the user-Video Events, the feature for having neither part nor lot in video of the user and the feature generation of the user are negative
Sample data；
The positive sample data and the negative sample data are trained using preset method, obtain user interest preference mould
Type, so that the user interest preference model scores to video according to the feature of user and the feature of video.
3. according to the method described in claim 1, it is characterized in that, the preset method includes：GBDT iteration decision tree is calculated
Method.
4. according to the method described in claim 1, it is characterized in that,
The user characteristics include：Age, gender, region；
The video features include：Video type, video tab.
5. according to the method described in claim 1, it is characterized in that, described obtain the preliminary recommendation video of target user, including：
Obtain user-Video Events；
According to user-Video Events, the similar users of target user are calculated；
According to the similar users of the target user, the initial recommendation video of the target user is generated.
6. according to the method described in claim 5, it is characterized in that, described according to user-Video Events, calculate target user's
Similar users, including：
Obtain the scoring of the video of each user；
User-video matrix is built according to the scoring of the video of each user；
Based on Similarity Algorithm, according to the user-video matrix, the similar users of the target user are calculated.
It is 7. according to the method described in claim 1, it is characterized in that, described according to preset user interest preference model, prediction
The scoring for recommending video, including：
Extract the user characteristics of the target user；
It is input in the user interest preference model, the user characteristics of the target user and the recommendation video with pre-
Survey the scoring for recommending video.
8. a kind of video recommendations device, which is characterized in that including：
Acquiring unit, for obtaining the initial recommendation video of target user；
Predicting unit, for according to preset user preferences modeling, predicting the scoring for recommending video；The user interest is inclined
Good model is by preset method to being obtained after positive sample data and the training of negative sample data；The positive sample data packet
It includes：The video features of user characteristics and the participation video of the user；The negative sample data include user characteristics and the use
Family has neither part nor lot in the video features of video；
Determination unit, for according to the scoring for recommending video, determining the preferred video of the target user；
Transmitting element, for the preferred video to be sent to the target user.
9. device according to claim 8, which is characterized in that further include：
Extraction unit, for according to the user-Video Events, extracting the feature of user that the user-Video Events include
With the feature of video；
First generation unit, for the feature of participation video according to user in the user video event and the spy of the user
Sign generation positive sample data；
Second generation unit, for according in the user-Video Events, the feature for having neither part nor lot in video of the user and described
The feature generation negative sample data of user；
Training unit for being trained using preset method to the positive sample data and the negative sample data, is obtained
User interest preference model, so that the user interest preference model carries out video according to the feature of user and the feature of video
Scoring.
10. device according to claim 8, which is characterized in that the acquiring unit, including：
First obtains subelement, for obtaining user-Video Events；
Computation subunit, for according to user-Video Events, calculating the similar users of target user；
Subelement is generated, for the similar users according to the target user, generates the initial recommendation video of the target user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810072044.3A CN108243357A (en) | 2018-01-25 | 2018-01-25 | A kind of video recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810072044.3A CN108243357A (en) | 2018-01-25 | 2018-01-25 | A kind of video recommendation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108243357A true CN108243357A (en) | 2018-07-03 |
Family
ID=62699193
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810072044.3A Pending CN108243357A (en) | 2018-01-25 | 2018-01-25 | A kind of video recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108243357A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109389168A (en) * | 2018-09-29 | 2019-02-26 | 国信优易数据有限公司 | Project recommendation model training method, item recommendation method and device |
| CN109889891A (en) * | 2019-03-05 | 2019-06-14 | 腾讯科技（深圳）有限公司 | Obtain the method, apparatus and storage medium of target media file |
| CN110012356A (en) * | 2019-04-16 | 2019-07-12 | 腾讯科技（深圳）有限公司 | Video recommendation method, device and equipment and computer storage medium |
| CN110275779A (en) * | 2019-06-20 | 2019-09-24 | 北京百度网讯科技有限公司 | A kind of resource acquiring method, device, equipment and storage medium |
| CN110401873A (en) * | 2019-06-17 | 2019-11-01 | 北京奇艺世纪科技有限公司 | Video clipping method, device, electronic equipment and computer-readable medium |
| CN110489574A (en) * | 2019-08-05 | 2019-11-22 | 东软集团股份有限公司 | A kind of multimedia messages recommended method, device and relevant device |
| CN110798718A (en) * | 2019-09-02 | 2020-02-14 | 腾讯科技（深圳）有限公司 | Video recommendation method and device |
| WO2020135193A1 (en) * | 2018-12-27 | 2020-07-02 | 深圳Tcl新技术有限公司 | Deep neural network-based video recommendation method and system, and storage medium |
| WO2020135054A1 (en) * | 2018-12-29 | 2020-07-02 | 广州市百果园信息技术有限公司 | Method, device and apparatus for video recommendation and storage medium |
| WO2020215962A1 (en) * | 2019-04-23 | 2020-10-29 | 腾讯科技（深圳）有限公司 | Video recommendation method and device, computer device and storage medium |
| CN113569668A (en) * | 2021-07-12 | 2021-10-29 | 杭州网易云音乐科技有限公司 | Method, medium, apparatus and computing device for determining highlight segments in video |
| CN113763086A (en) * | 2020-09-23 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Information recommendation method and device |
| CN113987260A (en) * | 2021-09-14 | 2022-01-28 | 北京百度网讯科技有限公司 | Video pushing method and device, electronic equipment and storage medium |
Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101551825A (en) * | 2009-05-15 | 2009-10-07 | 中国科学技术大学 | Personalized film recommendation system and method based on attribute description |
| CN101826114A (en) * | 2010-05-26 | 2010-09-08 | 南京大学 | Multi Markov chain-based content recommendation method |
| CN102207972A (en) * | 2011-06-15 | 2011-10-05 | 中山大学 | Television program recommending method and device for digital television |
| CN103051930A (en) * | 2012-12-21 | 2013-04-17 | 福建邮科通信技术有限公司 | Method and system for recommending mobile video based on flow analysis and user behavior analysis |
| CN103313108A (en) * | 2013-06-14 | 2013-09-18 | 山东科技大学 | Smart TV program recommending method based on context aware |
| CN103996143A (en) * | 2014-05-12 | 2014-08-20 | 华东师范大学 | Movie marking prediction method based on implicit bias and interest of friends |
| CN104156472A (en) * | 2014-08-25 | 2014-11-19 | 四达时代通讯网络技术有限公司 | Video recommendation method and system |
| CN105045931A (en) * | 2015-09-02 | 2015-11-11 | 南京邮电大学 | Video recommendation method and system based on Web mining |
| CN105404700A (en) * | 2015-12-30 | 2016-03-16 | 山东大学 | Collaborative filtering-based video program recommendation system and recommendation method |
| CN105808537A (en) * | 2014-12-29 | 2016-07-27 | Tcl集团股份有限公司 | A Storm-based real-time recommendation method and a system therefor |
| CN105847985A (en) * | 2016-03-30 | 2016-08-10 | 乐视控股（北京）有限公司 | Video recommendation method and device |
| CN105930425A (en) * | 2016-04-18 | 2016-09-07 | 乐视控股（北京）有限公司 | Personalized video recommendation method and apparatus |
| CN106454431A (en) * | 2016-10-14 | 2017-02-22 | 合肥工业大学 | Method and system for recommending television programs |
| CN106649540A (en) * | 2016-10-26 | 2017-05-10 | Tcl集团股份有限公司 | Video recommendation method and system |
| CN106776873A (en) * | 2016-11-29 | 2017-05-31 | 珠海市魅族科技有限公司 | A kind of recommendation results generation method and device |
| CN106779867A (en) * | 2016-12-30 | 2017-05-31 | 中国民航信息网络股份有限公司 | Support vector regression based on context-aware recommends method and system |
| US20170251258A1 (en) * | 2016-02-25 | 2017-08-31 | Adobe Systems Incorporated | Techniques for context aware video recommendation |
| CN107423335A (en) * | 2017-04-27 | 2017-12-01 | 电子科技大学 | A kind of negative sample system of selection for single class collaborative filtering problem |
| US20180007449A1 (en) * | 2012-06-21 | 2018-01-04 | Amazon Technologies, Inc. | Unobtrusively enhancing video content with extrinsic data |
| CN107563500A (en) * | 2017-09-14 | 2018-01-09 | 北京奇艺世纪科技有限公司 | A kind of video recommendation method and system based on user's head portrait |
| CN107563841A (en) * | 2017-08-03 | 2018-01-09 | 电子科技大学 | A kind of commending system decomposed that scored based on user |
-
2018
- 2018-01-25 CN CN201810072044.3A patent/CN108243357A/en active Pending
Patent Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101551825A (en) * | 2009-05-15 | 2009-10-07 | 中国科学技术大学 | Personalized film recommendation system and method based on attribute description |
| CN101826114A (en) * | 2010-05-26 | 2010-09-08 | 南京大学 | Multi Markov chain-based content recommendation method |
| CN102207972A (en) * | 2011-06-15 | 2011-10-05 | 中山大学 | Television program recommending method and device for digital television |
| US20180007449A1 (en) * | 2012-06-21 | 2018-01-04 | Amazon Technologies, Inc. | Unobtrusively enhancing video content with extrinsic data |
| CN103051930A (en) * | 2012-12-21 | 2013-04-17 | 福建邮科通信技术有限公司 | Method and system for recommending mobile video based on flow analysis and user behavior analysis |
| CN103313108A (en) * | 2013-06-14 | 2013-09-18 | 山东科技大学 | Smart TV program recommending method based on context aware |
| CN103996143A (en) * | 2014-05-12 | 2014-08-20 | 华东师范大学 | Movie marking prediction method based on implicit bias and interest of friends |
| CN104156472A (en) * | 2014-08-25 | 2014-11-19 | 四达时代通讯网络技术有限公司 | Video recommendation method and system |
| CN105808537A (en) * | 2014-12-29 | 2016-07-27 | Tcl集团股份有限公司 | A Storm-based real-time recommendation method and a system therefor |
| CN105045931A (en) * | 2015-09-02 | 2015-11-11 | 南京邮电大学 | Video recommendation method and system based on Web mining |
| CN105404700A (en) * | 2015-12-30 | 2016-03-16 | 山东大学 | Collaborative filtering-based video program recommendation system and recommendation method |
| US20170251258A1 (en) * | 2016-02-25 | 2017-08-31 | Adobe Systems Incorporated | Techniques for context aware video recommendation |
| CN105847985A (en) * | 2016-03-30 | 2016-08-10 | 乐视控股（北京）有限公司 | Video recommendation method and device |
| CN105930425A (en) * | 2016-04-18 | 2016-09-07 | 乐视控股（北京）有限公司 | Personalized video recommendation method and apparatus |
| CN106454431A (en) * | 2016-10-14 | 2017-02-22 | 合肥工业大学 | Method and system for recommending television programs |
| CN106649540A (en) * | 2016-10-26 | 2017-05-10 | Tcl集团股份有限公司 | Video recommendation method and system |
| CN106776873A (en) * | 2016-11-29 | 2017-05-31 | 珠海市魅族科技有限公司 | A kind of recommendation results generation method and device |
| CN106779867A (en) * | 2016-12-30 | 2017-05-31 | 中国民航信息网络股份有限公司 | Support vector regression based on context-aware recommends method and system |
| CN107423335A (en) * | 2017-04-27 | 2017-12-01 | 电子科技大学 | A kind of negative sample system of selection for single class collaborative filtering problem |
| CN107563841A (en) * | 2017-08-03 | 2018-01-09 | 电子科技大学 | A kind of commending system decomposed that scored based on user |
| CN107563500A (en) * | 2017-09-14 | 2018-01-09 | 北京奇艺世纪科技有限公司 | A kind of video recommendation method and system based on user's head portrait |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109389168A (en) * | 2018-09-29 | 2019-02-26 | 国信优易数据有限公司 | Project recommendation model training method, item recommendation method and device |
| CN109389168B (en) * | 2018-09-29 | 2021-07-13 | 国信优易数据股份有限公司 | Project recommendation model training method, project recommendation method and device |
| WO2020135193A1 (en) * | 2018-12-27 | 2020-07-02 | 深圳Tcl新技术有限公司 | Deep neural network-based video recommendation method and system, and storage medium |
| WO2020135054A1 (en) * | 2018-12-29 | 2020-07-02 | 广州市百果园信息技术有限公司 | Method, device and apparatus for video recommendation and storage medium |
| CN109889891A (en) * | 2019-03-05 | 2019-06-14 | 腾讯科技（深圳）有限公司 | Obtain the method, apparatus and storage medium of target media file |
| CN110012356A (en) * | 2019-04-16 | 2019-07-12 | 腾讯科技（深圳）有限公司 | Video recommendation method, device and equipment and computer storage medium |
| US11540019B2 (en) | 2019-04-23 | 2022-12-27 | Tencent Technology (Shenzhen) Company Limited | Video recommendation method and device, computer device and storage medium |
| WO2020215962A1 (en) * | 2019-04-23 | 2020-10-29 | 腾讯科技（深圳）有限公司 | Video recommendation method and device, computer device and storage medium |
| CN110401873A (en) * | 2019-06-17 | 2019-11-01 | 北京奇艺世纪科技有限公司 | Video clipping method, device, electronic equipment and computer-readable medium |
| CN110275779B (en) * | 2019-06-20 | 2022-07-08 | 北京百度网讯科技有限公司 | Resource acquisition method, device, equipment and storage medium |
| CN110275779A (en) * | 2019-06-20 | 2019-09-24 | 北京百度网讯科技有限公司 | A kind of resource acquiring method, device, equipment and storage medium |
| CN110489574A (en) * | 2019-08-05 | 2019-11-22 | 东软集团股份有限公司 | A kind of multimedia messages recommended method, device and relevant device |
| CN110489574B (en) * | 2019-08-05 | 2022-06-03 | 东软集团股份有限公司 | Multimedia information recommendation method and device and related equipment |
| CN110798718B (en) * | 2019-09-02 | 2021-10-08 | 腾讯科技（深圳）有限公司 | Video recommendation method and device |
| CN110798718A (en) * | 2019-09-02 | 2020-02-14 | 腾讯科技（深圳）有限公司 | Video recommendation method and device |
| CN113763086A (en) * | 2020-09-23 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Information recommendation method and device |
| CN113569668A (en) * | 2021-07-12 | 2021-10-29 | 杭州网易云音乐科技有限公司 | Method, medium, apparatus and computing device for determining highlight segments in video |
| CN113987260A (en) * | 2021-09-14 | 2022-01-28 | 北京百度网讯科技有限公司 | Video pushing method and device, electronic equipment and storage medium |
| WO2023040220A1 (en) * | 2021-09-14 | 2023-03-23 | 北京百度网讯科技有限公司 | Video pushing method and apparatus, and electronic device and storage medium |
| JP7490814B2 (en) | 2021-09-14 | 2024-05-27 | ベイジン バイドゥ ネットコム サイエンス テクノロジー カンパニー リミテッド | VIDEO PUSH METHOD, DEVICE, ELECTRONIC DEVICE, STORAGE MEDIUM, AND COMPUTER PROGRAM |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108243357A (en) | A kind of video recommendation method and device | |
| CN103559206B (en) | A kind of information recommendation method and system | |
| CN110704674B (en) | Video playing integrity prediction method and device | |
| US8959456B2 (en) | Information processing device, information processing method, and program for providing candidate information to a user | |
| WO2017181612A1 (en) | Personalized video recommendation method and device | |
| CN103198057B (en) | One kind adds tagged method and apparatus to document automatically | |
| CN103514304B (en) | Project recommendation method and device | |
| CN108628833B (en) | Method and device for determining summary of original content and method and device for recommending original content | |
| CN103455522B (en) | Recommendation method and system of application extension tools | |
| CN105654198B (en) | Brand advertisement effect optimization method capable of realizing optimal threshold value selection | |
| CN108108821A (en) | Model training method and device | |
| CN106326391A (en) | Method and device for recommending multimedia resources | |
| CN106407241A (en) | Video recommendation method and system | |
| CN106446078A (en) | Information recommendation method and recommendation apparatus | |
| CN111597446B (en) | Content pushing method and device based on artificial intelligence, server and storage medium | |
| CN105721899B (en) | A kind of method and system of video quality score | |
| CN108650532B (en) | Cable television on-demand program recommendation method and system | |
| US9245035B2 (en) | Information processing system, information processing method, program, and non-transitory information storage medium | |
| CN103984741A (en) | Method and system for extracting user attribute information | |
| KR20170107868A (en) | Method and system to recommend music contents by database composed of user's context, recommended music and use pattern | |
| CN107959865A (en) | Main broadcaster's method for pushing, device and computer equipment | |
| CN107645667A (en) | Video recommendation method, system and server apparatus | |
| CN108536676A (en) | Data processing method, device, electronic equipment and storage medium | |
| Ahamad et al. | An OWA‐based model for talent enhancement in cricket | |
| CN104410906A (en) | Detection method and detection device for video playing behavior |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180703 |