CN106604066A - Improved personalized recommendation method and system applied to video application - Google Patents
Improved personalized recommendation method and system applied to video application Download PDFInfo
- Publication number
- CN106604066A CN106604066A CN201611149095.9A CN201611149095A CN106604066A CN 106604066 A CN106604066 A CN 106604066A CN 201611149095 A CN201611149095 A CN 201611149095A CN 106604066 A CN106604066 A CN 106604066A
- Authority
- CN
- China
- Prior art keywords
- information
- video
- user
- app
- personalized recommendation
- 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.)
- Granted
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]
- H04N21/20—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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
-
- 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
- H04N21/478—Supplemental services, e.g. displaying phone caller identification, shopping application
- H04N21/47815—Electronic shopping
Abstract
The invention relates to an improved personalized recommendation method applied to a video application. The method includes the following steps that: S0, bullet screen content in the video application is filtered according to a preset rule; S1, the personal information of a user in the video application is obtained; S2, when a video in the application video is played, the type information of the video is obtained according to video label information, and video information is obtained through video application monitoring; S3, the friend circle information of the user is obtained according to the personal information of the user in the video application, and the initial video preference information of the user is predicted according to the personal information of the user; S4, the initial list of video personalized recommendations is obtained through the type information of the video obtained in step S2; and S5, the candidate list of the video personalized recommendations is screened through the preferences of the user in step S3, so that a final video personalized recommendation list can be obtained, and the final video personalized recommendation list is displayed on the video application.
Description
Technical field
The present invention relates to personalized recommendation technical field, personalized recommendation side in more particularly to a kind of improved video app
Method and system.
Background technology
The Internet is the important channel that people obtain information, and the user that is mainly characterized by of conventional internet finds certainly
During oneself things interested, need to carry out substantial amounts of search by browser, while needing artificially to filter out a large amount of uncorrelated
Result, it is cumbersome, and expend time and efforts.
By taking ecommerce as an example, the user that is mainly characterized by of traditional electronic commerce logs in each e-commerce platform, seeks
The commodity that oneself is interested are looked for, is then bought.But with the continuous expansion of ecommerce scale, businessman passes through shopping network
Stand there is provided substantial amounts of commodity, make user quickly to understand all of commodity, also cannot directly check the quality of commodity, user
Requiring a great deal of time can just find the commodity of oneself needs with energy.It is this to browse a large amount of unrelated information and product mistake
Journey, can undoubtedly make the consumer that is submerged in magnanimity information because without finding in oneself needs or commodity interested not
Cutout is lost, and is not only significantly increased the time cost that user does shopping, while making the conversion of the commodity purchasing of e-commerce platform
Rate is very low.
In prior art, it is proposed that according to user's purchase or navigation patterns, with a certain proposed algorithm feature is carried out
Books for example, are clustered first by the personalized recommendation method of information (such as merchandise news) according to books classification, content, are built
Vertical books cluster system, such as A and B is a class books.Then according to the navigation patterns and purchaser record of user, analysis user's sense
It is that A or history bought A that interest books, such as user browse at present commodity, you can by similar B book recommendations to A.
But resting on existing personalized recommendation method based on article, based on user or the individual character based on collaborative filtering more
Change recommendation method.It is not suitable for recommendation personalized in video app.
The content of the invention
In view of this, the present invention proposes a kind of improved video app of the personalized recommendation suitable for improved video app
Middle personalized recommendation method and system.
Personalized recommendation method in a kind of improved video app, it comprises the steps：
S0, in video app configure barrage delivery option；Barrage content was carried out according to default rule in video app
Filter；
S1, the personal information for obtaining user in video app；
S2, when video is played out in video app, according to the type information of video tab information acquisition video, and lead to
Cross video app and monitor time-out, retroversion, F.F. information in the playing duration information, the playing process that obtain the video；
S3, the circle of friends information that user is obtained according to the personal information of user in video app；According to the personal information of user
The preliminary video preference information of prediction user；The dominant expression information of user is extracted from the circle of friends information of user, from dominant
Analysis in expressing information obtains the emotion preference of user；
S4, the Preliminary List that video personalized recommendation is obtained by the type information of the video in step S2, by video
Playing duration information, playing process in suspend, fall back, F.F. information filters to the Preliminary List of video personalized recommendation
Obtain the alternate list of video personalized recommendation；
S5, the barrage interactive information received in video display process；Barrage interactive information is divided into into the bullet of user's transmission
Curtain information and the barrage information that other people send；The barrage information that counting user sends and the barrage information that other people send
Corresponding time temperature figure；User is obtained according to time temperature figure, other people are for the focus of the video；Extract focus pair
The video frame information answered and barrage interactive information；Analyzed by word implication and image recognition analysis obtain user, other
People is for the tendentiousness suggestion of the video；
It is S6, personalized to video by the user tendency suggestion in the emotion preference and step S5 of user in step S3
The alternate list of recommendation carries out screening and obtains final video personalized recommendation list；Final video individual character is shown on video app
Change recommendation list.
In personalized recommendation method in improved video app of the present invention,
It also comprises the steps：
Click, the broadcasting record of S7, acquisition user for the video in final video personalized recommendation list, and measuring point
Hit, play record, for being optimized to the video personalized recommendation list of next time.
In personalized recommendation method in improved video app of the present invention,
Step S1 includes：
Obtain the privacy settings information of userspersonal information of the user on video app；Judged by privacy settings information
Whether there is the authority of the userspersonal information for obtaining user on video app；When with authority, user is obtained in video
Userspersonal information on app；The personal information includes dominant information, recessive information and the friendship network letter of user
Breath；The dominant information of the user includes age, sex, the occupational information of user；The recessive information of the user includes user
Video click information.
In personalized recommendation method in improved video app of the present invention,
Broadcast information weights are set in step S2；Broadcast information weights are 1 plus when the playing duration of video and video
Long ratio；
Time-out, the reverse information of monitoring user；When time-out, the reverse information of user is got, extract suspend when and
The first video frame information before and after play time after retroversion in the range of the scheduled time；
The content information of the first video frame information is obtained by graphical analyses, the content information of the first video frame information is made
For positive content information；
The F.F. information of monitoring user；When the F.F. information of user is got, extract F.F. and start in termination interval
The second video frame information；
The content information of the second video frame information is obtained by graphical analyses, the content information of the second video frame information is made
For negative sense content information；
And the positive content information of storage frame information, negative sense content information and broadcast information weights.
The present invention also provides personalized recommendation system in a kind of improved video app, and it is included such as lower unit：
The configurating filtered unit of barrage, for configuring barrage delivery option in video app；Barrage content is pressed in video app
Filtered according to default rule；
Personal information acquiring unit, for obtaining video app in user personal information；
Broadcast information acquiring unit, for when video is played out in video app, being regarded according to video tab information acquisition
The type information of frequency, and obtain suspending in playing duration information, the playing process of the video, fall back by video app monitoring, it is fast
Enter information；
Information retrieval analytic unit, for obtaining the circle of friends information of user according to the personal information of user in video app；
The preliminary video preference information of user is predicted according to the personal information of user；The aobvious of user is extracted from the circle of friends information of user
Property expressing information, the analysis from dominant expression information obtains the emotion preference of user；
Recommend alternate list signal generating unit, for being regarded by the type information of the video in broadcast information acquiring unit
The Preliminary List of frequency personalized recommendation, by time-out, retroversion, F.F. information pair in playing duration information, the playing process of video
The Preliminary List of video personalized recommendation carries out being filtrated to get the alternate list of video personalized recommendation；
Barrage interactive information analytic unit, for receiving video display process in barrage interactive information；Barrage is interacted
The barrage information that information is divided into the barrage information of user's transmission and other people send；Counting user send barrage information with
And the corresponding time temperature figure of barrage information of other people transmissions；User is obtained according to time temperature figure, other people regard for this
The focus of frequency；Extract the corresponding video frame information of focus and barrage interactive information；Analyze and scheme by word implication
User is obtained as discriminatory analysiss, other people are for the tendentiousness suggestion of the video；
Consequently recommended list generation unit, for individual to video by the emotion preference of user in information retrieval analytic unit
The alternate list that propertyization is recommended carries out screening and obtains final video personalized recommendation list；Final video is shown on video app
Personalized recommendation list.
In personalized recommendation system in improved video app of the present invention,
It is also included such as lower unit：
Recommend feedback unit, for obtain user for the video in final video personalized recommendation list click, broadcast
Record is put, and recorded click, played record, for being optimized to the video personalized recommendation list of next time.
In personalized recommendation system in improved video app of the present invention,
The personal information acquiring unit includes：
Obtain the privacy settings information of userspersonal information of the user on video app；Judged by privacy settings information
Whether there is the authority of the userspersonal information for obtaining user on video app；When with authority, user is obtained in video
Userspersonal information on app；The personal information includes dominant information, recessive information and the friendship network letter of user
Breath；The dominant information of the user includes age, sex, the occupational information of user；The recessive information of the user includes user
Video click information.
In personalized recommendation system in improved video app of the present invention,
Broadcast information weights are set in the broadcast information acquiring unit；Broadcast information weights are 1 plus during the broadcasting of video
The long ratio with video duration；
Time-out, the reverse information of monitoring user；When time-out, the reverse information of user is got, extract suspend when and
The first video frame information before and after play time after retroversion in the range of the scheduled time；
The content information of the first video frame information is obtained by graphical analyses, the content information of the first video frame information is made
For positive content information；
The F.F. information of monitoring user；When the F.F. information of user is got, extract F.F. and start in termination interval
The second video frame information；
The content information of the second video frame information is obtained by graphical analyses, the content information of the second video frame information is made
For negative sense content information；
And the positive content information of storage frame information, negative sense content information and broadcast information weights.
Personalized recommendation method and system in the improved video app that the present invention is provided, relative to prior art, Neng Gouke
Resting on based on article, based on user or based on collaborative filtering the existing personalized recommendation method for taking prior art presence more
Personalized recommendation method；It is not suitable for the defect of recommendation personalized in video app.
Description of the drawings
Fig. 1 be the embodiment of the present invention improved video app in personalized recommendation system structured flowchart.
Specific embodiment
The embodiment of the present invention provides personalized recommendation method in a kind of improved video app, and it comprises the steps：
S0, in video app configure barrage delivery option；Barrage content was carried out according to default rule in video app
Filter；
By implementing this step, barrage information can be carried out the important information of personalized recommendation as auxiliary；Barrage is believed
The information directly commented on the frame of video of Each point in time in real time as user is ceased, the video of user can be directly expressed
Tendentiousness suggestion.
S1, the personal information for obtaining user in video app；
S2, when video is played out in video app, according to the type information of video tab information acquisition video, and lead to
Cross video app and monitor time-out, retroversion, F.F. information in the playing duration information, the playing process that obtain the video；
S3, the circle of friends information that user is obtained according to the personal information of user in video app；According to the personal information of user
The preliminary video preference information of prediction user；The dominant expression information of user is extracted from the circle of friends information of user, from dominant
Analysis in expressing information obtains the emotion preference of user；
S4, the Preliminary List that video personalized recommendation is obtained by the type information of the video in step S2, by video
Playing duration information, playing process in suspend, fall back, F.F. information filters to the Preliminary List of video personalized recommendation
Obtain the alternate list of video personalized recommendation；
S5, the barrage interactive information received in video display process；Barrage interactive information is divided into into the bullet of user's transmission
Curtain information and the barrage information that other people send；The barrage information that counting user sends and the barrage information that other people send
Corresponding time temperature figure；User is obtained according to time temperature figure, other people are for the focus of the video；Extract focus pair
The video frame information answered and barrage interactive information；Analyzed by word implication and image recognition analysis obtain user, other
People is for the tendentiousness suggestion of the video；
By implementing this step, can by time temperature figure obtain user, other people for the focus of the video, subtract
Lack the amount of analysis of frame of video, improve the efficiency of analysis and the accuracy of analysis.
S6, screening is carried out to the alternate list of video personalized recommendation by the emotion preference of user in step S3 obtain most
Whole video personalized recommendation list；Final video personalized recommendation list is shown on video app.
In embodiments of the present invention, personal information, the broadcast information of video, the circle of friends information of user are combined, can
The preference of user is predicted from all angles, better than existing personalized recommendation algorithm.
In personalized recommendation method in improved video app of the present invention,
It also comprises the steps：
Click, the broadcasting record of S7, acquisition user for the video in final video personalized recommendation list, and measuring point
Hit, play record, for being optimized to the video personalized recommendation list of next time.
In personalized recommendation method in improved video app of the present invention,
Step S1 includes：
Obtain the privacy settings information of userspersonal information of the user on video app；Judged by privacy settings information
Whether there is the authority of the userspersonal information for obtaining user on video app；When with authority, user is obtained in video
Userspersonal information on app；The personal information includes dominant information, recessive information and the friendship network letter of user
Breath；The dominant information of the user includes age, sex, the occupational information of user；The recessive information of the user includes user
Video click information.
In personalized recommendation method in improved video app of the present invention,
Broadcast information weights are set in step S2；Broadcast information weights are 1 plus when the playing duration of video and video
Long ratio；
Time-out, the reverse information of monitoring user；When time-out, the reverse information of user is got, extract suspend when and
The first video frame information before and after play time after retroversion in the range of the scheduled time；
The content information of the first video frame information is obtained by graphical analyses, the content information of the first video frame information is made
For positive content information；
The F.F. information of monitoring user；When the F.F. information of user is got, extract F.F. and start in termination interval
The second video frame information；
The content information of the second video frame information is obtained by graphical analyses, the content information of the second video frame information is made
For negative sense content information；
And the positive content information of storage frame information, negative sense content information and broadcast information weights.
By implementing the embodiment of the present invention, can in itself draw user for each fragment of the video from video information
Hobby so that follow-up recommendation is more accurate.
As shown in figure 1, the embodiment of the present invention also provides personalized recommendation system in a kind of improved video app, it includes
Such as lower unit：
The configurating filtered unit of barrage, for configuring barrage delivery option in video app；Barrage content is pressed in video app
Filtered according to default rule；
Personal information acquiring unit, for obtaining video app in user personal information；
Broadcast information acquiring unit, for when video is played out in video app, being regarded according to video tab information acquisition
The type information of frequency, and obtain suspending in playing duration information, the playing process of the video, fall back by video app monitoring, it is fast
Enter information；
Information retrieval analytic unit, for obtaining the circle of friends information of user according to the personal information of user in video app；
The preliminary video preference information of user is predicted according to the personal information of user；The aobvious of user is extracted from the circle of friends information of user
Property expressing information, the analysis from dominant expression information obtains the emotion preference of user；
Recommend alternate list signal generating unit, for being regarded by the type information of the video in broadcast information acquiring unit
The Preliminary List of frequency personalized recommendation, by time-out, retroversion, F.F. information pair in playing duration information, the playing process of video
The Preliminary List of video personalized recommendation carries out being filtrated to get the alternate list of video personalized recommendation；
Barrage interactive information analytic unit, for receiving video display process in barrage interactive information；Barrage is interacted
The barrage information that information is divided into the barrage information of user's transmission and other people send；Counting user send barrage information with
And the corresponding time temperature figure of barrage information of other people transmissions；User is obtained according to time temperature figure, other people regard for this
The focus of frequency；Extract the corresponding video frame information of focus and barrage interactive information；Analyze and scheme by word implication
User is obtained as discriminatory analysiss, other people are for the tendentiousness suggestion of the video；
Consequently recommended list generation unit, for individual to video by the emotion preference of user in information retrieval analytic unit
The alternate list that propertyization is recommended carries out screening and obtains final video personalized recommendation list；Final video is shown on video app
Personalized recommendation list.
In personalized recommendation system in improved video app of the present invention,
It is also included such as lower unit：
Recommend feedback unit, for obtain user for the video in final video personalized recommendation list click, broadcast
Record is put, and recorded click, played record, for being optimized to the video personalized recommendation list of next time.
In personalized recommendation system in improved video app of the present invention,
The personal information acquiring unit includes：
Obtain the privacy settings information of userspersonal information of the user on video app；Judged by privacy settings information
Whether there is the authority of the userspersonal information for obtaining user on video app；When with authority, user is obtained in video
Userspersonal information on app；The personal information includes dominant information, recessive information and the friendship network letter of user
Breath；The dominant information of the user includes age, sex, the occupational information of user；The recessive information of the user includes user
Video click information.
In personalized recommendation system in improved video app of the present invention,
Broadcast information weights are set in the broadcast information acquiring unit；Broadcast information weights are 1 plus during the broadcasting of video
The long ratio with video duration；
Time-out, the reverse information of monitoring user；When time-out, the reverse information of user is got, extract suspend when and
The first video frame information before and after play time after retroversion in the range of the scheduled time；
The content information of the first video frame information is obtained by graphical analyses, the content information of the first video frame information is made
For positive content information；
The F.F. information of monitoring user；When the F.F. information of user is got, extract F.F. and start in termination interval
The second video frame information；
The content information of the second video frame information is obtained by graphical analyses, the content information of the second video frame information is made
For negative sense content information；
And the positive content information of storage frame information, negative sense content information and broadcast information weights.
Personalized recommendation method and system in the improved video app that the present invention is provided, relative to prior art, Neng Gouke
Resting on based on article, based on user or based on collaborative filtering the existing personalized recommendation method for taking prior art presence more
Personalized recommendation method；It is not suitable for the defect of recommendation personalized in video app.
Hardware, computing device can be directly used with reference to the method or algorithm of the embodiments described herein description
Software module, or the combination of the two is implementing.Software module can be placed in random access memory, internal memory, read only memory, electricity can
It is known in programming ROM, electrically erasable ROM, depositor, hard disk, moveable magnetic disc, CD-ROM or technical field
Arbitrarily in the storage medium of other forms.
It is understood that for the person of ordinary skill of the art, can be done with technology according to the present invention design
Go out other various corresponding changes and deformation, and all these changes and deformation should all belong to the protection model of the claims in the present invention
Enclose.
Claims (8)
1. personalized recommendation method in a kind of improved video app, it comprises the steps：
S0, in video app configure barrage delivery option；Barrage content is filtered according to default rule in video app；
S1, the personal information for obtaining user in video app；
S2, when video is played out in video app, according to the type information of video tab information acquisition video, and by regarding
Frequency app monitors time-out, retroversion, F.F. information in the playing duration information, the playing process that obtain the video；
S3, the circle of friends information that user is obtained according to the personal information of user in video app；Predicted according to the personal information of user
The preliminary video preference information of user；The dominant expression information of user is extracted from the circle of friends information of user, from dominant expression
Analysis in information obtains the emotion preference of user；
S4, the Preliminary List that video personalized recommendation is obtained by the type information of the video in step S2, broadcasting by video
Put in duration information, playing process suspend, fall back, F.F. information is filtrated to get to the Preliminary List of video personalized recommendation
The alternate list of video personalized recommendation；
S5, the barrage interactive information received in video display process；Barrage interactive information is divided into into the barrage letter of user's transmission
Breath and the barrage information that other people send；The barrage information that counting user sends and the barrage information correspondence that other people send
Time temperature figure；User is obtained according to time temperature figure, other people are for the focus of the video；Extract focus corresponding
Video frame information and barrage interactive information；Analyzed by word implication and image recognition analysis obtain user, other people are right
In the tendentiousness suggestion of the video；
S6, by the user tendency suggestion in the emotion preference and step S5 of user in step S3 to video personalized recommendation
Alternate list carry out screening and obtain final video personalized recommendation list；Show that final video personalization is pushed away on video app
Recommend list.
2. personalized recommendation method in improved video app as claimed in claim 1, it is characterised in that
It also comprises the steps：
S7, obtain user for the video in final video personalized recommendation list click, play record, and record click,
Record is played, for being optimized to the video personalized recommendation list of next time.
3. personalized recommendation method in improved video app as claimed in claim 2, it is characterised in that
Step S1 includes：
Obtain the privacy settings information of userspersonal information of the user on video app；Judged whether by privacy settings information
With the authority for obtaining userspersonal information of the user on video app；When with authority, user is on video app for acquisition
Userspersonal information；The personal information includes dominant information, recessive information and the friendship network information of user；Institute
Stating the dominant information of user includes age, sex, the occupational information of user；The recessive information of the user includes the video of user
Click information.
4. personalized recommendation method in improved video app as claimed in claim 3, it is characterised in that
Broadcast information weights are set in step S2；Broadcast information weights are 1 plus the playing duration of video and video duration
Ratio；
Time-out, the reverse information of monitoring user；When time-out, the reverse information of user is got, extract when suspending and retroversion
The first video frame information before and after play time afterwards in the range of the scheduled time；
The content information of the first video frame information is obtained by graphical analyses, using the content information of the first video frame information as just
To content information；
The F.F. information of monitoring user；When the F.F. information of user is got, extract F.F. start to terminate in interval the
Two video frame informations；
The content information of the second video frame information is obtained by graphical analyses, using the content information of the second video frame information as negative
To content information；
And the positive content information of storage frame information, negative sense content information and broadcast information weights.
5. personalized recommendation system in a kind of improved video app, it is included such as lower unit：
The configurating filtered unit of barrage, for configuring barrage delivery option in video app；Barrage content is according to pre- in video app
If rule filtered；
Personal information acquiring unit, for obtaining video app in user personal information；
Broadcast information acquiring unit, for when video is played out in video app, according to video tab information acquisition video
Type information, and time-out, retroversion, F.F. letter in playing duration information, the playing process of the video are obtained by video app monitoring
Breath；
Information retrieval analytic unit, for obtaining the circle of friends information of user according to the personal information of user in video app；According to
The personal information of user predicts the preliminary video preference information of user；The dominant table of user is extracted from the circle of friends information of user
Up to information, the analysis from dominant expression information obtains the emotion preference of user；
Recommend alternate list signal generating unit, for obtaining video by the type information of the video in broadcast information acquiring unit
The Preliminary List that propertyization is recommended, by time-out, retroversion, F.F. information in playing duration information, the playing process of video to video
The Preliminary List of personalized recommendation carries out being filtrated to get the alternate list of video personalized recommendation；
Barrage interactive information analytic unit, for receiving video display process in barrage interactive information；By barrage interactive information
It is divided into the barrage information of user's transmission and the barrage information of other people transmissions；Counting user send barrage information and its
The corresponding time temperature figure of barrage information that other people send；User is obtained according to time temperature figure, other people are for the video
Focus；Extract the corresponding video frame information of focus and barrage interactive information；Analyzed by word implication and image is known
User Fen Xi not obtained, other people are for the tendentiousness suggestion of the video；
Consequently recommended list generation unit, for personalized to video by the emotion preference of user in information retrieval analytic unit
The alternate list of recommendation carries out screening and obtains final video personalized recommendation list；Final video individual character is shown on video app
Change recommendation list.
6. personalized recommendation system in improved video app as claimed in claim 5, it is characterised in that
It is also included such as lower unit：
Recommend feedback unit, for obtaining click of the user for the video in final video personalized recommendation list, broadcasting note
Record, and record click, play record, for being optimized to the video personalized recommendation list of next time.
7. personalized recommendation system in improved video app as claimed in claim 6, it is characterised in that
The personal information acquiring unit includes：
Obtain the privacy settings information of userspersonal information of the user on video app；Judged whether by privacy settings information
With the authority for obtaining userspersonal information of the user on video app；When with authority, user is on video app for acquisition
Userspersonal information；The personal information includes dominant information, recessive information and the friendship network information of user；Institute
Stating the dominant information of user includes age, sex, the occupational information of user；The recessive information of the user includes the video of user
Click information.
8. personalized recommendation system in improved video app as claimed in claim 7, it is characterised in that
Broadcast information weights are set in the broadcast information acquiring unit；Broadcast information weights be 1 plus the playing duration of video with
The ratio of video duration；
Time-out, the reverse information of monitoring user；When time-out, the reverse information of user is got, extract when suspending and retroversion
The first video frame information before and after play time afterwards in the range of the scheduled time；
The content information of the first video frame information is obtained by graphical analyses, using the content information of the first video frame information as just
To content information；
The F.F. information of monitoring user；When the F.F. information of user is got, extract F.F. start to terminate in interval the
Two video frame informations；
The content information of the second video frame information is obtained by graphical analyses, using the content information of the second video frame information as negative
To content information；
And the positive content information of storage frame information, negative sense content information and broadcast information weights.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611149095.9A CN106604066B (en) | 2016-12-13 | 2016-12-13 | Personalized recommendation method and system in improved video app |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611149095.9A CN106604066B (en) | 2016-12-13 | 2016-12-13 | Personalized recommendation method and system in improved video app |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106604066A true CN106604066A (en) | 2017-04-26 |
| CN106604066B CN106604066B (en) | 2020-06-26 |
Family
ID=58802318
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611149095.9A Active CN106604066B (en) | 2016-12-13 | 2016-12-13 | Personalized recommendation method and system in improved video app |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106604066B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107105314A (en) * | 2017-05-12 | 2017-08-29 | 北京小米移动软件有限公司 | Video broadcasting method and device |
| CN107911491A (en) * | 2017-12-27 | 2018-04-13 | 广东欧珀移动通信有限公司 | Information recommendation method, device and storage medium, server and mobile terminal |
| CN108419088A (en) * | 2018-02-08 | 2018-08-17 | 华南理工大学 | A kind of recommendation of the channels method towards high sudden user's request |
| CN109640126A (en) * | 2018-12-28 | 2019-04-16 | 北京奇艺世纪科技有限公司 | A kind of video broadcasting method, system and device and computer readable storage medium |
| CN109688479A (en) * | 2018-12-26 | 2019-04-26 | 北京蓦然认知科技有限公司 | A kind of barrage display methods, barrage display device and barrage display server |
| CN109831678A (en) * | 2019-02-26 | 2019-05-31 | 中国联合网络通信集团有限公司 | Short method for processing video frequency and system |
| CN110166811A (en) * | 2019-05-15 | 2019-08-23 | 口碑(上海)信息技术有限公司 | Processing method, device and the equipment of barrage information |
| CN110321479A (en) * | 2019-05-27 | 2019-10-11 | 哈尔滨工业大学（深圳） | A kind of secret protection Information Mobile Service recommended method and client, recommender system |
| WO2020026009A1 (en) * | 2018-08-01 | 2020-02-06 | 优视科技新加坡有限公司 | Video object recommendation method and apparatus, and device/terminal/server |
| CN111078944A (en) * | 2018-10-18 | 2020-04-28 | 中国电信股份有限公司 | Video content heat prediction method and device |
| CN112019920A (en) * | 2019-05-31 | 2020-12-01 | 腾讯科技（深圳）有限公司 | Video recommendation method, device and system and computer equipment |
| CN113423014A (en) * | 2021-06-08 | 2021-09-21 | 深圳康佳电子科技有限公司 | Playing information pushing method and device, terminal equipment and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102843586A (en) * | 2011-06-21 | 2012-12-26 | 华为软件技术有限公司 | Video recommendation method and terminal |
| CN103136275A (en) * | 2011-12-02 | 2013-06-05 | 盛乐信息技术（上海）有限公司 | System and method for recommending personalized video |
| CN104469508A (en) * | 2013-09-13 | 2015-03-25 | 中国电信股份有限公司 | Method, server and system for performing video positioning based on bullet screen information content |
| CN104661096A (en) * | 2013-11-21 | 2015-05-27 | 深圳市快播科技有限公司 | Video barrage adding method and device, video playing method and video player |
| CN104683431A (en) * | 2013-10-30 | 2015-06-03 | 联想（新加坡）私人有限公司 | Intelligent Mesh Object List Buildup |
| CN104980809A (en) * | 2015-06-30 | 2015-10-14 | 北京奇艺世纪科技有限公司 | Barrage processing method and apparatus |
| CN105282565A (en) * | 2015-09-29 | 2016-01-27 | 北京奇艺世纪科技有限公司 | Video recommendation method and device |
| CN105426548A (en) * | 2015-12-29 | 2016-03-23 | 海信集团有限公司 | Video recommendation method and device based on multiple users |
| US9380329B2 (en) * | 2009-03-30 | 2016-06-28 | Time Warner Cable Enterprises Llc | Personal media channel apparatus and methods |
| CN106162304A (en) * | 2015-04-28 | 2016-11-23 | 天脉聚源（北京）科技有限公司 | The player method of a kind of barrage information and system |
-
2016
- 2016-12-13 CN CN201611149095.9A patent/CN106604066B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9380329B2 (en) * | 2009-03-30 | 2016-06-28 | Time Warner Cable Enterprises Llc | Personal media channel apparatus and methods |
| CN102843586A (en) * | 2011-06-21 | 2012-12-26 | 华为软件技术有限公司 | Video recommendation method and terminal |
| CN103136275A (en) * | 2011-12-02 | 2013-06-05 | 盛乐信息技术（上海）有限公司 | System and method for recommending personalized video |
| CN104469508A (en) * | 2013-09-13 | 2015-03-25 | 中国电信股份有限公司 | Method, server and system for performing video positioning based on bullet screen information content |
| CN104683431A (en) * | 2013-10-30 | 2015-06-03 | 联想（新加坡）私人有限公司 | Intelligent Mesh Object List Buildup |
| CN104661096A (en) * | 2013-11-21 | 2015-05-27 | 深圳市快播科技有限公司 | Video barrage adding method and device, video playing method and video player |
| CN106162304A (en) * | 2015-04-28 | 2016-11-23 | 天脉聚源（北京）科技有限公司 | The player method of a kind of barrage information and system |
| CN104980809A (en) * | 2015-06-30 | 2015-10-14 | 北京奇艺世纪科技有限公司 | Barrage processing method and apparatus |
| CN105282565A (en) * | 2015-09-29 | 2016-01-27 | 北京奇艺世纪科技有限公司 | Video recommendation method and device |
| CN105426548A (en) * | 2015-12-29 | 2016-03-23 | 海信集团有限公司 | Video recommendation method and device based on multiple users |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107105314A (en) * | 2017-05-12 | 2017-08-29 | 北京小米移动软件有限公司 | Video broadcasting method and device |
| CN107105314B (en) * | 2017-05-12 | 2020-06-02 | 北京小米移动软件有限公司 | Video playing method and device |
| CN107911491A (en) * | 2017-12-27 | 2018-04-13 | 广东欧珀移动通信有限公司 | Information recommendation method, device and storage medium, server and mobile terminal |
| CN108419088A (en) * | 2018-02-08 | 2018-08-17 | 华南理工大学 | A kind of recommendation of the channels method towards high sudden user's request |
| WO2020026009A1 (en) * | 2018-08-01 | 2020-02-06 | 优视科技新加坡有限公司 | Video object recommendation method and apparatus, and device/terminal/server |
| CN111078944B (en) * | 2018-10-18 | 2023-04-07 | 中国电信股份有限公司 | Video content heat prediction method and device |
| CN111078944A (en) * | 2018-10-18 | 2020-04-28 | 中国电信股份有限公司 | Video content heat prediction method and device |
| CN109688479A (en) * | 2018-12-26 | 2019-04-26 | 北京蓦然认知科技有限公司 | A kind of barrage display methods, barrage display device and barrage display server |
| CN109640126A (en) * | 2018-12-28 | 2019-04-16 | 北京奇艺世纪科技有限公司 | A kind of video broadcasting method, system and device and computer readable storage medium |
| CN109831678A (en) * | 2019-02-26 | 2019-05-31 | 中国联合网络通信集团有限公司 | Short method for processing video frequency and system |
| CN110166811A (en) * | 2019-05-15 | 2019-08-23 | 口碑(上海)信息技术有限公司 | Processing method, device and the equipment of barrage information |
| CN110321479A (en) * | 2019-05-27 | 2019-10-11 | 哈尔滨工业大学（深圳） | A kind of secret protection Information Mobile Service recommended method and client, recommender system |
| CN110321479B (en) * | 2019-05-27 | 2021-07-20 | 哈尔滨工业大学（深圳） | Privacy protection mobile service recommendation method, client and recommendation system |
| CN112019920A (en) * | 2019-05-31 | 2020-12-01 | 腾讯科技（深圳）有限公司 | Video recommendation method, device and system and computer equipment |
| CN113423014A (en) * | 2021-06-08 | 2021-09-21 | 深圳康佳电子科技有限公司 | Playing information pushing method and device, terminal equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106604066B (en) | 2020-06-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106604066A (en) | Improved personalized recommendation method and system applied to video application | |
| US9003435B2 (en) | Method of recommending media content and media playing system thereof | |
| JP6291481B2 (en) | Determining the subsequent part of the current media program | |
| US9269090B2 (en) | Method, apparatus and computer program product for providing indications regarding recommended content | |
| US8838516B2 (en) | Near real-time analysis of dynamic social and sensor data to interpret user situation | |
| CN109241347B (en) | System and method for content reaction annotation | |
| CN106792171A (en) | Personalized recommendation method and system in intelligent video app | |
| US20220269723A1 (en) | Song similarity determination | |
| US20130268513A1 (en) | Annotations based on hierarchical categories and groups | |
| US20130097176A1 (en) | Method and system for data mining of social media to determine an emotional impact value to media content | |
| WO2013121470A1 (en) | Content presentation device, terminal, system, program, and method | |
| CN105975472A (en) | Method and device for recommendation | |
| US20150205580A1 (en) | Method and System for Sorting Online Videos of a Search | |
| CN106250553A (en) | A kind of service recommendation method and terminal | |
| CN109474845A (en) | Barrage control method, barrage processing server and computer readable storage medium | |
| CN106649655A (en) | Personalized recommending method and system in video app | |
| KR102131791B1 (en) | Method to provide recommended contents and associated contents | |
| KR20130090344A (en) | Apparatus, system, method and computer readable recording media storing the program for related recommendation of tv program contents and web contents | |
| CN108090206A (en) | Sort method and device, the electronic equipment of comment information | |
| KR101992411B1 (en) | Method, system and non-transitory computer-readable recording medium for providing scent recommendation based on sns | |
| KR20130110965A (en) | Sensibility evalution and contents recommendation method based on user feedback | |
| JP5245377B2 (en) | Article recommendation device, article recommendation method, and article recommendation program | |
| KR20140083637A (en) | Server and method for providing contents of customized based on user emotion | |
| KR20140002238A (en) | Method of measuring sensitivity based on user feedback and storage media storing the same | |
| Bratcher | Purses, pencil skirts, and podcasts: a content analysis of fashion brand PR |
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 |