CN105915934B - A kind of method and system returning identification program by video image - Google Patents
A kind of method and system returning identification program by video image Download PDFInfo
- Publication number
- CN105915934B CN105915934B CN201610300556.1A CN201610300556A CN105915934B CN 105915934 B CN105915934 B CN 105915934B CN 201610300556 A CN201610300556 A CN 201610300556A CN 105915934 B CN105915934 B CN 105915934B
- Authority
- CN
- China
- Prior art keywords
- video
- user
- image
- unit
- video frame
- 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.)
- Expired - Fee Related
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
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/234—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs
- H04N21/23418—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/433—Content storage operation, e.g. storage operation in response to a pause request, caching operations
- H04N21/4331—Caching operations, e.g. of an advertisement for later insertion during playback
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/475—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data
- H04N21/4756—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data for rating content, e.g. scoring a recommended movie
Abstract
A kind of system that identification program is returned by video image comprising following steps: shut off unit, extracts video frame images element for shutting off by video capability plug-in unit timing progress video;Uploading unit, for the video frame images element of extraction to be uploaded to background server by video capability plug-in unit;Content analysis unit for the currently watched video content of user to be analyzed video frame images element and obtained by background server, and extracts the characteristics of image of video content, characteristics of image is added in characteristics of image library;It repeats successively to execute shut off unit, uploading unit, content analysis unit;Demand analysis unit, for analyzing user group to the real demand of programme content or advertisement according to characteristics of image library.The present invention also provides a kind of methods for returning identification program by video image.
Description
Technical field
The present invention relates to video big data analysis technical fields, in particular to a kind of to return identification program by video image
Method and system.
Background technique
With internet+penetrate into every field, if possess a large amount of user as industry wins and failures, thriving and declining it is crucial because
Element.
In the prior art often through the means analysis such as questionnaire user for the demand of programme content, or to advertisement
Preference, not only expend a large amount of energy, and since statistical data is limited, accuracy is not often high.
Summary of the invention
In view of this, the present invention proposes a kind of method and system for returning identification program by video image.
A kind of system that identification program is returned by video image comprising following steps:
Shut off unit, extracts video frame images element for shutting off by video capability plug-in unit timing progress video;
Optionally, video capability plug-in unit can be by the way of internal or external.
Uploading unit, for the video frame images element of extraction to be uploaded to background server by video capability plug-in unit;
Content analysis unit, it is current for being analyzed by background server video frame images element and obtaining user
The video content of viewing, and the characteristics of image of video content is extracted, characteristics of image is added in characteristics of image library;It repeats successively
Execution is shut off unit, uploading unit, content analysis unit;
Demand analysis unit, for analyzing user group to the real need of programme content or advertisement according to characteristics of image library
It asks.
In the system of the present invention for returning identification program by video image, the unit that shuts off includes:
Comment thermal value threshold, the barrage amount threshold of user are set;
Video capability plug-in unit is set and carries out the period that video shuts off;
Whether the comment calorific value and/or barrage quantity that user's publication is judged within the period that each video shuts off are more than comment
Thermal value threshold, barrage amount threshold, when being more than, video capability plug-in unit carries out video and shuts off to extract video frame images element,
When being less than, one moment of random selection is shut off by video capability plug-in unit progress video to extract view within the period that video shuts off
Frequency frame pictorial element.
In the system of the present invention for returning identification program by video image, the uploading unit includes:
The video frame images element of extraction is stored in and uploads in buffer pool by video capability plug-in unit, uploads buffer pool for delaying
Deposit video frame images element to be uploaded;
It, will be upper when uploading the video frame images element cached in buffer pool is more than to upload the 70% of buffer pool storage accommodating
It passes after the video frame images element cached in buffer pool is compressed and uploads to background server.
In the system of the present invention for returning identification program by video image, the content analysis unit includes:
Background server decompressing video frame pictorial element;And the video frame images element after decompression is analyzed and is used
The currently watched video content in family;
Characteristics of image is extracted from video content, and described image feature includes the type of video, the age for watching the video
Section composition, lines feature, features described above constitute user's recessive character, user's recessive character are added in characteristics of image library;
Judge whether user issues comment, barrage, obtains the dominant spy of user if there is then carrying out analysis to comment, barrage
Sign, user's dominant character is added in characteristics of image library;
According to demand of user's recessive character analysis user group to programme content or advertisement in characteristics of image library, exist
When user's dominant character, the demand according to user's dominant character to programme content or advertisement is modified to obtain user group to section
The perhaps real demand of advertisement in mesh, otherwise directly as user group to the real demand of programme content or advertisement.
It is of the present invention by video image return identification program system in, judge user whether issue comment,
Barrage obtains user's dominant character if there is then carrying out analysis to comment, barrage, user's dominant character is added to characteristics of image
Include: in library
Establish comment, barrage data table corresponding with the time shaft of video frame element;By video frame element it is corresponding comment,
Barrage is segmented, and each lemma is obtained, to obtain the dominant character for representing user preference, and user's dominant character is added
Into characteristics of image library.
The present invention also provides a kind of methods for returning identification program by video image comprising following steps:
S1, video capability plug-in unit timing carry out video and shut off to extract video frame images element;
The video frame images element of extraction is uploaded to background server by S2, video capability plug-in unit;
The currently watched video content of user is analyzed video frame images element and obtained to S3, background server, and
The characteristics of image for extracting video content, characteristics of image is added in characteristics of image library;Step S1 is repeated to step S3;
S4, user group is analyzed to the real demand of programme content or advertisement according to characteristics of image library.
In the method for the present invention for returning identification program by video image, the step S1 includes:
Comment thermal value threshold, the barrage amount threshold of user are set;
Video capability plug-in unit is set and carries out the period that video shuts off;
Whether the comment calorific value and/or barrage quantity that user's publication is judged within the period that each video shuts off are more than comment
Thermal value threshold, barrage amount threshold, when being more than, video capability plug-in unit carries out video and shuts off to extract video frame images element,
When being less than, one moment of random selection is shut off by video capability plug-in unit progress video to extract view within the period that video shuts off
Frequency frame pictorial element.
In the method for the present invention for returning identification program by video image, the step S2 includes:
The video frame images element of extraction is stored in and uploads in buffer pool by video capability plug-in unit, uploads buffer pool for delaying
Deposit video frame images element to be uploaded;
It, will be upper when uploading the video frame images element cached in buffer pool is more than to upload the 70% of buffer pool storage accommodating
It passes after the video frame images element cached in buffer pool is compressed and uploads to background server.
In the method for the present invention for returning identification program by video image, the step S3 includes:
Background server decompressing video frame pictorial element;And the video frame images element after decompression is analyzed and is used
The currently watched video content in family;
Characteristics of image is extracted from video content, and described image feature includes the type of video, the age for watching the video
Section composition, lines feature, features described above constitute user's recessive character, user's recessive character are added in characteristics of image library;
Judge whether user issues comment, barrage, obtains the dominant spy of user if there is then carrying out analysis to comment, barrage
Sign, user's dominant character is added in characteristics of image library;
According to demand of user's recessive character analysis user group to programme content or advertisement in characteristics of image library, exist
When user's dominant character, the demand according to user's dominant character to programme content or advertisement is modified to obtain user group to section
The perhaps real demand of advertisement in mesh, otherwise directly as user group to the real demand of programme content or advertisement.
It is of the present invention by video image return identification program method in, judge user whether issue comment,
Barrage obtains user's dominant character if there is then carrying out analysis to comment, barrage, user's dominant character is added to characteristics of image
Include: in library
Establish comment, barrage data table corresponding with the time shaft of video frame element;By video frame element it is corresponding comment,
Barrage is segmented, and each lemma is obtained, to obtain the dominant character for representing user preference, and user's dominant character is added
Into characteristics of image library.
Implement the method and system provided by the invention for returning identification program by video image to have compared with prior art
Have following the utility model has the advantages that plug-in unit timing passes through video stop flow analysis and extracts frame figure by video (built-in/external) feature card
The pictorial element extracted is automatically uploaded to background server by pixel element, plug-in unit, and background server passes through frame pictorial element point
Analysis obtains the currently watched video content of user.And characteristics of image library can be formed by long-term accumulation, analyze user group
To the real demand of programme content or advertisement.A large amount of manpower and material resources are not only saved, and accuracy is high.
Detailed description of the invention
Fig. 1 is the structural block diagram of the system that identification program is returned by video image of the embodiment of the present invention.
Specific embodiment
As shown in Figure 1, a kind of system for returning identification program by video image comprising following steps:
Shut off unit, extracts video frame images element for shutting off by video capability plug-in unit timing progress video.
Uploading unit, for the video frame images element of extraction to be uploaded to background server by video capability plug-in unit;
Content analysis unit, it is current for being analyzed by background server video frame images element and obtaining user
The video content of viewing, and the characteristics of image of video content is extracted, characteristics of image is added in characteristics of image library;It repeats successively
Execution is shut off unit, uploading unit, content analysis unit;
Demand analysis unit, for analyzing user group to the real need of programme content or advertisement according to characteristics of image library
It asks.
In the system of the present invention for returning identification program by video image, the unit that shuts off includes:
Comment thermal value threshold, the barrage amount threshold of user are set;User may be implemented to which content of video frame most
It is the interest place of user for concern.It can be and positive evaluation is carried out to video frame content, or negative evaluation.
Video capability plug-in unit is set and carries out the period that video shuts off.It may be implemented to shut off to video and occupy the limit of computing resource
System and balance.Period length can independently be set.
Whether the comment calorific value and/or barrage quantity that user's publication is judged within the period that each video shuts off are more than comment
Thermal value threshold, barrage amount threshold, when being more than, video capability plug-in unit carries out video and shuts off to extract video frame images element,
When being less than, one moment of random selection is shut off by video capability plug-in unit progress video to extract view within the period that video shuts off
Frequency frame pictorial element.Thermal value threshold, barrage amount threshold are commented on by setting, can make which video frame is that user is closed the most
Note, then these video frames also most can really reflect user preferences.
In the system of the present invention for returning identification program by video image, the uploading unit includes:
The video frame images element of extraction is stored in and uploads in buffer pool by video capability plug-in unit, uploads buffer pool for delaying
Deposit video frame images element to be uploaded.By the way that last time buffer pool is arranged, network blockage can be led to avoid frequent last time file.
It, will be upper when uploading the video frame images element cached in buffer pool is more than to upload the 70% of buffer pool storage accommodating
It passes after the video frame images element cached in buffer pool is compressed and uploads to background server.By being more than to upload buffer pool
It is uploaded when storing the 70% of accommodating, the utilization of the timely and network bandwidth of upload can be taken into account.
In the system of the present invention for returning identification program by video image, the content analysis unit includes:
Background server decompressing video frame pictorial element;And the video frame images element after decompression is analyzed and is used
The currently watched video content in family;
Characteristics of image is extracted from video content, and described image feature includes the type of video, the age for watching the video
Section composition, lines feature, features described above constitute user's recessive character, user's recessive character are added in characteristics of image library;
Judge whether user issues comment, barrage, obtains the dominant spy of user if there is then carrying out analysis to comment, barrage
Sign, user's dominant character is added in characteristics of image library.The dominant character of user is best able to the hobby of reflection user.
According to demand of user's recessive character analysis user group to programme content or advertisement in characteristics of image library, exist
When user's dominant character, the demand according to user's dominant character to programme content or advertisement is modified to obtain user group to section
The perhaps real demand of advertisement in mesh, otherwise directly as user group to the real demand of programme content or advertisement.
It is of the present invention by video image return identification program system in, judge user whether issue comment,
Barrage obtains user's dominant character if there is then carrying out analysis to comment, barrage, user's dominant character is added to characteristics of image
Include: in library
Establish comment, barrage data table corresponding with the time shaft of video frame element;By video frame element it is corresponding comment,
Barrage is segmented, and each lemma is obtained, to obtain the dominant character for representing user preference, and user's dominant character is added
Into characteristics of image library.Such as user comment " this leading man is very damp ", then lemma can be " leading man " representative figure, "true"
Expression degree, " tide " expression feel quite pleased it.
The present invention also provides a kind of methods for returning identification program by video image comprising following steps:
S1, video capability plug-in unit timing carry out video and shut off to extract video frame images element;
The video frame images element of extraction is uploaded to background server by S2, video capability plug-in unit;
The currently watched video content of user is analyzed video frame images element and obtained to S3, background server, and
The characteristics of image for extracting video content, characteristics of image is added in characteristics of image library;Step S1 is repeated to step S3;
S4, user group is analyzed to the real demand of programme content or advertisement according to characteristics of image library.
In the method for the present invention for returning identification program by video image, the step S1 includes:
Comment thermal value threshold, the barrage amount threshold of user are set;
Video capability plug-in unit is set and carries out the period that video shuts off;
Whether the comment calorific value and/or barrage quantity that user's publication is judged within the period that each video shuts off are more than comment
Thermal value threshold, barrage amount threshold, when being more than, video capability plug-in unit carries out video and shuts off to extract video frame images element,
When being less than, one moment of random selection is shut off by video capability plug-in unit progress video to extract view within the period that video shuts off
Frequency frame pictorial element.
In the method for the present invention for returning identification program by video image, the step S2 includes:
The video frame images element of extraction is stored in and uploads in buffer pool by video capability plug-in unit, uploads buffer pool for delaying
Deposit video frame images element to be uploaded;
It, will be upper when uploading the video frame images element cached in buffer pool is more than to upload the 70% of buffer pool storage accommodating
It passes after the video frame images element cached in buffer pool is compressed and uploads to background server.
In the method for the present invention for returning identification program by video image, the step S3 includes:
Background server decompressing video frame pictorial element;And the video frame images element after decompression is analyzed and is used
The currently watched video content in family;
Characteristics of image is extracted from video content, and described image feature includes the type of video, the age for watching the video
Section composition, lines feature, features described above constitute user's recessive character, user's recessive character are added in characteristics of image library;
Judge whether user issues comment, barrage, obtains the dominant spy of user if there is then carrying out analysis to comment, barrage
Sign, user's dominant character is added in characteristics of image library;
According to demand of user's recessive character analysis user group to programme content or advertisement in characteristics of image library, exist
When user's dominant character, the demand according to user's dominant character to programme content or advertisement is modified to obtain user group to section
The perhaps real demand of advertisement in mesh, otherwise directly as user group to the real demand of programme content or advertisement.
It is of the present invention by video image return identification program method in, judge user whether issue comment,
Barrage obtains user's dominant character if there is then carrying out analysis to comment, barrage, user's dominant character is added to characteristics of image
Include: in library
Establish comment, barrage data table corresponding with the time shaft of video frame element;By video frame element it is corresponding comment,
Barrage is segmented, and each lemma is obtained, to obtain the dominant character for representing user preference, and user's dominant character is added
Into characteristics of image library.
It is understood that for those of ordinary skill in the art, can do in accordance with the technical idea of the present invention
Various other changes and modifications out, and all these changes and deformation all should belong to the protection model of the claims in the present invention
It encloses.
Claims (6)
1. a kind of system for returning identification program by video image, which is characterized in that it includes the following steps: the unit that shuts off,
Video frame images element is extracted for shutting off by video capability plug-in unit timing progress video;
Uploading unit, for the video frame images element of extraction to be uploaded to background server by video capability plug-in unit;
Content analysis unit, it is currently viewing for being analyzed by background server video frame images element and obtaining user
Video content, and extract the characteristics of image of video content, characteristics of image be added in characteristics of image library;Repetition successively executes
Shut off unit, uploading unit, content analysis unit;
Demand analysis unit, for analyzing user group to the real demand of programme content or advertisement according to characteristics of image library;
The unit that shuts off includes: comment thermal value threshold, the barrage amount threshold that user is arranged;
Video capability plug-in unit is set and carries out the period that video shuts off;
Whether the comment calorific value and/or barrage quantity that user's publication is judged within the period that each video shuts off are more than comment calorific value
Threshold value, barrage amount threshold, when being more than, video capability plug-in unit progress video shuts off to extract video frame images element, is not surpassing
Out-of-date, one moment of random selection is shut off by video capability plug-in unit progress video to extract video frame within the period that video shuts off
Pictorial element;
The uploading unit includes: that the video frame images element of extraction is stored in upload buffer pool by video capability plug-in unit, on
Buffer pool is passed for caching video frame images element to be uploaded;
It is slow by uploading when uploading the video frame images element cached in buffer pool is more than to upload the 70% of buffer pool storage accommodating
It rushes after the video frame images element cached in pond is compressed and uploads to background server.
2. a kind of system for returning identification program by video image as described in claim 1, which is characterized in that the content
Analytical unit includes: background server decompressing video frame pictorial element;And the video frame images element after decompression is analyzed
Obtain the currently watched video content of user;
Characteristics of image is extracted from video content, and described image feature includes the type of video, the age bracket structure for watching the video
At, lines feature, features described above constitutes user's recessive character, user's recessive character is added in characteristics of image library;
Judge whether user issues comment, barrage, obtains user's dominant character if there is then carrying out analysis to comment, barrage, it will
User's dominant character is added in characteristics of image library;
According to demand of user's recessive character analysis user group to programme content or advertisement in characteristics of image library, there are users
When dominant character, the demand according to user's dominant character to programme content or advertisement is modified to obtain user group in program
The perhaps real demand of advertisement, otherwise directly as user group to the real demand of programme content or advertisement.
3. a kind of system for returning identification program by video image as claimed in claim 2, which is characterized in that judge user
Whether publication comment, barrage, if there is then to comment, barrage carry out analysis obtain user's dominant character, by user's dominant character
Be added in characteristics of image library includes: to establish comment, barrage data table corresponding with the time shaft of video frame element;Pass through video frame
The corresponding comment of element, barrage are segmented, and each lemma is obtained, to obtain the dominant character for representing user preference, and will
User's dominant character is added in characteristics of image library.
4. a kind of method for returning identification program by video image, which is characterized in that it includes the following steps: S1, video function
Energy plug-in unit timing carries out video and shuts off to extract video frame images element;
The video frame images element of extraction is uploaded to background server by S2, video capability plug-in unit;
S3, background server analyze video frame images element and obtain the currently watched video content of user, and extract
Characteristics of image is added in characteristics of image library by the characteristics of image of video content;Step S1 is repeated to step S3;
S4, user group is analyzed to the real demand of programme content or advertisement according to characteristics of image library;
The step S1 includes: comment thermal value threshold, the barrage amount threshold that user is arranged;
Video capability plug-in unit is set and carries out the period that video shuts off;
Whether the comment calorific value and/or barrage quantity that user's publication is judged within the period that each video shuts off are more than comment calorific value
Threshold value, barrage amount threshold, when being more than, video capability plug-in unit progress video shuts off to extract video frame images element, is not surpassing
Out-of-date, one moment of random selection is shut off by video capability plug-in unit progress video to extract video frame within the period that video shuts off
Pictorial element;
The step S2 includes: that the video frame images element of extraction is stored in upload buffer pool by video capability plug-in unit, is uploaded
Buffer pool is for caching video frame images element to be uploaded;
It is slow by uploading when uploading the video frame images element cached in buffer pool is more than to upload the 70% of buffer pool storage accommodating
It rushes after the video frame images element cached in pond is compressed and uploads to background server.
5. a kind of method for returning identification program by video image as claimed in claim 4, which is characterized in that the step
S3 includes: background server decompressing video frame pictorial element;And the video frame images element after decompression is analyzed and is used
The currently watched video content in family;
Characteristics of image is extracted from video content, and described image feature includes the type of video, the age bracket structure for watching the video
At, lines feature, features described above constitutes user's recessive character, user's recessive character is added in characteristics of image library;
Judge whether user issues comment, barrage, obtains user's dominant character if there is then carrying out analysis to comment, barrage, it will
User's dominant character is added in characteristics of image library;
According to demand of user's recessive character analysis user group to programme content or advertisement in characteristics of image library, there are users
When dominant character, the demand according to user's dominant character to programme content or advertisement is modified to obtain user group in program
The perhaps real demand of advertisement, otherwise directly as user group to the real demand of programme content or advertisement.
6. a kind of method for returning identification program by video image as claimed in claim 5, which is characterized in that judge user
Whether publication comment, barrage, if there is then to comment, barrage carry out analysis obtain user's dominant character, by user's dominant character
Be added in characteristics of image library includes: to establish comment, barrage data table corresponding with the time shaft of video frame element;Pass through video frame
The corresponding comment of element, barrage are segmented, and each lemma is obtained, to obtain the dominant character for representing user preference, and will
User's dominant character is added in characteristics of image library.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610300556.1A CN105915934B (en) | 2016-05-09 | 2016-05-09 | A kind of method and system returning identification program by video image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610300556.1A CN105915934B (en) | 2016-05-09 | 2016-05-09 | A kind of method and system returning identification program by video image |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105915934A CN105915934A (en) | 2016-08-31 |
CN105915934B true CN105915934B (en) | 2019-07-12 |
Family
ID=56748745
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610300556.1A Expired - Fee Related CN105915934B (en) | 2016-05-09 | 2016-05-09 | A kind of method and system returning identification program by video image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105915934B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112333463A (en) * | 2020-09-27 | 2021-02-05 | 深圳Tcl新技术有限公司 | Program recommendation method, system, device and readable storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103442262A (en) * | 2013-08-15 | 2013-12-11 | 安徽科大讯飞信息科技股份有限公司 | User viewing behavior analysis method and system based on video programs on television terminal |
CN103763584A (en) * | 2013-11-15 | 2014-04-30 | 安徽科大讯飞信息科技股份有限公司 | Mobile terminal and server terminal-based information push method and system |
KR20140083654A (en) * | 2012-12-26 | 2014-07-04 | 주식회사 케이티 | Apparatus and method for generating information about object and, server for shearing information |
CN104811744A (en) * | 2015-04-27 | 2015-07-29 | 北京视博云科技有限公司 | Information putting method and system |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
AU2011202182B1 (en) * | 2011-05-11 | 2011-10-13 | Frequency Ip Holdings, Llc | Creation and presentation of selective digital content feeds |
-
2016
- 2016-05-09 CN CN201610300556.1A patent/CN105915934B/en not_active Expired - Fee Related
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20140083654A (en) * | 2012-12-26 | 2014-07-04 | 주식회사 케이티 | Apparatus and method for generating information about object and, server for shearing information |
CN103442262A (en) * | 2013-08-15 | 2013-12-11 | 安徽科大讯飞信息科技股份有限公司 | User viewing behavior analysis method and system based on video programs on television terminal |
CN103763584A (en) * | 2013-11-15 | 2014-04-30 | 安徽科大讯飞信息科技股份有限公司 | Mobile terminal and server terminal-based information push method and system |
CN104811744A (en) * | 2015-04-27 | 2015-07-29 | 北京视博云科技有限公司 | Information putting method and system |
Also Published As
Publication number | Publication date |
---|---|
CN105915934A (en) | 2016-08-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20210042960A1 (en) | Computer vision on broadcast video | |
CN109803152B (en) | Violation auditing method and device, electronic equipment and storage medium | |
CN109862397B (en) | Video analysis method, device, equipment and storage medium | |
KR102222087B1 (en) | Image recognition method and apparatus based on augmented reality | |
CN101360184A (en) | System and method for extracting key frame of video | |
WO2019000789A1 (en) | Live video recommending method and device, and server | |
CN110278485B (en) | Method and device for evaluating video quality | |
WO2018121541A1 (en) | User attribute extraction method and apparatus, and electronic device | |
US20140344455A1 (en) | Method and system to measure user engagement with content through event tracking on the client side | |
US10068352B2 (en) | Determining visibility of rendered content | |
CN110019954A (en) | A kind of recognition methods and system of the user that practises fraud | |
US20160300243A1 (en) | Determining ranking threshold for applications | |
CN111491202A (en) | Video publishing method, device, equipment and storage medium | |
CN102456199A (en) | Method and device for expanding internet user sample set and acquiring attribute parameter | |
CN110807548A (en) | Data acquisition method, device, equipment and medium based on wind power bidding user | |
CN105550207B (en) | Information popularization method and device | |
CN105915934B (en) | A kind of method and system returning identification program by video image | |
KR101189609B1 (en) | System and method for providing video related service based on image | |
RU2632427C1 (en) | Optimization of data exchange between client device and server | |
US9565413B2 (en) | Picture interaction method, apparatus, system and mobile terminal | |
CN101923564A (en) | Method for improving performance of webpage of representing three-dimensional object based on image cache | |
CN109558305B (en) | Log data sorting method and device | |
CN104740873A (en) | Image rendering method for game | |
CN104317880A (en) | Method special for microblog data acquisition mode | |
CN111352680A (en) | Information recommendation method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | 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 | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190712 Termination date: 20210509 |
|
CF01 | Termination of patent right due to non-payment of annual fee |