CN103731728A - Method for real-time audience investigation - Google Patents
Method for real-time audience investigation Download PDFInfo
- Publication number
- CN103731728A CN103731728A CN201410033047.8A CN201410033047A CN103731728A CN 103731728 A CN103731728 A CN 103731728A CN 201410033047 A CN201410033047 A CN 201410033047A CN 103731728 A CN103731728 A CN 103731728A
- Authority
- CN
- China
- Prior art keywords
- real
- beholder
- time
- data
- audience investigation
- 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
- 238000011835 investigation Methods 0.000 title claims abstract description 41
- 238000000034 method Methods 0.000 title claims abstract description 26
- 230000008921 facial expression Effects 0.000 claims abstract description 13
- 230000000694 effects Effects 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 4
- 206010053238 Amimia Diseases 0.000 claims description 3
- 208000019901 Anxiety disease Diseases 0.000 claims description 3
- 230000036506 anxiety Effects 0.000 claims description 3
- 230000001815 facial effect Effects 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 2
- 230000001960 triggered effect Effects 0.000 claims description 2
- 239000000463 material Substances 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
Images
Abstract
The invention provides a method for real-time audience rating investigation, which belongs to the technical field of digital televisions and network televisions, and the specific method of the invention is as follows: installing a high-definition camera in the viewing terminal; triggering a camera to start shooting a high-definition picture of the facial expression of the viewer through specific instruction data in the media stream, and synchronously decomposing the shot picture, extracting the facial expression elements of the viewer by the viewing terminal, and matching the facial expression elements with a preset expression mode to obtain the attitude of the viewer to a specific channel (program) in a specific time period. The result is sent to an operator in real time through a network for gathering and sorting; so as to adjust the program in time. The data acquisition is fast and real-time; the data is massive, and a large amount of manpower and material resources are saved; the data reliability is high, and the viewing condition is truly reflected; the data has consistency; the granularity of excitement and audience investigation is finer.
Description
Technical field
The present invention relates to Digital Television, Web TV technical field, specifically a kind of method of real-time audience investigation.
Background technology
Existing audience investigation adopts the mode such as questionnaire, telephone interview face to face more.Its drawback mainly contains:
One, not prompt enough, conventionally within several hours or several days after program is broadcast, just can complete investigation and statistics.
Two, effort, need to spend a large amount of manpowers and go to implement.The high enterprise of cost.
Three, the authenticity of data is not high, and the feedback that surveyee considers that for certain (as privacy concerns, introversive nature factor, inappropriate access time, watch then forget etc.) may objective reality is watched situation and s own situation.
Four, be limited by manpower and financial resources, the sample data amount of sample investigation is more limited, as: can only be confined to certain areas (province, city), or the omission of coverage rate aspect may be there is in the random investigation sample of selecting, the situation of mass viewer audiences can not be comprehensively reflected.
Five, for review, replay etc., repeatedly play, traditional investigation method can not effectively follow up.
Six, design investigates a matter quantity and content can not be adjusted as requested in time.
Seven, a small amount of option that survey data can only be based on limited, can not provide the data of meticulousr dynamics.
Eight, the serviceability of result data can be limited by investigator, statistician's quality.
Since two thousand, flourish due to the Internet, mobile communication, network technology, image technique obtain unprecedented development and application, the quality of high-definition camera is improved, price reduces, application surface is more extensive, and graphical analysis, mode-matching technique are also in various industries and field extensive use.Conventional digital TV operator, Web TV operator competitively fight for customer resources, improve program quality and viewing experience.
Under this background, how real-time, real, a large amount of to obtain user's viewing effect extremely important for operator.
Summary of the invention
Technical assignment of the present invention is the deficiency that solves existing investigation method, provide a kind of in real time, the method for obtaining audience investigation data of true, various dimensions, low cost, any amount sample.
Technical scheme of the present invention is:
A method for real-time audience investigation, it installs high-definition camera in rating terminal; By the specific instruction data-triggered camera in Media Stream, start to take the high definition picture of beholder's facial expression, rating terminal synchronizes decomposes, extracts beholder's facial expression element to the picture photographing, and mate with default expression pattern, draw the attitude of beholder to the specific channel (program) of specific time period; Result is sent to operator during by network implementation to be converged, arranges; To timely program is adjusted.
The method of described a kind of real-time audience investigation, it starts the high-definition camera in terminal, with certain frequency, takes the region (beholder region) before rating end face.
The method of described a kind of real-time audience investigation, its internal image processing module by rating terminal parses people's facial head portrait; Pattern matching obtains beholder's quantity, sex, the age.And each beholder is set up to independent database (filing) and store follow-up data until investigate complete.
The method of described a kind of real-time audience investigation, it is interval in control time, according to continuously taking enrich data source.The facial expression that catches beholder by pattern matching changes.The facial expression that draws beholder belongs to a certain in preset mode, as: smile, laugh, cry, wail, pay close attention to very much, do not pay close attention to, anxiety, fear, amimia, leave viewing area etc.
The method of described a kind of real-time audience investigation, once its locking beholder's a kind of expression or state, the individual figure and features characteristic together with beholder is reported to audience investigation data center by network at once.
The method of described a kind of real-time audience investigation, its viewing-data center, operator backstage can obtain view reception effect according to the mass data real-time statistics converging: the statisticss such as age distribution, Sex distribution, the distribution of default excitement feedback.
The method of described a kind of real-time audience investigation, it stops investigating after instruction when obtaining, and rating terminal is destroyed all beholders' of storage initial data.Protection privacy.And close the shooting of camera.
Arrange to trigger and start audience rating investigating order: by Software tool, in the fixed time stamp position (timestamp) of single program (media file), insert the order that audience investigation starts, stops.
Rating terminal (as Set Top Box, smart mobile phone, panel computer, PC etc.) starts the operating processes such as (or termination) camera shooting, image analysis, element extraction, pattern matching, reported result according to the order being resolved to.
Form and size that amount instruction data is little, can significantly not change media file; For the rating terminal of not supporting this instruction, can ignore and not affect normal broadcasting; Can not increase the extra processing load of rating terminal; Implement simple and convenient.
Can be more fine-grained time of realization investigation control, can realize investigation in any time of program; Traditional investigation to a complete programs can be resolved into a plurality of investigation of watching excitement; Data (as: polynary group of age, sex, viewing effect, concern duration etc.) that can export structure; Can catch a plurality of beholders' viewing effect simultaneously.
The invention has the beneficial effects as follows:
Obtain data fast, real-time; Data magnanimity, avoids the deviation such as region, crowd, time of sample; Save a large amount of manpower and materials, cost is low; Data are with a high credibility, truly reflect viewership; Data have continuity; Adopt the granularity of excitement investigation, audience investigation thinner; Technology realizes simpler, is easy to promote; The present invention extensively utilization and digital TV set-top box, network television-set top-set-box, panel computer, treat the rating terminals such as PC of camera.
Accompanying drawing explanation
Accompanying drawing 1 is the schematic diagram that starts, stops audience investigation instruction that inserts in program source of the present invention;
Accompanying drawing 2 is schematic diagrames that are separated into many group view single (site) persons from take the original image obtaining of the present invention;
Accompanying drawing 3 is schematic diagrames of the network configuration of rating terminal of the present invention and audience investigation data center;
Accompanying drawing 4 is schematic diagrames of putting the structural data of a plurality of beholder's figure and features features, viewing effect at one group of Preset Time of the present invention.
Embodiment
With reference to the accompanying drawings, content of the present invention is described to its implementation and the course of work with instantiation.
As shown in Figure 1, program conventionally the time point of limited number be to watch excitement.In the program making later stage, by Software tool, program is processed, in the default front and back, excitement position (can be also whole program) of watching, insert startup, stop audience investigation instruction.By to the default tracking of watching beholder's effect of excitement, can realize the more fine-grained analysis to program fragment view reception effect.(as Fig. 1)
Rating terminal after being resolved to the instruction of startup audience investigation from Streaming Media, and audience investigation flow process brings into operation.Idiographic flow is as follows:
1. start the high-definition camera that terminal carries, with certain frequency, take the region (beholder region) before rating end face.
2. by the internal image processing module of rating terminal, parse people's facial head portrait.Pattern matching obtains beholder's quantity, sex, the age.And each beholder is set up to independent database (filing) and store follow-up data until investigate complete.
3. interval in control time, according to continuously taking enrich data source.The facial expression that catches beholder by pattern matching changes.The facial expression that draws beholder belongs to a certain in preset mode, as: smile, laugh, cry, wail, pay close attention to very much, do not pay close attention to, anxiety, fear, amimia, leave viewing area etc.
4. once lock beholder's a kind of expression or state, the individual figure and features characteristic together with beholder is reported to audience investigation data center by network at once.As shown in Figure 2.
5. viewing-data center in operator backstage can obtain view reception effect according to the mass data real-time statistics converging: the statisticss such as age distribution, Sex distribution, the distribution of default excitement feedback.
6. stop investigating after instruction when obtaining, rating terminal is destroyed all beholders' of storage initial data.Protection privacy.And close the shooting of camera.
Claims (7)
1. a method for real-time audience investigation, is characterized in that, in rating terminal, high-definition camera is installed; By the specific instruction data-triggered camera in Media Stream, start to take the high definition picture of beholder's facial expression, rating terminal synchronizes decomposes, extracts beholder's facial expression element to the picture photographing, and mate with default expression pattern, draw the attitude of beholder to the specific channel (program) of specific time period; Result is sent to operator during by network implementation to be converged, arranges; To timely program is adjusted.
2. according to the method for a kind of real-time audience investigation described in claims 1, it is characterized in that starting the high-definition camera in terminal, with certain frequency, take the region (beholder region) before rating end face.
3. according to the method for a kind of real-time audience investigation described in claims 2, it is characterized in that the internal image processing module by rating terminal parses people's facial head portrait; Pattern matching obtains beholder's quantity, sex, the age, and each beholder is set up to independent database (filing) and store follow-up data until investigate complete.
4. according to the method for a kind of real-time audience investigation described in claims 3, it is characterized in that in control time interval, according to continuously taking enrich data source, the facial expression that catches beholder by pattern matching changes, the facial expression that draws beholder belongs to a certain in preset mode, as: smile, laugh, cry, wail, pay close attention to very much, do not pay close attention to, anxiety, fear, amimia, leave viewing area etc.
5. according to the method for a kind of real-time audience investigation described in claims 4, once it is characterized in that locking beholder's a kind of expression or state, the individual figure and features characteristic together with beholder is reported to audience investigation data center by network at once.
6. according to the method for a kind of real-time audience investigation described in claims 5, it is characterized in that viewing-data center, operator backstage can obtain view reception effect according to the mass data real-time statistics converging: the statisticss such as age distribution, Sex distribution, the distribution of default excitement feedback.
7. according to the method for a kind of real-time audience investigation described in claims 6, it is characterized in that stopping investigating after instruction when obtaining, rating terminal is destroyed all beholders' of storage initial data, protection privacy, and close the shooting of camera.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410033047.8A CN103731728A (en) | 2014-01-24 | 2014-01-24 | Method for real-time audience investigation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410033047.8A CN103731728A (en) | 2014-01-24 | 2014-01-24 | Method for real-time audience investigation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103731728A true CN103731728A (en) | 2014-04-16 |
Family
ID=50455625
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410033047.8A Pending CN103731728A (en) | 2014-01-24 | 2014-01-24 | Method for real-time audience investigation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103731728A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107710222A (en) * | 2015-06-26 | 2018-02-16 | 英特尔公司 | Mood detecting system |
| CN107832720A (en) * | 2017-11-16 | 2018-03-23 | 北京百度网讯科技有限公司 | information processing method and device based on artificial intelligence |
| CN110379360A (en) * | 2019-07-18 | 2019-10-25 | 福建晶彩光电科技股份有限公司 | It is a kind of for controlling the display control unit and system of full color display |
| CN111757153A (en) * | 2020-07-07 | 2020-10-09 | 深圳市九洲电器有限公司 | Method, system, equipment and readable storage medium for audience rating survey |
| CN111800665A (en) * | 2020-07-07 | 2020-10-20 | 深圳市九洲电器有限公司 | Method, system, device and readable storage medium for device health detection |
| CN112764352A (en) * | 2020-12-21 | 2021-05-07 | 深圳创维－Rgb电子有限公司 | Household environment adjusting method and device, server and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101588443A (en) * | 2009-06-22 | 2009-11-25 | 费炜 | Statistical device and detection method for television audience ratings based on human face |
| US20120324493A1 (en) * | 2011-06-17 | 2012-12-20 | Microsoft Corporation | Interest-based video streams |
| CN103024473A (en) * | 2013-01-05 | 2013-04-03 | 张荣华 | Audience rating survey system and method |
| CN103339649A (en) * | 2011-02-27 | 2013-10-02 | 阿弗科迪瓦公司 | Video recommendation based on affect |
-
2014
- 2014-01-24 CN CN201410033047.8A patent/CN103731728A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101588443A (en) * | 2009-06-22 | 2009-11-25 | 费炜 | Statistical device and detection method for television audience ratings based on human face |
| CN103339649A (en) * | 2011-02-27 | 2013-10-02 | 阿弗科迪瓦公司 | Video recommendation based on affect |
| US20120324493A1 (en) * | 2011-06-17 | 2012-12-20 | Microsoft Corporation | Interest-based video streams |
| CN103024473A (en) * | 2013-01-05 | 2013-04-03 | 张荣华 | Audience rating survey system and method |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107710222A (en) * | 2015-06-26 | 2018-02-16 | 英特尔公司 | Mood detecting system |
| CN107832720A (en) * | 2017-11-16 | 2018-03-23 | 北京百度网讯科技有限公司 | information processing method and device based on artificial intelligence |
| CN107832720B (en) * | 2017-11-16 | 2022-07-08 | 北京百度网讯科技有限公司 | Information processing method and device based on artificial intelligence |
| CN110379360A (en) * | 2019-07-18 | 2019-10-25 | 福建晶彩光电科技股份有限公司 | It is a kind of for controlling the display control unit and system of full color display |
| CN111757153A (en) * | 2020-07-07 | 2020-10-09 | 深圳市九洲电器有限公司 | Method, system, equipment and readable storage medium for audience rating survey |
| CN111800665A (en) * | 2020-07-07 | 2020-10-20 | 深圳市九洲电器有限公司 | Method, system, device and readable storage medium for device health detection |
| CN112764352A (en) * | 2020-12-21 | 2021-05-07 | 深圳创维－Rgb电子有限公司 | Household environment adjusting method and device, server and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103731728A (en) | Method for real-time audience investigation | |
| DE112011103903B4 (en) | Method for receiving a particular service and video display device | |
| US9380352B2 (en) | Method and system for playing set-top box startup advertisement, and set-top box | |
| US20110289532A1 (en) | System and method for interactive second screen | |
| RU2601446C2 (en) | Terminal apparatus, server apparatus, information processing method, program and interlocked application feed system | |
| US8893166B2 (en) | Method of surveying watching of image content, and broadcast receiving apparatus and server employing the same | |
| CN103369367B (en) | Streamable content is used to improve the system and method for Consumer's Experience | |
| US20160277808A1 (en) | System and method for interactive second screen | |
| CN103096182A (en) | Network television program information sharing method and system | |
| CN107959863A (en) | A kind of video reviewing method and system | |
| US10045059B2 (en) | Channel change server allocation | |
| US20130081085A1 (en) | Personalized tv listing user interface | |
| US20230283821A1 (en) | Data translation for video-viewing activity | |
| US20170318350A1 (en) | List-type content presentation device and method | |
| US20150348236A1 (en) | Method and system for video stream personalization | |
| CN105898583A (en) | Image recommendation method and electronic equipment | |
| US20200145706A1 (en) | Systems and methods for monitoring content distribution | |
| CN103546828B (en) | The generation method and device of previewing programs | |
| CN104080006A (en) | Video processing device and method | |
| KR20130001512A (en) | Method and system for providing information associated with image | |
| WO2016118836A1 (en) | Commercial-free audiovisual content | |
| CN109831699A (en) | Image audit processing method, device, electronic equipment and storage medium | |
| CN104935957B (en) | For playing the terminal system, 4k cloud platform and play system of 4k video | |
| CN110557686A (en) | System and method for realizing playing satellite low-bit-rate live broadcast program by mobile terminal | |
| WO2018000642A1 (en) | Method, terminal and server for identifying program channel |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20140416 |
|
| WD01 | Invention patent application deemed withdrawn after publication |