CN102984559A - Audience rating statistical system and method based on voice recognition - Google Patents
Audience rating statistical system and method based on voice recognition Download PDFInfo
- Publication number
- CN102984559A CN102984559A CN2012104283316A CN201210428331A CN102984559A CN 102984559 A CN102984559 A CN 102984559A CN 2012104283316 A CN2012104283316 A CN 2012104283316A CN 201210428331 A CN201210428331 A CN 201210428331A CN 102984559 A CN102984559 A CN 102984559A
- Authority
- CN
- China
- Prior art keywords
- user
- voice
- acquisition module
- data
- module
- 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
Images
Landscapes
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
Abstract
The invention provides an audience rating statistical system based on voice recognition. The audience rating statistical system based on the voice recognition comprises an audio acquisition module which is connected to a data acquisition module through a voice recognition module, and the data acquisition module is connected with a central data bank through a network. The audio acquisition module is used for acquiring voice information of users, the voice recognition module recognizes the acquired voice information according to voice features, the data acquisition module acquires viewing behavior data of the users according to the voice information, and the data are sent to the central data bank through the network to be carried with statistic analysis. Through the audience rating statistical system based on the voice recognition, a investigation process can be greatly simplified, a investigation range can be expanded to all viewing user individuals with the audience rating statistical system, respondents can be accurate to an individual as a unit by recognizing voice peculiarities, and due to the fact that only the voice peculiarities of the users can be adopted, the privacy of the user can be protected effectively.
Description
Technical field
The present invention relates to the intelligent TV set field, relate in particular to a kind of audience rating statistics system based on speech recognition and method.
Background technology
Audience ratings refers to watch that in certain period the target audience number of certain TV programme accounts for general objective crowd's proportion, represents with percentage.Be widely used at present each media and TV station, as the reference index of Promgramming, also thrown in the important evidence of advertisement as advertiser.
At present, known audience rating statistical is generally investigated company by third party's data, by phone, and survey, the mode sample investigations such as set-top box keys operation obtain audience ratings.
Along with the fast development of Digital Television with popularize, set-top box has become the equipment of televising of main flow.Investigation company also progressively turns to traditional phone, questionnaire investigation mode and uses the set-top box device operation to collect data, by the Internet data centralization is collected statistics.But present method of data capture also rests on specific modulated object button or the remote controller operational data analysis in operation mostly.The object of investigation is unit mainly with family or set-top box then.By above method statistic audience ratings usually exist operation complexity to increase, the field of investigation is little, by the indefinite problem of respondent.
Summary of the invention
The purpose of this invention is to provide a kind of audience rating statistics system and method that is based on voice, so that viewing-data is accurately added up.
The present invention is that the technical scheme that its technical problem of solution adopts is,
A kind of audience rating statistics system based on speech recognition, this system includes voice acquisition module, voice acquisition module is connected to data acquisition module by sound identification module, data acquisition module links to each other with central database by network, voice acquisition module is used for gathering user's voice messaging, the sound identification module voice messaging that identification gathers according to sound characteristic, data acquisition module gathers user audience data according to this voice messaging, and data communication device is crossed network is sent to the central database analysis that takes statistics.
Sound identification module also is connected with speech control module, and this speech control module links to each other with controlled plant, accepts user's phonetic order, and controlled plant is made corresponding control action.
Sound identification module also is connected with user's Registration Module, and sound identification module is distinguished the user according to sound characteristic, and user's Registration Module is registered respectively each user,
Utilize this system to carry out the method for audience rating statistical, comprising:
When the user televiewed, system identified user's sound characteristic automatically, recorded this user's the behavior of watching, and by the networking data was sent to central server as statistics and analysis.
When having other users' addings to watch, to register by phonetic order, system records new user's the behavior of watching simultaneously, and enrollment process comprises following steps:
1) user opens speech recognition apparatus or has embedded the players such as set-top box of sound identification module;
2) select to enter new user by remote controller or panel button and register the interface;
3) read aloud the literal of one section appointment according to being presented at the information of exporting on TV, projecting apparatus or other picture display devices;
4) obtain to input subscriber data behind the phonetic feature in system;
5) system preserves subscriber data and corresponding phonetic feature, and it is complete that new user registers operation.
Sound in its setting range of system automatic detecting, when finding unregistered user voice is arranged, prompting user registration on television set, enrollment process comprises following steps:
1) speech recognition apparatus has detected new user and adds and teleview;
2) speech recognition apparatus display reminding information on the picture output equipment, prompting user is registered new user;
3) user enters new user's register interface after confirming;
4) read aloud the literal of one section appointment according to being presented at the information of exporting on TV, projecting apparatus or other picture display devices;
5) obtain to input subscriber data behind the phonetic feature in system;
6) system preserves subscriber data and corresponding phonetic feature, and it is complete that new user registers operation.
The characteristics of this system are:
1. the sound that gathers in the setting range by the sound receiving equipment is analyzed;
2. it is individual to distinguish rating by the sound characteristic of identification different user;
3. by different user being distinguished in the analysis that collects sound and being collected the viewing behavior of different user;
4. watch crowd's variation by the sound realization Auto-Sensing in the detecting certain limit.
Above-mentioned functions user can on the basis of using existing TV set-top box or other playback equipments, be installed the audio identification module additional or the independently control of audio identification equipment realization voice and recognition function are installed.
The invention has the advantages that,
1. flexible for installation.Can install the audio identification module additional in existing set-top box or playback equipment, or be connected independently audio identification equipment with existing playback equipment, be applied in flexibly on the existing equipment.
2. easy and simple to handle.Need not button, only need to get final product complete operation with the daily the same phonetic order that sends of speaking, greatly reduce operation complexity.
3. not invasion of privacy.Only need collection user's sound characteristic can be finished the identification to the user, the problem of having avoided privacy of user to leak.
4. data are accurate, and acquisition range is wide.Because can be to each rating individuality viewing behavior of sampling respectively, the data that gather are more targeted, and have benefited from the normal rating that easy operation does not affect the user fully, can the investigation expanded range to all crowds who uses equipment, make obtained data more accurate, have more convincingness.
Description of drawings
Fig. 1 is the structural representation of the audience rating statistics system that proposes of the present invention;
Fig. 2 is new user's registering flow path figure;
Fig. 3 identifies new user's registering flow path figure automatically;
Fig. 4 is the workflow diagram of this audience rating statistics system;
Fig. 5 is the typical application scenarios schematic diagram of this audience rating statistics system.
Embodiment
For technological means, creation characteristic that the present invention is realized, reach purpose and effect is easy to understand, below in conjunction with diagram and specific embodiment, further set forth the present invention.
As shown in Figure 1, the audience rating statistics system that the present invention proposes includes voice acquisition module, voice acquisition module is connected to data acquisition module by sound identification module, data acquisition module links to each other with central database by network, voice acquisition module is used for gathering user's voice messaging, the sound identification module voice messaging that identification gathers according to sound characteristic, data acquisition module gathers user audience data according to this voice messaging, and data communication device is crossed network is sent to the central database analysis that takes statistics;
Sound identification module also is connected with speech control module, and this speech control module links to each other with controlled plant, accepts user's phonetic order, and controlled plant is made corresponding control action;
Sound identification module also is connected with user's Registration Module, and sound identification module is distinguished the user according to sound characteristic, and user's Registration Module is registered respectively each user.
Utilize this system to carry out the method for audience rating statistical, comprising:
When the user televiewed, system identified user's sound characteristic automatically, recorded this user's the behavior of watching, and by the networking data was sent to central server as statistics and analysis.
When having other users' addings to watch, to register by phonetic order, system records new user's the behavior of watching simultaneously.
Sound in its setting range of system automatic detecting, when finding unregistered user voice is arranged, prompting user registration on television set.
User's register step is as shown in Figure 2:
1. the user opens speech recognition apparatus or has embedded the players such as set-top box of sound identification module;
2. select to enter new user by remote controller or panel button and register the interface;
3. read aloud the literal of one section appointment according to being presented at the information of exporting on TV, projecting apparatus or other picture display devices;
4. obtain to input subscriber data behind the phonetic feature in system;
5. system preserves subscriber data and corresponding phonetic feature, and it is complete that new user registers operation.
Automatically the new user's register step of identification is as shown in Figure 3:
1. speech recognition apparatus has detected new user and adds and teleview;
2. speech recognition apparatus display reminding information on the picture output equipment, prompting user is registered new user;
3. the user enters new user's register interface after confirming;
4. read aloud the literal of one section appointment according to being presented at the information of exporting on TV, projecting apparatus or other picture display devices.
5. obtain to input subscriber data behind the phonetic feature in system;
6. system preserves subscriber data and corresponding phonetic feature, and it is complete that new user registers operation.
Speech recognition audience ratings supervisory control system workflow is as shown in Figure 4:
The user opens television set by phonetic order, and system will begin to record this user's viewing behavior; Pass through the phonetic order reporting system when other users add when televiewing, system will record new user's viewing behavior simultaneously; Send the phonetic order reporting system if new user forgets when adding rating, system can be by identifying its sound characteristic and automatically recording its viewing behavior when it is spoken; When the user passed through voice or other mode closing televisions, system can start shooting to user watched behavioral statistics all registrations or that detect between shutdown and be uploaded to central server in order to statistical analysis.
The typical application scenarios that native system is applied to family's television services as shown in Figure 5, sound identification module is accepted and reached to the sound in this scene in the speech recognition equipment certain limit by aphalangia to microphone.By the user identity in sound identification module analysis and sound recognition source and the instruction of sending.When identifying phonetic order, by control module peripheral equipment is sent control command, such as switching on and shutting down, channel switching etc.All user instructions and user watch the TV behavior to be sent to central server with performing an analysis and adding up by Data acquisition, module records, preservation and by the Internet.
Use this audience rating statistics system can greatly simplify fact-finding process; it is individual that the scope of investigation can expand all viewers of installing native system additional to; can will be accurate to by the respondent with individual artificial unit by the sound recognition speciality; and owing to the user's that only samples sound characteristic, can effectively protect user's privacy.
More than show and described basic principle of the present invention, principal character and advantage of the present invention.The technical staff of the industry should understand; the present invention is not restricted to the described embodiments; that describes in above-described embodiment and the specification just illustrates principle of the present invention; the present invention also has various changes and modifications without departing from the spirit and scope of the present invention, and these changes and improvements all fall in the claimed scope of the invention.The claimed scope of the present invention is defined by appending claims and equivalent thereof.
Claims (8)
1. audience rating statistics system based on speech recognition, it is characterized in that, this system includes voice acquisition module, voice acquisition module is connected to data acquisition module by sound identification module, data acquisition module links to each other with central database by network, voice acquisition module is used for gathering user's voice messaging, the sound identification module voice messaging that identification gathers according to sound characteristic, data acquisition module gathers user audience data according to this voice messaging, and data communication device is crossed network is sent to the central database analysis that takes statistics.
2. a kind of audience rating statistics system based on speech recognition according to claim 1, it is characterized in that sound identification module also is connected with speech control module, this speech control module links to each other with controlled plant, accept user's phonetic order, controlled plant is made corresponding control action.
3. a kind of audience rating statistics system based on speech recognition according to claim 1, it is characterized in that, sound identification module also is connected with user's Registration Module, and sound identification module is distinguished the user according to sound characteristic, and user's Registration Module is registered respectively each user.
4. utilize system claimed in claim 1 to carry out the method for audience rating statistical, it is characterized in that when the user televiewed, system identified user's sound characteristic automatically, record this user's the behavior of watching, and by the networking data are sent to central server as statistics and analysis.
5. method according to claim 4 is characterized in that, when having other users' addings to watch, registers by phonetic order, and system records new user's the behavior of watching simultaneously.
6. method according to claim 4 is characterized in that, the sound in its setting range of system automatic detecting, and when finding unregistered user voice is arranged, prompting user registration on television set.
7. method according to claim 5 is characterized in that, enrollment process comprises following steps:
1) user opens speech recognition apparatus or has embedded the players such as set-top box of sound identification module;
2) select to enter new user by remote controller or panel button and register the interface;
3) read aloud the literal of one section appointment according to being presented at the information of exporting on TV, projecting apparatus or other picture display devices;
4) obtain to input subscriber data behind the phonetic feature in system;
5) system preserves subscriber data and corresponding phonetic feature, and it is complete that new user registers operation.
8. method according to claim 6 is characterized in that, enrollment process comprises following steps:
1) speech recognition apparatus has detected new user and adds and teleview;
2) speech recognition apparatus display reminding information on the picture output equipment, prompting user is registered new user;
3) user enters new user's register interface after confirming;
4) read aloud the literal of one section appointment according to being presented at the information of exporting on TV, projecting apparatus or other picture display devices;
5) obtain to input subscriber data behind the phonetic feature in system;
6) system preserves subscriber data and corresponding phonetic feature, and it is complete that new user registers operation.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012104283316A CN102984559A (en) | 2012-10-31 | 2012-10-31 | Audience rating statistical system and method based on voice recognition |
| TW102138979A TW201436544A (en) | 2012-10-31 | 2013-10-28 | Audience rating statistical system and method based on voice recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012104283316A CN102984559A (en) | 2012-10-31 | 2012-10-31 | Audience rating statistical system and method based on voice recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102984559A true CN102984559A (en) | 2013-03-20 |
Family
ID=47858234
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012104283316A Pending CN102984559A (en) | 2012-10-31 | 2012-10-31 | Audience rating statistical system and method based on voice recognition |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN102984559A (en) |
| TW (1) | TW201436544A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104349183A (en) * | 2014-04-10 | 2015-02-11 | 江苏优因特智能科技有限公司 | Media television reception effect feedback collecting method realized through sound channel |
| CN104349182A (en) * | 2014-04-10 | 2015-02-11 | 江苏优因特智能科技有限公司 | Intelligent terminal media playing content feedback method realized through sound channel |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1282470A (en) * | 1997-11-20 | 2001-01-31 | 尼尔逊媒介研究股份有限公司 | Voice recognition unit for audience measurement system |
| CN101098453A (en) * | 2002-04-22 | 2008-01-02 | 尼尔逊媒介研究股份有限公司 | Methods and apparatus to collect audience information associated with a media presentation |
| CN101720048A (en) * | 2009-12-04 | 2010-06-02 | 山东大学 | Audience rating survey system and audience rating information searching method based on audio frequency characteristics |
| CN101938610A (en) * | 2010-09-27 | 2011-01-05 | 冠捷显示科技（厦门）有限公司 | Novel voiceprint recognition-based television device |
-
2012
- 2012-10-31 CN CN2012104283316A patent/CN102984559A/en active Pending
-
2013
- 2013-10-28 TW TW102138979A patent/TW201436544A/en unknown
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1282470A (en) * | 1997-11-20 | 2001-01-31 | 尼尔逊媒介研究股份有限公司 | Voice recognition unit for audience measurement system |
| CN101098453A (en) * | 2002-04-22 | 2008-01-02 | 尼尔逊媒介研究股份有限公司 | Methods and apparatus to collect audience information associated with a media presentation |
| CN101720048A (en) * | 2009-12-04 | 2010-06-02 | 山东大学 | Audience rating survey system and audience rating information searching method based on audio frequency characteristics |
| CN101938610A (en) * | 2010-09-27 | 2011-01-05 | 冠捷显示科技（厦门）有限公司 | Novel voiceprint recognition-based television device |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104349183A (en) * | 2014-04-10 | 2015-02-11 | 江苏优因特智能科技有限公司 | Media television reception effect feedback collecting method realized through sound channel |
| CN104349182A (en) * | 2014-04-10 | 2015-02-11 | 江苏优因特智能科技有限公司 | Intelligent terminal media playing content feedback method realized through sound channel |
Also Published As
| Publication number | Publication date |
|---|---|
| TW201436544A (en) | 2014-09-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9282350B2 (en) | Systems and methods for automated extraction of closed captions in real time or near real-time and tagging of streaming data for advertisements | |
| US20140278933A1 (en) | Methods and apparatus to measure audience engagement with media | |
| TWI399973B (en) | Methods, apparatus and machine readable medium storing instructions to distinguish a signal originating from a local device from a boradcast signal | |
| US20100169911A1 (en) | System for Automatically Monitoring Viewing Activities of Television Signals | |
| CN104584571B (en) | Audio-frequency fingerprint sequence is produced at set top box | |
| US20100122279A1 (en) | Method for Automatically Monitoring Viewing Activities of Television Signals | |
| CN104137557A (en) | Methods and apparatus for crediting a media presentation device | |
| US10455269B2 (en) | Systems and methods for automated extraction of closed captions in real time or near real-time and tagging of streaming data for advertisements | |
| WO2017119604A1 (en) | Audience rating calculation server, audience rating calculation method, and audience rating calculation remote device | |
| US10547905B2 (en) | Systems, methods, and devices for monitoring content viewership using short-range wireless communication | |
| US20240298056A1 (en) | Systems and Methods for Automated Extraction of Closed Captions in Real Time or Near Real-Time and Tagging of Streaming Data for Advertisements | |
| CN110691204B (en) | Audio and video processing method and device, electronic equipment and storage medium | |
| US9301019B1 (en) | Media correlation by feature matching | |
| Fink et al. | Social-and interactive-television applications based on real-time ambient-audio identification | |
| CN102929887A (en) | Quick video retrieval method and system based on sound feature identification | |
| CN102984559A (en) | Audience rating statistical system and method based on voice recognition | |
| CN104349182A (en) | Intelligent terminal media playing content feedback method realized through sound channel | |
| CN106651431A (en) | Advertising method and advertising device | |
| JP4219749B2 (en) | Audience rating survey system and audience rating survey method | |
| KR101155465B1 (en) | System for monitoring advertisements from broadcasting data and method thereof | |
| US20190318515A1 (en) | Information Processing Apparatus, Information Processing Method, And Program | |
| US9794599B2 (en) | Method and system for auditing multimedia content | |
| CN202102453U (en) | Image identification system of viewing investigators | |
| CN104349183B (en) | The method of the collection medium audience staining effect realized by sound channel | |
| CN202257603U (en) | Viewer identification device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| ASS | Succession or assignment of patent right |
Owner name: HUANG MINGGUO GALAYA LTD. Free format text: FORMER OWNER: QIANZHI HUDONG DIGITAL SCIENCE + TECHNOLOGY SHANGHAI CO., LTD. GALAYA LTD. Effective date: 20140515 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20140515 Address after: 200235, 8, Qinzhou Road, 100, Shanghai, Xuhui District Applicant after: Shanghai Shangen Huake Network Technology Co., Ltd. Applicant after: Huang Mingguo Applicant after: Galaya Limited Address before: 200235, 8, Qinzhou Road, 100, Shanghai, Xuhui District Applicant before: Shanghai Shangen Huake Network Technology Co., Ltd. Applicant before: Dry interactive digital technology (Shanghai) Co., Ltd. Applicant before: Galaya Limited |
|
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20130320 |