CN103500578B - Speech control method and apparatus - Google Patents
Speech control method and apparatus Download PDFInfo
- Publication number
- CN103500578B CN103500578B CN201310500587.8A CN201310500587A CN103500578B CN 103500578 B CN103500578 B CN 103500578B CN 201310500587 A CN201310500587 A CN 201310500587A CN 103500578 B CN103500578 B CN 103500578B
- Authority
- CN
- China
- Prior art keywords
- set top
- top box
- application
- word
- voice
- 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.)
- Active
Links
Landscapes
- Machine Translation (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses a kind of speech control method and apparatus, promoted the simple operation degree of the types of applications of mobile interconnected and the integration of three networks. Its technical scheme is: after voice are sampled, transfer to Set Top Box; Set Top Box changes into word after the voice of sampling are identified; Set Top Box carries out semanteme identification to the word after transforming, and word is resolved into control command, Apply Names and parameter three parts; Whether Set Top Box is inquired about in state of activation based on the Apply Names decompositing, and according to the state of control command control application, and parameter is sent into application operates.
Description
Technical field
The present invention relates to speech control technology, relate in particular to the language for the types of applications of mobile Internet and the integration of three networksSound control method and device.
Background technology
Development of Mobile Internet technology and triple play technology, make business and content great outburst, these business and content revealingAfter in end user's hand, user's property convenient for control is a very large difficult problem. Remote controller, mouse, finger sliding,The manipulation means such as gravity sensing emerge in an endless stream, but relatively the most naturally manipulation, or voice control. At present, due to languageSound recognition technology is constantly ripe, utilizes the mode that voice manipulate also constantly to occur in various terminals.
How effectively to manipulate Set Top Box by voice is current problem demanding prompt solution.
Summary of the invention
The object of the invention is to address the above problem, a kind of speech control method and apparatus is provided, promoted movementThe simple operation degree of the types of applications of the interconnected and integration of three networks.
Technical scheme of the present invention is: the present invention has disclosed a kind of speech control method, comprising:
After being sampled, voice transfer to Set Top Box;
Set Top Box changes into word after the voice of sampling are identified;
Set Top Box carries out semanteme identification to the word after transforming, and word is resolved into control command, Apply Names and parameterThree parts;
Whether Set Top Box is inquired about in state of activation based on the Apply Names decompositing, and applies according to control command controlState, and by parameter send into application operate.
According to an embodiment of speech control method of the present invention, speech recognition and semantic identification are known by the voice of Set Top BoxOther layer is realized.
According to an embodiment of speech control method of the present invention, the operation of application is called by the application manager of Set Top BoxCorresponding should being used for realized, and calling by the voice key-course of Set Top Box of application manager completes.
According to an embodiment of speech control method of the present invention, the state of the application that control command is controlled comprise open/Activate, close, inactivation, upgrading, unloading.
The present invention has also disclosed a kind of speech control device, comprises user end apparatus and Set Top Box, wherein:
User end apparatus comprises sampling module, after voice are sampled, transfers to Set Top Box;
Set Top Box comprises sound identification module, semantic identification module and application invocation module, wherein:
Sound identification module changes into word after the voice of sampling are identified;
Semantic identification module carries out semanteme identification to the word after transforming, and word is resolved into control command, applicationTitle and parameter three parts;
Whether application invocation module inquires about in state of activation based on the Apply Names decompositing, according to controlling lifeOrder control application state, and by parameter send into application operate.
According to an embodiment of speech control device of the present invention, the state of the application that control command is controlled comprise open/Activate, close, inactivation, upgrading, unloading.
The present invention contrasts prior art following beneficial effect: the solution of the present invention is after speech recognition, to carry out languageJustice identification, resolves into control command, Apply Names and parameter by voice command, then calls corresponding application placeReason. Compared to conventional art, the present invention can be generalized to the digital terminal of accepting speech control, includes but not limited to machineTop box, OTT, PAD, vehicle GPS etc. can be accepted the user terminal of phonetic entry.
Brief description of the drawings
Fig. 1 shows the flow chart of the preferred embodiment of speech control method of the present invention.
Fig. 2 shows the schematic diagram of the preferred embodiment of speech control device of the present invention.
Detailed description of the invention
Below in conjunction with drawings and Examples, the invention will be further described.
Fig. 1 shows the flow process of the preferred embodiment of speech control method of the present invention. Refer to Fig. 1, the present embodimentThe implementation step of speech control method details are as follows.
Step S10: transfer to Set Top Box after voice are sampled.
Step S12: the speech recognition layer of Set Top Box changes into word after the voice of sampling are identified.
Step S14: the speech recognition layer of Set Top Box carries out semanteme identification to the word after transforming, and word is resolved into controlOrder processed, Apply Names and parameter three parts.
For example, " turning on TV to CCTV-1 ", " opening ", for controlling, " TV " is TV applications, " CCTV-1 "For importing the parameter of TV applications into. For capable of dynamic increases the number of applying, this process need retrieve application registration database.
For an application, state of a control has: open/activate: application off-duty, in internal memory, becomes after openingState of activation, or application is after inactivation suspended state, is transformed into current application state; Close: will specify applicationTransfer closed condition to, releasing resource; Inactivation: become non-current state from current running status, but still in internal memory;Upgrading: updating operation is carried out in application; Unloading: delete application; Hang up; Backstage. Hang up and these two kinds, backstage commonIt seems that user substantially do not use, and therefore only need to consider front 5 kinds of states.
From user's angle, user's control command roughly has so several: " seeing " TV, and " object for appreciation " game," look into " weather, " looking into " data, " making a call ", " sending out " note, " input " name, " preservation " address list. ThisA little control languages are in speech recognition and change in this process of " control " " application " " parameter " and need to relate to.Substantially be all the meaning of " open/activate ".
Apply Names is the Part II of speech recognition, such as, " seeing that TV is to CCTV1 ", " TV " wherein justIt is Apply Names. Apply Names likely can be by breviary in voice control command, such as, user can be with " seeing CCTV1 "Replace and say " seeing that TV is to CCTV1 ", at this moment, need to carry out fuzzy Judgment Apply Names according to controlling parameter. Some is looked intoLess than Apply Names, the search engine that can jump out browser comes, directly according to the mode processing of Query Information. ExampleAs " what the capital of Switzerland is? " Deng order.
Parameter is for some application, and what biography was entered is a character string, removes to process this character by application-specificString, such as " CCTV1 " of " seeing that TV is to CCTV1 " is exactly application parameter. Again such as " send out micro-letter to Zhang San ",Wherein " Zhang San " is exactly parameter. Also has a kind of parameter, in current application. For example, be VOD in current applicationTime, user sends instructions " looking for lord of the rings three ", and application itself should be inputted " lord of the rings three " in film search, itAfter start search.
Step S16: whether Set Top Box is inquired about in state of activation based on the Apply Names decompositing, according to controlling lifeOrder control application state, and by parameter send into application operate.
The voice key-course of Set Top Box obtains after control command, Apply Names and the parameter that speech recognition layer gives, and callsApplication manager. Application manager whether in state of activation, is controlled the state of application according to application, and by parameterSending into application operates. Application, according to the processing of application parameter, oneself is responded and is represented by each application.
Fig. 2 shows the principle of the preferred embodiment of speech control device of the present invention, refers to Fig. 2, the present embodimentSpeech control device comprise user end apparatus 1 and Set Top Box 2.
User end apparatus 1 comprises sampling module 10, after voice are sampled, transfers to Set Top Box 2. Set Top Box 2 wrapsDraw together sound identification module 21, semantic identification module 22 and application invocation module 23. Sound identification module 21 to samplingVoice change into word after identifying. Semantic identification module 22 carries out semanteme identification to the word after transforming, by wordResolve into control command, Apply Names and parameter three parts, the state of the application that wherein control command is controlled comprises to be beatenOpen/activate, close, inactivation, upgrading, unloading. The Apply Names inquiry of application invocation module 23 based on decompositing isNo in state of activation, according to the state of control command control application, and parameter is sent into application operate.
Above-described embodiment be available to those of ordinary skill in the art realize and use of the present invention, the common skill in this areaArt personnel can without departing from the present invention in the case of the inventive idea, make various modifications or variation to above-described embodiment,Thereby protection scope of the present invention do not limit by above-described embodiment, and should be to meet the wound that claims are mentionedThe maximum magnitude of new property feature.
Claims (4)
1. a speech control method, comprising:
After being sampled, voice transfer to Set Top Box;
Set Top Box changes into word after the voice of sampling are identified;
Set Top Box carries out semanteme identification to the word after transforming, and word is resolved into control command, Apply Names and parameterThree parts, wherein speech recognition and semantic identification are realized by the speech recognition layer of Set Top Box;
Whether Set Top Box is inquired about in state of activation based on the Apply Names decompositing, and applies according to control command controlState, and by parameter send into application operate, wherein application operation called by the application manager of Set Top Box rightAnswer should be used for realize, calling by the voice key-course of Set Top Box of application manager completes.
2. speech control method according to claim 1, is characterized in that, the application that control command is controlledState comprise open/activate, close, inactivation, upgrading, unloading.
3. a speech control device, comprises user end apparatus and Set Top Box, wherein:
User end apparatus comprises sampling module, after voice are sampled, transfers to Set Top Box;
Set Top Box comprises sound identification module, semantic identification module and application invocation module, wherein:
Sound identification module changes into word after the voice of sampling are identified;
Semantic identification module carries out semanteme identification to the word after transforming, and word is resolved into control command, applicationTitle and parameter three parts, wherein sound identification module and semantic identification module are realized by the speech recognition layer of Set Top Box;
Whether application invocation module inquires about in state of activation based on the Apply Names decompositing, according to controlling lifeOrder control application state, and by parameter send into application operate, wherein application operation managed by the application of Set Top BoxReason device calls corresponding should being used for and realizes, and calling by the voice key-course of Set Top Box of application manager completes.
4. speech control device according to claim 3, is characterized in that, the application that control command is controlledState comprise open/activate, close, inactivation, upgrading, unloading.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310500587.8A CN103500578B (en) | 2013-10-22 | 2013-10-22 | Speech control method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310500587.8A CN103500578B (en) | 2013-10-22 | 2013-10-22 | Speech control method and apparatus |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103500578A CN103500578A (en) | 2014-01-08 |
| CN103500578B true CN103500578B (en) | 2016-05-11 |
Family
ID=49865782
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310500587.8A Active CN103500578B (en) | 2013-10-22 | 2013-10-22 | Speech control method and apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103500578B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106157955A (en) * | 2015-03-30 | 2016-11-23 | 阿里巴巴集团控股有限公司 | A kind of sound control method and device |
| CN104965596A (en) * | 2015-07-24 | 2015-10-07 | 上海宝宏软件有限公司 | Voice control system |
| CN105374366A (en) * | 2015-10-09 | 2016-03-02 | 广东小天才科技有限公司 | Method and system for recognizing semantics of wearable device |
| CN105407367A (en) * | 2015-11-09 | 2016-03-16 | 苏州美达瑞电子有限公司 | Signal input control system for digital television set top box |
| CN105869623A (en) * | 2015-12-07 | 2016-08-17 | 乐视网信息技术（北京）股份有限公司 | Video playing method and device based on speech recognition |
| WO2017128227A1 (en) * | 2016-01-28 | 2017-08-03 | 陈学良 | Method for calling application program and mobile terminal |
| CN105843069A (en) * | 2016-06-07 | 2016-08-10 | 深圳市中安伟讯科技有限公司 | Speech recognition-based smart home control method and system |
| CN107038052A (en) * | 2017-04-28 | 2017-08-11 | 陈银芳 | The method and terminal of voice uninstall file |
| CN107493494A (en) * | 2017-07-13 | 2017-12-19 | 安徽声讯信息技术有限公司 | Intelligent OTT boxes speech control system |
| CN108091329A (en) * | 2017-12-20 | 2018-05-29 | 江西爱驰亿维实业有限公司 | Method, apparatus and computing device based on speech recognition controlled automobile |
| CN108376543B (en) * | 2018-02-11 | 2021-07-13 | 深圳创维－Rgb电子有限公司 | Control method, device, equipment and storage medium for electrical equipment |
| CN109120774A (en) * | 2018-06-29 | 2019-01-01 | 深圳市九洲电器有限公司 | Terminal applies voice control method and system |
| CN111488446B (en) * | 2020-04-14 | 2021-10-15 | 湖北亿咖通科技有限公司 | Vehicle-mounted voice conversation method, computer storage medium and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102510426A (en) * | 2011-11-29 | 2012-06-20 | 安徽科大讯飞信息科技股份有限公司 | Personal assistant application access method and system |
| CN103260065A (en) * | 2013-05-23 | 2013-08-21 | 无锡德思普科技有限公司 | Set top box speech control method based on Android system |
| CN103269395A (en) * | 2013-04-22 | 2013-08-28 | 聚熵信息技术（上海）有限公司 | Speech control method and device based on screen locking state |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090013255A1 (en) * | 2006-12-30 | 2009-01-08 | Matthew John Yuschik | Method and System for Supporting Graphical User Interfaces |
| US8452597B2 (en) * | 2011-09-30 | 2013-05-28 | Google Inc. | Systems and methods for continual speech recognition and detection in mobile computing devices |
-
2013
- 2013-10-22 CN CN201310500587.8A patent/CN103500578B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102510426A (en) * | 2011-11-29 | 2012-06-20 | 安徽科大讯飞信息科技股份有限公司 | Personal assistant application access method and system |
| CN103269395A (en) * | 2013-04-22 | 2013-08-28 | 聚熵信息技术（上海）有限公司 | Speech control method and device based on screen locking state |
| CN103260065A (en) * | 2013-05-23 | 2013-08-21 | 无锡德思普科技有限公司 | Set top box speech control method based on Android system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103500578A (en) | 2014-01-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103500578B (en) | Speech control method and apparatus | |
| CN105654950B (en) | Adaptive voice feedback method and device | |
| US20240038219A1 (en) | Learning offline voice commands based on usage of online voice commands | |
| US20160350280A1 (en) | Processing natural language text with context-specific linguistic model | |
| CN106021463B (en) | Method, intelligent service system and the intelligent terminal of intelligent Service are provided based on artificial intelligence | |
| US20210342547A1 (en) | System for focused conversation context management in a reasoning agent/behavior engine of an agent automation system | |
| CN105550228B (en) | Intelligent storage device and based on the access recognition methods of Intelligent storage device, system | |
| CN108228764A (en) | A kind of single-wheel dialogue and the fusion method of more wheel dialogues | |
| US9898455B2 (en) | Natural language understanding cache | |
| CN106227792B (en) | Method and apparatus for pushed information | |
| KR102144868B1 (en) | Apparatus and method for providing call record | |
| CN105469789A (en) | Voice information processing method and voice information processing terminal | |
| CN104462064A (en) | Method and system for prompting content input in information communication of mobile terminals | |
| US20200104346A1 (en) | Bot-invocable software development kits to access legacy systems | |
| US11562735B1 (en) | Multi-modal spoken language understanding systems | |
| US11703343B2 (en) | Methods and systems for managing communication sessions | |
| CN114330474B (en) | Data processing method, device, computer equipment and storage medium | |
| US20230065223A1 (en) | Contextually-adaptive conversational interface | |
| EP3451189B1 (en) | A system and method for user query recognition | |
| US11195102B2 (en) | Navigation and cognitive dialog assistance | |
| US10529323B2 (en) | Semantic processing method of robot and semantic processing device | |
| CN109887490A (en) | The method and apparatus of voice for identification | |
| US11393475B1 (en) | Conversational system for recognizing, understanding, and acting on multiple intents and hypotheses | |
| CN103260065A (en) | Set top box speech control method based on Android system | |
| CN116261752A (en) | User-oriented actions based on audio conversations |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C53 | Correction of patent for invention or patent application | ||
| CB02 | Change of applicant information |
Address after: 201800 Shanghai city Jiading District town of Jiading Bole Road No. 70 building 2008 room 10 Applicant after: Shanghai Cloud Vision Networks Technology Co., Ltd. Address before: 201103, 9 building, Hechuan building, No. 2016, Xuhui District, Shanghai, Yishan Road Applicant before: Shanghai Cloud Vision Networks Technology Co., Ltd. |
|
| COR | Change of bibliographic data |
Free format text: CORRECT: ADDRESS; FROM: 201103 XUHUI, SHANGHAI TO: 201800 JIADING, SHANGHAI |
|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |