CN102006373B

CN102006373B - Vehicle-mounted service system and method based on voice command control

Info

Publication number: CN102006373B
Application number: CN201010556994.7A
Authority: CN
Inventors: 沈嘉鑫; 王力劭; 许军; 庞泽耀
Original assignee: SHENZHEN VCYBER TECHNOLOGY Co Ltd
Current assignee: Chengdu cheYin Intelligent Technology Co.,Ltd.
Priority date: 2010-11-24
Filing date: 2010-11-24
Publication date: 2015-01-28
Anticipated expiration: 2030-11-24
Also published as: CN102006373A

Abstract

The embodiment of the invention discloses a vehicle-mounted service system and method based on voice command control, relating to a vehicle-mounted service technique, which is characterized in that a user is only required to press the start button of a one-button type control device arranged on the fixed device of a vehicle, so that terminal equipment and a cloud computing platform server on the network side are connected through the one-button type control device; the gain service is obtained through a voice control mode; the gain service data is transmitted to a display device for display; and the purposes of simplifying the operation steps of the vehicle-mounted service for the user and enhancing the user experience of the vehicle-mounted service are realized. The technical scheme provided by the embodiment of the invention can be applied to the vehicles such as cars and the like.

Description

The vehicle-mounted service system controlled based on voice command and method

Technical field

The present invention relates to vehicle-mounted service technology, particularly relate to the vehicle-mounted service system and method that control based on voice command.

Background technology

Current, the development of mobile network is very fast, and the application based on mobile network can allow people in movement, obtain more abundanter information and service.Along with the development of Vehicle Technology, mobile unit also can carry out radio communication by SIM card, make user be expert at car process in obtain the value-added service (as interaction navigation, interaction multimedia service etc.) that provides of cellular carrier by mobile unit, mobile unit generally has large scale display screen, it can be used in showing the value-added service obtained, as play audio-visual video, the music, broadcast, essay, cross-talk, storytelling etc. of customization, or for showing real-time navigation route map.

In the prior art, if user needs same number to be both used in mobile terminal of mobile telephone, communicate while can be used on mobile unit again, then user needs first SIM card to be taken out from the mobile terminals such as mobile phone, then be installed in mobile unit and mobile unit just can be made to obtain value-added service from wireless carriers, and when user needs to carry out voice call with mobile terminals such as mobile phones, also need again SIM card to be installed back mobile terminal, make the complicated operation of user, the Consumer's Experience carrying out vehicle-mounted service is bad, this becomes inconvenient by causing the use of user, if mobile unit is integrated 3G module simultaneously, be then difficult to solve the cross-interference issue between multiple aerial signal, use multiple 3G network that user also can be made must to buy multiple network service license simultaneously, the expenses of surfing Internet of user can be caused like this to be multiplied.

Summary of the invention

Embodiments of the invention provide a kind of vehicle-mounted service side's system and method controlled based on voice command, simplify the operating procedure that user carries out vehicle-mounted service, improve the Consumer's Experience of vehicle-mounted service.This system has a vehicle-mounted mapping display device, and as having the display unit of wireless receiving sending module, it also can be the panel computer with LCDs.

This vehicle-mounted mapping display device can by multiple wireless environment (including but not limited to WiFi, WiMax, bluetooth and other privately owned wireless protocols) and mobile phone association, by open or encrypting traffic, can communicate with mobile phone with the communication protocol realizing defining.There is in mobile phone a control unit, it is for mailing to this vehicle-mounted mapping display device by mobile phone screen information, audio-frequency information and data control information, the communication module of this vehicle-mounted mapping display device can obtain these data by wireless network, and decoded by predetermined communication protocol, mobile phone screen information can be shown in real time, handset audio stream carried out play and control information that mobile phone terminal sends can be obtained to respond, as equipment state control etc.Simultaneously, this vehicle-mounted mapping display device also has some buttons or touch-screen feedback areas, oppositely can also send control information to the mobile phone terminal connected in advance by wireless network by these buttons or this vehicle-mounted mapping display device of touch-screen feedback areas, to its sending controling instruction signal, mobile phone terminal obtains these signals, and also can carry out state transformation by predefined communication control processor, as time-out during play content, continuation, F.F., rewind and control mobile phone are called out etc.This vehicle-mounted mapping display device can also install microphone additional, and by speaker's information gathering, and can pass to mobile phone by wireless network by microphone, mobile phone can process it, as speech recognition, is sent to and specifies remote equipment, voice call etc.

This vehicle-mounted mapping display device is mainly used in Mobile Telephone Gps, the value-added services such as multimedia interactive information map, and reverse operating mobile phone, its tool has the following advantages: (1) avoid when driving to the complex operations of mobile phone (although mobile phone operation should be forbidden when driving or forbid other all do not meet the action of safe driving, but can inevitably occur needing the special circumstances to mobile phone operation in driving procedure), human pilot only needs to operate accordingly this vehicle-mounted mapping display device, its all operation can be mapped in mobile phone, because this vehicle-mounted mapping display device has large scale display screen, make it easy to operate, reduce the probability of misoperation, achieve safety driving tips to travel, (2) human pilot is in non-driving procedure, as in the people such as to stop, the situation such as to have a rest in car, can use this vehicle-mounted mapping display device carry out multiple operation as played, seeing a film, listen to the music, amusement online or process corporate business, it is equivalent to a removable computer, carry out real-time communication by mobile phone in the external world, achieve strange land office, (3) a card active/standby devices application has been accomplished easily, realize the theory that a mobile phone just can " be got on the bus to automobile-used, get off to people's use ", after human pilot is got on the bus, only need mobile phone to be set to vehicle-mounted mapping display device connection status with this, and mobile phone can be carried with and need not be fixed on the visual position of human pilot, only need that this vehicle-mounted mapping display device is fixed on human pilot and be convenient to the visual position arrived, as being adsorbed onto on front windshield by vehicle frame.After getting off, human pilot just can directly leave after only needing to close this connection status, and do not need SIM cards of mobile phones repeatedly to plug from different equipment, thus also extend the useful life of SIM, and make human pilot use this system to become more simple and convenient.

For reaching above-mentioned target, embodiments of the invention adopt following technical scheme:

Based on the vehicle-mounted service system that voice command controls, comprise one-key type control device, terminal equipment, cloud computing platform server, display device, it is characterized in that:

Described one-key type control device, be arranged on the fixed part of vehicle, after pressing start key user, connected by direct or short haul connection mode and terminal equipment, and by directly or short haul connection mode drive described terminal equipment and cloud computing platform server to connect;

Described terminal equipment, after connecting with described one-key type control device, sets up voice conversation by voice call switching network or multiple radio data network with the cloud computing platform server of network side and is connected; Receive the first information of voice prompt that described cloud computing platform server sends, this the first information of voice prompt is play to user, receive the voice command of the startup value-added service that described user sends according to described first information of voice prompt, and the voice command of this startup value-added service is sent to described cloud computing platform server; Receive the value-added service voice directive command that described user sends, and this value-added service voice directive command is sent to described cloud computing platform server; Receive the value-added service control information that described cloud computing platform server sends, corresponding value-added service is started according to this value-added service control information, connect with providing the server of described value-added service, obtain Value added service data from this server, this Value added service data is sent to display unit by communication;

Described cloud computing platform server, comprises signer-independent sign language recognition module, and described cloud computing platform server is used for sending described first information of voice prompt to described terminal equipment, and described first information of voice prompt is used to indicate user and inputs value-added service type; Receive the voice command of the startup value-added service that described terminal equipment sends, resolved by the voice command of described signer-independent sign language recognition module to described startup value-added service, obtain and start value-added service order, start corresponding value-added service according to this startup value-added service order; Receive the value-added service voice directive command that described terminal equipment sends, by described signer-independent sign language recognition module, described value-added service voice directive command is resolved, obtain the indication information that described value-added service is relevant, the indication information relevant according to described value-added service generates value-added service control information; This value-added service control information is sent to described terminal equipment by the mode adopting note to issue or set up Mobile data passage;

Described display unit, for being established a communications link by communication and described terminal equipment, receive and show described terminal equipment send Value added service data.

Based on the vehicle-mounted method of servicing that voice command controls, comprising:

Press the start key of one-key type control device user after, described one-key type control device by directly or short haul connection mode and terminal equipment connect, wherein, described one-key type control device is arranged on the fixed part of vehicle, and described one-key type control device drives described terminal equipment and cloud computing platform server to connect by direct or short haul connection mode;

Described terminal equipment is set up voice conversation by voice call switching network or multiple radio data network with the cloud computing platform server of network side and is connected;

Described cloud computing platform server sends the first information of voice prompt by described voice conversation connection to described terminal equipment, and described first information of voice prompt is used to indicate described user and inputs value-added service type;

Described terminal equipment plays described first information of voice prompt to described user, receive the voice command of the startup value-added service that described user sends according to described first information of voice prompt, and the voice command of this startup value-added service is sent to described cloud computing platform server;

Described cloud computing platform server adopts the voice command of signer-independent sign language recognition technology to described startup value-added service to resolve, and obtains and starts value-added service order, starts corresponding value-added service according to this startup value-added service order;

Described terminal equipment receives the value-added service voice directive command that described user sends, and this value-added service voice directive command is sent to described cloud computing platform server;

Described cloud computing platform server adopts signer-independent sign language recognition technology to resolve described value-added service voice directive command, obtain the indication information that described value-added service is relevant, the indication information relevant according to described value-added service generates value-added service control information, and this value-added service control information is sent to described terminal equipment by the mode adopting note to issue or set up Mobile data passage;

Described terminal equipment starts corresponding value-added service according to this value-added service control information, connect with providing the server of described value-added service, obtain Value added service data from this server, this Value added service data is sent to display unit by communication;

Described display unit shows the Value added service data that described terminal equipment sends.

The vehicle-mounted service system based on voice command control that the embodiment of the present invention provides and method, user only need press the start key of the one-key type control device on the fixed part of the vehicle of setting, namely connect by the cloud computing platform server of this one-key type control device by terminal equipment and network side, value-added service is obtained by Voice command mode, and this Value added service data is sent to display unit display, reach and simplify the operating procedure that user carries out vehicle-mounted service, improve the object of the Consumer's Experience of vehicle-mounted service, achieve and substantially need not carry out any manual operation more when driving, and control only by voice command.Because cloud computing platform server can adopt signer-independent sign language recognition technology to resolve the voice command that terminal equipment sends, the versatility of the technical scheme that the embodiment of the present invention is provided is better, be applicable to different phonetic, the use of tone user, and it is also applicable to the identification of different dialect, as Guangdong language, the south of Fujian Province language etc., this system is also applicable to the identification of main flow foreign language simultaneously, as English, French, German, Japanese etc., and this system also has the function of the various different languages in automatic voice command recognition, during as employed Chinese and English in statement voice command as user simultaneously, this system can automatically identify Chinese in this voice command and English, and form correct voice command.Therefore above-mentioned advantage makes this system further increase the Consumer's Experience of vehicle-mounted service, makes the user of different regions use its dialect can operate this system, this for those mandarins not too standard user be particularly advantageous; Because this system can allow to use Chinese and English in the voice command of user simultaneously, this is very favorable for the white collar that those levels of cultures are higher, particularly those are possessed to the user of multilingual ability to exchange, due to they in Chinese of being everlasting in be mingled with English or Japanese etc., the function of this automatic identification different language of system makes them not need to convert unfamiliar Japanese or English to corresponding Chinese order, greatly facilitate the use of user, also improve the operating efficiency of this system simultaneously.Due to driver when driving, only need press a key, just can control to obtain value-added service by voice command, and the Value added service data obtained can be shown by the display unit on vehicle by terminal equipment, make driver not need operation terminal device of taking sb's mind off sth, reduce danger on the run.Because this display device can by the information MAP on terminal equipment on this display device, user/driver is made to carry out any operation by this display device to terminal equipment in rest or stop off, this system can be used as a removable computer, make driver can loosen mood on the one hand to recreate, simultaneously because this system has possessed function of surfing the Net, driver can be contacted by this system and the external world whenever and wherever possible, make to drive road no longer dull.

Accompanying drawing explanation

In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.

The vehicle-mounted service system structural representation controlled based on voice command that Fig. 1 provides for the embodiment of the present invention;

The vehicle-mounted method of servicing flow chart one controlled based on voice command that Fig. 2 provides for the embodiment of the present invention;

Fig. 3 for the embodiment of the present invention shown in Fig. 2 provide based on voice command control vehicle-mounted method of servicing in 205 flow chart;

The vehicle-mounted method of servicing flowchart 2 controlled based on voice command that Fig. 4 provides for the embodiment of the present invention.

Embodiment

Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.

Carry out the operating procedure complexity of vehicle-mounted service to solve user, the problem of vehicle-mounted service experience difference, the embodiment of the present invention provides a kind of vehicle-mounted service system based on voice command control and method.

As shown in Figure 1, the vehicle-mounted service system controlled based on voice command that the embodiment of the present invention provides, comprising: one-key type control device 101, terminal equipment 102, cloud computing platform server 103 and display unit 104;

Wherein, one-key type control device 101, be arranged on the fixed part of vehicle, after pressing start key user, connected by direct or short haul connection mode and terminal equipment 102, and by directly or short haul connection mode drive terminal equipment 102 and cloud computing platform server 103 to connect;

For the ease of user operation, as preferred embodiment, the fixed part of vehicle is specially steering wheel, but, in the use procedure of reality, the present invention does not limit the fixed part of vehicle, and the fixed part of vehicle on vehicle, other are convenient to the parts of user's touch, can also not repeat herein one by one.

In the present embodiment, terminal equipment can be mobile phone or PDA, and in the use procedure of reality, terminal equipment can also can carry out radio communication for other, and obtains the equipment of value-added service from wireless carriers.

In the present embodiment, short haul connection mode can be WiFi, WiMax, bluetooth, infrared and other privately owned wireless protocols.

Terminal equipment 102, after connecting with one-key type control device 101, sets up voice conversation by voice call switching network or multiple radio data network with the cloud computing platform server 103 of network side and is connected; Receive the first information of voice prompt that cloud computing platform server 103 sends, this the first information of voice prompt is play to user, receive the voice command of the startup value-added service that user sends according to the first information of voice prompt, and the voice command of this startup value-added service is sent to cloud computing platform server 103; Receive the value-added service voice directive command that user sends, and this value-added service voice directive command is sent to cloud computing platform server 103; Receive the value-added service control information that cloud computing platform server 103 sends, corresponding value-added service is started according to this value-added service control information, connect with providing the server of described value-added service, obtain Value added service data from this server, this Value added service data is sent to display unit 104 by communication;

In the present embodiment, value-added service can include but not limited to that navigation Service and video and audio play service etc.If value-added service is navigation Service, value-added service voice directive command is specially the voice directive command of object navigation address; If value-added service is video and audio play service, value-added service voice directive command is specially the voice directive command comprising object video and audio descriptor, such as: the voice indication information comprising song or video frequency program title, or comprise the voice indication information etc. of artist name, do not repeat one by one herein.

Cloud computing platform server 103, comprises signer-independent sign language recognition module, and cloud computing platform server 103 is for sending the first information of voice prompt to terminal equipment 102, and this first information of voice prompt is used to indicate user and inputs value-added service type; The voice command of the startup value-added service that receiving terminal apparatus 102 sends, by signer-independent sign language recognition module, the voice command starting value-added service is resolved, obtain and start value-added service order, start corresponding value-added service according to this startup value-added service order; The value-added service voice directive command that receiving terminal apparatus 102 sends, by signer-independent sign language recognition module, this value-added service voice directive command is resolved, obtain the indication information that this value-added service is relevant, the indication information relevant according to described value-added service generates value-added service control information; This value-added service control information is sent to terminal equipment 102 by the mode adopting note to issue or set up Mobile data passage.

Display unit 104, for being established a communications link by communication and terminal equipment 102, is received and the Value added service data of display terminal 102 transmission.

Such as: when value-added service is navigation Service, display unit 104 receives the navigation information (traffic route etc.) that also display terminal 102 obtains from navigation server; When value-added service is video and audio broadcasting service, display unit 104 receives the video image that also display terminal 102 obtains from video server, or receives the lyrics etc. of the song that also display terminal 102 obtains from audio server.

In the present embodiment, display unit 104 can be associated with terminal equipment 102 by multiple wireless environment (including but not limited to WiFi, WiMax, bluetooth and other privately owned wireless protocols), and by open or encrypting traffic, can communicate with terminal equipment 102 with the communication protocol realizing defining.

Further, in the present embodiment, cloud computing platform server 103 is previously stored with multiple wide spectrum phonetic feature storehouse, such as: the wide spectrum phonetic feature storehouse arranged according to place name, the wide spectrum phonetic feature storehouse arranged according to audio frequency and video title and the wide spectrum phonetic feature storehouse etc. arranged according to name.Signer-independent sign language recognition module is specifically for resolving the voice command starting value-added service, extract the first voice characteristics information, search the first wide spectrum phonetic feature storehouse according to this first voice characteristics information, obtain the startup value-added service order corresponding with this first voice characteristics information; And, specifically for resolving value-added service voice directive command, extract the second voice characteristics information, search the second wide spectrum phonetic feature storehouse according to this second voice characteristics information, obtain the indication information that the value-added service corresponding to this second voice characteristics information is relevant.

Wherein, in described first wide spectrum phonetic feature storehouse, there is the first wide spectrum voice characteristics information corresponding with affiliated first voice characteristics information, in described second wide spectrum phonetic feature storehouse, there is the second wide spectrum voice characteristics information corresponding with affiliated second voice characteristics information.

Wherein, above-mentioned first and second voice characteristics information comprise the spectrum distribution information of voice command, time domain waveform information, speech frame short-time spectrum, formant frequency and bandwidth, nasal sound union feature, spectrum correlated characteristic, tonality feature, power spectrum, frame energy, voice intensity and variation track feature lamp thereof, and other first and second voice characteristics information also can be use the one or more combination in above-mentioned various features information.

Such as: when value-added service is navigation Service, signer-independent sign language recognition module is resolved the voice command starting navigation Service, extract corresponding the first voice characteristics information (as spectrum distribution information etc.), search the wide spectrum phonetic feature storehouse arranged according to starting command keyword according to this first voice characteristics information, therefrom obtain the startup navigation Service order that this first voice characteristics information is corresponding; The voice directive command of signer-independent sign language recognition module to object navigation address is resolved, extract corresponding the second voice characteristics information (as spectrum distribution information etc.), search the wide spectrum phonetic feature storehouse arranged according to place name according to this second voice characteristics information, therefrom obtain the object navigation address that this second voice characteristics information is corresponding.

Wherein, further, the optimal way of above-mentioned navigation Service also can be: when the value-added service that user selects this system is navigation Service, user sends voice command (as " I will navigate "), signer-independent sign language recognition module is resolved the voice command (as " I will navigate ") starting navigation Service, extract corresponding the first voice characteristics information (the spectrum distribution information etc. as this voice command " I will navigate "), the wide spectrum phonetic feature storehouse arranged according to starting command keyword is searched according to this first voice characteristics information extracted, startup navigation Service order corresponding to this first voice characteristics information (as " I will navigate ") is obtained according to the wide spectrum phonetic feature storehouse of starting command keyword setting from this, thus the voice command (as " I will navigate ") identifying (namely obtaining) according to this further starts corresponding navigation Service, after navigation Service starts, the voice directive command (as " HaiLong Building ") of signer-independent sign language recognition module to object navigation address is resolved, extract second voice characteristics information (as spectrum distribution information etc.) corresponding with this voice directive command (as " HaiLong Building "), the wide spectrum phonetic feature storehouse arranged according to place name is searched according to this second voice characteristics information, place name corresponding to this second voice characteristics information (as " HaiLong Building ") is obtained according to the wide spectrum phonetic feature storehouse of place name setting from this, then the place name identified according to this obtains the navigation address (address as " HaiLong Building " place) corresponding to this place name.

And for example: when value-added service is video and audio order program service, signer-independent sign language recognition module is resolved the voice command starting video and audio order program service, extract corresponding the first voice characteristics information (as spectrum distribution information etc.), search the wide spectrum phonetic feature storehouse arranged according to starting command keyword according to this first voice characteristics information, therefrom obtain the startup navigation Service order that this first voice characteristics information is corresponding; Signer-independent sign language recognition module is resolved the voice directive command comprising object video and audio descriptor, extract corresponding the second voice characteristics information (as spectrum distribution information etc.), search the wide spectrum phonetic feature storehouse arranged according to video and audio descriptor according to this second voice characteristics information, therefrom obtain the video and audio descriptor that this second voice characteristics information is corresponding.

Wherein, further, the optimal way of above-mentioned video and audio order program service service also can be: when user-selected value-added service is video and audio order program service, after user sends voice command (as " viewing video "), signer-independent sign language recognition module is resolved the voice command (as " viewing video ") starting video and audio order program service, extract first voice characteristics information (as spectrum distribution information etc.) corresponding with the voice command (as " viewing video ") of this video and audio order program service, the wide spectrum phonetic feature storehouse arranged according to starting command keyword is searched according to this first voice characteristics information, the startup video and audio order program service order (as " viewing video ") corresponding with this first voice characteristics information is obtained according to the wide spectrum phonetic feature storehouse of starting command keyword setting from this, thus start corresponding video and audio order program service, after video and audio order program service starts, signer-independent sign language recognition module is resolved the voice directive command comprising object video and audio descriptor (as " love of thornbuss "), extract second voice characteristics information (as spectrum distribution information etc.) corresponding with this voice directive command (as " love of thornbuss "), the wide spectrum phonetic feature storehouse arranged according to video and audio descriptor is searched according to this second voice characteristics information, video and audio descriptor corresponding to this second voice characteristics information (as " love of thornbuss ") is obtained according to the wide spectrum phonetic feature storehouse of video and audio descriptor setting from this, then obtain and the information on services (film " love of thornbuss " as play) corresponding to it.

It should be noted that, the wide spectrum phonetic feature storehouse that the present embodiment provides is after the sound by gathering the whole of China various places, various people and these people (different background noise) under various circumstances, the set of the wide spectrum phonetic feature that essence extracts, this wide spectrum phonetic feature storehouse only depends on the information in existing " phonetic feature storehouse ", and does not rely on the phonetic feature training result of someone.Its advantage is: the selected sample in (1) this wide spectrum phonetic feature storehouse is extensive, comprises the pronunciation of the people of the different regions of country variant in the world.Such as, in China, have chosen the pronunciation of the national almost people in area, county and town of each province, and several large class is divided into the people of national different regions, as North China, the Northeast, the south of Fujian Province language is regional, Guangdong language is regional, the said mandarin of people of these different regions is with the local dialect, its feature is different, after they are sorted out respectively, the people in area of basic simlarity of being pronounced by the local dialect is classified as a class, and the completeness so both considering sample has also been taken into account and built database and produce the least possible redundant information; (2) carried out extracting its voice characteristics information to the sound under varying environment (background noise) or voice command, as after automobile engine is started the voice command that produces, after automobile window is opened, generation wind-dryness and tire are made an uproar lower produced voice command, the voice command produced under other people such as to chip in suddenly at the disturbed condition, voice command etc. produced after the engine is shut off; (3) this wide spectrum phonetic feature storehouse comprises mandarin feature database and the local dialect feature database, and wherein the local dialect feature database comprises the south of Fujian Province repertorie, Guangdong language storehouse, Shanghai native language storehouse etc.

At least one at least above-mentioned multiple situation has been considered in above-mentioned first and/or second voice characteristics information, as considered the situation etc. under the situation of the people of different regions or varying environment, namely the above-mentioned first and/or second voice characteristics information is the voice characteristics information extracted based on sound or the voice command of the people of different regions, or the above-mentioned first and/or second voice characteristics information is the voice characteristics information extracted based on sound or the voice command of the people be under varying environment.Which enhance the discrimination to the user of different regions or the voice command of driver.

Further, this wide spectrum phonetic feature storehouse also comprises foreign language feature database, wherein have in this foreign language feature database English storehouse, method repertorie, German storehouse, day the external language library of main flow such as repertorie.This system also has the automatic identification module of a feature database, and it distinguishes the feature database corresponding to this voice command for the voice command analysis sent user, and automatically selects corresponding feature database.Thus making user the language of country variant used in combination can send voice command, these language can come used in combination without screening in advance, and it is Chinese or foreign language on earth that this automatic identification module in planting modes on sink characteristic storehouse can automatically identify this voice command.

By above-mentioned the set up advantage of wide spectrum phonetic feature lab setting in above-mentioned cloud computing platform server is, reduce the dependence of the system to terminal equipment, terminal equipment in face of speaker is used as the collecting device of a kind of sound or voice command, by the transfer of data of the sound collected or voice command to background server group as cloud computing platform server goes to identify, the high-performance identification that so both can play under multiserver aggregated structure calculates, also can use above-mentioned large-scale phonetic feature storehouse simultaneously, and do not need terminal equipment to possess speech recognition capabilities.

In the present embodiment, the voice messaging of 95% can be identified by signer-independent sign language recognition module, in order to guarantee the voice messaging that 100% identifies user, the Consumer's Experience of the vehicle-mounted service of further raising, alternatively, as shown in Figure 1, cloud computing platform server 103 can also comprise signer-independent sign language recognition operator attendance module, this signer-independent sign language recognition operator attendance module, for when signer-independent sign language recognition module None-identified starts the voice command of value-added service, the voice command of this startup value-added service is identified, obtain corresponding startup value-added service order, and/or, for when signer-independent sign language recognition module None-identified value-added service voice directive command, this value-added service voice directive command is identified, obtain the indication information that described value-added service is relevant.

The vehicle-mounted service system controlled based on voice command that the embodiment of the present invention provides, user only need press the start key of the one-key type control device on the fixed part of the vehicle of setting, namely connect by the cloud computing platform server of this one-key type control device by terminal equipment and network side, value-added service is obtained by Voice command mode, and this Value added service data is sent to display unit display, reach and simplify the operating procedure that user carries out vehicle-mounted service, improve the object of the Consumer's Experience of vehicle-mounted service.Because cloud computing platform server can be resolved the voice command that terminal equipment sends by signer-independent sign language recognition module, the versatility of the technical scheme that the embodiment of the present invention is provided is better, be applicable to different regions, there is user's use of different phonetic, the local dialect, further increase the Consumer's Experience of vehicle-mounted service.Due to driver when driving, only need press a key, just can control to obtain value-added service by voice command, and the Value added service data obtained can be shown by the display unit on vehicle by terminal equipment, make driver not need operation terminal device of taking sb's mind off sth, reduce danger on the run.

Another embodiment of the present invention also provides a kind of vehicle-mounted service system controlled based on voice command, this system is substantially identical with the vehicle-mounted service system controlled based on voice command as shown in Figure 1, its difference is, the vehicle-mounted service system controlled based on voice command that the present embodiment provides, cloud computing platform server 103, can also be used for being connected by voice conversation sending the second information of voice prompt to terminal equipment 102, this second information of voice prompt is used to indicate user and inputs value-added service voice directive command; Terminal equipment 102, can also be used for playing the second information of voice prompt to user.

The vehicle-mounted service system controlled based on voice command that the embodiment of the present invention provides, user only need press the start key of the one-key type control device on the fixed part of the vehicle of setting, namely connect by the cloud computing platform server of this one-key type control device by terminal equipment and network side, value-added service is obtained by Voice command mode, and this Value added service data is sent to display unit display, reach and simplify the operating procedure that user carries out vehicle-mounted service, improve the object of the Consumer's Experience of vehicle-mounted service.Because cloud computing platform server can be resolved the voice command that terminal equipment sends by signer-independent sign language recognition module, the versatility of the technical scheme that the embodiment of the present invention is provided is better, be applicable to different regions, there is user's use of different phonetic, tone, further increase the Consumer's Experience of vehicle-mounted service.Due to driver when driving, only need press a key, just can control to obtain value-added service by voice command, and the Value added service data obtained can be shown by the display unit on vehicle by terminal equipment, make driver not need operation terminal device of taking sb's mind off sth, reduce danger on the run.Further, because cloud computing platform server sends the second information of voice prompt by terminal equipment to user, make user can send value-added service voice directive command according to this second information of voice prompt, avoid owing to there is communication failure (as channel block causes cloud computing platform server not receive the voice command of the startup value-added service that user sends) and cause cloud computing platform server info process mistake, the problem that the whole vehicle-mounted service system controlled based on voice command is paralysed, and then improve the reliability of the vehicle-mounted service system controlled based on voice command, ensure the Consumer's Experience of vehicle-mounted service.

Further embodiment of this invention also provides a kind of vehicle-mounted service system controlled based on voice command, this system is substantially identical with the vehicle-mounted service system controlled based on voice command as shown in Figure 1, its difference is, the vehicle-mounted service system controlled based on voice command that the present embodiment provides, cloud computing platform server 103 can also be used for verifying terminal equipment 102, the voice command of the startup value-added service obtained from terminal equipment is fed back to user by cloud computing platform server again, and point out user to confirm, when just performing the voice command of this transmission after the positive reply obtaining user, when after the negative reply obtaining user, cloud computing platform server resends this voice command, and when still can not get the positive reply of user after carrying out limited number of time circulation, this system turns to signer-independent sign language recognition operator attendance module, uses the voice command of this operator attendance module to this startup value-added service to identify.This limited number of time circulation can be 1 time or more times.

The vehicle-mounted service system controlled based on voice command that the embodiment of the present invention provides, in simplification user operation, improve on the Consumer's Experience basis of vehicle-mounted service, can verify terminal equipment further, thus ensure that the safety and reliability of the vehicle-mounted service system controlled based on voice command.

Yet another embodiment of the invention also provides a kind of vehicle-mounted service system controlled based on voice command, this system is substantially identical with the vehicle-mounted service system controlled based on voice command as shown in Figure 1, and its difference is: terminal equipment 102 can also be used for being connected by the operating state of communication to display unit 104 and controlling its information displaying etc.

Further, display unit 104 can comprise key area and/or touch-screen feedback areas, described display unit 104 can also be used for the operational order being received user by key area and/or touch-screen feedback areas, this operational order is sent to terminal equipment 102, receives and the value-added service more new data of display terminal 102 transmission; Terminal equipment 102, the operational order that receiving and displaying device 102 sends can also be used for, obtain value-added service more new data according to this operational order from the server provided value added service, by this value-added service, more new data or this terminal equipment send to display unit 104 in real time according to this realtime graphic that more new data upgrades.

Such as: when value-added service is video playback service, when Value added service data is video stream data, display unit 104 can from F.F. or the fast reverse operation instruction of crossing key area and/or touch-screen feedback areas reception user transmission, this operational order is sent to terminal equipment 102, terminal equipment 102 obtains F.F. or the later video stream data of rewind time point according to this operational order to video server, and sends to display unit 104 to show this video stream data.

The vehicle-mounted service system controlled based on voice command that yet another embodiment of the invention provides, on the beneficial effect basis that scheme shown in Fig. 1 reaches, interoperability can be carried out between display unit and terminal equipment, thus it is more simple and convenient to make user carry out the operation of vehicle-mounted service, improve the experience that user carries out vehicle-mounted service, and owing to simplifying vehicle-mounted service operations, ensure the traffic safety of driver further.

As shown in Figure 2, the embodiment of the present invention also provides a kind of vehicle-mounted method of servicing controlled based on voice command, it is characterized in that, comprising:

201, press the start key of one-key type control device user after, one-key type control device by directly or short haul connection mode and terminal equipment connect, wherein, one-key type control device is arranged on the fixed part of vehicle, and one-key type control device drives terminal equipment and cloud computing platform server to connect by direct or short haul connection mode.

202, terminal equipment is set up voice conversation by voice call switching network or multiple radio data network with the cloud computing platform server of network side and is connected.

203, cloud computing platform server sends the first information of voice prompt by voice conversation connection to terminal equipment, and described first information of voice prompt is used to indicate user and inputs value-added service type.

In the present embodiment, value-added service type can include but not limited to: navigation Service and video and audio play service etc.

204, terminal equipment plays the first information of voice prompt to user, receives the voice command of the startup value-added service that user sends according to the first information of voice prompt, and the voice command of this startup value-added service is sent to cloud computing platform server.

205, cloud computing platform server adopts signer-independent sign language recognition technology to resolve the voice command starting value-added service, obtains and starts value-added service order, starts corresponding value-added service according to this startup value-added service order.

Particularly, as shown in Figure 3,205 can comprise:

2051, the voice command of cloud computing platform server to described startup value-added service is resolved, and extracts the first voice characteristics information;

2052, cloud computing platform server searches the first wide spectrum phonetic feature storehouse according to the first voice characteristics information, from the first wide spectrum phonetic feature storehouse, obtain the startup value-added service order corresponding with described first voice characteristics information.

206, terminal equipment receives the value-added service voice directive command that user sends, and this value-added service voice directive command is sent to cloud computing platform server.

In the present embodiment, if value-added service is navigation Service, value-added service voice directive command is specially the voice directive command of object navigation address; If value-added service is video and audio play service, value-added service voice directive command is specially the voice directive command comprising object video and audio descriptor, such as: the voice indication information comprising song or video frequency program title, or comprise the voice indication information etc. of artist name, do not repeat one by one herein.

207, cloud computing platform server adopts signer-independent sign language recognition technology to resolve value-added service voice directive command, obtain the indication information that value-added service is relevant, the indication information relevant according to described value-added service generates value-added service control information, and this value-added service control information is sent to described terminal equipment by the mode adopting note to issue or set up Mobile data passage.

In this step, cloud computing platform server adopts signer-independent sign language recognition technology to resolve value-added service voice directive command, the step obtaining the indication information that value-added service is correlated with can comprise: cloud computing platform server is resolved value-added service voice directive command, extract the second voice characteristics information, search the second wide spectrum phonetic feature storehouse according to the second voice characteristics information, from this second wide spectrum phonetic feature storehouse, obtain the relevant indication information of the value-added service corresponding to described second voice characteristics information.

208, terminal equipment starts corresponding value-added service according to this value-added service control information, connect with the server provided value added service, obtain Value added service data from this server, this Value added service data is sent to display unit by communication.

209, the Value added service data of display unit display terminal transmission.

It should be noted that, the wide spectrum phonetic feature storehouse that the present embodiment provides is after the sound by gathering the whole of China various places, various people and these people (different background noise) under various circumstances, the set of the wide spectrum phonetic feature that essence extracts, this wide spectrum phonetic feature storehouse only depends on the information in existing " phonetic feature storehouse ", and does not rely on the phonetic feature training result of someone.

Its advantage is: the selected sample in (1) this wide spectrum phonetic feature storehouse is extensive, comprises the pronunciation of the people of the different regions of country variant in the world.Such as, in China, have chosen the pronunciation of the national almost people in area, county and town of each province, and several large class is divided into the people of national different regions, as North China, the Northeast, the south of Fujian Province language is regional, Guangdong language is regional, the said mandarin of people of these different regions is with the local dialect, its feature is different, after they are sorted out respectively, the people in area of basic simlarity of being pronounced by the local dialect is classified as a class, and the completeness so both considering sample has also been taken into account and built database and produce the least possible redundant information; (2) carried out extracting its voice characteristics information to the sound under varying environment (background noise) or voice command, as after automobile engine is started the voice command that produces, after automobile window is opened, generation wind-dryness and tire are made an uproar lower produced voice command, the voice command produced under other people such as to chip in suddenly at the disturbed condition, voice command etc. produced after the engine is shut off; (3) this wide spectrum phonetic feature storehouse comprises mandarin feature database and the local dialect feature database, and wherein the local dialect feature database comprises the south of Fujian Province repertorie, Guangdong language storehouse, Shanghai native language storehouse etc.

In the present embodiment, the voice messaging of 95% can be identified by signer-independent sign language recognition technology, in order to guarantee the voice messaging that 100% identifies user, the Consumer's Experience of the vehicle-mounted service of further raising, alternatively, the vehicle-mounted method of servicing controlled based on voice command that the embodiment of the present invention provides, can also comprise:

When cloud computing platform server cannot by starting the voice command of value-added service described in the identification of signer-independent sign language recognition technology time, cloud computing platform server is identified by the voice command of signer-independent sign language recognition operator attendance module to this startup value-added service, obtain corresponding startup value-added service order, and/or

When cloud computing platform server cannot pass through signer-independent sign language recognition technology identification value-added service voice directive command, cloud computing platform server is identified this value-added service voice directive command by signer-independent sign language recognition operator attendance module, obtains the indication information that value-added service is relevant.

The embodiment of the present invention provide based on voice command control vehicle-mounted method of servicing specific implementation can provide see the embodiment of the present invention as shown in Figure 1 based on voice command control vehicle-mounted service system described in, repeat no more herein.

The vehicle-mounted method of servicing controlled based on voice command that the embodiment of the present invention provides, user only need press the start key of the one-key type control device on the fixed part of the vehicle of setting, namely connect by the cloud computing platform server of this one-key type control device by terminal equipment and network side, value-added service is obtained by Voice command mode, and this Value added service data is sent to display unit display, reach and simplify the operating procedure that user carries out vehicle-mounted service, improve the object of the Consumer's Experience of vehicle-mounted service.Because cloud computing platform server can be resolved the voice command that terminal equipment sends by signer-independent sign language recognition module, the versatility of the technical scheme that the embodiment of the present invention is provided is better, be applicable to different regions, there is user's use of different phonetic, tone, further increase the Consumer's Experience of vehicle-mounted service.Due to driver when driving, only need press a key, just can control to obtain value-added service by voice command, and the Value added service data obtained can be shown by the display unit on vehicle by terminal equipment, make driver not need operation terminal device of taking sb's mind off sth, reduce danger on the run.

Another embodiment of the present invention also provides a kind of vehicle-mounted method of servicing controlled based on voice command, and the method is substantially identical with the vehicle-mounted method of servicing controlled based on voice command as shown in Figure 2, and its difference is, as shown in Figure 4, after 205, before 206, can also comprise:

210, cloud computing platform server sends the second information of voice prompt by terminal equipment described in voice conversation link box, and the second information of voice prompt is used to indicate described user and inputs value-added service voice directive command;

211, terminal equipment plays described second information of voice prompt to user.

The vehicle-mounted method of servicing controlled based on voice command that the embodiment of the present invention provides, user only need press the start key of the one-key type control device on the fixed part of the vehicle of setting, namely connect by the cloud computing platform server of this one-key type control device by terminal equipment and network side, value-added service is obtained by Voice command mode, and this Value added service data is sent to display unit display, reach and simplify the operating procedure that user carries out vehicle-mounted service, improve the object of the Consumer's Experience of vehicle-mounted service.Because cloud computing platform server can be resolved the voice command that terminal equipment sends by signer-independent sign language recognition module, the versatility of the technical scheme that the embodiment of the present invention is provided is better, be applicable to different regions, there is user's use of different phonetic, tone, further increase the Consumer's Experience of vehicle-mounted service.Due to driver when driving, only need press a key, just can control to obtain value-added service by voice command, and the Value added service data obtained can be shown by the display unit on vehicle by terminal equipment, make driver not need operation terminal device of taking sb's mind off sth, reduce danger on the run.Further, because cloud computing platform server sends the second information of voice prompt by terminal equipment to user, make user can send value-added service voice directive command according to this second information of voice prompt, avoid owing to there is communication failure (as channel block causes cloud computing platform server not receive the voice command of the startup value-added service that user sends) and cause cloud computing platform server info process mistake, the problem that the whole vehicle-mounted service system controlled based on voice command is paralysed, and then improve the reliability of the vehicle-mounted service system controlled based on voice command, ensure the Consumer's Experience of vehicle-mounted service.

Further embodiment of this invention also provides a kind of vehicle-mounted method of servicing controlled based on voice command, the method is substantially identical with the vehicle-mounted method of servicing controlled based on voice command as shown in Figure 2, its difference is, after 202, before 203, can also comprise: cloud computing platform server is verified described terminal equipment.Then now, 203 are: when being verified, and cloud computing platform server sends the first information of voice prompt by voice conversation connection to described terminal equipment.

The vehicle-mounted method of servicing controlled based on voice command that the embodiment of the present invention provides, in simplification user operation, improve on the Consumer's Experience basis of vehicle-mounted service, can verify terminal equipment further, thus ensure that the safety and reliability of the vehicle-mounted method of servicing controlled based on voice command.

Yet another embodiment of the invention also provides a kind of vehicle-mounted method of servicing controlled based on voice command, the method is substantially identical with the vehicle-mounted method of servicing controlled based on voice command as shown in Figure 2, and its difference is: the vehicle-mounted method of servicing controlled based on voice command that the present embodiment provides can also comprise: the step that terminal equipment is controlled by the operating state of communication to display unit.

Further, the vehicle-mounted method of servicing based on voice command control that the present embodiment provides also comprises: display unit receives the operational order of user by key area and/or touch-screen feedback areas, and this operational order is sent to described terminal equipment; Terminal equipment obtains value-added service more new data according to described operational order from providing the server of described value-added service, and by this value-added service, more new data or this terminal equipment send to described display unit in real time according to this realtime graphic that more new data upgrades; And display unit shows the step of described value-added service more new data.

The vehicle-mounted method of servicing controlled based on voice command that yet another embodiment of the invention provides, on the beneficial effect basis that scheme shown in Fig. 2 reaches, interoperability can be carried out between display unit and terminal equipment, thus it is more simple and convenient to make user carry out the operation of vehicle-mounted service, improve the experience that user carries out vehicle-mounted service, and owing to simplifying vehicle-mounted service operations, ensure the traffic safety of driver further.

The vehicle-mounted service system based on voice command control that the embodiment of the present invention provides and method, can be applied in the vehicles such as automobile, realize the object obtaining vehicle-mounted service when driving.

Through the above description of the embodiments, those skilled in the art can be well understood to the mode that the present invention can add required common hardware by software and realize, and can certainly pass through hardware, but in a lot of situation, the former is better execution mode.Based on such understanding, technical scheme of the present invention can embody with the form of software product the part that prior art contributes in essence in other words, this computer software product is stored in the storage medium that can read, as the floppy disk of computer, hard disk or CD etc., comprise some instructions and perform method described in each embodiment of the present invention in order to make a computer equipment (can be personal computer, server, or the network equipment etc.).

The above; be only the specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, is anyly familiar with those skilled in the art in the technical scope that the present invention discloses; change can be expected easily or replace, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should described be as the criterion with the protection range of claim.

Claims

1., based on the vehicle-mounted service system that voice command controls, comprise one-key type control device, terminal equipment, cloud computing platform server and display unit, it is characterized in that:

Described one-key type control device, be arranged on the fixed part of vehicle, after pressing start key user, connected by direct or short haul connection mode and terminal equipment, and drive described terminal equipment and cloud computing platform server to connect by direct or short haul connection mode, wherein, described start key is arranged on described one-key type control device;

2. system according to claim 1, it is characterized in that, described signer-independent sign language recognition module is specifically for resolving the voice command of described startup value-added service, extract the first voice characteristics information, the first wide spectrum phonetic feature storehouse is searched according to this first voice characteristics information, obtain the startup value-added service order corresponding with described first voice characteristics information, and

Specifically for resolving described value-added service voice directive command, extract the second voice characteristics information, search the second wide spectrum phonetic feature storehouse according to this second voice characteristics information, obtain the indication information that the value-added service corresponding to described second voice characteristics information is relevant.

3. system according to claim 1, is characterized in that, described cloud computing platform server also comprises signer-independent sign language recognition operator attendance module;

Described signer-independent sign language recognition operator attendance module, for when starting the voice command of value-added service described in described signer-independent sign language recognition module None-identified, the voice command of this startup value-added service being identified, obtaining corresponding startup value-added service order, and/or

For when described in described signer-independent sign language recognition module None-identified during value-added service voice directive command, this value-added service voice directive command is identified, obtain the indication information that described value-added service is relevant.

4. system according to claim 1, is characterized in that,

Described cloud computing platform server, also send the second information of voice prompt for being connected by described voice conversation to described terminal equipment, described second information of voice prompt is used to indicate described user and inputs value-added service voice directive command;

Described terminal equipment, also for playing described second information of voice prompt to described user.

5. system according to claim 1, is characterized in that, described cloud computing platform server, also for verifying described terminal equipment.

6. system according to claim 1, is characterized in that, described terminal equipment, also for being controlled by the operating state of communication to described display unit.

7. system according to claim 1, is characterized in that,

Described display unit, comprise key area and/or touch-screen feedback areas, described display unit is also for receiving the operational order of user by described key area and/or touch-screen feedback areas, described operational order is sent to described terminal equipment, receive and show described terminal equipment send value-added service more new data;

Described terminal equipment, also for receiving the operational order that described display unit sends, obtain value-added service more new data according to this operational order from providing the server of described value-added service, by this value-added service, more new data or this terminal equipment send to described display unit in real time according to this realtime graphic that more new data upgrades.

8. the system according to claim 1-7 any one, is characterized in that, described terminal equipment is mobile phone or PDA.

9. the system according to claim 1-7 any one, is characterized in that, the fixed part of described vehicle is steering wheel.

10. the system according to claim 1-7 any one, is characterized in that, described short haul connection mode is WiFi, WiMax, bluetooth, infrared and other privately owned wireless protocols.

11. systems according to claim 1-7 any one, is characterized in that, described display unit and described terminal equipment the communication used that connects be WiFi, WiMax, bluetooth, infrared and other privately owned wireless protocols.

12. systems according to claim 2, it is characterized in that, described cloud computing platform server comprises the first wide spectrum phonetic feature storehouse and the second wide spectrum phonetic feature storehouse further, in described first wide spectrum phonetic feature storehouse, there is the first wide spectrum voice characteristics information corresponding with described first voice characteristics information, in described second wide spectrum phonetic feature storehouse, there is the second wide spectrum voice characteristics information corresponding with described second voice characteristics information.

13. systems according to claim 2, is characterized in that, the described first and/or second wide spectrum phonetic feature storehouse comprises mandarin feature database and the local dialect feature database.

14. systems according to claim 13, is characterized in that, wherein the local dialect feature database comprises the south of Fujian Province repertorie, Guangdong language storehouse, Shanghai native language storehouse.

15. systems according to claim 1-7 any one, described cloud computing platform server is also for verifying terminal equipment, the voice command of the startup value-added service obtained from terminal equipment is fed back to user by cloud computing platform server again, and point out user to confirm, when just performing the voice command of this transmission after the positive reply obtaining user.

16. systems according to claim 1-7 any one, described cloud computing platform server is also for verifying terminal equipment, the voice command of the startup value-added service obtained from terminal equipment is fed back to user by cloud computing platform server again, and point out user to confirm, when after the negative reply obtaining user, cloud computing platform server resends this voice command, and when still can not get the positive reply of user after carrying out limited number of time circulation, this system turns to signer-independent sign language recognition operator attendance module, the voice command of this operator attendance module to this startup value-added service is used to identify.

17. systems according to claim 16, is characterized in that, the circulation of this limited number of time is more than 1 time.

18. systems according to claim 13, is characterized in that, the described first and/or second wide spectrum phonetic feature storehouse also comprises foreign language feature database.

19. systems according to claim 18, is characterized in that, have the external language library of main flow in this foreign language feature database, and the external language library of described main flow comprises: English storehouse, method repertorie, German storehouse, day repertorie.

20. systems according to claim 18, it is characterized in that, this system also has the automatic identification module of a feature database, and it distinguishes the feature database corresponding to this voice command for the voice command analysis sent user, and automatically selects corresponding feature database.

21. 1 kinds of vehicle-mounted method of servicing controlled based on voice command, is characterized in that, comprising:

22. methods according to claim 21, it is characterized in that, described cloud computing platform server adopts the voice command of signer-independent sign language recognition technology to described startup value-added service to resolve, obtain startup value-added service order to comprise: the voice command of described cloud computing platform server to described startup value-added service is resolved, extract the first voice characteristics information, search the first wide spectrum phonetic feature storehouse according to described first voice characteristics information, obtain the startup value-added service order corresponding with described first voice characteristics information; And,

Described cloud computing platform server adopts signer-independent sign language recognition technology to resolve described value-added service voice directive command, the indication information obtaining described value-added service relevant comprises: described cloud computing platform server is resolved described value-added service voice directive command, extract the second voice characteristics information, search the second wide spectrum phonetic feature storehouse according to described second voice characteristics information, obtain the indication information that the value-added service corresponding to described second voice characteristics information is relevant.

23. methods according to claim 21, is characterized in that, also comprise:

When described cloud computing platform server cannot by starting the voice command of value-added service described in the identification of signer-independent sign language recognition technology time, described cloud computing platform server is identified by the voice command of signer-independent sign language recognition operator attendance module to this startup value-added service, obtain corresponding startup value-added service order, and/or

When described cloud computing platform server cannot pass through value-added service voice directive command described in the identification of signer-independent sign language recognition technology, described cloud computing platform server is identified this value-added service voice directive command by signer-independent sign language recognition operator attendance module, obtains the indication information that described value-added service is relevant.

24. methods according to claim 21, is characterized in that, also comprise:

Described cloud computing platform server sends the second information of voice prompt by described voice conversation connection to described terminal equipment, and described second information of voice prompt is used to indicate described user and inputs value-added service voice directive command;

Described terminal equipment plays described second information of voice prompt to described user.

25. methods according to claim 21, is characterized in that, also comprise:

Described cloud computing platform server is verified described terminal equipment;

Then, when described being verified, described cloud computing platform server sends the first information of voice prompt by described voice conversation connection to described terminal equipment.

26. methods according to claim 21, is characterized in that, also comprise:

Described terminal equipment is controlled by the operating state of communication to described display unit.

27. methods according to claim 21, is characterized in that, also comprise:

Described display unit receives the operational order of user by key area and/or touch-screen feedback areas, and this operational order is sent to described terminal equipment;

Described terminal equipment obtains value-added service more new data according to described operational order from providing the server of described value-added service, and by this value-added service, more new data or this terminal equipment send to described display unit in real time according to this realtime graphic that more new data upgrades;

Described display unit shows described value-added service more new data.

28. methods according to claim 21-27 any one, it is characterized in that, described terminal equipment is mobile phone or PDA.

29. methods according to claim 21-27 any one, it is characterized in that, the fixed part of described vehicle is steering wheel.

30. methods according to claim 21-27 any one, it is characterized in that, described short haul connection mode is WiFi, WiMax, bluetooth, infrared and other privately owned wireless protocols.

31. methods according to claim 21-27 any one, is characterized in that, described display unit and described terminal equipment the communication used that connects be WiFi, WiMax, bluetooth, infrared and other privately owned wireless protocols.

32. methods according to claim 22, it is characterized in that, described cloud computing platform server comprises the first wide spectrum phonetic feature storehouse and the second wide spectrum phonetic feature storehouse further, in described first wide spectrum phonetic feature storehouse, there is the first wide spectrum voice characteristics information corresponding with affiliated first voice characteristics information, in described second wide spectrum phonetic feature storehouse, there is the second wide spectrum voice characteristics information corresponding with affiliated second voice characteristics information.

33. methods according to claim 22, is characterized in that, the described first and/or second wide spectrum phonetic feature storehouse comprises mandarin feature database and the local dialect feature database.

34. methods according to claim 30, is characterized in that, wherein the local dialect feature database comprises the south of Fujian Province repertorie, Guangdong language storehouse, Shanghai native language storehouse.

35. methods according to claim 21-27 any one, described cloud computing platform server is also for verifying terminal equipment, the voice command of the startup value-added service obtained from terminal equipment is fed back to user by cloud computing platform server again, and point out user to confirm, when just performing the voice command of this transmission after the positive reply obtaining user.

36. methods according to claim 21-27 any one, described cloud computing platform server is also for verifying terminal equipment, the voice command of the startup value-added service obtained from terminal equipment is fed back to user by cloud computing platform server again, and point out user to confirm, when after the negative reply obtaining user, cloud computing platform server resends this voice command, and when still can not get the positive reply of user after carrying out limited number of time circulation, this cloud computing platform server turns to signer-independent sign language recognition operator attendance module, the voice command of this operator attendance module to this startup value-added service is used to identify.

37. methods according to claim 36, is characterized in that, the circulation of this limited number of time is more than 1 time.

38. methods according to claim 33, is characterized in that, the described first and/or second wide spectrum phonetic feature storehouse also comprises foreign language feature database.

39., according to method according to claim 38, is characterized in that, have the external language library of main flow in this foreign language feature database, and the external language library of described main flow comprises: English storehouse, method repertorie, German storehouse, day repertorie.

40. according to method according to claim 38, it is characterized in that, described cloud computing platform server also has the automatic identification module of a feature database, and it distinguishes the feature database corresponding to this voice command for the voice command analysis sent user, and automatically selects corresponding feature database.