CN105469797A - Method and system for controlling switching-over from intelligent voice identification to manual services - Google Patents
Method and system for controlling switching-over from intelligent voice identification to manual services Download PDFInfo
- Publication number
- CN105469797A CN105469797A CN201511013971.0A CN201511013971A CN105469797A CN 105469797 A CN105469797 A CN 105469797A CN 201511013971 A CN201511013971 A CN 201511013971A CN 105469797 A CN105469797 A CN 105469797A
- Authority
- CN
- China
- Prior art keywords
- manual service
- user
- voice
- intelligent sound
- recognition
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000013019 agitation Methods 0.000 claims description 8
- 230000036651 mood Effects 0.000 claims description 8
- 230000002996 emotional effect Effects 0.000 claims description 7
- 230000008451 emotion Effects 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 235000021167 banquet Nutrition 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 241001672694 Citrus reticulata Species 0.000 description 1
- 206010039740 Screaming Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention provides a method and system for controlling switching-over from intelligent voice identification to manual services, wherein voice identification is carried out through receiving of voice information sent by a user; and the quantity of identification failure times is increased by one if the identification fails. Whether the quantity of the identification failure times reaches a preset threshold is determined, wherein steps are executed and the manual services are started according to a preset hotline number if the quantity reaches the preset threshold, so that the problem that the user cannot control equipment via voices after the multiple times of voice identification failures, and the voice identification equipment cannot automatically connect a manual service platform according to the user's demands can be overcome, and the user's voice identification operations become convenient.
Description
Technical field
The present invention relates to speech recognition technology, the control method of in particular a kind of intelligent sound identification switching manual service and system.
Background technology
Speech recognition technology, has been widely used in teaching, robot and onboard system at present.The application of speech recognition technology comprises phonetic dialing, Voice Navigation, indoor equipment control, voice document searching, simple dictation data inputting etc.
Because our national dialect is many, widely different between language, current speech recognition technology discrimination is for the crowd being ignorant of mandarin, discrimination is still not high, and identification error often causes user to reduce functions of the equipments experience sense, especially can not get the help wanted when user's urgent need.The effect that speech recognition wants is reached in crucial moment.Speech recognition capabilities is not unceasing study and lifting in user's use procedure also, and each identification error can constantly repeat in next time, intelligent poor.
Therefore, prior art awaits further improvement.
Summary of the invention
In view of above-mentioned weak point of the prior art, the object of the invention is to the control method for user provides a kind of intelligent sound identification to transfer manual service and system, overcome repeatedly speech recognition failure in prior art, cannot automatically access manual service platform defect according to the demand of user.
The technical scheme that technical solution problem of the present invention adopts is as follows:
A control method for intelligent sound identification switching manual service, wherein, comprising:
The voice messaging that A, reception user send, carries out speech recognition to it; If recognition failures, then perform step B, if identify successfully, then perform step C;
B, recognition failures number of times is added one, and judge whether recognition failures number of times reaches predetermined threshold, if so, then perform step D, otherwise return steps A;
Whether comprise default keyword in the voice messaging that C, judgement identify, if contain, then perform step D, otherwise the voice messaging that will identify exports;
D, according to the hot line number preset, access manual service platform.
The control method of described intelligent sound identification switching manual service, wherein, described step also comprises:
The voice identification result that E, acquisition manual service identify, is stored into recognition feature database by the voice messaging of institute's speech recognition result and corresponding user thereof.
The control method of described intelligent sound identification switching manual service, wherein, described step C also comprises:
C1, acquisition user speech waveform character vector, described user speech waveform character vector is compared with storaged voice waveform character vector, if comparison success, then performs step D, otherwise repeat this step, described storaged voice waveform character vector is corresponding with emotional characteristics.
The control method of described intelligent sound identification switching manual service, wherein, described default keyword comprises: word and the mood of the instruction of access manual service platform are characterized by agitation, disappointment or angry word.
The control method of described intelligent sound identification switching manual service, wherein, also comprises before described steps A:
A0, whether to identify containing class alerting signal in ambient sound, if identify class alerting signal, then perform step D, otherwise return steps A; Described class alerting signal comprises: alerting signal and collision alarm.
A control system for intelligent sound identification switching manual service, wherein, comprising:
Sound identification module, for receiving the voice messaging that user sends, carries out speech recognition to it;
Counting module, for when after speech recognition failure, adds one by recognition failures number of times, and judges whether recognition failures number of times reaches predetermined threshold;
Keyword identification module, for judging whether comprise default keyword in the voice messaging that identifies;
Connect artificial module, for according to the hot line number preset, access manual service platform.
The control system of described intelligent sound identification switching manual service, wherein, comprising:
Self-learning module, for obtaining the voice identification result that manual service identifies, by institute's speech recognition result and the phonetic storage that sends with the user corresponding to it to recognition feature database.
The control system of described intelligent sound identification switching manual service, wherein, keyword identification module comprises:
Emotion identification unit, user obtains user speech waveform character vector, is compared by described user speech waveform character vector with storaged voice waveform character vector; Described storaged voice waveform character vector is corresponding with emotional characteristics.
The control system of described intelligent sound identification switching manual service, wherein, described default keyword comprises: word and the mood of the instruction of access manual service platform are characterized by agitation, disappointment or angry word.
The control system of described intelligent sound identification switching manual service, wherein, described system also comprises:
Whether Signal analysis module, for identifying containing class alerting signal in ambient sound, if identify class alerting signal, then according to the hot line number preset, connecting manual service, otherwise repeating speech recognition; Described class alerting signal comprises: alerting signal and collision alarm.
Beneficial effect, the invention provides control method and the system of a kind of intelligent sound identification switching manual service, by receiving the voice messaging that user sends, carrying out speech recognition to it; If recognition failures, recognition failures number of times is added one.Judge whether recognition failures number of times reaches predetermined threshold, if, then perform step, according to the hot line number preset, connect manual service, thus after overcoming repeatedly speech recognition failure, user cannot be controlled equipment by voice, and speech recognition apparatus does not have automatically according to the problem of the demand access manual service platform of user, and the speech recognition operation for user provides convenient convenient.
Accompanying drawing explanation
Fig. 1 is the flow chart of steps of the control method of a kind of intelligent sound identification switching manual service of the present invention.
Fig. 2 is the theory structure schematic diagram of the control system of a kind of intelligent sound identification switching manual service of the present invention.
Embodiment
For making object of the present invention, technical scheme and advantage clearly, clearly, developing simultaneously referring to accompanying drawing, the present invention is described in more detail for embodiment.Should be appreciated that specific embodiment described herein only for explaining the present invention, being not intended to limit the present invention.
In prior art, speech recognition can generally be applied on vehicle-mounted, intelligent terminal or home appliance, user sends phonetic control command, the said equipment operates accordingly according to the phonetic control command of user, and therefore the control method by intelligent sound identification switching manual service provided by the present invention is applicable to the above-mentioned field relating to speech recognition.
The invention provides the control method of a kind of intelligent sound identification switching manual service, as shown in Figure 1, described method comprises:
The voice messaging that S11, reception user send, carries out speech recognition to it; And judge that whether speech recognition is successful, if recognition failures, then perform step S21, if identify successfully, then perform step S3.
First speech recognition equipment receives the voice messaging that user sends, and to the speech recognition that user sends.Described speech recognition equipment can for being arranged on the speech recognition equipment in on-vehicle host, or the speech recognition equipment be arranged in intelligent terminal or be arranged on the speech recognition equipment of home appliance inside, user receives the phonetic order of user, described phonetic order is identified, and by the control chip that the phonetic order identified is transferred to vehicle-mounted master controller or is transferred in intelligent terminal or home appliance, trigger action instruction.
In this step, the voice messaging of the user got is identified, if identify, perform step S3, otherwise perform step S21.
S21, recognition failures number of times is added one, and perform step S221, judge whether recognition failures number of times reaches predetermined threshold, if so, then perform step S4, otherwise return step S11.
If speech recognition failure in above-mentioned steps S12, then the number of times of failure is added one, and judge whether accumulative recognition failures number of times reaches predetermined threshold, if reach predetermined threshold, then trigger and perform step S4, otherwise return step S11, continue to receive the voice messaging that sends of user, and voice messaging identifies, if identification error again, then the number of times of recognition failures is added one, until the number of times of recognition failures reaches predetermined threshold.
In order to realize better serving the demand that same user is interior at one time, in this step, the gate time of accumulative recognition failures number of times is controlled, such as: within half an hour, the number of times of recognition failures adds up, if exceed half an hour, then think that this voice messaging received and the voice messaging of recognition failures recorded before half an hour are not sames, current situation carries out recognition failures to another voice messaging that user sends, then counter and timer all reset, unlatching is to the recognition time of this speech recognition operation and the number of times of recognition failures counts and timing.
Whether comprise default keyword in the voice messaging that S3, judgement identify, if contain, then perform step S4, otherwise the voice messaging that will identify exports.
Whether if identify the voice messaging of user, then judge containing the keyword preset it, described keyword is: word and the mood of the instruction of access manual service platform are characterized by agitation, disappointment or angry word.Such as: the word of access manual service platform instruction is: manual service, the service of attending a banquet or special messenger's service etc., described mood is characterized by agitation, disappointment or angry word and is: be tired of or the word etc. of mouth of screaming an obscenity.After receiving above-mentioned keyword, directly perform step S4.
In order to improve the identification to user emotion change, this step also comprises:
S31, acquisition user speech waveform character vector, described user speech waveform character vector is compared with storaged voice waveform character vector, if comparison success, then performs step S4, otherwise repeat this step, described storaged voice waveform character vector is corresponding with emotional characteristics.
By comparing to user speech waveform character vector, judging that whether excited with characterizing consumer its speech waveform proper vector be consistent, if unanimously, then illustrating that user may be under the mood of agitation or indignation, therefore enters step S4.
S4, according to the hot line number preset, access manual service platform.
If in above-mentioned steps, exceed predetermined threshold number of times all unidentified go out the voice messaging of user, or identify user to unidentified go out its voice messaging and after sending the situation performing manual service or want to enter manual service, then according to the manual service platform hot line number preset, access manual service platform, carries out the speech recognition of manual platform.
In specific implementation process, after access manual service platform, identify the dialect belonging to the voice messaging of user, the dialect kind correspondence according to identifying is linked into attending a banquet on manual service platform of affiliated dialect kind.
It is conceivable that, above-mentioned work can be realized by the background server containing various dialect databases too, namely the dialect belonging to voice messaging of user is first found out, dialect information characteristics in described voice messaging and dialect databases belonging to it is matched, and the information matched is turned back to voice messaging identification, by background server for its speech recognition does further Informational support.
In order to improve the accuracy rate of speech recognition apparatus to user speech identification, this method also comprises:
S5, obtain the voice identification result that manual service land identification goes out, by institute's speech recognition result and be stored into recognition feature database.
It is the process of speech recognition equipment self study in this step, namely it receives the voice identification result that manual service land identification goes out, and institute's speech recognition result and corresponding voice messaging thereof are stored in recognition feature database, when user is after sending described voice messaging, directly can obtain the voice identification result corresponding with described voice messaging from recognition feature database, avoid again to the problem of described voice messaging recognition failures, improve the accuracy of user speech identification.
In order to improve the intelligent of speech recognition equipment, also comprise before described step S1:
S0, whether to identify containing class alerting signal in ambient sound, if identify class alerting signal, then perform step S4, otherwise return step S1; Described class alerting signal comprises: alerting signal and collision alarm.That is to say, after speech recognition equipment gets signal similar containing alerting signal in environment, then directly enter manual service platform.The appearance of described alerting signal and collision alarm may mean vehicle-mounted generation severe crash, needs emergency relief, therefore after this type of signal being detected, directly connects manual service, for user provides convenient.
Be identified as example to carry out user instruction to the speech recognition apparatus on vehicle-mounted below, method of the present invention is further explained.
When user is at steering vehicle, by voice, phonetic control command is sent to on-vehicle host: such as: open vehicle mounted guidance, report the steering orders such as real-time road condition information, the speech recognition apparatus now on-vehicle host installed identifies the phonetic control command that user sends, if the language sent due to this user is the local dialect, speech recognition apparatus cannot identify the steering order that it sends, then this speech recognition failure, it adds one automatically on the number of times of recognition failures, if user sends three same phonetic control commands, equal recognition failures, and predetermined threshold value is three times, then on-vehicle host connects the manual service platform on vehicle net backstage automatically, by manually coming to identify its voice operating instruction, if identify successfully, then vehicle net service platform is pushing outside the information corresponding to phonetic order to corresponding on-vehicle host, the object information of this speech recognition is also sent to it, then when user sends above-mentioned phonetic control command to on-vehicle host again, on-vehicle host just can go out content corresponding to it by Auto-matching, and control to operate accordingly.
Concrete, when carrying out speech recognition, also carry out the identification of keyword and emotional change, if identify user send the instruction of access manual service or find because repeatedly recognition failures user emotion is irritated or angry, then also automatically connect manual service, provide convenience for user solves required problem in time.
Based on the above method, the invention also discloses the control system of a kind of intelligent sound identification switching manual service, as shown in Figure 2, comprising:
Sound identification module 110, for receiving the voice messaging that user sends, carries out speech recognition to it; Its function is as described in step S11 and step S12.
Counting module 120, for when after speech recognition failure, adds one by recognition failures number of times, and judges whether recognition failures number of times reaches predetermined threshold; Its function is as described in step S21 and step S22.
Keyword identification module 130, for judging whether comprise default keyword in the voice messaging that identifies; Its function is as described in step S3.
Connect artificial module 140, for according to the hot line number preset, access manual service platform, its function is as described in step S4.
Described system also comprises:
Self-learning module, for obtaining the voice identification result that manual service identifies, by institute's speech recognition result and the phonetic storage that sends with user corresponding to it to recognition feature database.
Described keyword identification module comprises:
Emotion identification unit, user obtains user speech waveform character vector, is compared by described user speech waveform character vector with storaged voice waveform character vector; Described storaged voice waveform character vector is corresponding with emotional characteristics.
Described default keyword comprises: word and the mood of the instruction of access manual service platform are characterized by agitation, disappointment or angry word.
Described system also comprises:
Whether Signal analysis module, for identifying containing class alerting signal in ambient sound, if identify class alerting signal, then according to the hot line number preset, connecting manual service, otherwise repeating speech recognition; Described class alerting signal comprises: alerting signal and collision alarm.
Beneficial effect, the invention provides control method and the system of a kind of intelligent sound identification switching manual service, by receiving the voice messaging that user sends, carrying out speech recognition to it; If recognition failures, recognition failures number of times is added one.Judge whether recognition failures number of times reaches predetermined threshold, if so, then perform step, according to the hot line number preset, connect manual service.The method of the invention and system, by after repeatedly speech recognition failure, automatically access manual service, realize the problem that user cannot be controlled equipment by voice, for user provides convenience when using voice to know.
Be understandable that, for those of ordinary skills, can be equal to according to technical scheme of the present invention and inventive concept thereof and replace or change, and all these change or replace the protection domain that all should belong to the claim appended by the present invention.
Claims (10)
1. a control method for intelligent sound identification switching manual service, is characterized in that, comprising:
The voice messaging that A, reception user send, carries out speech recognition to it; If recognition failures, then perform step B, if identify successfully, then perform step C;
B, recognition failures number of times is added one, and judge whether recognition failures number of times reaches predetermined threshold, if so, then perform step D, otherwise return steps A;
Whether comprise default keyword in the voice messaging that C, judgement identify, if contain, then perform step D, otherwise the voice messaging that will identify exports;
D, according to the hot line number preset, access manual service platform.
2. according to claim 1 intelligent sound identification switching manual service control method, it is characterized in that, described step also comprises:
The voice identification result that E, acquisition manual service identify, is stored into recognition feature database by the voice messaging of institute's speech recognition result and corresponding user thereof.
3. according to claim 1 intelligent sound identification switching manual service control method, it is characterized in that, described step C also comprises:
C1, acquisition user speech waveform character vector, described user speech waveform character vector is compared with storaged voice waveform character vector, if comparison success, then performs step D, otherwise repeat this step, described storaged voice waveform character vector is corresponding with emotional characteristics.
4. the control method of intelligent sound identification switching manual service according to claim 1, it is characterized in that, described default keyword comprises: word and the mood of the instruction of access manual service platform are characterized by agitation, disappointment or angry word.
5. according to any one of claim 1-4 intelligent sound identification switching manual service control method, it is characterized in that, also comprise before described steps A:
A0, whether to identify containing class alerting signal in ambient sound, if identify class alerting signal, then perform step D, otherwise return steps A; Described class alerting signal comprises: alerting signal and collision alarm.
6. a control system for intelligent sound identification switching manual service, is characterized in that, comprising:
Sound identification module, for receiving the voice messaging that user sends, carries out speech recognition to it;
Counting module, for when after speech recognition failure, adds one by recognition failures number of times, and judges whether recognition failures number of times reaches predetermined threshold;
Keyword identification module, for judging whether comprise default keyword in the voice messaging that identifies;
Connect artificial module, for according to the hot line number preset, access manual service platform.
7. according to claim 6 intelligent sound identification switching manual service control system, it is characterized in that, comprising:
Self-learning module, for obtaining the voice identification result that manual service identifies, by institute's speech recognition result and the phonetic storage that sends with user corresponding to it to recognition feature database.
8. according to claim 6 intelligent sound identification switching manual service control system, it is characterized in that, keyword identification module comprises:
Emotion identification unit, user obtains user speech waveform character vector, is compared by described user speech waveform character vector with storaged voice waveform character vector; Described storaged voice waveform character vector is corresponding with emotional characteristics.
9. the control system of intelligent sound identification switching manual service according to claim 6, it is characterized in that, described default keyword comprises: word and the mood of the instruction of access manual service platform are characterized by agitation, disappointment or angry word.
10. according to any one of claim 6-9 intelligent sound identification switching manual service control system, it is characterized in that, described system also comprises:
Whether Signal analysis module, for identifying containing class alerting signal in ambient sound, if identify class alerting signal, then according to the hot line number preset, connecting manual service, otherwise repeating speech recognition; Described class alerting signal comprises: alerting signal and collision alarm.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201511013971.0A CN105469797A (en) | 2015-12-31 | 2015-12-31 | Method and system for controlling switching-over from intelligent voice identification to manual services |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201511013971.0A CN105469797A (en) | 2015-12-31 | 2015-12-31 | Method and system for controlling switching-over from intelligent voice identification to manual services |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105469797A true CN105469797A (en) | 2016-04-06 |
Family
ID=55607424
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201511013971.0A Pending CN105469797A (en) | 2015-12-31 | 2015-12-31 | Method and system for controlling switching-over from intelligent voice identification to manual services |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105469797A (en) |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107708938A (en) * | 2016-04-15 | 2018-02-16 | 深圳前海达闼云端智能科技有限公司 | A kind of cloud robot system, robot and robot cloud platform |
CN108319631A (en) * | 2017-01-16 | 2018-07-24 | 网智服务国际股份有限公司 | Intelligent control system of knowledge base and feedback method thereof |
CN109040485A (en) * | 2018-08-30 | 2018-12-18 | 山东高速股份有限公司 | A kind of high-speed service hot line intelligent panoramic speech guide system based on natural language processing |
CN109243438A (en) * | 2018-08-24 | 2019-01-18 | 上海擎感智能科技有限公司 | A kind of car owner's emotion adjustment method, system and storage medium |
CN109525737A (en) * | 2018-12-03 | 2019-03-26 | 商客通尚景信息技术江苏有限公司 | A kind of call Cut-in control method and system |
CN109688281A (en) * | 2018-12-03 | 2019-04-26 | 复旦大学 | A kind of intelligent sound exchange method and system |
CN109889676A (en) * | 2017-12-06 | 2019-06-14 | 通用汽车环球科技运作有限责任公司 | Consultant's seamless connection |
CN109981910A (en) * | 2019-02-22 | 2019-07-05 | 中国联合网络通信集团有限公司 | Business recommended method and apparatus |
CN110675856A (en) * | 2019-10-14 | 2020-01-10 | 苏州思必驰信息科技有限公司 | Man-machine conversation method and device for call center |
CN110970017A (en) * | 2018-09-27 | 2020-04-07 | 北京京东尚科信息技术有限公司 | Human-computer interaction method and system and computer system |
CN111277712A (en) * | 2019-07-11 | 2020-06-12 | 上海联逾信息技术有限公司 | Telephone calling-out system based on language type classification processing |
CN111626706A (en) * | 2020-05-27 | 2020-09-04 | 中国联合网络通信集团有限公司 | User intention identification method and device |
CN112017663A (en) * | 2020-08-14 | 2020-12-01 | 博泰车联网(南京)有限公司 | Voice generalization method and device and computer storage medium |
CN112667762A (en) * | 2020-12-25 | 2021-04-16 | 贵州北斗空间信息技术有限公司 | Method for quickly constructing GIS (geographic information System) through zero programming |
CN112802475A (en) * | 2020-12-30 | 2021-05-14 | 厦门市美亚柏科信息股份有限公司 | Automatic application login method based on voice recognition and computer readable storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101136962A (en) * | 2006-08-30 | 2008-03-05 | 许军 | Telephone switching system and switching method thereof |
CN101707640A (en) * | 2009-09-04 | 2010-05-12 | 西安鼎辉通信技术有限责任公司 | Push-to-talk (PTT) voice mobile phone terminal, communication service system and communication service method thereof |
CN102625005A (en) * | 2012-03-05 | 2012-08-01 | 广东天波信息技术股份有限公司 | Call center system with function of real-timely monitoring service quality and implement method of call center system |
CN103440767A (en) * | 2013-09-04 | 2013-12-11 | 彭博 | Highway-driving-information vehicle-mounted terminal, monitoring system and method |
CN104144192A (en) * | 2013-05-10 | 2014-11-12 | 北京四维图新科技股份有限公司 | Voice interaction method and device and vehicle-mounted communication terminal |
CN104751843A (en) * | 2013-12-25 | 2015-07-01 | 上海博泰悦臻网络技术服务有限公司 | Voice service switching method and voice service switching system |
-
2015
- 2015-12-31 CN CN201511013971.0A patent/CN105469797A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101136962A (en) * | 2006-08-30 | 2008-03-05 | 许军 | Telephone switching system and switching method thereof |
CN101707640A (en) * | 2009-09-04 | 2010-05-12 | 西安鼎辉通信技术有限责任公司 | Push-to-talk (PTT) voice mobile phone terminal, communication service system and communication service method thereof |
CN102625005A (en) * | 2012-03-05 | 2012-08-01 | 广东天波信息技术股份有限公司 | Call center system with function of real-timely monitoring service quality and implement method of call center system |
CN104144192A (en) * | 2013-05-10 | 2014-11-12 | 北京四维图新科技股份有限公司 | Voice interaction method and device and vehicle-mounted communication terminal |
CN103440767A (en) * | 2013-09-04 | 2013-12-11 | 彭博 | Highway-driving-information vehicle-mounted terminal, monitoring system and method |
CN104751843A (en) * | 2013-12-25 | 2015-07-01 | 上海博泰悦臻网络技术服务有限公司 | Voice service switching method and voice service switching system |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107708938A (en) * | 2016-04-15 | 2018-02-16 | 深圳前海达闼云端智能科技有限公司 | A kind of cloud robot system, robot and robot cloud platform |
CN108319631A (en) * | 2017-01-16 | 2018-07-24 | 网智服务国际股份有限公司 | Intelligent control system of knowledge base and feedback method thereof |
CN109889676A (en) * | 2017-12-06 | 2019-06-14 | 通用汽车环球科技运作有限责任公司 | Consultant's seamless connection |
CN109243438B (en) * | 2018-08-24 | 2023-09-26 | 上海擎感智能科技有限公司 | Method, system and storage medium for regulating emotion of vehicle owner |
CN109243438A (en) * | 2018-08-24 | 2019-01-18 | 上海擎感智能科技有限公司 | A kind of car owner's emotion adjustment method, system and storage medium |
CN109040485A (en) * | 2018-08-30 | 2018-12-18 | 山东高速股份有限公司 | A kind of high-speed service hot line intelligent panoramic speech guide system based on natural language processing |
CN109040485B (en) * | 2018-08-30 | 2020-08-28 | 山东高速股份有限公司 | High-speed service hotline intelligent panoramic voice navigation system based on natural language processing |
CN110970017A (en) * | 2018-09-27 | 2020-04-07 | 北京京东尚科信息技术有限公司 | Human-computer interaction method and system and computer system |
CN109525737A (en) * | 2018-12-03 | 2019-03-26 | 商客通尚景信息技术江苏有限公司 | A kind of call Cut-in control method and system |
CN109688281A (en) * | 2018-12-03 | 2019-04-26 | 复旦大学 | A kind of intelligent sound exchange method and system |
CN109981910A (en) * | 2019-02-22 | 2019-07-05 | 中国联合网络通信集团有限公司 | Business recommended method and apparatus |
CN111277712A (en) * | 2019-07-11 | 2020-06-12 | 上海联逾信息技术有限公司 | Telephone calling-out system based on language type classification processing |
CN110675856A (en) * | 2019-10-14 | 2020-01-10 | 苏州思必驰信息科技有限公司 | Man-machine conversation method and device for call center |
CN111626706A (en) * | 2020-05-27 | 2020-09-04 | 中国联合网络通信集团有限公司 | User intention identification method and device |
CN112017663A (en) * | 2020-08-14 | 2020-12-01 | 博泰车联网(南京)有限公司 | Voice generalization method and device and computer storage medium |
CN112017663B (en) * | 2020-08-14 | 2024-04-30 | 博泰车联网(南京)有限公司 | Voice generalization method and device and computer storage medium |
CN112667762A (en) * | 2020-12-25 | 2021-04-16 | 贵州北斗空间信息技术有限公司 | Method for quickly constructing GIS (geographic information System) through zero programming |
CN112667762B (en) * | 2020-12-25 | 2023-04-25 | 贵州北斗空间信息技术有限公司 | Method for quickly constructing GIS system by zero programming |
CN112802475A (en) * | 2020-12-30 | 2021-05-14 | 厦门市美亚柏科信息股份有限公司 | Automatic application login method based on voice recognition and computer readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105469797A (en) | Method and system for controlling switching-over from intelligent voice identification to manual services | |
JP6828001B2 (en) | Voice wakeup method and equipment | |
CN108346430B (en) | Dialogue system, vehicle having dialogue system, and dialogue processing method | |
US20170162191A1 (en) | Prioritized content loading for vehicle automatic speech recognition systems | |
CN103903619B (en) | A kind of method and system improving speech recognition accuracy | |
CN109841212B (en) | Speech recognition system and speech recognition method for analyzing commands with multiple intents | |
CN104282305A (en) | Result arbitrating system and method for speech system | |
CN103928027B (en) | Adaptive approach and system for voice system | |
CN111309889A (en) | Method and device for text processing | |
US20200027452A1 (en) | Speech recognition for vehicle voice commands | |
CN106297785A (en) | A kind of intelligent service system based on car networking | |
CN110262273A (en) | A kind of home equipment control method, device, storage medium and smart home system | |
CN110648661A (en) | Dialogue system, vehicle, and method for controlling vehicle | |
CN109920410B (en) | Apparatus and method for determining reliability of recommendation based on environment of vehicle | |
CN111400438A (en) | Method and device for identifying multiple intentions of user, storage medium and vehicle | |
EP3570276A1 (en) | Dialogue system, and dialogue processing method | |
CN105467986A (en) | Full-automatic onsite control automobile driving method via Chinese speech | |
CN113239178A (en) | Intention generation method, server, voice control system and readable storage medium | |
CN110570867A (en) | Voice processing method and system for locally added corpus | |
CN113674742B (en) | Man-machine interaction method, device, equipment and storage medium | |
CN104375816A (en) | Method for controlling automobile driving by Chinese texts in short or long range | |
CN104914859A (en) | Full-automatic foreign language voice field control driving automobile system | |
CN105609105A (en) | Speech recognition system and speech recognition method | |
CN105827798A (en) | Processing method of position information and electronic device | |
CN105404292A (en) | Fully automatic foreign language speech remote control car driving method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: 528100 F3 (F3), C District, southwest garden of Sanshui center science and Technology Industrial Park, Foshan, Guangdong Applicant after: Guangdong Ecar Telematics Service Co.,Ltd. Address before: 528100, No. 1, No. 1, Inner Ring North Road, Donghai Road, Donghai Road, Sanshui District, Guangdong Province, 203.204 Applicant before: Guangdong Ecar Telematics Service Co.,Ltd. |
|
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160406 |