CN109473100A - Business scenario voice man-machine interaction method and its system based on speech recognition - Google Patents
Business scenario voice man-machine interaction method and its system based on speech recognition Download PDFInfo
- Publication number
- CN109473100A CN109473100A CN201811341744.4A CN201811341744A CN109473100A CN 109473100 A CN109473100 A CN 109473100A CN 201811341744 A CN201811341744 A CN 201811341744A CN 109473100 A CN109473100 A CN 109473100A
- Authority
- CN
- China
- Prior art keywords
- scene
- speech recognition
- voice
- module
- user
- 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
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; 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 OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Abstract
The invention discloses a kind of the business scenario voice man-machine interaction method based on speech recognition, the phonetic order of reception user's input, progress speech recognition；After text out to be identified, semantic parsing is carried out according to text text, identification user is intended to and target vocabulary；According to the user's intention and target vocabulary identified, locked service scene.The business scenario voice man-machine interactive system based on speech recognition that the invention also discloses a kind of, including speech recognition module, semantic meaning analysis module and scene locking module.This invention ensures that the sequence of voice control, ensure that the continuous of special sound order group is reached and accurately executed, avoids conflict of qualification, cause voice chaotic, cause to position mistake, while ensure that the driving safety of vehicle.
Description
Technical field
The present invention relates to technical field of voice recognition, and in particular to a kind of business scenario voice based on speech recognition is man-machine
Exchange method and its system.
Background technique
With the fast development of mobile Internet and car networking, mobile application relevant to vehicle is more and more now, such as
Passenger traffic, shipping are also increasingly dependent on mobile interchange equipment now.
And for vehicle drive security standpoint, driver should not onboard carry out unsafe mobile device gesture behaviour
Make, thus we need another more convenient and safe man-machine interaction mode, and voice can regard one of as.
Have benefited from the fast development of current speech and semantics recognition, we can be used similar to Iflytek or Baidu
Voice carries out most of common semantic parsing.However in some specific transactions scenes, traditional semantic parsing substantially cannot
Successfully, this is because the order word in special scenes is more uncommon, conventional semanteme cannot be used to parse intention.And
And usual human-computer interaction, all by, confirmation, in next step up to the process of completion etc., and voice input has very big answer
Polygamy, same time are likely to be received different voice inputs, if we to different voice commands without control, it is this
Situation, which will result in, is difficult to complete specific scenery control, we illustrate this voice control scene:
1) driver needs to navigate to Tian An-men, and voice inputs " I will arrive Tian An-men "
2) Baidu or Iflytek, which parse, is intended to " arriving ", and destination is " Tian An-men "
3) route map that should start navigation application, and plan away Tian An-men is parsed according to intention and destination,
There may be several
4) then the ideal input of scene should be " Article 3 ", " selection Article 3 ", if user inputs Article 3,
Entire navigation action can be smoothly down until complete；But if accidentally say that " making a phone call " three words, voice can be gone
Starting dialing app, is caused using confusion.
Summary of the invention
Based on this, in view of the above-mentioned problems, guaranteeing special sound order it is necessary to propose a kind of sequence for guaranteeing voice control
The business scenario voice man-machine interaction method and its system based on speech recognition of group continuously reached and accurately execute.
The present invention provides a kind of business scenario voice man-machine interaction method based on speech recognition, and its technical solution is as follows:
A kind of business scenario voice man-machine interaction method based on speech recognition, comprising the following steps:
A, the phonetic order of user's input is received, speech recognition is carried out；
B, after text out to be identified, semantic parsing is carried out according to text text, identification user is intended to and target word
It converges；
C, according to the user's intention and target vocabulary identified, locked service scene.
In the technical scheme, by voice input module, it is responsible for voiced translation being text, and parse semanteme, identifies
User's intention and target vocabulary out then according to intention third-party application corresponding to target vocabulary searching routing starting, and lock
Service scenarios, locked service scene, subsequent voice input the order to be formed and do not meet with current scene, then disregard；After making
Continuous voice input inputs within the scope of same type with voice before, avoids conflict of qualification, causes voice chaotic, and it is fixed to cause
Bit-errors.
Preferably, the step c the following steps are included:
According to defined common voice service scenarios type, the scene type of third-party application transmitting, locking clothes are received
Business scene.In addition to by receiving user's intention and target vocabulary locking scene, common voice service scene type also may be selected
Scene locking is carried out, is more convenient, is intuitive, efficiently；Avoid only mistake occur to the definition of scene by voice.
Preferably, further comprising the steps of:
If subsequent voice instruction matches with service scenarios, subsequent voice instruction is received；If subsequent voice instruction with
Service scenarios mismatch, then do not receive subsequent voice instruction, and issue the prompt re-entered.The technical program is specific right
The method that subsequent voice instruction is handled can know voice in Same Scene so that the judgement to voice is more acurrate
Not, the classification without first carrying out type to the voice received is handled, and further ensures the continuous of special sound order group
Reach, while improving the accuracy of order execution.
Preferably, further comprising the steps of:
After locked service scene, sends the user identified and be intended to third-party application；
After the completion of third-party application processing, the lock state of the service scenarios is released.
In the technical scheme, service application is carried out, third-party application is responsible for executing movement, and after completing to be intended to, solution
Lock order scene；Continuously reaching for special sound order group is further realized, a serial order is smoothly transferred to
Position, had not only improved the accuracy of speech recognition, but also improve the efficiency of entire human-computer interaction.
Preferably, further comprising the steps of:
After locked service scene, if untreated relevant user is intended within the presetting processing time, automatically terminate
The lock state of the service scenarios；
After locked service scene, if the voice number of input is more than pre-determined times, the service scenarios are automatically terminated
Lock state.
If the voice number of voice input of untreated user for a long time or input has been more than presetting number,
Locking is then automatically terminated, phonetic order is continued waiting for, user can re-enter voice and identify, release, improve without artificial
The efficiency of drive safety and speech recognition, while preventing data redundancy, disorder；Moreover, time-out time can be set according to demand,
Sufficiently meet user demand.
The business scenario voice man-machine interactive system based on speech recognition that the present invention also provides a kind of, technical solution is such as
Under:
A kind of business scenario voice man-machine interactive system based on speech recognition, including speech recognition module, semantic parsing
Module and scene locking module, in which:
Speech recognition module carries out speech recognition for receiving the phonetic order of user's input；
Semantic meaning analysis module carries out semantic parsing according to text text, identification is used after text out to be identified
Family is intended to and target vocabulary；
Scene locking module, for according to the user's intention and target vocabulary identified, locked service scene.
Preferably, the scene locking module includes that common scene locks submodule, for according to defined common-use words
Sound service scenarios type receives the scene type of third-party application transmitting, locked service scene.
It preferably, further include phonetic decision module, for judging whether subsequent voice instruction matches with service scenarios, such as
Fruit is then to receive subsequent voice instruction；If it is not, then not receiving, and issue the prompt re-entered.
It preferably, further include being intended to sending module and scene releasing module, in which:
Be intended to sending module, for the user identified being sent and being intended to third-party application after locked service scene；
Scene releases module, for releasing the lock state of the service scenarios after the completion of third-party application processing.
It preferably, further include that time-out releases module and super secondary releasing module, in which:
Time-out releases module, after being used for locked service scene, if the untreated relevant use within the presetting processing time
Family is intended to, then automatically terminates the lock state of the service scenarios；
Super secondary releasing module, after being used for locked service scene, if the voice number of input is more than pre-determined times, automatically
Release the lock state of the service scenarios.
The beneficial effects of the present invention are:
1, this invention ensures that the sequence of voice control, ensure that the continuous of special sound order group is reached and accurately held
Row, avoids conflict of qualification, causes voice chaotic, causes to position mistake, while ensure that the driving safety of vehicle.
2, subsequent voice is instructed and is judged with whether service scenarios match, fully ensure that special sound order group
Continuity enables voice to be sufficiently identified, and then intention represented by quick obtaining voice, is exactly found corresponding positioning.
3, it is responsible for executing movement by third-party application, and after completing to be intended to, unlocking command scene, so that one serial
Order can smoothly be transmitted in place, not only improve the accuracy of speech recognition, but also improve the efficiency of entire human-computer interaction.
4, the voice primary to untreated user for a long time inputs, and automatically terminates scene locking, continues waiting for voice and refer to
It enables, user can re-enter voice and identify, release without artificial, improve the efficiency of drive safety and speech recognition, together
When prevent data redundancy, disorder；Moreover, time-out time can be set according to demand, sufficiently meet user demand.
Detailed description of the invention
Fig. 1 is the one of which of the business scenario voice man-machine interaction method described in the embodiment of the present invention based on speech recognition
Flow chart；
Fig. 2 is another stream of the business scenario voice man-machine interaction method described in the embodiment of the present invention based on speech recognition
Cheng Tu；
Fig. 3 is the one of which of the business scenario voice man-machine interactive system described in the embodiment of the present invention based on speech recognition
Functional block diagram；
Fig. 4 is that the another kind of the business scenario voice man-machine interactive system described in the embodiment of the present invention based on speech recognition is former
Manage block diagram.
Description of symbols:
10- speech recognition module；20- semantic meaning analysis module；30- scene locking module；40- voice match module；50-
Scape releases module；60- often uses scene locking module；701- time-out releases module；The super secondary releasing module of 702-.
Specific embodiment
The embodiment of the present invention is described in detail with reference to the accompanying drawing.
Embodiment 1
As shown in Figure 1, a kind of business scenario voice man-machine interaction method based on speech recognition, comprising the following steps:
A, the phonetic order of user's input is received, speech recognition is carried out；
B, after text out to be identified, semantic parsing is carried out according to text text, identification user is intended to and target word
It converges；
C, according to the user's intention and target vocabulary identified, locked service scene；
D, subsequent voice input is received, if subsequent voice instruction matches with service scenarios, receives and identifies the subsequent language
Sound, and the subsequent voice after identification is sent to third-party application；If subsequent voice instruction is mismatched with service scenarios, do not receive
Subsequent voice instruction, and issue the prompt re-entered；
E, after the completion of third-party application processing, the lock state of the service scenarios is released.
In the present embodiment, by voice input module, it is responsible for voiced translation being text, and parse semanteme, identifies
User is intended to and target vocabulary, then according to intention third-party application corresponding to target vocabulary searching routing starting, and locks clothes
Business scene, locked service scene, subsequent voice input the order to be formed and do not meet with current scene, then disregard；Make subsequent
Voice input inputted within the scope of same type with voice before, avoid conflict of qualification, cause voice chaotic, cause to position
Mistake；Meet if subsequent voice inputs the order to be formed with current scene, carry out service application, third-party application is responsible for holding
Action is made, and after completing to be intended to, unlocking command scene；Continuously reaching for special sound order group is realized, so that a series
Order can smoothly transmit in place, not only improved the accuracy of speech recognition, but also improve the efficiency of entire human-computer interaction.
Embodiment 2
As shown in Fig. 2, a kind of business scenario voice man-machine interaction method based on speech recognition, comprising the following steps:
A, according to defined common voice service scenarios type, the scene type of third-party application transmitting, locking are received
Service scenarios；
B, the phonetic order of user's input is received, speech recognition is carried out；
C, after text out to be identified, semantic parsing is carried out according to text text, identification user is intended to and target word
It converges；
D, the user that identifies of judgement be intended to and target vocabulary whether locking service scenarios, if it is, to third
Fang Yingyong sends the voice after the identification；If it is not, then not sending, and issue the prompt re-entered；
E, after the completion of third-party application processing, the lock state of the service scenarios is released.
In addition to by receiving user's intention and target vocabulary locking scene, common voice service scene type also may be selected
Scene locking is carried out, is more convenient, is intuitive, efficiently；Avoid only mistake occur to the definition of scene by voice.
Embodiment 3
The present embodiment is on the basis of embodiment 1, further comprising the steps of:
After locked service scene, if untreated relevant user is intended within the presetting processing time, automatically terminate
The lock state of the service scenarios；
After locked service scene, if the voice number of input is more than pre-determined times, the service scenarios are automatically terminated
Lock state.
Embodiment 4
The present embodiment is further comprising the steps of on the basis of embodiment 2:
After locked service scene, if untreated relevant user is intended within the presetting processing time, automatically terminate
The lock state of the service scenarios；
After locked service scene, if the voice number of input is more than pre-determined times, the service scenarios are automatically terminated
Lock state.
If the voice number of voice input of untreated user for a long time or input has been more than presetting number,
Locking is then automatically terminated, phonetic order is continued waiting for, user can re-enter voice and identify, release, improve without artificial
The efficiency of drive safety and speech recognition, while preventing data redundancy, disorder；Moreover, time-out time can be set according to demand,
Sufficiently meet user demand.
Embodiment 5
The present embodiment is the system of embodiment 1, as shown in figure 3, a kind of business scenario voice based on speech recognition is man-machine
Interactive system, including speech recognition module 10, semantic meaning analysis module 20, scene locking module 30, voice match module 40 and field
Scape releases module 50, in which:
Speech recognition module 10 carries out speech recognition for receiving the phonetic order of user's input；
Semantic meaning analysis module 20 carries out semantic parsing, identification according to text text after text out to be identified
User is intended to and target vocabulary；
Scene locking module 30, for according to the user's intention and target vocabulary identified, locked service scene；
Voice match module 40, for receiving subsequent voice input, if subsequent voice instruction matches with service scenarios,
It receives and identifies the subsequent voice, and send the subsequent voice after identification to third-party application；If subsequent voice instruction and service field
Scape mismatches, then does not receive subsequent voice instruction, and issue the prompt re-entered；
Scene releases module 50, after the completion of third-party application processing, releases the lock state of the service scenarios.
Embodiment 6
The present embodiment is the system of embodiment 2, as shown in figure 4, a kind of business scenario voice based on speech recognition is man-machine
Interactive system, including common scene locking module 60, speech recognition module 10, semantic meaning analysis module 20, voice match module 40
Module 50 is released with scene, in which:
Common scene locking module 60 receives third-party application and passes according to defined common voice service scenarios type
The scene type passed, locked service scene；
Speech recognition module 10 carries out speech recognition for receiving the phonetic order of user's input；
Semantic meaning analysis module 20, it is to be identified go out text after, semantic parsing is carried out according to text text, identifies user
Intention and target vocabulary；
Voice match module 40, the user for judging to identify is intended to and whether target vocabulary is in the service field of locking
Scape, if it is, sending the voice after the identification to third-party application；If it is not, then do not send, and issue mentioning of re-entering
Show；
Scene releases module 50, after the completion of third-party application processing, releases the lock state of the service scenarios.
The scene locking module 30 includes that common scene locks submodule 301, for according to defined common voice
Service scenarios type receives the scene type of third-party application transmitting, locked service scene.
Embodiment 7
The present embodiment is the system of embodiment 3, as shown in figure 3, further including that time-out releases module 701 and super secondary releasing module
702, in which:
Time-out releases module 701, after being used for locked service scene, if untreated relevant within the presetting processing time
User is intended to, then automatically terminates the lock state of the service scenarios；
Super secondary releasing module 702, after being used for locked service scene, if the voice number of input is more than pre-determined times,
Automatically terminate the lock state of the service scenarios.
Embodiment 8
The present embodiment is the system of embodiment 4, as shown in figure 4, further including that time-out releases module 701 and super secondary releasing module
702, in which:
Time-out releases module 701, after being used for locked service scene, if untreated relevant within the presetting processing time
User is intended to, then automatically terminates the lock state of the service scenarios；
Super secondary releasing module 702, after being used for locked service scene, if the voice number of input is more than pre-determined times,
Automatically terminate the lock state of the service scenarios.
A specific embodiment of the invention above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
Limitations on the scope of the patent of the present invention therefore cannot be interpreted as.It should be pointed out that for those of ordinary skill in the art
For, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to guarantor of the invention
Protect range.
Claims (10)
1. a kind of business scenario voice man-machine interaction method based on speech recognition, which comprises the following steps:
A, the phonetic order of user's input is received, speech recognition is carried out；
B, after text out to be identified, semantic parsing is carried out according to text text, identification user is intended to and target vocabulary；
C, according to the user's intention and target vocabulary identified, locked service scene.
2. the business scenario voice man-machine interaction method according to claim 1 based on speech recognition, which is characterized in that institute
State step c the following steps are included:
According to defined common voice service scenarios type, the scene type of third-party application transmitting, locked service field are received
Scape.
3. the business scenario voice man-machine interaction method according to claim 1 or 2 based on speech recognition, feature exist
In further comprising the steps of:
If subsequent voice instruction matches with service scenarios, subsequent voice instruction is received；If subsequent voice instruction and service
Scene mismatches, then does not receive subsequent voice instruction, and issue the prompt re-entered.
4. the business scenario voice man-machine interaction method according to claim 1 or 2 based on speech recognition, feature exist
In further comprising the steps of:
After locked service scene, sends the user identified and be intended to third-party application；
After the completion of third-party application processing, the lock state of the service scenarios is released.
5. the business scenario voice man-machine interaction method according to claim 1 or 2 based on speech recognition, feature exist
In further comprising the steps of:
After locked service scene, if untreated relevant user is intended within the presetting processing time, the clothes are automatically terminated
The lock state for scene of being engaged in；
After locked service scene, if the voice number of input is more than pre-determined times, the locking of the service scenarios is automatically terminated
State.
6. a kind of business scenario voice man-machine interactive system based on speech recognition, which is characterized in that including speech recognition module,
Semantic meaning analysis module and scene locking module, in which:
Speech recognition module carries out speech recognition for receiving the phonetic order of user's input；
Semantic meaning analysis module carries out semantic parsing, identification user's meaning according to text text after text out to be identified
Figure and target vocabulary；
Scene locking module, for according to the user's intention and target vocabulary identified, locked service scene.
7. the business scenario voice man-machine interactive system according to claim 6 based on speech recognition, which is characterized in that institute
Stating scene locking module includes that common scene locks submodule, for connecing according to defined common voice service scenarios type
Receive the scene type of third-party application transmitting, locked service scene.
8. the business scenario voice man-machine interactive system according to claim 6 or 7 based on speech recognition, feature exist
In further including phonetic decision module, for judging whether subsequent voice instruction matches with service scenarios, if it is, reception
Subsequent voice instruction；If it is not, then not receiving, and issue the prompt re-entered.
9. the business scenario voice man-machine interactive system according to claim 6 or 7 based on speech recognition, feature exist
In further including being intended to sending module and scene to release module, in which:
Be intended to sending module, for the user identified being sent and being intended to third-party application after locked service scene；
Scene releases module, for releasing the lock state of the service scenarios after the completion of third-party application processing.
10. the business scenario voice man-machine interactive system according to claim 6 or 7 based on speech recognition, feature exist
In further including that time-out releases module and super secondary releasing module, in which:
Time-out releases module, after being used for locked service scene, if untreated relevant user's meaning within the presetting processing time
Figure, then automatically terminate the lock state of the service scenarios；
Super secondary releasing module, for if the voice number of input is more than pre-determined times, automatically terminating after locked service scene
The lock state of the service scenarios.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811341744.4A CN109473100A (en) | 2018-11-12 | 2018-11-12 | Business scenario voice man-machine interaction method and its system based on speech recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811341744.4A CN109473100A (en) | 2018-11-12 | 2018-11-12 | Business scenario voice man-machine interaction method and its system based on speech recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109473100A true CN109473100A (en) | 2019-03-15 |
Family
ID=65671708
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811341744.4A Pending CN109473100A (en) | 2018-11-12 | 2018-11-12 | Business scenario voice man-machine interaction method and its system based on speech recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109473100A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110265010A (en) * | 2019-06-05 | 2019-09-20 | 四川驹马科技有限公司 | The recognition methods of lorry multi-person speech and system based on Baidu's voice |
| CN110880324A (en) * | 2019-10-31 | 2020-03-13 | 北京大米科技有限公司 | Voice data processing method and device, storage medium and electronic equipment |
| CN112269473A (en) * | 2020-12-23 | 2021-01-26 | 深圳市蓝凌软件股份有限公司 | Man-machine interaction method and system based on flexible scene definition |
| WO2021027267A1 (en) * | 2019-08-15 | 2021-02-18 | 华为技术有限公司 | Speech interaction method and apparatus, terminal and storage medium |
| CN112669831A (en) * | 2019-09-29 | 2021-04-16 | 百度在线网络技术（北京）有限公司 | Voice recognition control method and device, electronic equipment and readable storage medium |
| CN112787899A (en) * | 2021-01-08 | 2021-05-11 | 青岛海尔特种电冰箱有限公司 | Equipment voice interaction method, computer readable storage medium and refrigerator |
| CN112995270A (en) * | 2019-12-18 | 2021-06-18 | 本田技研工业株式会社 | Intelligent system, control method of intelligent system, and storage medium |
| CN113990301A (en) * | 2021-12-28 | 2022-01-28 | 广州小鹏汽车科技有限公司 | Voice interaction method and device, server and readable storage medium thereof |
| CN114143401A (en) * | 2021-11-24 | 2022-03-04 | 建信金融科技有限责任公司 | Telephone customer service response adaptation method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107293294A (en) * | 2016-03-31 | 2017-10-24 | 腾讯科技（深圳）有限公司 | A kind of voice recognition processing method and device |
| CN107564518A (en) * | 2017-08-21 | 2018-01-09 | 百度在线网络技术（北京）有限公司 | Smart machine control method, device and computer equipment |
| CN108062212A (en) * | 2016-11-08 | 2018-05-22 | 沈阳美行科技有限公司 | A kind of voice operating method and device based on scene |
| CN108228764A (en) * | 2017-12-27 | 2018-06-29 | 神思电子技术股份有限公司 | A kind of single-wheel dialogue and the fusion method of more wheel dialogues |
| JP2018159729A (en) * | 2017-03-22 | 2018-10-11 | 株式会社東芝 | Interaction system construction support device, method and program |
-
2018
- 2018-11-12 CN CN201811341744.4A patent/CN109473100A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107293294A (en) * | 2016-03-31 | 2017-10-24 | 腾讯科技（深圳）有限公司 | A kind of voice recognition processing method and device |
| CN108062212A (en) * | 2016-11-08 | 2018-05-22 | 沈阳美行科技有限公司 | A kind of voice operating method and device based on scene |
| JP2018159729A (en) * | 2017-03-22 | 2018-10-11 | 株式会社東芝 | Interaction system construction support device, method and program |
| CN107564518A (en) * | 2017-08-21 | 2018-01-09 | 百度在线网络技术（北京）有限公司 | Smart machine control method, device and computer equipment |
| CN108228764A (en) * | 2017-12-27 | 2018-06-29 | 神思电子技术股份有限公司 | A kind of single-wheel dialogue and the fusion method of more wheel dialogues |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110265010A (en) * | 2019-06-05 | 2019-09-20 | 四川驹马科技有限公司 | The recognition methods of lorry multi-person speech and system based on Baidu's voice |
| US11922935B2 (en) | 2019-08-15 | 2024-03-05 | Huawei Technologies Co., Ltd. | Voice interaction method and apparatus, terminal, and storage medium |
| WO2021027267A1 (en) * | 2019-08-15 | 2021-02-18 | 华为技术有限公司 | Speech interaction method and apparatus, terminal and storage medium |
| CN112669831B (en) * | 2019-09-29 | 2022-10-21 | 百度在线网络技术（北京）有限公司 | Voice recognition control method and device, electronic equipment and readable storage medium |
| CN112669831A (en) * | 2019-09-29 | 2021-04-16 | 百度在线网络技术（北京）有限公司 | Voice recognition control method and device, electronic equipment and readable storage medium |
| CN110880324A (en) * | 2019-10-31 | 2020-03-13 | 北京大米科技有限公司 | Voice data processing method and device, storage medium and electronic equipment |
| CN112995270B (en) * | 2019-12-18 | 2024-03-05 | 本田技研工业株式会社 | Intelligent agent system, control method for intelligent agent system, and storage medium |
| CN112995270A (en) * | 2019-12-18 | 2021-06-18 | 本田技研工业株式会社 | Intelligent system, control method of intelligent system, and storage medium |
| CN112269473B (en) * | 2020-12-23 | 2021-05-11 | 深圳市蓝凌软件股份有限公司 | Man-machine interaction method and system based on flexible scene definition |
| CN112269473A (en) * | 2020-12-23 | 2021-01-26 | 深圳市蓝凌软件股份有限公司 | Man-machine interaction method and system based on flexible scene definition |
| CN112787899B (en) * | 2021-01-08 | 2022-10-28 | 青岛海尔特种电冰箱有限公司 | Equipment voice interaction method, computer readable storage medium and refrigerator |
| CN112787899A (en) * | 2021-01-08 | 2021-05-11 | 青岛海尔特种电冰箱有限公司 | Equipment voice interaction method, computer readable storage medium and refrigerator |
| CN114143401A (en) * | 2021-11-24 | 2022-03-04 | 建信金融科技有限责任公司 | Telephone customer service response adaptation method and device |
| CN114143401B (en) * | 2021-11-24 | 2024-04-12 | 建信金融科技有限责任公司 | Telephone customer service response adapting method and device |
| CN113990301A (en) * | 2021-12-28 | 2022-01-28 | 广州小鹏汽车科技有限公司 | Voice interaction method and device, server and readable storage medium thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109473100A (en) | Business scenario voice man-machine interaction method and its system based on speech recognition | |
| EP3444813B1 (en) | User-guided arbitration of speech processing results | |
| US20060287868A1 (en) | Dialog system | |
| US20140358545A1 (en) | Multiple Parallel Dialogs in Smart Phone Applications | |
| US20150056951A1 (en) | Vehicle telematics unit and method of operating the same | |
| CN109903770A (en) | The devices and methods therefor of language mistake for correcting user | |
| US8509396B2 (en) | Automatic creation of complex conversational natural language call routing system for call centers | |
| US20150302851A1 (en) | Gesture-based cues for an automatic speech recognition system | |
| CN107680588A (en) | Intelligent sound air navigation aid, device and storage medium | |
| CN112541068A (en) | Method, system, device and storage medium for recognizing intention of voice conversation | |
| CN111094924A (en) | Data processing apparatus and method for performing voice-based human-machine interaction | |
| US10964318B2 (en) | Dialogue management | |
| CN103187062A (en) | Vehicle-mounted data processing device and preservation service data processing system | |
| EP3444812B1 (en) | Automatic speech recognition system, corresponding method and computer-readable medium | |
| CN110556102A (en) | intention recognition and execution method, device, vehicle-mounted voice conversation system and computer storage medium | |
| CN112214589A (en) | Method for multi-round session framework based on cold start | |
| EP3444814A1 (en) | Unified n-best asr results | |
| KR102566822B1 (en) | Method and apparatus for providing chatbot service | |
| CN111524508A (en) | Voice conversation system and voice conversation implementation method | |
| CN107545895B (en) | Information processing method and electronic device | |
| CN112002325B (en) | Multi-language voice interaction method and device | |
| CN109741741A (en) | Control method, intelligent terminal and the computer readable storage medium of intelligent terminal | |
| CN111737442B (en) | Intelligent customer service multi-round session management method and device | |
| US11646031B2 (en) | Method, device and computer-readable storage medium having instructions for processing a speech input, transportation vehicle, and user terminal with speech processing | |
| US9858918B2 (en) | Root cause analysis and recovery systems and methods |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190315 |
|
| RJ01 | Rejection of invention patent application after publication |