CN110349576A - Power system operation instruction executing method, apparatus and system based on speech recognition - Google Patents
Power system operation instruction executing method, apparatus and system based on speech recognition Download PDFInfo
- Publication number
- CN110349576A CN110349576A CN201910408481.2A CN201910408481A CN110349576A CN 110349576 A CN110349576 A CN 110349576A CN 201910408481 A CN201910408481 A CN 201910408481A CN 110349576 A CN110349576 A CN 110349576A
- Authority
- CN
- China
- Prior art keywords
- character string
- speech
- words
- phrases
- power system
- 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 34
- 238000012546 transfer Methods 0.000 claims abstract description 19
- 238000006243 chemical reaction Methods 0.000 claims abstract description 16
- 238000013507 mapping Methods 0.000 claims description 19
- 230000014509 gene expression Effects 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 239000012141 concentrate Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012544 monitoring process 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
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- 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
- G10L2015/223—Execution procedure of a spoken command
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 discloses a kind of power system operation instruction executing method, apparatus and system based on speech recognition, including phonetic order collection is obtained, it includes operational order and electric network model title that the phonetic order, which is concentrated,；The audio stream on-line conversion that will acquire based on speech-recognition services is at character string；Based on the words and phrases mapped file safeguarded, two times transfer is carried out to the character string, forms new character string；Phonetic order collection based on acquisition carries out automatic identification to the new character string, obtains operational order, completes power system operation instruction execution.The present invention is serviced by integrated speech identification, the voice of system operators is converted to text, and then execute corresponding system command, is had the characteristics that flexible and convenient and identification is accurate, is improved the efficiency of system automation operation.
Description
Technical field
The invention belongs to power system dispatching automation technique fields, and in particular to a kind of electric system behaviour based on speech recognition
Make instruction executing method, apparatus and system.
Background technique
Speech recognition technology (Auto Speech Recognize, ASR) problem to be solved is to allow computer can
The voice of " understanding " mankind comes out the text information for including in voice " extraction ".ASR technology is equivalent to pacifies to computer system
It loads onto " ear ", and then realizes that the information age, this most natural, most convenient and fast means carried out man-machine communication and friendship using " voice "
Mutually.
In automation system for the power network dispatching, many times need in different application programs and the selection of a large amount of data
Manual operations is carried out, proficiency and accuracy to operator have no small requirement.It can pole using speech recognition technology
Big the step of simplifying part operation, reduce the work difficulty of system operators, to improve the efficiency of dispatching automation monitoring.
The speech recognition technology of Iflytek company maintains the leading position at home at present, the clothes of speech recognition provided by it
Business (Auto Transcribe Server, ATS) and client-side interface (Auto Transcribe Client, ATC) can be square
Being integrated with dispatch automated system just, realizes the voice control function of operational order.
Summary of the invention
In view of the above-mentioned problems, the present invention proposes a kind of power system operation instruction executing method based on speech recognition, lead to
Integrated speech identification service is crossed, the voice of system operators text is converted to, and then execute corresponding system command, had
Feature flexible and convenient and that identification is accurate, improves the efficiency of system automation operation.
In order to achieve the above technical purposes, reach above-mentioned technical effect, the invention is realized by the following technical scheme:
In a first aspect, the present invention provides a kind of power system operation instruction executing method based on speech recognition, comprising:
Phonetic order collection is obtained, it includes operational order and electric network model title that the phonetic order, which is concentrated,；
The audio stream on-line conversion that will acquire based on speech-recognition services is at character string；
Based on the words and phrases mapped file safeguarded, two times transfer is carried out to the character string, forms new character string；
Phonetic order collection based on acquisition carries out automatic identification to the new character string, obtains operational order, completes electricity
Force system operational order executes.
Preferably, the phonetic order collection is the regular expression of a string of character string forms.
Preferably, the audio stream on-line conversion that will acquire based on speech-recognition services is specifically included at character string
Following steps:
Driver of sound card is called, obtains audio stream from microphone port, and real-time transmission is to speech-recognition services；
The audio stream of acquisition is converted into character string immediately online by the speech-recognition services.
Preferably, the speech-recognition services also judge automatically whether audio stream terminates, and sound is continued to if not terminating
Frequency flows；If finishing, the character string identified is returned immediately.
Preferably, the method also includes:
It is concentrated to the phonetic order and increases new operational order and electric network model title.
Preferably, described based on the words and phrases mapped file safeguarded, two times transfer is carried out to the character string, is formed new
Character string specifically includes:
By the wrong words and phrases unsteady state operation of the identification in words and phrases mapping relations original in the speech-recognition services at just
True words and phrases form the words and phrases mapping relations safeguarded；
Two times transfer is carried out to the character string based on the words and phrases mapping relations safeguarded, forms new character string.
Second aspect, the present invention provides a kind of power system operation instruction executing method based on speech recognition, comprising:
Module is obtained, for obtaining phonetic order collection, it includes operational order and electric network model name that the phonetic order, which is concentrated,
Claim；
First conversion module, the audio stream on-line conversion for will acquire based on speech-recognition services is at character string；
Second conversion module, for carrying out two times transfer, shape to the character string based on the words and phrases mapped file safeguarded
The character string of Cheng Xin；
Identification module carries out automatic identification to the new character string for the phonetic order collection based on acquisition, is grasped
It instructs, completes power system operation instruction execution.
Preferably, the phonetic order collection is the regular expression of a string of character string forms.
Preferably, described based on the words and phrases mapped file safeguarded, two times transfer is carried out to the character string, is formed new
Character string specifically includes:
By the wrong words and phrases unsteady state operation of the identification in words and phrases mapping relations original in the speech-recognition services at just
True words and phrases form the words and phrases mapping relations safeguarded；
Two times transfer is carried out to the character string based on the words and phrases mapping relations safeguarded, forms new character string.
The third aspect, the present invention provides a kind of power system operation instruction execution system for speech-recognition services,
Include:
Processor is adapted for carrying out each instruction；And
Equipment is stored, is suitable for storing a plurality of instruction, described instruction is suitable for by processor load and perform claim requires first
Step described in any one of aspect.
Compared with prior art, beneficial effects of the present invention:
A kind of power system operation instruction executing method based on speech recognition proposed by the present invention, is known by integrated speech
It does not service, the voice of system operators is converted to text, and then execute corresponding system command, have flexible and convenient and know
Not accurate feature, reduces the work difficulty of system operators at the step of can greatly simplifying part operation, to improve and be
It unites automatically-monitored efficiency.
Detailed description of the invention
Fig. 1 is the architecture diagram of an embodiment of the present invention；
Fig. 2 is the instruction identification flow diagram of an embodiment of the present invention.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to embodiments, to the present invention
It is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not used to
It limits the scope of protection of the present invention.
Application principle of the invention is explained in detail with reference to the accompanying drawing.
Embodiment 1
The embodiment of the invention provides a kind of power system operation instruction executing method based on speech recognition, including it is following
Step:
Step (1) obtains phonetic order collection, and it includes operational order and electric network model title that the phonetic order, which is concentrated,；
In a kind of specific embodiment of the embodiment of the present invention, the phonetic order collection be a string of character string forms just
Then expression formula, for cooperating realization that the character string for meeting specified rule is converted to the corresponding operational order of electric system, specifically
Ground, the acquisition process of the phonetic order collection are as follows:
Firstly, induction and conclusion goes out the function process of voice operating can be used, specified station wiring diagram is such as opened, number is called
According to library maintenance tool, alarm today etc. is inquired；
Secondly, in function process can the model name that occur with parametric form, such as plant stand title, compartment name and set
Standby title extracts, and phonetic order collection corresponding with electric system is formed in conjunction with process, such as " opens the wiring of xxx plant stand
Figure " respective operations instruction " GExplorer-pic xxx.g-push-context 1 "；
Further, in order to improve the accuracy rate of identification, the method also includes: Xiang Suoshu phonetic order concentrate increase it is new
Operational order and electric network model title；
The audio stream on-line conversion that step (2) will acquire based on speech-recognition services is at character string；
Specifically, described to will acquire based on speech-recognition services in a kind of specific embodiment of the embodiment of the present invention
The audio stream on-line conversion arrived at character string, specifically includes the following steps:
The driver of sound card of call operation system obtains audio stream from microphone port, and directly real-time transmission to voice is known
Not Fu Wu (ATS), without compressing and converting format or save audio file；
The audio stream of acquisition is converted into character string immediately online by the speech-recognition services, realizes efficient speech recognition
Translate function；
Further, in the other embodiments of the embodiment of the present invention, the speech-recognition services also judge automatically sound
Whether frequency stream terminates, and audio stream is continued to if not terminating；If finishing, the character string identified is returned immediately, is had
Body realizes process are as follows:
When obtaining audio stream, by identifying the pause length of sentence, judges whether phonetic order has been conveyed and finish, certainly
It is dynamic to terminate to obtain audio stream operation, and recognition result is returned immediately, promote the operating experience of user；
Step (3) carries out two times transfer based on the words and phrases mapped file safeguarded, to the character string, forms new character
String；
Due between speech-recognition services algorithm itself and operator's intonation, the tone, pronunciation there are difference, recognition result without
Method reaches complete accurate；For this reason, it may be necessary to be commonly used in the character string of acquisition and identify that wrong words and phrases carry out secondary turn
It changes, then system operatio process is translated to by phonetic order collection, that is, the accuracy of identification instruction can be improved.In the embodiment of the present invention
A kind of specific embodiment in, it is described based on the words and phrases mapped file safeguarded, two times transfer, shape are carried out to the character string
The character string of Cheng Xin, specifically includes:
By the wrong words and phrases unsteady state operation of the identification in words and phrases mapping relations original in the speech-recognition services at just
True words and phrases form the words and phrases mapping relations safeguarded；Such as: by establishing words and phrases mapping relations, such as " kilovolt=kV ", " directly
Row=execution " etc.；
Two times transfer is carried out to the character string obtained by step (2) based on the words and phrases mapping relations safeguarded to obtain newly
Character string；
Step (4) carries out automatic identification to the new character string based on the phonetic order collection of acquisition, obtains operational order,
Complete power system operation instruction execution；The automatic identification process specifically: concentrate new character string and phonetic order
Each character string is compared, to complete the process that character string is converted into operational order, this part can use existing skill
Art.
Embodiment 2
The embodiment of the invention provides a kind of power system operation instruction executing method based on speech recognition, comprising:
Obtain module；Phonetic order collection is obtained, it includes operational order and electric network model title that the phonetic order, which is concentrated,；It is excellent
Selection of land, the phonetic order collection are the regular expressions of a string of character string forms；
First conversion module, the audio stream on-line conversion for will acquire based on speech-recognition services is at character string；
Second conversion module, for carrying out two times transfer, shape to the character string based on the words and phrases mapped file safeguarded
The character string of Cheng Xin；Preferably, described based on the words and phrases mapped file safeguarded, two times transfer, shape are carried out to the character string
The character string of Cheng Xin, specifically includes: by the wrong word of the identification in words and phrases mapping relations original in the speech-recognition services
Sentence unsteady state operation forms the words and phrases mapping relations safeguarded at correct words and phrases；Based on the words and phrases mapping relations safeguarded
Two times transfer is carried out to the character string, forms new character string；
Identification module carries out automatic identification to the new character string for the phonetic order collection based on acquisition, is grasped
It instructs, completes power system operation instruction execution.
Rest part is same as Example 1.
Embodiment 3
A kind of power system operation instruction execution system based on speech-recognition services is provided in the embodiment of the present invention, is wrapped
It includes:
Processor is adapted for carrying out each instruction；And
Equipment is stored, is suitable for storing a plurality of instruction, described instruction is suitable for by processor load and perform claim requires to implement
The step of described in example 1.
Rest part is same as Example 1.
In summary:
The present invention proposes a kind of power system operation instruction executing method based on speech recognition, is identified by integrated speech
The voice of system operators is converted to text, and then executes corresponding system command by service, has flexible and convenient and identification
Accurate feature improves the efficiency of system automation operation.
The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention.The technology of the industry
Personnel are it should be appreciated that the present invention is not limited to the above embodiments, and the above embodiments and description only describe this
The principle of invention, without departing from the spirit and scope of the present invention, various changes and improvements may be made to the invention, these changes
Change and improvement all fall within the protetion scope of the claimed invention.The claimed scope of the invention by appended claims and its
Equivalent thereof.
Claims (10)
1. a kind of power system operation instruction executing method based on speech recognition characterized by comprising
Phonetic order collection is obtained, it includes operational order and electric network model title that the phonetic order, which is concentrated,；
The audio stream on-line conversion that will acquire based on speech-recognition services is at character string；
Based on the words and phrases mapped file safeguarded, two times transfer is carried out to the character string, forms new character string；
Phonetic order collection based on acquisition carries out automatic identification to the new character string, obtains operational order, completes power train
Operational order of uniting executes.
2. a kind of power system operation instruction executing method based on speech recognition according to claim 1, feature exist
In: the phonetic order collection is the regular expression of a string of character string forms.
3. a kind of power system operation instruction executing method based on speech recognition according to claim 1, feature exist
In, the method also includes:
It is concentrated to the phonetic order and increases new operational order and electric network model title.
4. a kind of power system operation instruction executing method based on speech recognition according to claim 1, feature exist
In: the audio stream on-line conversion that will acquire based on speech-recognition services at character string, specifically includes the following steps:
Driver of sound card is called, obtains audio stream from microphone port, and real-time transmission is to speech-recognition services；
The audio stream of acquisition is converted into character string immediately online by the speech-recognition services.
5. a kind of power system operation instruction executing method based on speech recognition according to claim 4, feature exist
In the speech-recognition services also judge automatically whether audio stream terminates, and audio stream is continued to if not terminating；If terminating
, then the character string identified is returned immediately.
6. a kind of power system operation instruction executing method based on speech recognition according to claim 1, feature exist
In, it is described based on the words and phrases mapped file safeguarded, two times transfer is carried out to the character string, forms new character string, specifically
Include:
By the wrong words and phrases unsteady state operation of the identification in words and phrases mapping relations original in the speech-recognition services at correct
Words and phrases form the words and phrases mapping relations safeguarded；
Two times transfer is carried out to the character string based on the words and phrases mapping relations safeguarded, forms new character string.
7. a kind of power system operation instruction executing method based on speech recognition characterized by comprising
Module is obtained, for obtaining phonetic order collection, it includes operational order and electric network model title that the phonetic order, which is concentrated,；
First conversion module, the audio stream on-line conversion for will acquire based on speech-recognition services is at character string；
Second conversion module is formed new for carrying out two times transfer to the character string based on the words and phrases mapped file safeguarded
Character string；
Identification module carries out automatic identification to the new character string for the phonetic order collection based on acquisition, obtains operation and refer to
It enables, completes power system operation instruction execution.
8. the power system operation instruction executing method according to claim 7 based on speech recognition, it is characterised in that: institute
Predicate sound instruction set is the regular expression of a string of character string forms.
9. the power system operation instruction executing method according to claim 7 based on speech recognition, it is characterised in that: institute
It states based on the words and phrases mapped file safeguarded, two times transfer is carried out to the character string, new character string is formed, specifically includes:
By the wrong words and phrases unsteady state operation of the identification in words and phrases mapping relations original in the speech-recognition services at correct
Words and phrases form the words and phrases mapping relations safeguarded；
Two times transfer is carried out to the character string based on the words and phrases mapping relations safeguarded, forms new character string.
10. a kind of power system operation instruction execution system based on speech-recognition services characterized by comprising
Processor is adapted for carrying out each instruction；And
Equipment is stored, is suitable for storing a plurality of instruction, described instruction is suitable for by processor load and perform claim requires to appoint in 1~6
Step described in one.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910408481.2A CN110349576A (en) | 2019-05-16 | 2019-05-16 | Power system operation instruction executing method, apparatus and system based on speech recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910408481.2A CN110349576A (en) | 2019-05-16 | 2019-05-16 | Power system operation instruction executing method, apparatus and system based on speech recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110349576A true CN110349576A (en) | 2019-10-18 |
Family
ID=68173901
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910408481.2A Pending CN110349576A (en) | 2019-05-16 | 2019-05-16 | Power system operation instruction executing method, apparatus and system based on speech recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110349576A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111105799A (en) * | 2019-12-09 | 2020-05-05 | 国网浙江省电力有限公司杭州供电公司 | Offline voice recognition device and method based on pronunciation quantification and electric power special word bank |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101079996A (en) * | 2006-05-22 | 2007-11-28 | 北京盛开交互娱乐科技有限公司 | An interactive digital multimedia making method based on video and audio |
| CN102298443A (en) * | 2011-06-24 | 2011-12-28 | 华南理工大学 | Smart home voice control system combined with video channel and control method thereof |
| CN103369398A (en) * | 2013-07-01 | 2013-10-23 | 安徽广电信息网络股份有限公司 | Voice searching method and voice searching system based on television EPG (electronic program guide) information |
| CN103730112A (en) * | 2013-12-25 | 2014-04-16 | 安徽讯飞智元信息科技有限公司 | Multi-channel voice simulation and acquisition method |
| CN104462600A (en) * | 2014-12-31 | 2015-03-25 | 科大讯飞股份有限公司 | Method and device for achieving automatic classification of calling reasons |
| CN105159870A (en) * | 2015-06-26 | 2015-12-16 | 徐信 | Processing system for precisely completing continuous natural speech textualization and method for precisely completing continuous natural speech textualization |
| CN107146618A (en) * | 2017-06-16 | 2017-09-08 | 北京云知声信息技术有限公司 | Method of speech processing and device |
| CN107393526A (en) * | 2017-07-19 | 2017-11-24 | 腾讯科技（深圳）有限公司 | Speech silence detection method, device, computer equipment and storage medium |
| CN107741928A (en) * | 2017-10-13 | 2018-02-27 | 四川长虹电器股份有限公司 | A kind of method to text error correction after speech recognition based on field identification |
| CN108305628A (en) * | 2017-06-27 | 2018-07-20 | 腾讯科技（深圳）有限公司 | Audio recognition method, device, computer equipment and storage medium |
| CN108417209A (en) * | 2018-03-02 | 2018-08-17 | 国家电网公司华中分部 | A kind of power scheduling morpheme extraction method based on natural language processing technique |
| CN109461436A (en) * | 2018-10-23 | 2019-03-12 | 广东小天才科技有限公司 | A kind of correcting method and system of speech recognition pronunciation mistake |
| CN109727592A (en) * | 2017-10-31 | 2019-05-07 | 上海幻电信息科技有限公司 | O&M instruction executing method, medium and terminal based on natural language speech interaction |
-
2019
- 2019-05-16 CN CN201910408481.2A patent/CN110349576A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101079996A (en) * | 2006-05-22 | 2007-11-28 | 北京盛开交互娱乐科技有限公司 | An interactive digital multimedia making method based on video and audio |
| CN102298443A (en) * | 2011-06-24 | 2011-12-28 | 华南理工大学 | Smart home voice control system combined with video channel and control method thereof |
| CN103369398A (en) * | 2013-07-01 | 2013-10-23 | 安徽广电信息网络股份有限公司 | Voice searching method and voice searching system based on television EPG (electronic program guide) information |
| CN103730112A (en) * | 2013-12-25 | 2014-04-16 | 安徽讯飞智元信息科技有限公司 | Multi-channel voice simulation and acquisition method |
| CN104462600A (en) * | 2014-12-31 | 2015-03-25 | 科大讯飞股份有限公司 | Method and device for achieving automatic classification of calling reasons |
| CN105159870A (en) * | 2015-06-26 | 2015-12-16 | 徐信 | Processing system for precisely completing continuous natural speech textualization and method for precisely completing continuous natural speech textualization |
| CN107146618A (en) * | 2017-06-16 | 2017-09-08 | 北京云知声信息技术有限公司 | Method of speech processing and device |
| CN108305628A (en) * | 2017-06-27 | 2018-07-20 | 腾讯科技（深圳）有限公司 | Audio recognition method, device, computer equipment and storage medium |
| CN107393526A (en) * | 2017-07-19 | 2017-11-24 | 腾讯科技（深圳）有限公司 | Speech silence detection method, device, computer equipment and storage medium |
| CN107741928A (en) * | 2017-10-13 | 2018-02-27 | 四川长虹电器股份有限公司 | A kind of method to text error correction after speech recognition based on field identification |
| CN109727592A (en) * | 2017-10-31 | 2019-05-07 | 上海幻电信息科技有限公司 | O&M instruction executing method, medium and terminal based on natural language speech interaction |
| CN108417209A (en) * | 2018-03-02 | 2018-08-17 | 国家电网公司华中分部 | A kind of power scheduling morpheme extraction method based on natural language processing technique |
| CN109461436A (en) * | 2018-10-23 | 2019-03-12 | 广东小天才科技有限公司 | A kind of correcting method and system of speech recognition pronunciation mistake |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111105799A (en) * | 2019-12-09 | 2020-05-05 | 国网浙江省电力有限公司杭州供电公司 | Offline voice recognition device and method based on pronunciation quantification and electric power special word bank |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106354835A (en) | Artificial dialogue auxiliary system based on context semantic understanding | |
| CN109446307A (en) | A kind of method for realizing dialogue management in Intelligent dialogue | |
| CN107644643A (en) | A kind of voice interactive system and method | |
| CN106683678A (en) | Artificial telephone customer service auxiliary system and method | |
| CN106228974A (en) | Control method based on speech recognition, Apparatus and system | |
| CN111429915A (en) | Scheduling system and scheduling method based on voice recognition | |
| CN113140219A (en) | Regulation and control instruction generation method and device, electronic equipment and storage medium | |
| CN107679147A (en) | Human-computer dialogue formula electric network information based on speech recognition has access to methods of exhibiting | |
| CN107845381A (en) | A kind of method and system of robot semantic processes | |
| CN111178081B (en) | Semantic recognition method, server, electronic device and computer storage medium | |
| CN111179928A (en) | Intelligent control method for power transformation and distribution station based on voice interaction | |
| CN113314106A (en) | Electric power information query and regulation function calling method based on voice and intention recognition | |
| CN112035630A (en) | Dialogue interaction method, device, equipment and storage medium combining RPA and AI | |
| CN109120513A (en) | Full media system and implementation method based on intelligent robot response | |
| CN115643341A (en) | Artificial intelligence customer service response system | |
| CN112016327A (en) | Intelligent structured text extraction method and device based on multiple rounds of conversations and electronic equipment | |
| CN111384778B (en) | Intelligent operation and maintenance system for power distribution network equipment | |
| CN110349576A (en) | Power system operation instruction executing method, apparatus and system based on speech recognition | |
| CN113593565B (en) | Intelligent home device management and control method and system | |
| WO2016027909A1 (en) | Data structure, interactive voice response device, and electronic device | |
| CN109727594A (en) | Method of speech processing and device | |
| CN109243458A (en) | A kind of speech recognition system for intelligent robot | |
| CN109040492A (en) | A kind of intelligent sound customer service robot | |
| CN112309396A (en) | AI virtual robot state dynamic setting system | |
| CN104575496A (en) | Method and device for automatically sending multimedia documents and mobile terminal |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191018 |