CN113948079A - Power distribution network scheduling man-machine interaction method based on artificial intelligence voice recognition - Google Patents
Power distribution network scheduling man-machine interaction method based on artificial intelligence voice recognition Download PDFInfo
- Publication number
- CN113948079A CN113948079A CN202111157614.7A CN202111157614A CN113948079A CN 113948079 A CN113948079 A CN 113948079A CN 202111157614 A CN202111157614 A CN 202111157614A CN 113948079 A CN113948079 A CN 113948079A
- Authority
- CN
- China
- Prior art keywords
- voice
- user
- distribution network
- power distribution
- dispatching
- 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 44
- 230000003993 interaction Effects 0.000 title claims abstract description 35
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 36
- 238000004458 analytical method Methods 0.000 claims abstract description 13
- 230000008569 process Effects 0.000 claims abstract description 13
- 238000010606 normalization Methods 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims description 18
- 230000006870 function Effects 0.000 claims description 15
- 238000006243 chemical reaction Methods 0.000 claims description 13
- 238000004891 communication Methods 0.000 claims description 9
- 238000005516 engineering process Methods 0.000 claims description 8
- 230000005236 sound signal Effects 0.000 claims description 7
- 230000004044 response Effects 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 4
- 238000007405 data analysis Methods 0.000 claims description 3
- 230000007123 defense Effects 0.000 claims description 3
- 230000008447 perception Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 230000001629 suppression Effects 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 230000009471 action Effects 0.000 description 8
- 230000008859 change Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000033228 biological regulation Effects 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000003786 synthesis reaction Methods 0.000 description 3
- 230000002452 interceptive effect Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 230000007958 sleep Effects 0.000 description 1
- 238000013518 transcription Methods 0.000 description 1
- 230000035897 transcription Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
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
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/065—Adaptation
- G10L15/07—Adaptation to the speaker
-
- 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
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/1822—Parsing for meaning understanding
-
- 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
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
- G10L21/0216—Noise filtering characterised by the method used for estimating noise
-
- 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
-
- 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
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
- G10L21/0216—Noise filtering characterised by the method used for estimating noise
- G10L2021/02161—Number of inputs available containing the signal or the noise to be suppressed
- G10L2021/02166—Microphone arrays; Beamforming
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)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Signal Processing (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention relates to a power distribution network dispatching man-machine interaction method based on artificial intelligence voice recognition, which comprises the following steps: the user terminal equipment collects the user voice request and carries out analysis processing through an analysis processing module; carrying out protocol assembly on the analyzed voice information, and outputting the voice information to an intelligent voice engine through an access layer; the intelligent voice engine carries out normalization processing and differential output on the user request, analyzes the real intention of the user request and transmits key information to a back-end service module for processing the intention of the user; and the rear-end service module processes the intention of the user and converts the intention into corresponding power grid dispatching operation. The method is beneficial to improving the distribution network scheduling disposal efficiency and the intelligent level of the distribution network scheduling system.
Description
Technical Field
The invention belongs to the field of power distribution automation of a power system, and particularly relates to a power distribution network dispatching man-machine interaction method based on artificial intelligence voice recognition.
Background
At present, the regulation and control work of the power distribution network is mainly realized by manual touch interaction. The application of the intelligent voice technology in the distribution network regulation and control of daily business is popularized, the functions of intelligent voice interaction, voice text conversion, voice semantic analysis, voice operation control and the like are realized, the intelligentization level of the intelligent distribution network scheduling system can be improved, the man-machine interaction efficiency is improved, and the real-time regulation and control capability and the daily business handling efficiency of a regional power grid are enhanced.
Disclosure of Invention
The invention aims to provide a power distribution network scheduling man-machine interaction method based on artificial intelligence voice recognition, which is beneficial to improving the efficiency of distribution network scheduling treatment.
In order to achieve the purpose, the invention adopts the technical scheme that: a power distribution network dispatching man-machine interaction method based on artificial intelligence voice recognition comprises the following steps:
the user terminal equipment collects the user voice request and carries out analysis processing through an analysis processing module;
carrying out protocol assembly on the analyzed voice information, and outputting the voice information to an intelligent voice engine through an access layer;
the intelligent voice engine carries out normalization processing and differential output on the user request, analyzes the real intention of the user request and transmits key information to a back-end service module for processing the intention of the user;
and the rear-end service module processes the intention of the user and converts the intention into corresponding power grid dispatching operation.
Furthermore, the analysis processing link processes the voice through two modules, namely a voice signal conversion module and a noise processing module, the voice signal conversion module is used for converting the voice into a format file which can be recognized by a computer, and the noise processing module is used for improving the accuracy of voice acquisition and further extracting characteristic parameters contained in the voice of the user.
Further, the step of extracting the user voice by the sound signal conversion module is as follows:
firstly, preprocessing is carried out, including sampling and automatic gain control of an input voice signal;
secondly, extracting characteristic parameters of the user voice, including a formant of the sound wave and the tone of the sound;
thirdly, carrying out classification processing on the extracted characteristic parameters of the voice by respectively adopting algorithm training and pattern library training to finish semantic output in the voice; the knowledge including power grid stock equipment information, power grid safety specifications, a dispatcher term library and distribution network dispatching disposal chapters is learned through training;
and finally, performing pattern matching, namely performing matching degree test on the extracted voice to be tested and the voice of the pattern library, and finally finishing semantic output in the voice.
Further, a microphone array technology is adopted to obtain the sound of a user; the microphone array is a recording system which adopts two or more microphones to be arranged and combined according to a certain rule and acquires and processes sound in a set space; the microphone array effectively picks up sound through sound source positioning, beam forming, noise suppression, reverberation resistance, echo cancellation and voice enhancement so as to improve the artificial intelligence voice recognition effect and hear the voice of a user clearly.
Further, the protocol assembly of the analyzed voice information is completed through a connection layer application, the connection layer application is mainly responsible for communication between the equipment side and the cloud service, a communication protocol between the equipment side and the cloud service is defined, and the communication protocol mainly comprises three parts, namely an instruction, an event and a side state.
Further, the intelligent voice engine is used for performing normalization processing and differential output on the input of the multi-voice source, accurately analyzing the voice intention of the user, and transmitting the voice request key information of the user to the rear-end service module for specifically processing the user intention.
Further, the voice is output to the intelligent voice engine through an access layer, wherein the access layer is mainly responsible for accessing and forwarding voice requests of users, and performs scheduling and data analysis of global traffic, and meanwhile has a security defense function; after mass user voice requests occur, the system is responsible for load distribution of the voice requests of the users and sharing the pressure of the server in order to share the pressure of the cloud server, so that the problems that the user requests are lost and the response is not timely are avoided under the condition that the server is accessed highly.
Furthermore, the back-end service module is mainly a scheduling module of the power grid system function, and is used for intelligently making a decision to call a relevant power distribution network system to complete response operation according to semantic requirements in user voice and by combining perception of power grid equipment and states, user habits and interactive context.
Compared with the prior art, the invention has the following beneficial effects: the artificial intelligence voice technology is introduced into the daily human-computer interaction scene of distribution network scheduling, so that the intelligent level of the intelligent distribution network scheduling system is improved, and the daily service handling efficiency is improved. The method comprises the steps of realizing full-scene coordination of power grid dispatching through machine learning and intelligent interaction, simplifying power grid equipment, acquiring power grid operation situation through mass acquisition data of a power distribution master station, predicting potential equipment control requirements of users according to voice requests of dispatching users by learning and memorizing power grid dispatching of the users, timely and actively making reminders and suggestions for the users, selecting one or more optimal instructions to respond, and better meeting the power grid dispatching requirements.
Drawings
FIG. 1 is a flow chart of a method implementation of an embodiment of the present invention.
Fig. 2 is a flow chart of the implementation of the voice open circuit diagram in the embodiment of the present invention.
Fig. 3 is a flow chart of the implementation of the voice shutdown circuit diagram in the embodiment of the present invention.
FIG. 4 is a flow chart of the implementation of the positioning of the speech equipment in the embodiment of the present invention
Fig. 5 is a flow chart of implementation of the registering of the voice device in the embodiment of the present invention.
Fig. 6 is a flowchart of an implementation of a voice placement service in an embodiment of the present invention.
Fig. 7 is a flow chart of an implementation of the voice switch remote control in the embodiment of the present invention.
Fig. 8 is a flowchart of an implementation of a voice device recall in an embodiment of the present invention.
FIG. 9 is a flow chart of an implementation of a voice statistics query in an embodiment of the present invention.
Detailed Description
The invention is further explained below with reference to the drawings and the embodiments.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
As shown in fig. 1, the present embodiment provides a power distribution network scheduling human-computer interaction method based on artificial intelligence voice recognition, including the following steps:
1. the user end equipment collects the user voice request and carries out analysis processing through the analysis processing module.
The analysis processing link is processed through a sound signal conversion module and a noise processing module, the sound signal conversion module is used for converting the voice into a format file which can be recognized by a computer, the noise processing module is used for improving the accuracy of voice collection, and then characteristic parameters contained in the voice of a user are extracted.
The step of extracting the user voice by the sound signal conversion module is as follows:
firstly, preprocessing is carried out, including sampling and automatic gain control of an input voice signal;
secondly, extracting characteristic parameters of the user voice, including a formant of the sound wave, the tone of the sound and the like;
thirdly, carrying out classification processing on the extracted characteristic parameters of the voice by respectively adopting algorithm training and pattern library training to finish semantic output in the voice; according to the characteristic data in the voice information: the method comprises the following steps of (1) combining objects and operation descriptions, carrying out classification processing on different objects and different operation descriptions to realize different operation purposes, and finally converting the objects and the operation descriptions into computer languages; the knowledge including power grid stock equipment information, power grid safety specifications, a dispatcher term library and distribution network dispatching disposal chapters is learned through training;
and finally, performing pattern matching, namely performing matching degree test on the extracted voice to be tested and the voice of the pattern library, and finally finishing semantic output in the voice.
The invention adopts the microphone array technology to obtain the sound of the user; the microphone array is a recording system which adopts two or more microphones to be arranged and combined according to a certain rule and acquires and processes sound in a set space; the microphone array effectively picks up sound through algorithms such as sound source positioning, beam forming, noise suppression, reverberation resistance, echo cancellation, voice enhancement and the like so as to improve the artificial intelligent voice recognition effect and hear the voice of a user clearly.
2. And carrying out protocol assembly on the analyzed voice information, and outputting the voice information to the intelligent voice engine through the access layer.
The protocol assembly of the analyzed voice information is completed through a connection layer application, the protocol assembly is mainly responsible for communication of the equipment end and the cloud service, a communication protocol between the equipment end and the cloud service is defined, and the communication protocol mainly comprises three parts, namely an instruction, an event and an end state.
3. The intelligent voice engine carries out normalization processing and differential output on the user request, analyzes the real intention of the user request and transmits the key information to the back-end service module for processing the intention of the user.
The intelligent voice engine is used for carrying out normalization processing and differential output on the input of the multi-voice source, accurately analyzing the voice intention of the user and transmitting the voice request key information of the user to the rear-end service module for specifically processing the user intention.
The voice request is output to an intelligent voice engine through an access layer, wherein the access layer is mainly responsible for accessing and forwarding the voice request of a user, carries out scheduling and data analysis of global flow and has a safety defense function; after mass user voice requests occur, the system is responsible for load distribution of the voice requests of the users and sharing the pressure of the server in order to share the pressure of the cloud server, so that the problems that the user requests are lost and the response is not timely and the like cannot be caused under the condition of high access of the server.
4. And the rear-end service module processes the intention of the user and converts the intention into corresponding power grid dispatching operation.
The back-end service module is mainly a dispatching module of the power grid system function and is used for intelligently making a decision to call a relevant power distribution network system to complete response operation according to semantic requirements in user voice and by combining perception of power grid equipment and states, user habits and interactive context.
The invention relates to a man-machine interaction method for dispatching a power distribution network based on artificial intelligence voice recognition, which comprises the following specific implementation processes:
1. artificial intelligent speech recognition and synthesis
The method supports a voice text conversion function, adopts a machine learning technology in the field of artificial intelligence, learns the pronunciation habit, dialect characteristics, vocabularies in the professional field and other information of a user through learning the spoken pronunciation of the user, and converts a section of speech (audio) spoken by the user into a section of text.
(1) Basic speech function, artificial intelligence speech recognition
And the artificial intelligence voice recognition and voice synthesis of the universal language and the professional term of the city are supported. Intelligent noise reduction is supported. The user inputs through the microphone, filters noisy noise, detects the distance of collecting a sound. One-time awakening and continuous identification are supported. The support sets the awakening word to trigger and start the voice recognition, the voice can be continuously spoken for many times after awakening, and the voice automatically sleeps after a period of time without use.
(2) Voice input method
And the method supports voice to replace keyboard typing, supports voice instant transcription and supports voice writing of documents.
(3) Speech synthesis, text-to-speech
And the method supports playing a text word in an audio mode in a mode that a user is accustomed to according to the local language habit.
2. Speech model training
By adopting the machine learning technology in the field of artificial intelligence, the pronunciation habit and dialect characteristics of a user are mastered through learning spoken pronunciation of the user, a professional model and a voice general model recognition library in Jiuchi city are constructed, the recognition accuracy of common instructions is improved, and the recognition accuracy of equipment in various cities is improved.
The speech model training content mainly comprises:
1) substation name training
2) Line name training
3) Device name training
4) Device serial number name training
5) Operation card name training
6) And operation intention training, which comprises opening (viewing, browsing and the like) of the graph, closing the graph, positioning equipment, listing, picking the graph, setting, releasing, remotely controlling, controlling the score, controlling the combination, converting the operation order into the cold standby operation order and the like, continuing the operation, cancelling the operation, ending the operation, calling the test, inquiring, counting and the like. The operation intention training aims at identifying key fields of all operation intentions, and if the intention identification effect is found to be poor in the actual interaction process, the linguistic data can be manually added to update the model, the richer the linguistic data is, the more variable the language environment can be adapted to by the intention, and the identification accuracy is higher.
3. Semantic parsing
(1) The method supports the semantic analysis technology, constructs a voice command structural model, and decomposes a section of speech of a user into voice which can be understood by a computer through word segmentation, keyword retrieval and other processing.
(2) And (5) carrying out multiple rounds of conversations. And in the voice interaction process, multiple rounds of interaction are carried out with the user, a call-back scene is constructed, information input by the user is acquired step by step, and the operation intention of the user is determined.
4. Voice to operation function
(1) Voice tone map
The voice of the picture retrieval input by the audio equipment is supported, the voice is actively analyzed into the contained action instruction and the voice instruction of the operation content, and the action instruction and the voice instruction are converted into the picture retrieval instruction, so that the voice interaction of the picture retrieval service is realized, including normally retrieving the graphics and closing the graphics.
The flow of implementing the voice open circuit diagram in this embodiment is shown in fig. 2.
The implementation flow of the voice closed circuit diagram in this embodiment is shown in fig. 3.
(2) Speech device positioning
The voice interaction method comprises the steps of supporting the active analysis of an equipment positioning command input by audio equipment into a voice command containing an action command and operation content, and supporting the conversion into an equipment positioning and graph opening command according to the equipment type and equipment name matching mode to realize the voice interaction of equipment positioning services, wherein the positioning equipment type comprises a station room, a bus, a switch, a disconnecting link, a distribution transformer, a meter box and the like, and the user selection is supported when a plurality of matching results exist.
The implementation flow of the positioning of the speech device in this embodiment is shown in fig. 4.
(3) Voice hanging plate
The device listing voice input by the audio device is actively analyzed into the voice command containing the action command and the operation content, and the voice command is converted into the listing command, so that the voice interaction of the listing service is realized, including listing and picking of the device.
The implementation flow of the listing of the voice device in this embodiment is shown in fig. 5.
(4) Voice setting
The voice of the built-in service input by the audio equipment is supported to be actively analyzed into the voice commands containing the action commands and the operation contents, and the voice commands are converted into the built-in commands, so that the voice interaction of the built-in service is realized, and the voice interaction comprises remote signaling setting, remote monitoring setting and the like.
The implementation flow of the voice placing service in this embodiment is shown in fig. 6.
(5) Voice remote control
The voice of the switch remote control input by the audio equipment is actively analyzed into the voice instructions containing the action instructions and the operation contents, and the voice instructions are converted into the voice instructions of the switch remote control, so that the voice interaction of the switch remote control service is realized, and the operations of remote control verification, remote control execution and the like are carried out on the appointed switch.
The implementation flow of the voice switch remote control in this embodiment is shown in fig. 7.
(6) Voice low-voltage equipment call and test
The voice interaction of the equipment operation data calling service is realized by supporting the statistical query voice input by the audio equipment, actively analyzing the statistical query voice into the voice command containing the action command and the operation content and converting the voice command into the low-voltage equipment calling command, wherein the calling command comprises a low-voltage switch state, the current voltage of an ammeter and the like.
The implementation flow of the voice device call in this embodiment is shown in fig. 8.
(7) Speech statistics query
Support statistical query speech input by audio equipment and actively analyze the speech into packets
And the voice command containing the action command and the operation content is converted into a statistical query command, so that the voice interaction of the statistical query service is realized, and the operations comprise opening a statistical query total interface, opening a statistical query formulation interface and the like.
The flow of implementing the voice statistic query in this embodiment is shown in fig. 9.
5. Voice broadcast reminder
And the free-organized text content is converted into an audio file through a voice platform to be played.
(1) The intelligent alarm clock is timed to remind by voice, key information is actively broadcasted, and functions such as plan application of 'six time nodes' management and control reminding, voice broadcast guiding operation steps, document reading and the like are achieved.
(2) The method comprises the steps of ordering by voice telephone, prompting by ring closing and opening operations, having a knowledge learning function, constructing a power grid real-time base, and having a prompting function once a command ticket is subjected to misoperation after rules and typical operation tickets are imported into the knowledge base.
(3) And a fault abnormal signal reminding function for reminding during fault notification, abnormal judgment, notification inspection, abnormal handling and reminding.
6. Voice setting-up operation ticket
The method supports the drawing up of an operation order command input by the audio equipment, actively analyzes the operation order command into an operation text containing operation steps, operation equipment and operation content, and supports the online transmission of the operation text to the intelligent instruction order billing system.
The method supports the active recognition of the operating equipment according to the voice, multiple recognition results of the standing book information of the positioning equipment support manual selection, and the final text of the operation ticket supports manual editing.
The method realizes the function of < voice drafting command item > without influencing the service logic of the current intelligent ticketing system and mature networked command issuing process, and aims to reduce the complexity of manually filling command items in the intelligent ticketing system and improve the accuracy of operating equipment and operating steps.
7. Voice intelligent shift
The system supports the recording and storage of the shift change records through voice, identifies the information of the shift change personnel through a fingerprint mode and records the information in the system, and automatically generates the shift change records.
The foregoing is directed to preferred embodiments of the present invention, other and further embodiments of the invention may be devised without departing from the basic scope thereof, and the scope thereof is determined by the claims that follow. However, any simple modification, equivalent change and modification of the above embodiments according to the technical essence of the present invention are within the protection scope of the technical solution of the present invention.
Claims (8)
1. A power distribution network dispatching man-machine interaction method based on artificial intelligence voice recognition is characterized by comprising the following steps:
user end equipment collects user voice request and carries out information conversion through an analysis processing link;
carrying out protocol assembly on the analyzed voice information, and outputting the voice information to an intelligent voice engine through an access layer;
the intelligent voice engine carries out normalization processing and differential output on the user request, analyzes the real intention of the user request and transmits key information to a back-end service module for processing the intention of the user;
and the rear-end service module processes the intention of the user and converts the intention into corresponding power grid dispatching operation.
2. The human-computer interaction method for dispatching the power distribution network based on the artificial intelligence voice recognition is characterized in that the analysis processing link carries out processing through two modules, namely a sound signal conversion module and a noise processing module, the sound signal conversion module is used for converting voice into a format file which can be recognized by a computer, and the noise processing module is used for improving the accuracy of voice collection and further extracting characteristic parameters contained in the voice of a user.
3. The human-computer interaction method for dispatching the power distribution network based on artificial intelligence voice recognition as claimed in claim 2, wherein the step of extracting the user voice by the sound signal conversion module is as follows:
firstly, preprocessing is carried out, including sampling and automatic gain control of an input voice signal;
secondly, extracting characteristic parameters of the user voice, including a formant of the sound wave and the tone of the sound;
thirdly, carrying out classification processing on the extracted characteristic parameters of the voice by respectively adopting algorithm training and pattern library training to finish semantic output in the voice; the knowledge including power grid stock equipment information, power grid safety specifications, a dispatcher term library and distribution network dispatching disposal chapters is learned through training;
according to the characteristic data in the voice information: the object and the operation description are combined, different objects and different operation descriptions are combined, different operation purposes are realized through classification processing, and the different operation purposes are finally converted into computer languages.
4. The artificial intelligence voice recognition-based power distribution network scheduling man-machine interaction method according to claim 1, wherein a microphone array technology is adopted to obtain the sound of a user; the microphone array is a recording system which adopts two or more microphones to be arranged and combined according to a certain rule and acquires and processes sound in a set space; the microphone array effectively picks up sound through sound source positioning, beam forming, noise suppression, reverberation resistance, echo cancellation and voice enhancement so as to improve the artificial intelligence voice recognition effect and hear the voice of a user clearly.
5. The artificial intelligence voice recognition-based power distribution network dispatching man-machine interaction method according to claim 1, wherein the protocol assembly of the analyzed voice information is completed through a connection layer application, the connection layer application is mainly responsible for communication between a device side and a cloud service, a communication protocol between the device side and the cloud service is defined, and the communication protocol mainly comprises three parts, namely an instruction, an event and a side state.
6. The human-computer interaction method for dispatching the power distribution network based on artificial intelligence voice recognition according to claim 1, wherein the intelligent voice engine is configured to perform normalization processing and differential output on the input of the multiple voice sources, accurately analyze the intention of the user voice, and transmit the voice request key information of the user to a back-end service module that specifically processes the intention of the user.
7. The human-computer interaction method for dispatching the power distribution network based on the artificial intelligence voice recognition is characterized in that the human-computer interaction method is output to an intelligent voice engine through an access layer, wherein the access layer is mainly responsible for accessing and forwarding voice requests of users, carries out dispatching and data analysis of global traffic and has a safety defense function; after mass user voice requests occur, the system is responsible for load distribution of the voice requests of the users and sharing the pressure of the server in order to share the pressure of the cloud server, so that the problems that the user requests are lost and the response is not timely are avoided under the condition that the server is accessed highly.
8. The human-computer interaction method for dispatching the power distribution network based on the artificial intelligence voice recognition is characterized in that the back-end service module is mainly a dispatching module of the power distribution network system function and is used for intelligently making a decision to call a relevant power distribution network system to complete response operation according to semantic requirements in user voice and by combining perception of power distribution network equipment and states, user habits and interaction context.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111157614.7A CN113948079A (en) | 2021-09-30 | 2021-09-30 | Power distribution network scheduling man-machine interaction method based on artificial intelligence voice recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111157614.7A CN113948079A (en) | 2021-09-30 | 2021-09-30 | Power distribution network scheduling man-machine interaction method based on artificial intelligence voice recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113948079A true CN113948079A (en) | 2022-01-18 |
Family
ID=79329079
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111157614.7A Pending CN113948079A (en) | 2021-09-30 | 2021-09-30 | Power distribution network scheduling man-machine interaction method based on artificial intelligence voice recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113948079A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117435716A (en) * | 2023-12-20 | 2024-01-23 | 国网浙江省电力有限公司宁波供电公司 | Data processing method and system of power grid man-machine interaction terminal |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20190107289A (en) * | 2019-08-30 | 2019-09-19 | 엘지전자 주식회사 | Artificial robot and method for speech recognitionthe same |
| CN111145746A (en) * | 2019-12-27 | 2020-05-12 | 安徽讯呼信息科技有限公司 | Man-machine interaction method based on artificial intelligence voice |
| CN111489748A (en) * | 2019-10-18 | 2020-08-04 | 广西电网有限责任公司 | Intelligent voice scheduling auxiliary system |
| CN112599124A (en) * | 2020-11-20 | 2021-04-02 | 内蒙古电力(集团)有限责任公司电力调度控制分公司 | Voice scheduling method and system for power grid scheduling |
| CN113314106A (en) * | 2021-05-19 | 2021-08-27 | 国网辽宁省电力有限公司 | Electric power information query and regulation function calling method based on voice and intention recognition |
-
2021
- 2021-09-30 CN CN202111157614.7A patent/CN113948079A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20190107289A (en) * | 2019-08-30 | 2019-09-19 | 엘지전자 주식회사 | Artificial robot and method for speech recognitionthe same |
| CN111489748A (en) * | 2019-10-18 | 2020-08-04 | 广西电网有限责任公司 | Intelligent voice scheduling auxiliary system |
| CN111145746A (en) * | 2019-12-27 | 2020-05-12 | 安徽讯呼信息科技有限公司 | Man-machine interaction method based on artificial intelligence voice |
| CN112599124A (en) * | 2020-11-20 | 2021-04-02 | 内蒙古电力(集团)有限责任公司电力调度控制分公司 | Voice scheduling method and system for power grid scheduling |
| CN113314106A (en) * | 2021-05-19 | 2021-08-27 | 国网辽宁省电力有限公司 | Electric power information query and regulation function calling method based on voice and intention recognition |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117435716A (en) * | 2023-12-20 | 2024-01-23 | 国网浙江省电力有限公司宁波供电公司 | Data processing method and system of power grid man-machine interaction terminal |
| CN117435716B (en) * | 2023-12-20 | 2024-06-11 | 国网浙江省电力有限公司宁波供电公司 | Data processing method and system of power grid man-machine interaction terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111489748A (en) | Intelligent voice scheduling auxiliary system | |
| US11645547B2 (en) | Human-machine interactive method and device based on artificial intelligence | |
| CN111755001A (en) | Artificial intelligence-based power grid rapid dispatching and commanding system and method | |
| CN107016993A (en) | The voice interactive system and method for a kind of smart home | |
| CN107506166A (en) | Information cuing method and device, computer installation and readable storage medium storing program for executing | |
| CN105244042B (en) | A kind of speech emotional interactive device and method based on finite-state automata | |
| CN110032742A (en) | Respond sentence generating device, method and storage medium and voice interactive system | |
| CN109271533A (en) | A kind of multimedia document retrieval method | |
| CN111429915A (en) | Scheduling system and scheduling method based on voice recognition | |
| CN108847221A (en) | Audio recognition method, device, storage medium and electronic equipment | |
| CN108364650A (en) | The adjusting apparatus and method of voice recognition result | |
| CN107085717A (en) | A kind of family's monitoring method, service end and computer-readable recording medium | |
| CN113140219A (en) | Regulation and control instruction generation method and device, electronic equipment and storage medium | |
| CN111384778B (en) | Intelligent operation and maintenance system for power distribution network equipment | |
| CN109670020A (en) | A kind of voice interactive method, system and device | |
| CN114818649A (en) | Service consultation processing method and device based on intelligent voice interaction technology | |
| CN116417003A (en) | Voice interaction system, method, electronic device and storage medium | |
| CN112667909A (en) | Method and device for recommending scenes in smart home | |
| CN113948079A (en) | Power distribution network scheduling man-machine interaction method based on artificial intelligence voice recognition | |
| CN117149977A (en) | Intelligent collecting robot based on robot flow automation | |
| CN117713377A (en) | Intelligent voice joint debugging system of dispatching automation master station | |
| CN113438515A (en) | IPTV terminal government affair consultation method and system based on intelligent interaction | |
| Tsujino et al. | Speech Recognition and Spoken Language Understanding for Mobile Personal Assistants: A Case Study of" Shabette Concier" | |
| CN106920546A (en) | The method and device of Intelligent Recognition voice | |
| CN107357859A (en) | A kind of intelligent terminal for realizing that knowledge base shows automatically by voice collecting |
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 |