CN112599124A - Voice scheduling method and system for power grid scheduling - Google Patents
Voice scheduling method and system for power grid scheduling Download PDFInfo
- Publication number
- CN112599124A CN112599124A CN202011310565.1A CN202011310565A CN112599124A CN 112599124 A CN112599124 A CN 112599124A CN 202011310565 A CN202011310565 A CN 202011310565A CN 112599124 A CN112599124 A CN 112599124A
- Authority
- CN
- China
- Prior art keywords
- voice
- scheduling
- model
- intention
- power grid
- 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 47
- 230000008569 process Effects 0.000 claims abstract description 31
- 230000003993 interaction Effects 0.000 claims abstract description 28
- 238000012549 training Methods 0.000 claims description 15
- 238000013527 convolutional neural network Methods 0.000 claims description 8
- 230000015572 biosynthetic process Effects 0.000 claims description 7
- 238000003786 synthesis reaction Methods 0.000 claims description 7
- 238000013135 deep learning Methods 0.000 claims description 2
- 230000007787 long-term memory Effects 0.000 claims 1
- 230000006403 short-term memory Effects 0.000 claims 1
- 230000006870 function Effects 0.000 description 12
- 230000009471 action Effects 0.000 description 10
- 238000013473 artificial intelligence Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 230000002457 bidirectional effect Effects 0.000 description 2
- 210000004556 brain Anatomy 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000011664 signaling Effects 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
- G10L15/26—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
-
- 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
- G10L17/00—Speaker identification or verification techniques
- G10L17/04—Training, enrolment or model building
-
- 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
- G10L17/00—Speaker identification or verification techniques
- G10L17/18—Artificial neural networks; Connectionist approaches
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a voice scheduling method facing power grid scheduling, which comprises the following steps: establishing an intelligent voice interaction model; establishing an intention recognition model; establishing a conversation process management knowledge graph; correcting the intention recognition model through a dialogue process management knowledge graph; converting the voice instruction of the dispatcher into a text through an intelligent voice interaction model, and returning voice information needing to be interacted with the dispatcher; identifying and analyzing the instruction converted into the text through an intention identification model; the invention greatly improves the working efficiency of the dispatching personnel and lightens the working intensity of the dispatching personnel.
Description
Technical Field
The invention belongs to the technical field of power grid dispatching operation, and particularly relates to a voice dispatching method and system for power grid dispatching.
Background
As a core driving force of a new industrial revolution, artificial intelligence has remarkable effect on the aspects of enabling and improving the traditional industry and urging the new industry to grow, and is expected to cause great revolution of economic structures. China highly attaches importance to the development of artificial intelligence industry, and policies of a plurality of national levels are developed successively from 2016, and development tasks are implemented hierarchically from product, enterprise and industry levels. Under the promotion of artificial intelligence strategies and capital markets of various countries, enterprises, products and services with artificial intelligence emerge endlessly. Artificial intelligence consumption level products such as automatic driving, industrial robot, intelligent medical treatment, unmanned aerial vehicle, intelligent house assistant breed the rise, and artificial intelligence and each field of each trade of economic society fuse the innovation level and constantly promote. With the construction and the improvement of new technologies such as a regulation cloud platform and the like, the data volume and the computing capacity of the power system are greatly improved recently, and favorable conditions are created for developing the technical research of the artificial intelligent robot in the field of power regulation.
With the rapid development of power systems, the market-oriented work of power is promoted, the integration characteristics of large power grids become more and more obvious, and the coupling relationship between different elements in the systems and the external environment is continuously enhanced. The types of power grid resources are continuously enriched, the new energy ratio is continuously improved, new control targets such as the improvement of the new energy consumption level are continuously evolved, and the uncertainty of the power grid state is further enhanced. A series of deep development changes of the power system and the regulation and control service enable the complexity of the scheduling control strategy and the regulation to be continuously improved, and higher requirements are provided for automation and intellectualization of the regulation and control service. The power dispatching control center is a 'command brain' integrating high-value data, analysis rules, expert experience and calculation decisions, the existing regulation and control mode mainly takes manual experience analysis as a main mode, a dispatcher needs to perform experience knowledge correlation on massive and diverse data and scheme models, more repetitive 'human brain labor' is needed, and the efficiency is low, so that intelligent regulation and control are realized, and the working intensity of the regulator is reduced.
Disclosure of Invention
The invention aims to provide a voice scheduling method and system for power grid scheduling, which can perform scheduling operation on a power grid through voice interaction.
In order to achieve the purpose, the invention provides the following technical scheme:
in a first aspect, a voice scheduling method facing power grid scheduling is provided, including:
establishing an intelligent voice interaction model;
establishing an intention recognition model;
establishing a conversation process management knowledge graph;
correcting the intention recognition model through a dialogue process management knowledge graph;
converting the voice instruction of the dispatcher into a text through an intelligent voice interaction model, and returning voice information needing to be interacted with the dispatcher;
identifying and analyzing the instruction converted into the text through an intention identification model;
and executing the analyzed instruction to realize scheduling operation.
With reference to the first aspect, further, the intelligent voice interaction model is established based on a scheduling professional business scenario and includes voice recognition, natural language understanding, and voice synthesis, and the voice recognition includes a hot word training model.
With reference to the first aspect, further, the intelligent voice interaction model training employs a power grid professional corpus.
With reference to the first aspect, further, the intention recognition model is built based on a text convolutional neural network.
With reference to the first aspect, further, the dialogue flow management knowledge graph is established based on a deep learning framework long-short term memory network-conditional random field + convolutional neural network.
With reference to the first aspect, further, the modifying the intention recognition model through the dialogue process management knowledge graph specifically includes: and establishing an error intention iterative training model in the dialogue process management knowledge graph, sorting and identifying the error intention through the error intention iterative training model, and performing iterative updating training on the intention.
With reference to the first aspect, further, the scheduling operation includes device status query, device status operation, voice mapping, and network operation rule question answering.
In a second aspect, a voice scheduling system for power grid scheduling is provided, including:
a modeling module: the intelligent voice interaction model is established; establishing an intention recognition model; establishing a conversation process management knowledge graph; correcting the intention recognition model through a dialogue process management knowledge graph;
a voice scheduling module: the intelligent voice interaction model is used for converting the voice instruction of the dispatcher into a text and returning voice information needing to be interacted with the dispatcher;
identifying and analyzing the instruction converted into the text through an intention identification model;
and executing the analyzed instruction to realize scheduling operation.
The beneficial technical effects are as follows: according to the invention, an intelligent voice interaction model, an intention recognition model and a dialogue management knowledge graph are established to carry out voice interaction with a dispatcher, and a language model and a semantic understanding model suitable for the regulation and control specialty are trained and formed by combining the characteristics of the regulation and control specialty, so that the operation intention of the dispatcher is accurately recognized, and the dispatching operation on the power grid is completed. In the process of establishing each model, a self-learning mechanism is integrated, iterative training can be carried out on scheduling professional terms with errors and operation intents with errors, the speech recognition accuracy and the intention recognition accuracy are improved, the speech recognition accuracy is over 95%, the semantic understanding accuracy is over 98%, and the interaction success rate is about 98%. The work efficiency of the dispatching personnel is greatly improved, and the burden is reduced.
Drawings
FIG. 1 is a system architecture diagram of the present invention;
FIG. 2 is a flow chart of the device status query function of the present invention;
FIG. 3 is a flow chart of the device state operation function of the present invention;
FIG. 4 is a flow chart of the voice mapping function of the present invention;
FIG. 5 is a flow chart of a question-answering function of the grid operation rules of the present invention;
FIG. 6 is a schematic diagram of intelligent voice interaction in the present invention;
fig. 7 is a flow chart of a multi-turn dialog in the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the case of the example 1, the following examples are given,
as shown in fig. 1 to 7, the invention provides a voice scheduling method for power grid scheduling, which implements scheduling of a power grid by establishing an artificial intelligence system model fused with a self-learning mechanism according to requirements of equipment and information-assisted operation scenes, and mainly includes the following aspects:
establishing an intelligent voice interaction model covering voice recognition and voice synthesis based on scheduling professional service scenes, wherein the model is established based on scheduling professional service scenes and a power grid professional corpus, is mainly used for recognizing voice instructions of a dispatcher, converting the voice instructions into texts and returning voice information needing to be interacted with the dispatcher;
the intelligent voice interaction is a process of converting natural language into text and converting the text into voice, and the process mainly comprises the following steps: speech recognition, natural language understanding and speech synthesis 3 parts. The technical implementation is shown in fig. 6.
Speech Recognition (ASR) is a process of converting speech into text, and first, collects a large amount of text and audio-controlled corpora, and constructs a corpus of "universal small sample set + electric power professional lexicon". Using the corpus, acoustic models are trained based on a Bidirectional Recurrent Neural Network (BRNN) and a Convolutional Neural Network (CNN), and language models are trained based on a statistical Ngram model and an RNN model of the neural network. And obtaining a characteristic sequence by processing voice noise and extracting characteristics, matching the characteristic sequence with the characteristic sequence in a training library through voice decoding, and obtaining an output voice text according to the characteristic sequence with the highest comprehensive score of the acoustic model and the language model. In addition, a power professional dictionary is constructed, so that new power vocabularies can be configured at any time, and the voice is converted into text.
Natural Language Understanding (NLU) is used for understanding knowledge and intention of user voice and is mainly realized by building intention recognition and slot filling models based on a deep neural network. Firstly, collecting the operation intention of a user, designing the possible interactive dialogue of the regulation and control business scene according to the intention, wherein the dialogue contents are the collected regulation and control corpus samples. And then, marking the intention and the slot position in the regulating and controlling corpus by adopting a Rasa marking tool to form a marked corpus sample. And finally, establishing an intention recognition model based on a convolutional neural network (TextCNN) by using the labeled corpus sample, and establishing a slot filling model based on a bidirectional long-short term memory network (BilSTM-CRF), thereby constructing a natural language understanding model. In the process, the services of power grid analysis, calculation, operation and the like in the intelligent regulation and control system can be combined to perform operations of information inquiry, calculation, operation and the like.
And (4) speech synthesis (TTS), inputting the text to be synthesized into a speech synthesis engine for processing, setting characteristic parameters of the synthesized speech, and then using a Speak method to realize speech reading, thereby completing the conversion of the text into the speech.
The voice interaction is completed based on the Torontal conversation, the multi-turn conversation technology is that a person and a robot can freely and smoothly talk, and the robot locks the intention of the talker through the content of the talk, so that the whole talk process is matched and guided. As shown in fig. 7, the multi-turn dialogue system mainly includes 6 functional modules, such as speech recognition, natural language understanding, dialogue state tracking, dialogue strategy learning, natural language generation, and speech synthesis, which establish a natural language understanding model and a dialogue management model based on a natural language processing technology and a deep neural network, and can support man-machine multi-turn dialogue in the field of power grid regulation and control, and assist the regulation and control personnel in completing intelligent response to complex problems.
In order to recognize and analyze the text instructions, an intention recognition model is required to be established, and the intention recognition model is established based on a text convolutional neural network (TextCNN); however, in the power grid dispatching operation, the situations of electric power professional term recognition errors and intention recognition errors exist due to the fact that the expressions of the professional terms are diverse, and in order that the model can be trained and grown in an iterative mode fast, a hotword training model is built in the voice recognition model based on a self-learning mechanism, the model can train the electric power professional terms on line in real time, the intelligence of the model can grow fast, and the accuracy of voice recognition is guaranteed. In addition, an error intention iterative training model is established in the dialogue process management knowledge graph based on a self-learning mechanism, the model can sort and identify the error intentions, iterative updating training is carried out on the intentions, the intelligence of the model is improved, the error intentions are ensured to be updated into the model in a short time, the intention identification model is corrected, and the intention identification accuracy of the intention identification model is improved.
And finally, calling the analyzed various operation scheduling operation instructions through various interfaces provided by a real-time library of the intelligent control system.
The scheduling operation mainly includes the following aspects:
1) device status query
The equipment state query function supports query of information such as a power grid running state, an equipment remote signaling state, an equipment remote measurement value, a power grid power supply loop closing state and the like based on the intelligent regulation and control system.
The overall flow of the device status query function is shown in fig. 2. The self-learning intelligent voice interaction module receives a voice query instruction of a dispatcher in real time, the self-learning intention recognition module recognizes and analyzes the instruction, key information such as a query object and a query action is extracted, a knowledge graph is managed through a conversation process to form an equipment state query action, and the equipment state query action is sent to equipment state query service in a convention format.
The equipment state query service acquires model information, topological information and real-time data of the power grid through a real-time library interface of the intelligent control system, analyzes the state of a query object, and returns result information in an agreed format to the conversation process management knowledge graph.
2) Device state operation
The equipment state operation function supports the card hanging and card picking operation of the equipment.
The overall flow of the device status operation function is shown in fig. 3. The self-learning intelligent voice interaction module receives a voice operation instruction of an operator in real time, the self-learning intention recognition module recognizes and analyzes the instruction, extracts key information such as an operation object and an operation action, manages a knowledge graph through a conversation process to form an operation equipment state action, and sends the operation equipment state action to equipment state operation service in a conventional format.
The equipment state operation service calls an equipment state operation interface provided by the intelligent control system to complete setting of the equipment state, acquires the state information of the operation object equipment through a real-time library interface of the intelligent control system, verifies the operation result according to the state information, and finally returns the result information in the agreed format to the conversation process management knowledge graph.
3) Voice tone map
The voice map adjusting function supports opening of graphical interfaces such as a tidal current diagram, a single line diagram and an interval diagram in the intelligent control system through voice.
The overall flow of the voice mapping function is shown in fig. 4. The self-learning intelligent voice interaction module receives a voice chart adjusting instruction of an operator in real time, the self-learning intention identification module identifies and analyzes the instruction, graphic name information is extracted, a knowledge graph is managed through a conversation process to form a chart adjusting action, and the chart adjusting action is sent to a chart opening service by adopting an agreed format.
The starting picture service calls a starting picture interface provided by a man-machine platform of the intelligent control system, transmits parameters such as graphic picture names and the like, triggers a new or current man-machine picture browser to open a corresponding graphic picture, and checks whether the starting picture is successful.
4) Power grid operation rule question-answering
The power grid operation rule question-answering function supports intelligent retrieval and intelligent answering of power grid regulation and control rules such as power grid operation rules and fault handling rules.
The overall flow of the power grid operation rule question-answering function is shown in fig. 5. The self-learning intelligent voice interaction module receives an operation rule query instruction of an operator in real time, the self-learning intention recognition module recognizes and analyzes the instruction, key information in the instruction is extracted, an operation rule query action is formed through a conversation process management knowledge graph, the operation rule query action is sent to a power grid operation rule base service in a conventional format, the power grid operation rule base service is based on a regulation knowledge base, retrieval is carried out according to the query instruction, and a retrieval result is returned to the conversation process management knowledge graph.
Example 2
The invention also provides a voice scheduling system facing to power grid scheduling, which comprises:
a modeling module: the intelligent voice interaction model is established; establishing an intention recognition model; establishing a conversation process management knowledge graph; correcting the intention recognition model through a dialogue process management knowledge graph;
a voice scheduling module: the intelligent voice interaction model is used for converting the voice instruction of the dispatcher into a text and returning voice information needing to be interacted with the dispatcher;
identifying and analyzing the instruction converted into the text through an intention identification model;
and executing the analyzed instruction to realize scheduling operation.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (8)
1. A voice scheduling method facing power grid scheduling is characterized by comprising the following steps:
establishing an intelligent voice interaction model;
establishing an intention recognition model;
establishing a conversation process management knowledge graph;
correcting the intention recognition model through a dialogue process management knowledge graph;
converting the voice instruction of the dispatcher into a text through an intelligent voice interaction model, and returning voice information needing to be interacted with the dispatcher;
identifying and analyzing the instruction converted into the text through an intention identification model;
and executing the analyzed instruction to realize scheduling operation.
2. The power grid scheduling-oriented voice scheduling method according to claim 1, wherein: the intelligent voice interaction model is established based on the scheduling professional business scene and comprises voice recognition, natural language understanding and voice synthesis, wherein the voice recognition comprises a hot word training model.
3. The power grid scheduling-oriented voice scheduling method according to claim 1, wherein: and the intelligent voice interaction model training adopts a power grid professional corpus.
4. The power grid scheduling-oriented voice scheduling method according to claim 1, wherein: the intention recognition model is built based on a text convolutional neural network.
5. The power grid scheduling-oriented voice scheduling method according to claim 1, wherein the conversation process management knowledge graph is established based on a deep learning framework long and short term memory network-conditional random field + convolutional neural network.
6. The power grid scheduling-oriented voice scheduling method according to claim 1, wherein the modifying the intention recognition model through the conversation process management knowledge base specifically comprises: and establishing an error intention iterative training model in the dialogue process management knowledge graph, sorting and identifying the error intention through the error intention iterative training model, and performing iterative updating training on the intention.
7. The power grid scheduling oriented voice scheduling method of claim 1, wherein the scheduling operation comprises a device state query, a device state operation, a voice map, and a grid operation rule question-answer.
8. The power grid scheduling-oriented voice scheduling method according to claim 1, comprising:
a modeling module: the intelligent voice interaction model is established; establishing an intention recognition model; establishing a conversation process management knowledge graph; correcting the intention recognition model through a dialogue process management knowledge graph;
a voice scheduling module: the intelligent voice interaction model is used for converting the voice instruction of the dispatcher into a text and returning voice information needing to be interacted with the dispatcher;
identifying and analyzing the instruction converted into the text through an intention identification model;
and executing the analyzed instruction to realize scheduling operation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011310565.1A CN112599124A (en) | 2020-11-20 | 2020-11-20 | Voice scheduling method and system for power grid scheduling |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011310565.1A CN112599124A (en) | 2020-11-20 | 2020-11-20 | Voice scheduling method and system for power grid scheduling |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112599124A true CN112599124A (en) | 2021-04-02 |
Family
ID=75183506
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011310565.1A Pending CN112599124A (en) | 2020-11-20 | 2020-11-20 | Voice scheduling method and system for power grid scheduling |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112599124A (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113112236A (en) * | 2021-04-19 | 2021-07-13 | 云南电网有限责任公司迪庆供电局 | Intelligent distribution network scheduling system and method based on voice and voiceprint recognition |
CN113283695A (en) * | 2021-04-19 | 2021-08-20 | 贵州电网有限责任公司 | Power dispatching intelligent agent implementation method and system based on artificial intelligence |
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 |
CN113470652A (en) * | 2021-06-30 | 2021-10-01 | 山东恒远智能科技有限公司 | Voice recognition and processing method based on industrial Internet |
CN113590749A (en) * | 2021-07-30 | 2021-11-02 | 广东电网有限责任公司 | Telephone anti-error method, device, equipment and storage medium for power system |
CN113689851A (en) * | 2021-07-27 | 2021-11-23 | 国家电网有限公司 | Scheduling professional language understanding system and method |
CN113687719A (en) * | 2021-08-23 | 2021-11-23 | 广东电网有限责任公司 | Intelligent interaction method and device suitable for voice information |
CN113807642A (en) * | 2021-06-25 | 2021-12-17 | 国网浙江省电力有限公司金华供电公司 | Power dispatching intelligent interaction method based on program-controlled telephone |
CN113849604A (en) * | 2021-09-27 | 2021-12-28 | 广东纬德信息科技股份有限公司 | NLP-based power grid regulation and control method, system, equipment and storage medium |
US20220028373A1 (en) * | 2020-07-24 | 2022-01-27 | Comcast Cable Communications, Llc | Systems and methods for training voice query models |
CN114171021A (en) * | 2021-11-29 | 2022-03-11 | 国网江苏省电力有限公司南京供电分公司 | Distribution network virtual scheduling system and method based on artificial intelligence |
CN114333807A (en) * | 2021-12-24 | 2022-04-12 | 北京百度网讯科技有限公司 | Power scheduling method, device, equipment, storage medium and program |
CN115101067A (en) * | 2022-06-16 | 2022-09-23 | 陈明华 | Smart power grids voice system based on block chain technique |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106569998A (en) * | 2016-10-27 | 2017-04-19 | 浙江大学 | Text named entity recognition method based on Bi-LSTM, CNN and CRF |
CN108874774A (en) * | 2018-06-05 | 2018-11-23 | 浪潮软件股份有限公司 | A kind of service calling method and system based on intention understanding |
CN110059170A (en) * | 2019-03-21 | 2019-07-26 | 北京邮电大学 | More wheels based on user's interaction talk with on-line training method and system |
CN110209791A (en) * | 2019-06-12 | 2019-09-06 | 百融云创科技股份有限公司 | It is a kind of to take turns dialogue intelligent speech interactive system and device more |
CN111489748A (en) * | 2019-10-18 | 2020-08-04 | 广西电网有限责任公司 | Intelligent voice scheduling auxiliary system |
CN111737458A (en) * | 2020-05-21 | 2020-10-02 | 平安国际智慧城市科技股份有限公司 | Intention identification method, device and equipment based on attention mechanism and storage medium |
CN111881280A (en) * | 2020-07-28 | 2020-11-03 | 南方电网深圳数字电网研究院有限公司 | Intelligent man-machine interaction system and method for power industry |
-
2020
- 2020-11-20 CN CN202011310565.1A patent/CN112599124A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106569998A (en) * | 2016-10-27 | 2017-04-19 | 浙江大学 | Text named entity recognition method based on Bi-LSTM, CNN and CRF |
CN108874774A (en) * | 2018-06-05 | 2018-11-23 | 浪潮软件股份有限公司 | A kind of service calling method and system based on intention understanding |
CN110059170A (en) * | 2019-03-21 | 2019-07-26 | 北京邮电大学 | More wheels based on user's interaction talk with on-line training method and system |
CN110209791A (en) * | 2019-06-12 | 2019-09-06 | 百融云创科技股份有限公司 | It is a kind of to take turns dialogue intelligent speech interactive system and device more |
CN111489748A (en) * | 2019-10-18 | 2020-08-04 | 广西电网有限责任公司 | Intelligent voice scheduling auxiliary system |
CN111737458A (en) * | 2020-05-21 | 2020-10-02 | 平安国际智慧城市科技股份有限公司 | Intention identification method, device and equipment based on attention mechanism and storage medium |
CN111881280A (en) * | 2020-07-28 | 2020-11-03 | 南方电网深圳数字电网研究院有限公司 | Intelligent man-machine interaction system and method for power industry |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20220028373A1 (en) * | 2020-07-24 | 2022-01-27 | Comcast Cable Communications, Llc | Systems and methods for training voice query models |
CN113283695A (en) * | 2021-04-19 | 2021-08-20 | 贵州电网有限责任公司 | Power dispatching intelligent agent implementation method and system based on artificial intelligence |
CN113112236A (en) * | 2021-04-19 | 2021-07-13 | 云南电网有限责任公司迪庆供电局 | Intelligent distribution network scheduling system and method based on voice and voiceprint recognition |
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 |
CN113807642A (en) * | 2021-06-25 | 2021-12-17 | 国网浙江省电力有限公司金华供电公司 | Power dispatching intelligent interaction method based on program-controlled telephone |
CN113470652A (en) * | 2021-06-30 | 2021-10-01 | 山东恒远智能科技有限公司 | Voice recognition and processing method based on industrial Internet |
CN113689851A (en) * | 2021-07-27 | 2021-11-23 | 国家电网有限公司 | Scheduling professional language understanding system and method |
CN113689851B (en) * | 2021-07-27 | 2024-02-02 | 国家电网有限公司 | Scheduling professional language understanding system and method |
CN113590749A (en) * | 2021-07-30 | 2021-11-02 | 广东电网有限责任公司 | Telephone anti-error method, device, equipment and storage medium for power system |
CN113687719A (en) * | 2021-08-23 | 2021-11-23 | 广东电网有限责任公司 | Intelligent interaction method and device suitable for voice information |
CN113849604A (en) * | 2021-09-27 | 2021-12-28 | 广东纬德信息科技股份有限公司 | NLP-based power grid regulation and control method, system, equipment and storage medium |
CN114171021A (en) * | 2021-11-29 | 2022-03-11 | 国网江苏省电力有限公司南京供电分公司 | Distribution network virtual scheduling system and method based on artificial intelligence |
CN114333807A (en) * | 2021-12-24 | 2022-04-12 | 北京百度网讯科技有限公司 | Power scheduling method, device, equipment, storage medium and program |
CN115101067A (en) * | 2022-06-16 | 2022-09-23 | 陈明华 | Smart power grids voice system based on block chain technique |
CN115101067B (en) * | 2022-06-16 | 2024-04-16 | 陈明华 | Smart power grids voice system based on blockchain technique |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112599124A (en) | Voice scheduling method and system for power grid scheduling | |
CN111666381B (en) | Task type question-answer interaction system oriented to intelligent control | |
CN110717018A (en) | Industrial equipment fault maintenance question-answering system based on knowledge graph | |
CN111104498A (en) | Semantic understanding method in task type dialogue system | |
CN110083110A (en) | End to end control method and control system based on natural intelligence | |
CN111429915A (en) | Scheduling system and scheduling method based on voice recognition | |
CN106557165B (en) | The action simulation exchange method and device and smart machine of smart machine | |
CN107679147A (en) | Human-computer dialogue formula electric network information based on speech recognition has access to methods of exhibiting | |
CN113314106A (en) | Electric power information query and regulation function calling method based on voice and intention recognition | |
CN112632288A (en) | Power dispatching system and method based on knowledge graph | |
CN111475655A (en) | Power distribution network knowledge graph-based power scheduling text entity linking method | |
CN110110095A (en) | A kind of power command text matching technique based on shot and long term memory Recognition with Recurrent Neural Network | |
CN111950297A (en) | Abnormal event oriented relation extraction method | |
CN116166688A (en) | Business data retrieval method, system and processing equipment based on natural language interaction | |
CN113140219A (en) | Regulation and control instruction generation method and device, electronic equipment and storage medium | |
CN113326367B (en) | Task type dialogue method and system based on end-to-end text generation | |
CN111695763B (en) | Scheduling system and method based on voice question and answer | |
CN117149977A (en) | Intelligent collecting robot based on robot flow automation | |
CN111597790B (en) | Natural language processing system based on artificial intelligence | |
CN112863485A (en) | Accent voice recognition method, apparatus, device and storage medium | |
CN117524202A (en) | Voice data retrieval method and system for IP telephone | |
CN110728980A (en) | Intelligent service bus system based on voice and conversation robot | |
CN113689851B (en) | Scheduling professional language understanding system and method | |
CN115688805A (en) | Electric power virtual scheduling method and system based on element-multitask learning | |
KR20230116143A (en) | Counseling Type Classification System |
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: 20210402 |
|
RJ01 | Rejection of invention patent application after publication |