CN112530434A - Automatic intelligent robot on duty scheduling system of power station - Google Patents
Automatic intelligent robot on duty scheduling system of power station Download PDFInfo
- Publication number
- CN112530434A CN112530434A CN202011513811.3A CN202011513811A CN112530434A CN 112530434 A CN112530434 A CN 112530434A CN 202011513811 A CN202011513811 A CN 202011513811A CN 112530434 A CN112530434 A CN 112530434A
- Authority
- CN
- China
- Prior art keywords
- image
- module
- voice
- processing
- recognition
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/253—Grammatical analysis; Style critique
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/08—Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L15/14—Speech classification or search using statistical models, e.g. Hidden Markov Models [HMMs]
- G10L15/142—Hidden Markov Models [HMMs]
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—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 OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/20—Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
- G10L2015/025—Phonemes, fenemes or fenones being the recognition units
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Abstract
Automatic intelligent robot on duty dispatch system of power station relates to the power station. The voice recognition system comprises a voice recognition module, a semantic recognition module, an image recognition module, an intelligent interaction module, a processing module and a database, wherein the voice recognition module is connected with the semantic recognition module; after the image information is analyzed and processed by the image identification module, the analyzed data is sent to the processing module; the processing module compares the analyzed data with the database data to obtain a processing result, and then converts the processing result into a voice signal or a picture signal through the intelligent interaction module to be issued. The invention combines artificial intelligence and power service, applies the artificial intelligence and the power service to power scheduling, and establishes a technical support means for intelligent and efficient debugging of information access of the dispatching automation plant station.
Description
Technical Field
The invention relates to a power station, in particular to an automatic intelligent robot on-duty dispatching system for a power station, which realizes automatic access to dispatching of a power supply bureau by adopting robot on-duty.
Background
The modern power grid needs dispatching automation information support, and the work that each station accesses the power grid and the station end information is accessed to the dispatching automation master station needs to be carried out.
At present, the common practice is to perform modeling, drawing graphs, warehousing models, communication joint debugging, data access joint debugging and other steps according to a master station, and rely on a scheduling end to synchronously communicate with debugging personnel at a plant end in real time through telephone, so that a lot of manpower is consumed, troubleshooting is time-consuming, error is easy to occur, debugging time is short, the once completion accuracy cannot reach 100%, efficiency is low, and stable and safe operation of a power grid is influenced.
The power supply bureau is developing the smart grid pilot construction, which not only needs the information access of the new station, but also needs the information access of the original station to the automatic system of the local dispatching and the distribution network dispatching, the follow-up workload is huge, the access information quality requirement is high, and the challenge is brought to the automatic work.
Disclosure of Invention
The invention aims to solve the problems that the existing dispatching end is communicated with a station end through a telephone, the efficiency is low, and the operation of a power grid is influenced, and provides a power station automatic intelligent robot watching dispatching system which adopts robot watching to realize automatic access to dispatching of a power supply bureau.
The invention discloses a substation automation intelligent robot on-duty scheduling system which is characterized by comprising a voice recognition module, a semantic recognition module, an image recognition module, an intelligent interaction module, a processing module and a database, wherein the voice recognition module is connected with the semantic recognition module; after the image information is analyzed and processed by the image identification module, the analyzed data is sent to the processing module; the processing module compares the analyzed data with database data to obtain a processing result, and then converts the processing result into a voice signal or a picture signal through the intelligent interaction module to be issued; wherein:
1) the speech recognition comprises the following steps:
(1) pretreatment: the method comprises the steps of carrying out mute processing, high-pitch pre-emphasis, noise reduction and dereverberation in sequence to eliminate interference and highlight voice characteristics;
(2) waveform framing: cutting the complete time domain waveform into small segments, wherein each segment is called a frame, the length of each frame is 25 milliseconds, and the two frames are overlapped by 25-10=15 milliseconds, so that framing with the frame length of 25ms and frame shift of 10ms is realized;
(3) acoustic feature extraction: extracting the acoustic features of the framing waveform, changing a frame waveform into a multi-dimensional vector, wherein the acoustic features are X-dimensional, the framing waveform is set as a matrix of rows and N columns, and the matrix is called an observation sequence, and the observation sequence contains the content information of the frame of voice;
(4) pattern matching: identifying frames as states, each frame obtaining a state number; the state combination is phonemes, the pronunciation of a word is composed of phonemes, the English phoneme set comprises 39 phonemes, and the Chinese phoneme set comprises all initials, finals and tones; combining the phonemes into words; in the process, matching between the voice and a module library is completed by adopting a hidden Markov model or a Gaussian mixture model, so that voice recognition is completed;
2) the image recognition process is divided into two parts of image processing and image recognition:
(1) image processing: the method comprises the steps of adopting digital image processing including image sampling, image enhancement, image restoration, image coding and compression and image segmentation, programming an original image into a form suitable for computer to extract features;
(2) image recognition: a statistical method, a syntax recognition method, a neural network method, a template matching method and a geometric transformation method are adopted, and the method specifically comprises the following steps:
statistical method: finding out the rules and extracting the characteristics reflecting the essential characteristics of the image to carry out image recognition;
syntax identification method: the method adopts symbols to describe the image characteristics, decomposes the complex image into single-layer or multi-layer relatively simple sub-images by a layered description method, and mainly highlights the spatial structure relationship information of the identified object;
③ the neural network method: a complex network system formed by a large number of simple processing units connected with each other extensively by recognizing the image with a neural network algorithm;
template matching method: comparing the template of the known object with all unknown objects in the image by using a digital quantity or a symbol string;
a geometric transformation method: all points on a given shape curve in the image are converted into Hough space to form peak points for detecting defective shapes;
3) semantic recognition: the method comprises three steps of lexical analysis, semantic analysis and information extraction:
(1) lexical analysis: converting an input sentence from a word sequence into a word and part-of-speech sequence;
(2) semantic analysis: comparing by using an electric power semantic knowledge base, mapping each word in the language to a vector space with a fixed dimension, and judging the similarity of the words according to the space distance of the word vectors;
(3) information extraction: extracting information of a specified type from the unstructured or semi-structured text, and converting the unstructured text into structured information by means of information merging, redundancy elimination and conflict resolution;
4) intelligent interaction: the method is characterized in that character information is converted into standard and smooth voice in real time for reading aloud, firstly, a character sequence is converted into a phonological sequence, and then, a voice waveform is generated according to the phonological sequence, so that intelligent response interaction is realized.
The automatic intelligent robot on-duty dispatching system for the power station combines new technologies such as artificial intelligence and the like with power services, is applied to power dispatching, establishes a support means for dispatching automatic plant station information access intelligent and efficient debugging technologies, solves the problems of labor consumption, low efficiency and the like of the long-term access debugging work under the condition of not influencing the operation of the existing main station automatic system, effectively improves the debugging efficiency of newly built and technically improved transformer stations, shortens the debugging time, and accelerates the production and power restoration progress of new equipment.
Detailed Description
Example 1: a power station automation intelligent robot on-duty scheduling system comprises a voice recognition module, a semantic recognition module, an image recognition module, an intelligent interaction module, a processing module and a database, wherein the voice recognition module is connected with the semantic recognition module; after the image information is analyzed and processed by the image identification module, the analyzed data is sent to the processing module; the processing module compares the analyzed data with database data to obtain a processing result, and then converts the processing result into a voice signal or a picture signal through the intelligent interaction module to be issued; wherein:
1) the speech recognition comprises the following steps:
(1) pretreatment: the method comprises the steps of carrying out mute processing, high-pitch pre-emphasis, noise reduction and dereverberation in sequence to eliminate interference and highlight voice characteristics;
(2) waveform framing: cutting the complete time domain waveform into small segments, wherein each segment is called a frame, the length of each frame is 25 milliseconds, and the two frames are overlapped by 25-10=15 milliseconds, so that framing with the frame length of 25ms and frame shift of 10ms is realized;
(3) acoustic feature extraction: extracting the acoustic features of the framing waveform, changing a frame waveform into a multi-dimensional vector, wherein the acoustic features are X-dimensional, the framing waveform is set as a matrix of rows and N columns, and the matrix is called an observation sequence, and the observation sequence contains the content information of the frame of voice;
(4) pattern matching: identifying frames as states, each frame obtaining a state number; the state combination is phonemes, the pronunciation of a word is composed of phonemes, the English phoneme set comprises 39 phonemes, and the Chinese phoneme set comprises all initials, finals and tones; combining the phonemes into words; in the process, matching between the voice and a module library is completed by adopting a hidden Markov model or a Gaussian mixture model, so that voice recognition is completed;
2) the image recognition process is divided into two parts of image processing and image recognition:
(1) image processing: the method comprises the steps of adopting digital image processing including image sampling, image enhancement, image restoration, image coding and compression and image segmentation, programming an original image into a form suitable for computer to extract features;
(2) image recognition: a statistical method, a syntax recognition method, a neural network method, a template matching method and a geometric transformation method are adopted, and the method specifically comprises the following steps:
statistical method: finding out the rules and extracting the characteristics reflecting the essential characteristics of the image to carry out image recognition;
syntax identification method: the method adopts symbols to describe the image characteristics, decomposes the complex image into single-layer or multi-layer relatively simple sub-images by a layered description method, and mainly highlights the spatial structure relationship information of the identified object;
③ the neural network method: a complex network system formed by a large number of simple processing units connected with each other extensively by recognizing the image with a neural network algorithm;
template matching method: comparing the template of the known object with all unknown objects in the image by using a digital quantity or a symbol string;
a geometric transformation method: all points on a given shape curve in the image are converted into Hough space to form peak points for detecting defective shapes;
3) semantic recognition: the method comprises three steps of lexical analysis, semantic analysis and information extraction:
(1) lexical analysis: converting an input sentence from a word sequence into a word and part-of-speech sequence;
(2) semantic analysis: comparing by using an electric power semantic knowledge base, mapping each word in the language to a vector space with a fixed dimension, and judging the similarity of the words according to the space distance of the word vectors;
(3) information extraction: extracting information of a specified type from the unstructured or semi-structured text, and converting the unstructured text into structured information by means of information merging, redundancy elimination and conflict resolution;
4) intelligent interaction: the method is characterized in that character information is converted into standard and smooth voice in real time for reading aloud, firstly, a character sequence is converted into a phonological sequence, and then, a voice waveform is generated according to the phonological sequence, so that intelligent response interaction is realized.
Claims (1)
1. A power station automation intelligent robot on-duty scheduling system is characterized by comprising a voice recognition module, a semantic recognition module, an image recognition module, an intelligent interaction module, a processing module and a database, wherein the voice recognition module is connected with the semantic recognition module, the processing module is respectively connected with the semantic recognition module, the image recognition module, the intelligent interaction module and the database, a voice command is processed by the voice recognition module and then sent to the semantic recognition module for analysis, and the analyzed data enters the processing module; after the image information is analyzed and processed by the image identification module, the analyzed data is sent to the processing module; the processing module compares the analyzed data with database data to obtain a processing result, and then converts the processing result into a voice signal or a picture signal through the intelligent interaction module to be issued; wherein:
1) the speech recognition comprises the following steps:
(1) pretreatment: the method comprises the steps of carrying out mute processing, high-pitch pre-emphasis, noise reduction and dereverberation in sequence to eliminate interference and highlight voice characteristics;
(2) waveform framing: cutting the complete time domain waveform into small segments, wherein each segment is called a frame, the length of each frame is 25 milliseconds, and the two frames are overlapped by 25-10=15 milliseconds, so that framing with the frame length of 25ms and frame shift of 10ms is realized;
(3) acoustic feature extraction: extracting the acoustic features of the framing waveform, changing a frame waveform into a multi-dimensional vector, wherein the acoustic features are X-dimensional, the framing waveform is set as a matrix of rows and N columns, and the matrix is called an observation sequence, and the observation sequence contains the content information of the frame of voice;
(4) pattern matching: identifying frames as states, each frame obtaining a state number; the state combination is phonemes, the pronunciation of a word is composed of phonemes, the English phoneme set comprises 39 phonemes, and the Chinese phoneme set comprises all initials, finals and tones; combining the phonemes into words; in the process, matching between the voice and a module library is completed by adopting a hidden Markov model or a Gaussian mixture model, so that voice recognition is completed;
2) the image recognition process is divided into two parts of image processing and image recognition:
(1) image processing: the method comprises the steps of adopting digital image processing including image sampling, image enhancement, image restoration, image coding and compression and image segmentation, programming an original image into a form suitable for computer to extract features;
(2) image recognition: a statistical method, a syntax recognition method, a neural network method, a template matching method and a geometric transformation method are adopted, and the method specifically comprises the following steps:
statistical method: finding out the rules and extracting the characteristics reflecting the essential characteristics of the image to carry out image recognition;
syntax identification method: the method adopts symbols to describe the image characteristics, decomposes the complex image into single-layer or multi-layer relatively simple sub-images by a layered description method, and mainly highlights the spatial structure relationship information of the identified object;
③ the neural network method: a complex network system formed by a large number of simple processing units connected with each other extensively by recognizing the image with a neural network algorithm;
template matching method: comparing the template of the known object with all unknown objects in the image by using a digital quantity or a symbol string;
a geometric transformation method: all points on a given shape curve in the image are converted into Hough space to form peak points for detecting defective shapes;
3) semantic recognition: the method comprises three steps of lexical analysis, semantic analysis and information extraction:
(1) lexical analysis: converting an input sentence from a word sequence into a word and part-of-speech sequence;
(2) semantic analysis: comparing by using an electric power semantic knowledge base, mapping each word in the language to a vector space with a fixed dimension, and judging the similarity of the words according to the space distance of the word vectors;
(3) information extraction: extracting information of a specified type from the unstructured or semi-structured text, and converting the unstructured text into structured information by means of information merging, redundancy elimination and conflict resolution;
4) intelligent interaction: the method is characterized in that character information is converted into standard and smooth voice in real time for reading aloud, firstly, a character sequence is converted into a phonological sequence, and then, a voice waveform is generated according to the phonological sequence, so that intelligent response interaction is realized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011513811.3A CN112530434A (en) | 2020-12-21 | 2020-12-21 | Automatic intelligent robot on duty scheduling system of power station |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011513811.3A CN112530434A (en) | 2020-12-21 | 2020-12-21 | Automatic intelligent robot on duty scheduling system of power station |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112530434A true CN112530434A (en) | 2021-03-19 |
Family
ID=75001821
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011513811.3A Pending CN112530434A (en) | 2020-12-21 | 2020-12-21 | Automatic intelligent robot on duty scheduling system of power station |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112530434A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113823269A (en) * | 2021-09-07 | 2021-12-21 | 广西电网有限责任公司贺州供电局 | Method for automatically storing power grid dispatching command based on voice recognition |
| CN115482807A (en) * | 2022-08-11 | 2022-12-16 | 天津大学 | Detection method and system for voice interaction of intelligent terminal |
| CN116095532A (en) * | 2023-01-31 | 2023-05-09 | 上海智臻智能网络科技股份有限公司 | Device and method for intelligent debugging of remote data of master station and factory station |
| CN117854506A (en) * | 2024-03-07 | 2024-04-09 | 鲁东大学 | Robot voice intelligent interaction system |
| CN117854506B (en) * | 2024-03-07 | 2024-05-14 | 鲁东大学 | Robot voice intelligent interaction system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103985382A (en) * | 2014-05-23 | 2014-08-13 | 国家电网公司 | Power grid dispatching auxiliary interactive method based on speech recognition technology |
| CN104123939A (en) * | 2014-06-06 | 2014-10-29 | 国家电网公司 | Substation inspection robot based voice interaction control method |
| CN106407993A (en) * | 2016-09-13 | 2017-02-15 | 成都创慧科达科技有限公司 | Intelligent voice robot system based on image recognition technology and method thereof |
| CN108447475A (en) * | 2018-03-02 | 2018-08-24 | 国家电网公司华中分部 | A kind of method for building up of the speech recognition modeling based on electric power dispatching system |
| CN111489748A (en) * | 2019-10-18 | 2020-08-04 | 广西电网有限责任公司 | Intelligent voice scheduling auxiliary system |
| CN213461246U (en) * | 2020-09-02 | 2021-06-15 | 云南电网有限责任公司玉溪供电局 | Automatic intelligent robot on duty device of electric wire netting dispatch |
-
2020
- 2020-12-21 CN CN202011513811.3A patent/CN112530434A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103985382A (en) * | 2014-05-23 | 2014-08-13 | 国家电网公司 | Power grid dispatching auxiliary interactive method based on speech recognition technology |
| CN104123939A (en) * | 2014-06-06 | 2014-10-29 | 国家电网公司 | Substation inspection robot based voice interaction control method |
| CN106407993A (en) * | 2016-09-13 | 2017-02-15 | 成都创慧科达科技有限公司 | Intelligent voice robot system based on image recognition technology and method thereof |
| CN108447475A (en) * | 2018-03-02 | 2018-08-24 | 国家电网公司华中分部 | A kind of method for building up of the speech recognition modeling based on electric power dispatching system |
| CN111489748A (en) * | 2019-10-18 | 2020-08-04 | 广西电网有限责任公司 | Intelligent voice scheduling auxiliary system |
| CN213461246U (en) * | 2020-09-02 | 2021-06-15 | 云南电网有限责任公司玉溪供电局 | Automatic intelligent robot on duty device of electric wire netting dispatch |
Non-Patent Citations (4)
| Title |
|---|
| 天津滨海迅腾科技集团有限公司: "《走进大数据与人工智能》", 31 August 2018 * |
| 岳文辉 等: "图像识别技术及其在机械零件无损检测中的应用", 《中国安全科学学报》 * |
| 施云波: "《普通高等教育物联网工程专业"十三五"规划教材 无线传感器网络技术概论》", 30 September 2017 * |
| 苏新宁 等: "《数据挖掘理论与技术》", 30 June 2006 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113823269A (en) * | 2021-09-07 | 2021-12-21 | 广西电网有限责任公司贺州供电局 | Method for automatically storing power grid dispatching command based on voice recognition |
| WO2023036014A1 (en) * | 2021-09-07 | 2023-03-16 | 广西电网有限责任公司贺州供电局 | Method for automatically saving power grid scheduling command on basis of voice recognition |
| CN115482807A (en) * | 2022-08-11 | 2022-12-16 | 天津大学 | Detection method and system for voice interaction of intelligent terminal |
| CN116095532A (en) * | 2023-01-31 | 2023-05-09 | 上海智臻智能网络科技股份有限公司 | Device and method for intelligent debugging of remote data of master station and factory station |
| CN116095532B (en) * | 2023-01-31 | 2023-11-10 | 国家电网有限公司华中分部 | Device and method for intelligent debugging of remote data of master station and factory station |
| CN117854506A (en) * | 2024-03-07 | 2024-04-09 | 鲁东大学 | Robot voice intelligent interaction system |
| CN117854506B (en) * | 2024-03-07 | 2024-05-14 | 鲁东大学 | Robot voice intelligent interaction system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112530434A (en) | Automatic intelligent robot on duty scheduling system of power station | |
| CN109255113B (en) | Intelligent proofreading system | |
| CN111489748A (en) | Intelligent voice scheduling auxiliary system | |
| CN109376353B (en) | Natural language processing-based power grid starting operation ticket generation device and method | |
| CN111477216B (en) | Training method and system for voice and meaning understanding model of conversation robot | |
| CN111613212B (en) | Speech recognition method, system, electronic device and storage medium | |
| CN111429915A (en) | Scheduling system and scheduling method based on voice recognition | |
| CN104882141A (en) | Serial port voice control projection system based on time delay neural network and hidden Markov model | |
| CN108763338A (en) | A kind of News Collection&Edit System based on power industry | |
| CN110991188A (en) | Ticket forming method applied to distribution network scheduling intelligent ticket forming system | |
| CN115858758A (en) | Intelligent customer service knowledge graph system with multiple unstructured data identification | |
| CN115249479A (en) | BRNN-based power grid dispatching complex speech recognition method, system and terminal | |
| CN111695763B (en) | Scheduling system and method based on voice question and answer | |
| CN113470650A (en) | Operation ticket anti-error method based on voice recognition | |
| Zhang et al. | Research on spectrum sensing system based on composite neural network | |
| CN116665674A (en) | Internet intelligent recruitment publishing method based on voice and pre-training model | |
| CN116230020A (en) | Speech emotion recognition and classification method | |
| CN113920992A (en) | Distribution network scheduling voice interaction method based on artificial intelligence | |
| CN116092342A (en) | Automatic response and quality assessment method and system for controller simulation training | |
| CN111489745A (en) | Chinese speech recognition system applied to artificial intelligence | |
| CN114792518A (en) | Voice recognition system based on scheduling domain technology, method thereof and storage medium | |
| CN112863485A (en) | Accent voice recognition method, apparatus, device and storage medium | |
| CN116095532B (en) | Device and method for intelligent debugging of remote data of master station and factory station | |
| CN111353305A (en) | Automatic program execution method based on natural language recognition | |
| CN111246026A (en) | Recording processing method based on convolutional neural network and connectivity time sequence classification |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210319 |
|
| WD01 | Invention patent application deemed withdrawn after publication |