CN114171021A - Distribution network virtual scheduling system and method based on artificial intelligence - Google Patents
Distribution network virtual scheduling system and method based on artificial intelligence Download PDFInfo
- Publication number
- CN114171021A CN114171021A CN202111432478.8A CN202111432478A CN114171021A CN 114171021 A CN114171021 A CN 114171021A CN 202111432478 A CN202111432478 A CN 202111432478A CN 114171021 A CN114171021 A CN 114171021A
- Authority
- CN
- China
- Prior art keywords
- voice
- scheduling
- artificial intelligence
- decision
- data
- 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 52
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 50
- 238000009826 distribution Methods 0.000 title claims abstract description 49
- 238000012423 maintenance Methods 0.000 claims abstract description 30
- 230000008569 process Effects 0.000 claims abstract description 29
- 238000012549 training Methods 0.000 claims abstract description 26
- 238000003058 natural language processing Methods 0.000 claims abstract description 25
- 238000004519 manufacturing process Methods 0.000 claims abstract description 6
- 230000015572 biosynthetic process Effects 0.000 claims description 23
- 238000003786 synthesis reaction Methods 0.000 claims description 23
- 238000007726 management method Methods 0.000 claims description 13
- 238000004886 process control Methods 0.000 claims description 9
- 238000013135 deep learning Methods 0.000 claims description 8
- 238000005516 engineering process Methods 0.000 claims description 8
- 230000000007 visual effect Effects 0.000 claims description 7
- 230000005540 biological transmission Effects 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 230000011664 signaling Effects 0.000 claims description 6
- 210000001503 joint Anatomy 0.000 claims description 4
- 238000011084 recovery Methods 0.000 claims description 4
- 230000009471 action Effects 0.000 claims description 3
- 238000013523 data management Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 238000004148 unit process Methods 0.000 claims description 2
- 238000003032 molecular docking Methods 0.000 claims 1
- 230000008859 change Effects 0.000 description 6
- 230000009466 transformation Effects 0.000 description 4
- 230000003993 interaction Effects 0.000 description 3
- 230000008439 repair process Effects 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000003252 repetitive effect Effects 0.000 description 2
- 238000013518 transcription Methods 0.000 description 2
- 230000035897 transcription Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000012384 transportation and delivery 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
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
-
- 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
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/02—Methods for producing synthetic speech; Speech synthesisers
-
- 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
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/487—Arrangements for providing information services, e.g. recorded voice services or time announcements
- H04M3/493—Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
- H04M3/4936—Speech interaction details
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
- H04M3/527—Centralised call answering arrangements not requiring operator intervention
-
- 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
- G10L2015/225—Feedback of the input speech
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention relates to the technical field of distribution network scheduling, in particular to a distribution network virtual scheduling system and a method based on artificial intelligence, wherein the distribution network virtual scheduling system based on artificial intelligence comprises an artificial intelligence engine module and a virtual scheduling application module; the artificial intelligence engine module is used for training according to historical telephone recording data in the process of executing the scheduled maintenance scheduling business by a manual dispatcher to obtain a voice model for recognizing voice data; the system is used for carrying out voice recognition on real-time voice data of a user through a trained voice model, then understanding semantics through a natural language processing algorithm, and finally responding decision voice data to the user; and the virtual scheduling application module is used for integrating and interacting with the existing distribution network production service system according to the decision of the artificial intelligence engine module, constructing an intelligent application facing the distribution network scheduled maintenance scheduling, and controlling the scheduling process. The invention improves the distribution network dispatching operation efficiency.
Description
Technical Field
The invention relates to the technical field of distribution network scheduling, in particular to a distribution network virtual scheduling system and method based on artificial intelligence.
Background
With the rapid development of society and economy, the power demand is continuously increased, the pressure of a power system is increasingly heavy, and how to efficiently regulate and control limited power energy and efficiently process various equipment problems meets the requirements of social production and life is particularly urgent and important. From the point of view of power demand, on the one hand, electrical employees are faced with more and more work and increasing work intensity; on the other hand, the number of electric power personnel is gradually reduced, the work demand is increased, and the problem of manpower tension is gradually highlighted. In addition, from the future trend of power distribution network informatization construction, the number of related information systems is increased. However, a large amount of operations in the above-mentioned work belong to a single repetitive work, which is mainly reflected in that the original business process has a complicated manual processing flow, a high repetition rate, is prone to error, has low efficiency, requires a large amount of manpower and time investment, and is difficult to effectively exert the professional ability and value of the staff.
Disclosure of Invention
The invention aims to provide a distribution network virtual scheduling system and method based on artificial intelligence, and improve the distribution network scheduling operation efficiency.
In order to solve the technical problems, the technical scheme of the invention is as follows: the distribution network virtual scheduling system based on artificial intelligence comprises an artificial intelligence engine module and a virtual scheduling application module;
the artificial intelligence engine module is used for training according to historical telephone recording data in the process of executing the scheduled maintenance scheduling business by a manual dispatcher to obtain a voice model for recognizing voice data; the system is used for carrying out voice recognition on real-time voice data of a user through a trained voice model, then understanding semantics through a natural language processing algorithm, and finally responding decision voice data to the user;
and the virtual scheduling application module is used for integrating and interacting with the existing distribution network production service system according to the decision of the artificial intelligence engine module, constructing an intelligent application facing the distribution network scheduled maintenance scheduling, and controlling the scheduling process.
Preferably, the artificial intelligence engine module comprises a voice service module and an AI multi-turn dialogue engine module;
the voice service module is used for training the language model and the acoustic model to obtain a voice model for voice recognition and realizing voice recognition and voice synthesis;
and the AI multi-turn dialogue engine module is used for identifying the real-time voice of the user according to the voice service module and feeding back the real-time voice to the user.
Preferably, the artificial intelligence engine module further comprises a service scenario module, which is used for interfacing with an external system interface, synchronizing scheduling data, implementing feedback of an AI execution action, and storing the whole AI scheduling process.
Preferably, the voice service module comprises a voice recognition unit, a model training unit and a voice synthesis unit;
the voice recognition unit is used for recognizing and transcribing historical telephone recording data into text data in the process of executing the scheduled maintenance scheduling service by a manual dispatcher;
the model training unit is used for adopting the recording data and the text data as the input of the voice model training, training the language model and the acoustic model through a deep learning algorithm and combining the language model and the acoustic model to obtain a trained voice model; the real-time voice recognition system is used for recognizing real-time voice data of a user through a trained voice model to obtain a text recognition result;
and the voice synthesis unit is used for converting the decision text generated by the AI multi-turn dialogue engine module into decision voice close to the speaking of a natural person by adopting a TTS voice synthesis technology and sending the decision voice to the user.
Preferably, the AI multi-turn dialog engine module includes a voice packet receiving and recombining unit, a natural language processing unit and a service decision unit;
the voice packet receiving and recombining unit is used for butt joint with a telephone exchange system through an SIP protocol, receiving a voice signaling real-time data stream, recombining voice data and calling a voice service module through an SDK (software development kit) to obtain a text recognition result of the voice data;
the natural language processing unit is used for processing the text recognition result by adopting a natural language processing algorithm to acquire text semantics;
and the service decision unit is used for generating a decision text according to the text semantics, and is used for calling the voice service module through the SDK to convert the decision text into decision voice data and transmitting the decision voice data to the telephone switching system so as to send the decision voice data to the user.
Preferably, the virtual scheduling application module includes: the system comprises a scheduling process control module and a visual application management module;
the scheduling process control module is used for managing and commanding the work flows of operation order early issuing, operation mode changing operation, operation state changing operation, work permission reporting, reporting operation, phase checking and power transmission recovery operation in the scheduling execution service;
the visual application management module is used for visually displaying the function items of scheduling task management, task on-line monitoring, scheduling log management, intelligent voice assistant, basic data management and system setting.
A distribution network virtual scheduling method based on artificial intelligence is characterized in that: by adopting the distribution network virtual scheduling system based on artificial intelligence, the method comprises the following steps:
step 1: the artificial intelligence engine module trains according to historical telephone recording data in the process of executing the scheduled maintenance scheduling service by a manual dispatcher to obtain a voice model for recognizing voice data;
step 2: the artificial intelligence engine module carries out voice recognition on real-time voice data of the user through a trained voice model, then understands semantics through a natural language processing algorithm, carries out decision making according to the semantics and a control scheduling method of the virtual scheduling application module, and finally responds decision-making voice data to the user.
Preferably, the step 1 specifically comprises:
step 1.1: the voice recognition unit recognizes and transcribes the historical telephone recording data into text data according to the historical telephone recording data in the process of executing the scheduled maintenance scheduling service by a manual dispatcher;
step 1.2: the model training unit takes the recorded data and the text data as the input of the voice model training, trains the language model and the acoustic model through a deep learning algorithm and combines the language model and the acoustic model to obtain a trained voice model.
Preferably, the step 2 specifically comprises:
step 2.1: the voice packet receiving and recombining unit is used for being in butt joint with a telephone exchange system through an SIP protocol, receiving a voice signaling real-time data stream, recombining voice data, and calling a trained voice model through an SDK for recognition to obtain a text recognition result of the voice data;
step 2.2: the natural language processing unit processes the text recognition result by adopting a natural language processing algorithm to obtain text semantics;
step 2.3: the business decision unit generates a decision text according to the text semantics;
step 2.4: and calling a voice synthesis unit through the SDK, converting the decision text into decision voice close to the speaking of a natural person by adopting a TTS voice synthesis technology, transmitting the decision voice to a telephone exchange system, and sending the decision voice to a user.
Compared with the prior art, the invention has the following beneficial effects:
according to the method, technologies such as voice recognition, voice synthesis, multiple rounds of man-machine conversation and man-machine interaction in the field of artificial intelligence are adopted, a manual mode is replaced by virtual robot scheduling, an invoicing system, a power distribution automation system and a program control telephone system are integrated to complete a command function of an operation degree station, the problems of large traffic, scheduling telephone congestion and personnel shortage are solved practically, the effect of power grid command is effectively played, the overall operation efficiency and the safety level of distribution network maintenance services are improved, and distribution network scheduling mode digitization and intelligent transformation are promoted.
Drawings
FIG. 1 is a schematic diagram of a scheduling system according to the present invention;
FIG. 2 is an architecture diagram of the dispatch system of the present invention;
FIG. 3 is a flow chart of a scheduling method of the present invention.
1. An artificial intelligence engine module; 11. a voice service module; 111. a voice recognition unit; 112. a model training unit; 113. a speech synthesis unit; 12. an AI multi-turn dialog engine module; 121. a voice packet receiving and recombining unit; 122. a natural language processing unit; 123. a service decision unit; 13. a service scene module; 2. a virtual scheduling application module; 21. a scheduling process control module; 22. and a visual application management module.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings and specific embodiments.
Referring to fig. 1 and fig. 2, the present invention is a distribution network virtual scheduling system based on artificial intelligence, which includes an artificial intelligence engine module 1 and a virtual scheduling application module 2. The artificial intelligence engine module 1 is used for providing a virtual seat commander based on an artificial intelligence technology and realizing the functions of business decision and human-computer interaction; the virtual scheduling application module 2 is integrated and interacted with the existing distribution network production service system by using the intelligent computing processing service provided by the artificial intelligent engine module 1 to construct an intelligent application facing the distribution network scheduled maintenance scheduling.
The artificial intelligence engine module 1 is used for training according to historical telephone recording data in the process of executing the scheduled maintenance scheduling business by a manual dispatcher to obtain a voice model for recognizing voice data; the system is used for carrying out voice recognition on real-time voice data of a user through a trained voice model, then understanding semantics through a natural language processing algorithm, and finally responding decision voice data to the user;
the artificial intelligence engine module 1 includes a voice service module 11, an AI multi-turn dialog engine module 12, and a business scenario module 13.
The voice service module 11 is used for training a language model and an acoustic model to obtain a voice model for voice recognition, and is used for realizing voice recognition and voice synthesis; the voice service module 11 includes a voice recognition unit 111, a model training unit 112, and a voice synthesis unit 113;
the voice recognition unit 111 is used for recognizing and transcribing historical telephone recording data into text data in the process of executing the scheduled maintenance scheduling service by a manual dispatcher;
the model training unit 112 is configured to use the recorded data and the text data as input for speech model training, train a language model and an acoustic model through a deep learning algorithm, combine the language model and the acoustic model to obtain a trained speech model, and provide a speech recognition function in the form of Service (SDK); the real-time voice recognition system is used for recognizing real-time voice data of a user through a trained voice model to obtain a text recognition result;
the speech synthesis unit 113 is configured to convert the decision text generated by the AI multi-turn dialog engine module 12 into decision speech close to the speaking of a natural person by using a TTS speech synthesis technology, and send the decision speech to the user.
The AI multi-turn dialog engine module 12 is used for recognizing the real-time voice of the user according to the voice service module 11 and feeding back the real-time voice to the user by AI so as to complete the process from speaking of multiple turns of users to feeding back the AI; the AI multi-turn dialog engine module 12 includes a voice packet receiving and recombining unit 121, a natural language processing unit 122 and a service decision unit 123;
the voice packet receiving and recombining unit 121 is configured to interface with a telephone switching system through an SIP protocol, receive a voice signaling real-time data stream, recombine voice data, and call the voice service module 11 through an SDK to obtain a text recognition result of the voice data;
the natural language processing unit 122 is configured to process the text recognition result through natural language processing algorithms such as word segmentation, named entity recognition, slot filling, similarity matching, intention recognition, and the like, understand the semantics of the input text, and obtain text semantics;
the service decision unit 123 is configured to generate a decision text according to the service requirement and the text semantic, and is configured to call the voice service module 11 through the SDK to convert the decision text into decision voice data, transmit the decision voice data to the telephone switching system, and send the decision voice data to the user;
and the service scene module 13 is used for interfacing an external system interface, synchronizing service data, realizing the control logic of the operation ticket and the feedback of an AI execution action in the conversation process, storing the whole AI scheduling process, and presenting the conversation process and the execution process of the operation ticket through the interface.
And the virtual scheduling application module 2 is used for integrating and interacting with the existing distribution network production service system according to the decision of the artificial intelligence engine module 1, constructing an intelligent application facing the distribution network scheduled maintenance scheduling, and controlling the scheduling process. The virtual scheduling application module 2 comprises a scheduling process control module 21 and a visual application management module 22; the scheduling process control module 21 is used for managing and commanding the work flows of operation order in the scheduling execution service, operation mode change operation, operation state change operation, work permission report, report operation, phase checking and power transmission recovery operation; the visual application management module 22 is used for visually displaying functional items such as scheduling task management, task online monitoring, scheduling log management, intelligent voice assistant, basic data management, system setting and the like, so that a worker can conveniently master the working condition of a virtual seat commander, and log records are provided to trace the execution condition of each step.
In this embodiment, the specific control process of the scheduling process control module 21 is as follows:
(1) issuing an operation ticket in advance: the operation ticket is sent to a field department offline, for example, a timely communication tool and other methods are used for shooting the operation ticket and transmitting the operation ticket to a maintenance class or a rush-repair class; after an operation ticket is drawn by a transportation party and checked by a dispatching desk, the operation ticket is sent to an AI system, the AI system finishes sending the operation ticket to a power distribution operation and maintenance room and a power transformation operation and maintenance room and finishes checking the operation ticket with the power distribution operation and maintenance room and the power transformation operation and maintenance room; and after the operation is finished, sending the operation ticket to the dispatching desk.
(2) Operation mode change job: according to the planned operation time of the manual dispatcher for invoicing and maintenance, a pre-order call is dialed to an emergency maintenance class, and the emergency maintenance class receives a task and then arrives at the site; and arriving at the site to perform dispatching dialogue operation of sending and receiving orders.
(3) Operation state change job: performing order sending and order receiving scheduling dialogue operation according to the planned starting time of the work task to complete the change of the field operation mode; and if the field personnel do not dial the call to the dispatching desk after the overdue period, the intelligent dispatching commander dials the call for reminding.
(4) Work approval and work reporting: after the operation state is changed, the intelligent scheduling commander performs work permission description and details an operation safety region through man-machine conversation; and after receiving the instruction, the field personnel perform field operation, after the operation, incoming calls complete work report through man-machine conversation, the intelligent dispatching commander judges the work completion condition and state, if all verification passes, the work report is completed, and otherwise, the field personnel is reminded or the manual dispatching desk is switched.
(5) Reporting and throwing work: calling in from the field personnel to an intelligent dispatching commander for reporting; then, the intelligent scheduling commander acquires corresponding information of the application form equipment for operation according to the content of the operation ticket; the intelligent scheduling commander verifies the installation, test condition and contact application form of the new equipment reported on site; the intelligent scheduling commander checks that the follow-up operation is not executed in a suspended mode, and informs a human agent to carry out picture examination and picture loading work (the name of equipment on a report list is strictly checked by the human scheduler in advance, if the name is found to be incorrect, the operation ticket is cancelled, and an AI report program is not entered); and after finishing the image examination and image loading work, the manual seat clicks to continue AI to execute the subsequent operation order content.
(6) Nuclear phase: recognizing a phase checking instruction from an operation ticket by the AI; when a site calls in or an AI calls out, the AI permits the nuclear phase work to start; when the on-site reporting that the nuclear phase work is finished and the phase is correct, the nuclear phase work is finished; when the on-site reporting phase is abnormal and people transferring working hours are required, the AI suspends the execution and transfers to a manual seat; after the manual processing is completed, the AI is handed over again to continue to execute the rest operation/work content.
(7) And (3) power transmission operation is resumed: and issuing orders, receiving orders, task permission and work report man-machine interaction are carried out according to the work items of the work ticket.
Referring to fig. 2, starting from a technical architecture, the basic service component based on the cloud platform flying operating system of the invention includes an object storage OSS, a load balancing SLB, an elastic computing ECS, a high-availability version relational database rds (mysql), a cache service Redis and an elastic search service ElasticSearch, and the specific technical architecture is shown in fig. 2.
The intelligent dialogue engine comprises a general AI component and an industry AI engine, and the industry AI engine is formed by constructing an AI solution through the combination of the general AI component.
The general AI components include speech recognition, speech transcription, NLP natural language processing techniques, intent understanding, natural language synthesis, information extraction, knowledge maps, machine learning, deep learning, and the like.
The industry AI engine comprises field personnel incoming call voice transcription, a multi-round scheduling dialogue system, scheduling content semantic understanding, a task decision engine, repeated text generation, voice synthesis and the like.
Referring to fig. 3, the invention provides a distribution network virtual scheduling method based on artificial intelligence, which adopts a distribution network virtual scheduling system based on artificial intelligence, and the method comprises the following steps:
step 1: the artificial intelligence engine module 1 is used for training according to historical telephone recording data in the process of executing a scheduled maintenance scheduling service by a manual dispatcher to obtain a voice model for recognizing voice data; the method specifically comprises the following steps:
step 1.1: the voice recognition unit 111 recognizes and transcribes the historical telephone recording data into text data according to the execution plan maintenance scheduling service process of the manual dispatcher;
step 1.2: the model training unit 112 takes the recorded data and the text data as the input of the speech model training, trains the language model and the acoustic model through the deep learning algorithm and combines the language model and the acoustic model to obtain a trained speech model;
step 2: the artificial intelligence engine module 1 carries out voice recognition on real-time voice data of a user through a trained voice model, then understands semantics through a natural language processing algorithm, carries out decision making according to the semantics and a control scheduling method of the virtual scheduling application module 2, and finally responds decision-making voice data to the user; the method specifically comprises the following steps:
step 2.1: the voice packet receiving and recombining unit 121 is configured to interface with a telephone switching system through an SIP protocol, receive a voice signaling real-time data stream, recombine voice data, and call a trained voice model through an SDK for recognition, so as to obtain a text recognition result of the voice data;
step 2.2: the natural language processing unit 122 processes the text recognition result by using a natural language processing algorithm to obtain text semantics;
step 2.3: the service decision unit 123 generates a decision text according to the text semantics;
step 2.4: the speech synthesis unit 113 is invoked by SDK to convert the decision text into decision speech that approximates the speech of a natural person using TTS speech synthesis techniques and transmit it to the telephone switching system for delivery to the user.
The invention constructs an artificial intelligence engine module for upgrading on the basis of integrating business systems such as a program control telephone system, a power distribution automation system, an invoicing system and the like, constructs a scheduling and emergency repair business intelligent virtual seat commander through technologies such as voice recognition, semantic intention understanding, natural language synthesis, information extraction, machine learning, deep learning and the like, assists and replaces the work of artificial repetitive telephone seats, and converts low-efficiency working modes such as manual dispatching order receiving, emergency repair processing result feedback and the like of an emergency repair operation and maintenance team; on the basis, the function of dispatching and commanding the service of the distribution network is completed through a dispatching service process control module (identity confirmation, operation mode change, state operation, work and report, phase verification and report and power transmission recovery), and the intelligent capability of the distribution network command is improved through the planned maintenance and dispatching service of the distribution network of branch lines and main lines. The invention can be applied to the planned dispatching operation of distribution network branch lines and distribution network power transmission and transformation equipment, and realizes that machine intelligence replaces a large amount of unnecessary manual repeated labor, thereby effectively playing the role of power grid command and improving the overall operation efficiency of distribution network maintenance service.
The parts not involved in the present invention are the same as or implemented using the prior art.
The foregoing is a more detailed description of the present invention that is presented in conjunction with specific embodiments, and the practice of the invention is not to be considered limited to those descriptions. For those skilled in the art to which the invention pertains, several simple deductions or substitutions can be made without departing from the spirit of the invention, and all shall be considered as belonging to the protection scope of the invention.
Claims (9)
1. Distribution network virtual dispatching system based on artificial intelligence, its characterized in that: the system comprises an artificial intelligence engine module and a virtual scheduling application module;
the artificial intelligence engine module is used for training according to historical telephone recording data in the process of executing the scheduled maintenance scheduling business by a manual dispatcher to obtain a voice model for recognizing voice data; the system is used for carrying out voice recognition on real-time voice data of a user through a trained voice model, then understanding semantics through a natural language processing algorithm, and finally responding decision voice data to the user;
and the virtual scheduling application module is used for integrating and interacting with the existing distribution network production service system according to the decision of the artificial intelligence engine module, constructing an intelligent application facing the distribution network scheduled maintenance scheduling, and controlling the scheduling process.
2. The artificial intelligence based distribution network virtual scheduling system of claim 1, wherein: the artificial intelligence engine module comprises a voice service module and an AI multi-turn dialogue engine module;
the voice service module is used for training the language model and the acoustic model to obtain a voice model for voice recognition and realizing voice recognition and voice synthesis;
and the AI multi-turn dialogue engine module is used for identifying the real-time voice of the user according to the voice service module and feeding back the real-time voice to the user.
3. The artificial intelligence based distribution network virtual scheduling system of claim 2, wherein: the artificial intelligence engine module also comprises a service scene module which is used for docking an external system interface, synchronously scheduling data, realizing the feedback of AI execution actions and storing the whole AI scheduling process.
4. The artificial intelligence based distribution network virtual scheduling system of claim 2, wherein: the voice service module comprises a voice recognition unit, a model training unit and a voice synthesis unit;
the voice recognition unit is used for recognizing and transcribing historical telephone recording data into text data in the process of executing the scheduled maintenance scheduling service by a manual dispatcher;
the model training unit is used for adopting the recording data and the text data as the input of the voice model training, training the language model and the acoustic model through a deep learning algorithm and combining the language model and the acoustic model to obtain a trained voice model; the real-time voice recognition system is used for recognizing real-time voice data of a user through a trained voice model to obtain a text recognition result;
and the voice synthesis unit is used for converting the decision text generated by the AI multi-turn dialogue engine module into decision voice close to the speaking of a natural person by adopting a TTS voice synthesis technology and sending the decision voice to the user.
5. The artificial intelligence based distribution network virtual scheduling system of claim 2, wherein: the AI multi-turn dialogue engine module comprises a voice packet receiving and recombining unit, a natural language processing unit and a business decision unit;
the voice packet receiving and recombining unit is used for butt joint with a telephone exchange system through an SIP protocol, receiving a voice signaling real-time data stream, recombining voice data and calling a voice service module through an SDK (software development kit) to obtain a text recognition result of the voice data;
the natural language processing unit is used for processing the text recognition result by adopting a natural language processing algorithm to acquire text semantics;
and the service decision unit is used for generating a decision text according to the text semantics, and is used for calling the voice service module through the SDK to convert the decision text into decision voice data and transmitting the decision voice data to the telephone switching system so as to send the decision voice data to the user.
6. The artificial intelligence based distribution network virtual scheduling system of claim 1, wherein: a virtual scheduling application module comprising: the system comprises a scheduling process control module and a visual application management module;
the scheduling process control module is used for managing and commanding the work flows of operation order early issuing, operation mode changing operation, operation state changing operation, work permission reporting, reporting operation, phase checking and power transmission recovery operation in the scheduling execution service;
the visual application management module is used for visually displaying the function items of scheduling task management, task on-line monitoring, scheduling log management, intelligent voice assistant, basic data management and system setting.
7. A distribution network virtual scheduling method based on artificial intelligence is characterized in that: the artificial intelligence based distribution network virtual scheduling system of any one of claims 1-6 is adopted, and the method comprises the following steps:
step 1: the artificial intelligence engine module trains according to historical telephone recording data in the process of executing the scheduled maintenance scheduling service by a manual dispatcher to obtain a voice model for recognizing voice data;
step 2: the artificial intelligence engine module carries out voice recognition on real-time voice data of the user through a trained voice model, then understands semantics through a natural language processing algorithm, carries out decision making according to the semantics and a control scheduling method of the virtual scheduling application module, and finally responds decision-making voice data to the user.
8. The artificial intelligence based distribution network virtual scheduling method according to claim 7, wherein: the step 1 specifically comprises the following steps:
step 1.1: the voice recognition unit recognizes and transcribes the historical telephone recording data into text data according to the historical telephone recording data in the process of executing the scheduled maintenance scheduling service by a manual dispatcher;
step 1.2: the model training unit takes the recorded data and the text data as the input of the voice model training, trains the language model and the acoustic model through a deep learning algorithm and combines the language model and the acoustic model to obtain a trained voice model.
9. The distribution network virtual scheduling method based on artificial intelligence of claim 8, wherein: the step 2 specifically comprises the following steps:
step 2.1: the voice packet receiving and recombining unit is used for being in butt joint with a telephone exchange system through an SIP protocol, receiving a voice signaling real-time data stream, recombining voice data, and calling a trained voice model through an SDK for recognition to obtain a text recognition result of the voice data;
step 2.2: the natural language processing unit processes the text recognition result by adopting a natural language processing algorithm to obtain text semantics;
step 2.3: the business decision unit generates a decision text according to the text semantics;
step 2.4: and calling a voice synthesis unit through the SDK, converting the decision text into decision voice close to the speaking of a natural person by adopting a TTS voice synthesis technology, transmitting the decision voice to a telephone exchange system, and sending the decision voice to a user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111432478.8A CN114171021A (en) | 2021-11-29 | 2021-11-29 | Distribution network virtual scheduling system and method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111432478.8A CN114171021A (en) | 2021-11-29 | 2021-11-29 | Distribution network virtual scheduling system and method based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114171021A true CN114171021A (en) | 2022-03-11 |
Family
ID=80481467
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111432478.8A Pending CN114171021A (en) | 2021-11-29 | 2021-11-29 | Distribution network virtual scheduling system and method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114171021A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114971202A (en) * | 2022-04-29 | 2022-08-30 | 国网浙江省电力有限公司杭州市临安区供电公司 | Intelligent distribution network scheduling method and system |
| CN114974247A (en) * | 2022-06-22 | 2022-08-30 | 国网福建省电力有限公司 | Voice instruction virtual robot applied to power dispatching |
| CN115101067A (en) * | 2022-06-16 | 2022-09-23 | 陈明华 | Smart power grids voice system based on block chain technique |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| KR20190116041A (en) * | 2018-03-23 | 2019-10-14 | 주식회사 포지큐브 | System and method for providing interactive customer response service using virtual host character based on artificial intelligence |
| CN111416914A (en) * | 2020-01-07 | 2020-07-14 | 国网浙江省电力有限公司金华供电公司 | Artificial intelligence voice interaction service system |
| 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 |
| CN113194203A (en) * | 2020-09-30 | 2021-07-30 | 杭州方得智能科技有限公司 | Communication system, answering and dialing method and communication system for hearing-impaired people |
| 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 |
| CN113361970A (en) * | 2021-07-07 | 2021-09-07 | 国网甘肃省电力公司兰州供电公司 | Virtual dispatcher system based on intelligent power dispatching engine and dispatching method |
-
2021
- 2021-11-29 CN CN202111432478.8A patent/CN114171021A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20190116041A (en) * | 2018-03-23 | 2019-10-14 | 주식회사 포지큐브 | System and method for providing interactive customer response service using virtual host character based on artificial intelligence |
| 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 |
| CN111416914A (en) * | 2020-01-07 | 2020-07-14 | 国网浙江省电力有限公司金华供电公司 | Artificial intelligence voice interaction service system |
| CN113194203A (en) * | 2020-09-30 | 2021-07-30 | 杭州方得智能科技有限公司 | Communication system, answering and dialing method and communication system for hearing-impaired people |
| 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 |
| CN113361970A (en) * | 2021-07-07 | 2021-09-07 | 国网甘肃省电力公司兰州供电公司 | Virtual dispatcher system based on intelligent power dispatching engine and dispatching method |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114971202A (en) * | 2022-04-29 | 2022-08-30 | 国网浙江省电力有限公司杭州市临安区供电公司 | Intelligent distribution network scheduling method and system |
| 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 |
| CN114974247A (en) * | 2022-06-22 | 2022-08-30 | 国网福建省电力有限公司 | Voice instruction virtual robot applied to power dispatching |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114171021A (en) | Distribution network virtual scheduling system and method based on artificial intelligence | |
| CN109345072A (en) | Dispatching method for distribution branch line scheduling scenario | |
| CN209374053U (en) | Dispatching intelligent monitor and check system | |
| CN112599124A (en) | Voice scheduling method and system for power grid scheduling | |
| CN113258669B (en) | Networked intelligent scheduling method and terminal based on distribution network maintenance | |
| WO2019137206A1 (en) | Oil and gas pipeline scada system | |
| CN113361970B (en) | Virtual dispatcher system and dispatching method based on power intelligent dispatching engine | |
| CN109063090A (en) | Automate operation management system | |
| CN109753654A (en) | A method of it realizing that workflow quickly generates based on special-purpose software and algorithm and distributes | |
| CN104899245A (en) | Scheduled flight dynamic intelligence real-time broadcasting method | |
| CN109190008A (en) | Automate operation management method | |
| CN108805417A (en) | A kind of implementation method and power scheduling instruction system of power scheduling instruction | |
| CN113140219A (en) | Regulation and control instruction generation method and device, electronic equipment and storage medium | |
| CN109120513A (en) | Full media system and implementation method based on intelligent robot response | |
| CN111680916A (en) | Electric power distribution virtual dispatcher device and method | |
| CN102868226A (en) | Implementation method for electronic command distribution between electric power dispatching and monitoring | |
| CN110210784A (en) | A kind of people's vehicle scheduling system | |
| CN106022648A (en) | Electric power scheduling report form coordination and generation method | |
| CN111627447A (en) | Cloud sharing intelligent voice Ai speaking system | |
| CN111524031A (en) | Implementation method and system for intelligently generating operation steps based on analysis operation tasks | |
| CN111145742A (en) | Plan command execution method and system based on voice instruction | |
| CN115347674A (en) | Distribution network virtual production command system and method | |
| CN110049047A (en) | A kind of power communication maintenance is self-service to permit to handle system | |
| CN114782055A (en) | Portable all-round operation panel of electric power marketing | |
| CN113794754A (en) | Electronic operation ticket control system and method based on mobile application |
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 |