CN111832977A - Maintenance application automatic ticketing method based on natural language parsing - Google Patents
Maintenance application automatic ticketing method based on natural language parsing Download PDFInfo
- Publication number
- CN111832977A CN111832977A CN202010750791.5A CN202010750791A CN111832977A CN 111832977 A CN111832977 A CN 111832977A CN 202010750791 A CN202010750791 A CN 202010750791A CN 111832977 A CN111832977 A CN 111832977A
- Authority
- CN
- China
- Prior art keywords
- maintenance
- overhaul
- regulation
- natural language
- application
- 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
- 238000012423 maintenance Methods 0.000 title claims abstract description 90
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000004458 analytical method Methods 0.000 claims abstract description 32
- 238000012545 processing Methods 0.000 claims abstract description 18
- 238000004806 packaging method and process Methods 0.000 claims abstract description 12
- 238000003058 natural language processing Methods 0.000 claims abstract description 10
- 238000005516 engineering process Methods 0.000 claims abstract description 9
- 238000004141 dimensional analysis Methods 0.000 claims abstract description 6
- 238000001914 filtration Methods 0.000 claims abstract description 6
- 238000003860 storage Methods 0.000 claims abstract description 6
- 238000004140 cleaning Methods 0.000 claims abstract description 4
- 230000011218 segmentation Effects 0.000 claims description 22
- 238000010586 diagram Methods 0.000 claims description 4
- 238000009826 distribution Methods 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 3
- 238000012856 packing Methods 0.000 claims 1
- 230000005540 biological transmission Effects 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000009191 jumping Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003252 repetitive effect Effects 0.000 description 2
- 238000009412 basement excavation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003990 capacitor Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- General Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Educational Administration (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Development Economics (AREA)
- Public Health (AREA)
- Game Theory and Decision Science (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a maintenance application automatic ticketing method based on natural language parsing, which comprises the following steps: step 100, reading a regulation and control maintenance work history record as a sample, and performing cleaning and filtering operation on the sample data to complete correlation and correspondence of a maintenance application record and a maintenance operation record; 200, carrying out multi-dimensional analysis on the sample data by utilizing a natural language processing technology to form a control field corpus and simplify the analysis processing process of subsequent overhaul applications; step 300, learning relevant knowledge of the power system, classifying and completing structured storage and input, and establishing a regulation and control language feature point model set; step 400, carrying out quick analysis processing on the overhaul application based on the regulation and control language feature point model set so as to realize the packaging and grouping of the overhaul application; and 500, checking the integrity of the safety measures of the maintenance work, deducing an operation scheme and an operation command, and automatically generating an operation order. The invention can automatically generate the operation ticket according to the overhaul application.
Description
Technical Field
The invention relates to the technical field of electric power overhaul, in particular to an overhaul application automatic ticketing method based on natural language parsing.
Background
With the scale enlargement of a power grid and the rapid development of new energy, the operation characteristics are increasingly complex, the centralized monitoring unattended mode of the transformer substation is comprehensively implemented by the integrated regulation and control, in the actual dispatching operation, operators need to manually associate, analyze and process a large amount of data and knowledge rules, particularly under the integrated regulation and control mode of the large operation, the operators need to complete the manual work of operation tasks and operation schemes by relying on manual experience for comprehensive power failure application, operation modes, operation rules and the like, the repetitive work is more, the emphasis is difficult to timely and rapidly extract, the effective decision support cannot be obtained, and the intelligent work means of the operation schemes is lacked.
Therefore, the technical field of artificial intelligence is combined with the knowledge characteristics of the power grid, and the automatic, programmed and intelligent schemes of excavation, regulation and control operation are researched, so that the planning efficiency is improved, the power failure risk is reduced, and the negative influence of power failure maintenance on the operation of the power grid is minimized.
Disclosure of Invention
The invention aims to provide an automatic ticket forming method for overhaul application based on natural language analysis, which aims to solve the technical problem in the prior art.
In order to solve the technical problems, the invention specifically provides the following technical scheme:
an automatic ticket-forming method for overhaul application based on natural language analysis comprises the following steps:
reading a regulation and control maintenance work history record as a sample, and performing cleaning and filtering operation on the sample data to complete correlation correspondence between a maintenance application record and a maintenance operation record;
performing multi-dimensional analysis on the sample data by using a natural language processing technology to form a regulation and control field corpus;
learning relevant knowledge of the power system, classifying the sample data, completing structured storage and input, and establishing a regulation and control language feature point model set;
carrying out rapid analysis processing on the overhaul application based on the regulation and control language feature point model set, and packaging and grouping the overhaul application records;
checking the integrity of the safety measures of the maintenance work, deducing an operation scheme and an operation command, and automatically generating an operation order.
Optionally, the work history record includes: the power grid power failure maintenance system comprises power grid historical power failure maintenance application data, maintenance application associated scheduling operation tickets and operation commands, a power grid equipment model, a transformer substation main wiring diagram and a normal operation mode.
Optionally, the performing multidimensional analysis on the sample data by using a natural language processing technology to form a control field corpus includes:
the steps of simplifying the analysis processing process of the subsequent overhaul application include word segmentation recognition, named entity recognition, lexical analysis of part of speech tagging, syntactic analysis of dependency relationship analysis, semantic analysis of word sense disambiguation, intention recognition and semantic representation, and pragmatic analysis of generating an operation command by combining equipment characteristic points and overhaul work characteristic points.
Optionally, the checking the integrity of the security measure specifically includes:
checking safety measure items, wherein the safety measure items comprise whether power failure of equipment is needed or not, whether stop protection is needed or not, whether reclosing is needed or not, whether a side band is needed or not for a switch, whether a nuclear phase is needed or not, whether phasing is needed or not, whether protection is needed or not, whether a measurement vector is needed or not, and whether power supply of other equipment is influenced or not.
Optionally, in the step, a natural language processing technology is used to perform multidimensional analysis on the sample data, so as to form a control field corpus, and simplify an analysis processing process of a subsequent overhaul application, including:
analyzing historical maintenance application records one by one, analyzing maintenance contents and power failure ranges in the power failure maintenance application, and extracting structural information of equipment types, voltage levels, stations, equipment numbers and names and protection models;
adopting a ternary grammar model based on a Markov model, segmenting the residual content after extracting the structured information through a standard corpus, and finding a segmentation method corresponding to the maximum probability by calculating the joint distribution probability corresponding to various segmentation methods, namely finding the optimal segmentation;
and constructing a regulation and control field corpus on the basis of the standard corpus according to the optimal word segmentation obtained by processing the sample through the natural language, and extracting characteristic points of electric power overhaul work.
Optionally, the step of learning the relevant knowledge of the power system, classifying and completing structured storage entry, and establishing a regulation and control language feature point model set includes:
acquiring a power grid equipment basic model, learning an equipment wiring mode, an operation mode and account parameter information;
various regulations of operation under various wiring modes and operation modes of a power grid are learned and dispatched, the regulations are structurally split and then are input into a rule base, and the regular rule base is regularly updated and dispatched;
various regulations of protection related operations in the learning protection rules, protection configuration of lines and buses and the like are structurally split and recorded into a rule base;
and forming a regulation and control language feature point model set according to the relevant knowledge of the power system and the regulation and control field corpus and according to the voltage grade, the equipment type, the wiring mode and the maintenance work type.
Optionally, the step of performing fast parsing processing of the overhaul application based on the regulation and control language feature point model set to realize packaging and grouping of the overhaul application includes:
analyzing the power failure range and the maintenance content in the maintenance application based on the regulation and control language feature point model set;
and summarizing all the maintenance request sheets, and automatically packaging and grouping the maintenance request sheets according to the maintenance purpose and the maintenance time.
Optionally, the checking integrity of the safety measures of the maintenance work, deriving the operation scheme and the operation command, and automatically generating the operation ticket includes:
automatically analyzing the required safety measures according to the characteristic points of the overhaul work content;
and generating a corresponding operation command according to the requirements of the analyzed safety measures and by combining the wiring mode, the operation mode, the dispatching right attribution and the voltage grade of the equipment.
Optionally, the various regulations of the learning and dispatching rules for various wiring modes and operation modes of the power grid include a general rule, a specific wiring mode rule, and a specific device rule.
Compared with the prior art, the invention has the following beneficial effects:
according to the method, through deep research on power grid regulation operation, by obtaining a maintenance application ticket, performing natural language processing in combination with an electric power regulation context, automatically analyzing and extracting effective contents in maintenance application, matching according to a maintenance work rule knowledge base, analyzing a real power failure range and work steps, realizing grouping and packaging of maintenance application, and combining an operation rule knowledge base, applying conventional maintenance, and realizing automatic generation of an operation ticket according to the maintenance application.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It should be apparent that the drawings in the following description are merely exemplary, and that other embodiments can be derived from the drawings provided by those of ordinary skill in the art without inventive effort.
FIG. 1 is a flow chart of a method according to an embodiment of the present invention;
fig. 2 is a flow chart of an embodiment of 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.
As shown in fig. 1, the invention provides an automatic ticketing method for an overhaul application based on natural language parsing, which comprises the following steps:
and step 100, reading the regulation and control maintenance work history record as a sample, and performing cleaning and filtering operation on the sample data to complete correlation and correspondence of the maintenance application record and the maintenance operation record.
The sample data mainly comprises historical power grid power failure overhaul application data, overhaul application associated scheduling operation tickets and operation commands, a power grid equipment model, a transformer substation main wiring diagram and a normal operation mode.
200, carrying out multi-dimensional analysis on the sample data by utilizing a natural language processing technology to form a control field corpus and simplify the analysis processing process of subsequent overhaul applications; the method mainly comprises word segmentation recognition, named entity recognition, lexical analysis of part of speech tagging, grammar analysis of dependency relationship analysis, semantic analysis of word meaning disambiguation, intention recognition and semantic representation, and pragmatic analysis for generating an operation command by combining equipment characteristic points and overhaul work characteristic points.
Step 300, learning relevant knowledge of the power system, classifying and completing structured storage and input, and establishing a regulation and control language feature point model set;
and 400, carrying out quick analysis processing on the overhaul application based on the regulation and control language feature point model set so as to realize the packaging and grouping of the overhaul application.
And 500, checking the integrity of safety measures of maintenance work, deducing an operation scheme and an operation command, and automatically generating an operation order, wherein the safety measure item mainly comprises whether the power failure of the equipment needs power failure, whether stop protection is needed, whether stop and reclosure are needed, whether a switch needs a side band, whether a nuclear phase is needed, whether phasing is needed, whether protection is needed, whether a measurement vector is needed, and whether power supply of other equipment is influenced.
The implementation method of the step 200 comprises the following steps:
analyzing historical maintenance application records one by one, analyzing maintenance contents and power failure ranges in the power failure maintenance application, and extracting structural information of equipment types, voltage levels, stations, equipment numbers and names and protection models.
And (3) segmenting the residual content after the extraction of the structured information by adopting a ternary grammar model based on a Markov model through a standard corpus, and finding a segmentation method corresponding to the maximum probability by calculating the joint distribution probability corresponding to various segmentation methods, namely finding the optimal segmentation.
And constructing a regulation and control field corpus on the basis of the standard corpus according to the optimal word segmentation obtained by processing the sample through the natural language, and extracting characteristic points of electric power overhaul work.
The implementation method of step 300 includes:
acquiring a power grid equipment basic model, learning an equipment wiring mode, an operation mode and account parameter information;
the method comprises the steps of learning various regulations of operation under various wiring modes and operation modes of a power grid, performing structured splitting, inputting a rule base, and regularly updating a regular rule base for scheduling.
Various regulations of protection related operations in the learning protection rules, protection configuration of lines and buses and the like are structurally split and recorded into a rule base.
And forming a regulation and control language feature point model set according to the relevant knowledge of the power system and the regulation and control field corpus and according to the voltage grade, the equipment type, the wiring mode and the maintenance work type.
The implementation method of step 400 includes:
and analyzing the power failure range and the maintenance content in the maintenance application based on the regulation and control language feature point model set.
And summarizing all the maintenance request sheets, and automatically packaging and grouping the maintenance request sheets according to the maintenance purpose and the maintenance time.
The implementation method of step 500 includes:
and automatically analyzing the required safety measures according to the characteristic points of the overhaul work content.
And generating a corresponding operation command according to the requirements of the analyzed safety measures and by combining the wiring mode, the operation mode, the dispatching right attribution and the voltage grade of the equipment.
As a preferred scheme of the invention, various regulations of various wiring modes and operation modes of the power grid in the learning and dispatching rules comprise general rules, specific wiring mode rules and specific equipment rules.
If the production control area is not directly accessed for iterative improvement, other historical data which are not used for analyzing and constructing an expert model can be accessed as a test sample for iterative improvement.
The invention is based on natural language processing technology in the field of artificial intelligence, combines the knowledge characteristics of the power grid, deeply studies and regulates maintenance business process of maintenance work and scheduling operation scheme compilation rules, intelligently judges relevant works such as mode arrangement, protection coordination and the like in various maintenance work processes according to maintenance purposes based on the wiring mode and the operation mode of power grid topology, ensures the accuracy of generating operation schemes and the reasonability of arrangement of working measures, identifies the power failure range and the working content of maintenance application, realizes the grouping and packaging of the maintenance application, realizes the intelligent combination of a plurality of maintenance works, shortens the power failure window period, determines the operation mode according to the power grid topology, automatically generates operation schemes, checks the integrity of operation safety measures, improves the planning compilation efficiency, and simultaneously ensures the accuracy of operation and the reasonability of arrangement of the working measures, reducing the repetitive manual work.
As shown in fig. 2, a specific embodiment of an automatic overhaul application ticketing method based on natural language parsing according to the present invention is provided as follows:
1) the method comprises the steps of butt-jointing historical power failure maintenance application data of a power grid for at least one year, maintenance application associated scheduling operation tickets and operation commands, a power grid equipment model, a transformer substation main wiring diagram and a normal operation mode, carrying out preliminary processing analysis on each maintenance application record, and filtering unexecuted or no actual operation ticket associated record;
2) analyzing historical maintenance application records one by one, analyzing maintenance contents and power failure ranges in the power failure maintenance application, extracting structural information such as equipment types, voltage levels, stations, equipment numbers and names, protection models and the like, and not carrying out segmentation and word segmentation on the structural information; segmenting the rest content after extracting the structured information by a standard corpus, tracing the segmentation forwards by using a ternary grammar, and finding a segmentation method corresponding to the maximum probability by calculating the joint distribution probability corresponding to various segmentation methods, namely finding the optimal segmentation;
3) for example, "disconnect 110kV jump station and jump the line 121 switch, pull open 110kV jump station and jump the line 1014 disconnecting link of line side, pull open 110kV jump station and jump the line 1034 disconnecting link of line side of two;
4) the computer judges that the knife gate number needs to be cut and divides the knife gate number into 1014 and 1034 numbers;
5) finally, the equipment is positioned into two equipment, namely 'jumping stand station/110 kV.1014 disconnecting link' and 'jumping stand station/110 kV.1034 disconnecting link';
6) constructing a regulation and control field corpus on the basis of a standard corpus according to the optimal word segmentation obtained by processing a sample through a natural language, and extracting electric power overhaul working characteristic points;
7) acquiring information such as a power grid equipment basic model, a wiring mode, an operation mode and a machine account parameter of learning equipment;
8) the method comprises the steps of learning various wiring modes of a power grid and various regulations of operation under the operation mode of the power grid including general rules, specific wiring mode rules and specific equipment rules, performing structural splitting and inputting into a rule base, wherein the regular rule base needs to be updated regularly due to the adjustment of the operation mode and the operation specification of the power grid;
9) various regulations for protecting related operations in the learning protection rules, protection configurations of lines and buses, and the like, for example: provision of protection operation for each voltage class; the operation requirements are included in the modes of side bands, single power supplies and the like; the operation modes of the bus, the main transformer and the neutral point are as follows; protection configuration of lines and buses and the like, decomposing protection rules, and structurally splitting the protection rules according to voltage levels and operation modes to form a rule base of the protection rules;
10) forming a regulation and control language feature point model set according to the relevant knowledge of the power system and the regulation and control field corpus, voltage grade, equipment type, wiring mode, maintenance work category and the like;
11) the basic characteristic points of the power system are obtained through extraction, such as: voltage classes including 1000kV, 750kV, 500kV, 330kV, 220kV, 110kV, 66kV and 35 kV; the connection modes comprise 3/2 connection, double bus tape bypass, double buses, single bus tape bypass, single bus, inner bridge connection, outer bridge connection and the like;
12) and refining to obtain the relevant characteristic points of the equipment, such as: the equipment types comprise a circuit breaker, an isolating switch, a grounding disconnecting link, a main transformer, a bus, a line, a voltage transformer, a station transformer, a capacitor, a reactor and the like; a device state comprising: running, hot standby, cold standby and overhauling; equipment operation including various item-by-item orders and comprehensive orders; equipment parameters, manufacturer, model, impedance value, etc.;
13) analyzing maintenance equipment and safety measures to obtain maintenance purposes and requirements; collecting all maintenance request forms, and automatically packaging and grouping the maintenance request forms according to maintenance purposes and maintenance time;
14) for example, the method is tested by adopting a historical overhaul record and an operation scheme in non-sample data, and analysis processing is carried out on two power failure overhaul request sheets aiming at overhaul application '201 x/02/02 jump station 110kV jump connection 121 switch and line quit operation', '201 x/02/02 jump station 110kV jump connection 1014 disconnecting link overhaul';
15) firstly, retrieving maintenance applications according to maintenance time, packaging and grouping the maintenance applications to perform preliminary filtering, then completing maintenance application merging, and according to the topological relation that maintenance equipment has mutual influence on power cut and transmission except that the time is the same or similar, the maintenance equipment in the embodiment comprises the same equipment, and the maintenance equipment can be naturally merged;
16) obtaining relevant equipment in an overall overhaul task, comprising: jump connecting wires, a jump station/110 kV.121 switch and a jump station/110 kV.1014 disconnecting link;
17) extracting information related to the plant station and the equipment, comprising the following steps: the station name of the jumping-up station; the related devices all belong to the same scheduling administration unit; the line administration unit: high-voltage power transmission;
18) automatically analyzing the required safety measures according to the characteristic points of the overhaul work content;
19) generating a corresponding operation command according to the requirements of the analyzed safety measures by combining a wiring mode, an operation mode, the dispatching right attribution of equipment, the voltage grade and the like;
20) through observation and comparison, the information generated automatically is completely consistent with the information in the actual operation ticket system except the information which needs to be temporarily filled according to the actual situation, such as a high-voltage power transmission reporter, and the information meets the requirement of the generation of the operation scheme.
The above embodiments are only exemplary embodiments of the present application, and are not intended to limit the present application, and the protection scope of the present application is defined by the claims. Various modifications and equivalents may be made by those skilled in the art within the spirit and scope of the present application and such modifications and equivalents should also be considered to be within the scope of the present application.
Claims (9)
1. An automatic ticket-forming method for overhaul application based on natural language analysis is characterized in that: the method comprises the following steps:
reading a regulation and control maintenance work history record as a sample, and performing cleaning and filtering operation on the sample data to complete correlation correspondence between a maintenance application record and a maintenance operation record;
performing multi-dimensional analysis on the sample data by using a natural language processing technology to form a regulation and control field corpus;
learning relevant knowledge of the power system, classifying the sample data, completing structured storage and input, and establishing a regulation and control language feature point model set;
carrying out rapid analysis processing on the overhaul application based on the regulation and control language feature point model set, and packaging and grouping the overhaul application records;
checking the integrity of the safety measures of the maintenance work, deducing an operation scheme and an operation command, and automatically generating an operation order.
2. The automatic ticketing method for overhaul applications based on natural language parsing as claimed in claim 1, wherein: the work history record includes: the power grid power failure maintenance system comprises power grid historical power failure maintenance application data, maintenance application associated scheduling operation tickets and operation commands, a power grid equipment model, a transformer substation main wiring diagram and a normal operation mode.
3. The automatic ticketing method for overhaul applications based on natural language parsing as claimed in claim 2, wherein: performing multi-dimensional analysis on the sample data by using a natural language processing technology to form a regulation and control field corpus comprises:
the steps of simplifying the analysis processing process of the subsequent overhaul application include word segmentation recognition, named entity recognition, lexical analysis of part of speech tagging, syntactic analysis of dependency relationship analysis, semantic analysis of word sense disambiguation, intention recognition and semantic representation, and pragmatic analysis of generating an operation command by combining equipment characteristic points and overhaul work characteristic points.
4. The automatic ticketing method for overhaul applications based on natural language parsing as claimed in claim 3, wherein: the checking of the integrity of the safety measures specifically comprises:
checking safety measure items, wherein the safety measure items comprise whether power failure of equipment is needed or not, whether stop protection is needed or not, whether reclosing is needed or not, whether a side band is needed or not for a switch, whether a nuclear phase is needed or not, whether phasing is needed or not, whether protection is needed or not, whether a measurement vector is needed or not, and whether power supply of other equipment is influenced or not.
5. The automatic ticketing method for overhaul applications based on natural language parsing as claimed in claim 1, wherein: the step utilizes natural language processing technology to carry out multi-dimensional analysis on the sample data, forms a control field corpus, and simplifies the analysis processing process of subsequent overhaul application, and comprises the following steps:
analyzing historical maintenance application records one by one, analyzing maintenance contents and power failure ranges in the power failure maintenance application, and extracting structural information of equipment types, voltage levels, stations, equipment numbers and names and protection models;
adopting a ternary grammar model based on a Markov model, segmenting the residual content after extracting the structured information through a standard corpus, and finding a segmentation method corresponding to the maximum probability by calculating the joint distribution probability corresponding to various segmentation methods, namely finding the optimal segmentation;
and constructing a regulation and control field corpus on the basis of the standard corpus according to the optimal word segmentation obtained by processing the sample through the natural language, and extracting characteristic points of electric power overhaul work.
6. The automatic ticketing method for overhaul applications based on natural language parsing as claimed in claim 1, wherein: the steps of learning relevant knowledge of the power system, classifying and completing structured storage and entry, and establishing a regulation and control language feature point model set comprise:
acquiring a power grid equipment basic model, learning an equipment wiring mode, an operation mode and account parameter information;
various regulations of operation under various wiring modes and operation modes of a power grid are learned and dispatched, the regulations are structurally split and then are input into a rule base, and the regular rule base is regularly updated and dispatched;
various regulations of protection related operations in the learning protection rules, protection configuration of lines and buses and the like are structurally split and recorded into a rule base;
and forming a regulation and control language feature point model set according to the relevant knowledge of the power system and the regulation and control field corpus and according to the voltage grade, the equipment type, the wiring mode and the maintenance work type.
7. The method for automatically forming the ticket of the overhaul application based on the natural language parsing of claim 1, wherein the step of performing the fast parsing processing of the overhaul application based on the regulation and control language feature point model set to realize the packing and grouping of the overhaul application comprises the following steps:
analyzing the power failure range and the maintenance content in the maintenance application based on the regulation and control language feature point model set;
and summarizing all the maintenance request sheets, and automatically packaging and grouping the maintenance request sheets according to the maintenance purpose and the maintenance time.
8. The method for automatically forming the ticket of the overhaul application based on natural language parsing as claimed in claim 1, wherein the steps of checking the integrity of the safety measures of the overhaul work, deriving the operation scheme and the operation command, and automatically generating the operation ticket comprise:
automatically analyzing the required safety measures according to the characteristic points of the overhaul work content;
and generating a corresponding operation command according to the requirements of the analyzed safety measures and by combining the wiring mode, the operation mode, the dispatching right attribution and the voltage grade of the equipment.
9. The automatic ticket-making method for overhaul application based on natural language parsing as claimed in claim 6, wherein the various regulations of various wiring modes and operation modes of the power grid in the learning and dispatching regulations comprise general rules, specific wiring mode rules and specific equipment rules.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010750791.5A CN111832977A (en) | 2020-07-30 | 2020-07-30 | Maintenance application automatic ticketing method based on natural language parsing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010750791.5A CN111832977A (en) | 2020-07-30 | 2020-07-30 | Maintenance application automatic ticketing method based on natural language parsing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111832977A true CN111832977A (en) | 2020-10-27 |
Family
ID=72920451
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010750791.5A Pending CN111832977A (en) | 2020-07-30 | 2020-07-30 | Maintenance application automatic ticketing method based on natural language parsing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111832977A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112528627A (en) * | 2020-12-16 | 2021-03-19 | 中国南方电网有限责任公司 | Maintenance suggestion identification method based on natural language processing |
| CN112885352A (en) * | 2021-01-26 | 2021-06-01 | 广东电网有限责任公司 | Corpus construction method and device, computer equipment and storage medium |
| CN113033195A (en) * | 2021-03-15 | 2021-06-25 | 国网江苏省电力有限公司南通供电分公司 | Method for generating scheduling operation sequence by intelligently analyzing overhaul application ticket |
| CN113792548A (en) * | 2021-08-30 | 2021-12-14 | 国网天津市电力公司 | Automatic cover generation system and method based on text word segmentation and statistical verification |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103679350A (en) * | 2013-11-28 | 2014-03-26 | 四川蓝讯宝迩电子科技有限公司 | Power grid switching operation ticket automatic generating system and method |
| CN108985468A (en) * | 2018-06-27 | 2018-12-11 | 中国南方电网有限责任公司 | A method of the single intelligence of association maintenance generates operation order |
| CN111340253A (en) * | 2020-02-17 | 2020-06-26 | 国网山东省电力公司东营供电公司 | Main network maintenance request form analysis method and system |
-
2020
- 2020-07-30 CN CN202010750791.5A patent/CN111832977A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103679350A (en) * | 2013-11-28 | 2014-03-26 | 四川蓝讯宝迩电子科技有限公司 | Power grid switching operation ticket automatic generating system and method |
| CN108985468A (en) * | 2018-06-27 | 2018-12-11 | 中国南方电网有限责任公司 | A method of the single intelligence of association maintenance generates operation order |
| CN111340253A (en) * | 2020-02-17 | 2020-06-26 | 国网山东省电力公司东营供电公司 | Main network maintenance request form analysis method and system |
Non-Patent Citations (2)
| Title |
|---|
| 李治 等: "基于自然语言分析及专家系统的智能调度操作票系统研究与应用", 河北电力技术, vol. 38, no. 06, 31 December 2019 (2019-12-31), pages 1 - 3 * |
| 陆承宇 等: "基于隐马尔可夫模型的智能站操作票内容提取技术的研究", 能源工程, no. 02, 20 April 2019 (2019-04-20), pages 1 - 3 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112528627A (en) * | 2020-12-16 | 2021-03-19 | 中国南方电网有限责任公司 | Maintenance suggestion identification method based on natural language processing |
| CN112885352A (en) * | 2021-01-26 | 2021-06-01 | 广东电网有限责任公司 | Corpus construction method and device, computer equipment and storage medium |
| CN113033195A (en) * | 2021-03-15 | 2021-06-25 | 国网江苏省电力有限公司南通供电分公司 | Method for generating scheduling operation sequence by intelligently analyzing overhaul application ticket |
| CN113792548A (en) * | 2021-08-30 | 2021-12-14 | 国网天津市电力公司 | Automatic cover generation system and method based on text word segmentation and statistical verification |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111832977A (en) | Maintenance application automatic ticketing method based on natural language parsing | |
| CN111985653B (en) | Power grid fault knowledge recommendation and knowledge management system and method based on knowledge graph | |
| CN108345739B (en) | Method for identifying CIME and SVG model file information to realize protection fixed value on-line check function and obtain model | |
| CN110674282B (en) | Expert knowledge rule base-based one-key sequential control operation order intelligent simulation method | |
| CN110175324B (en) | Power grid operation instruction verification method and system based on data mining | |
| CN115357726A (en) | Fault disposal plan digital model establishing method based on knowledge graph | |
| CN110188345A (en) | A kind of intelligent identification Method and device of electric power operation ticket | |
| CN113095050A (en) | Intelligent ticketing method, system, equipment and storage medium | |
| CN109766416A (en) | A kind of new energy policy information abstracting method and system | |
| CN116028646A (en) | Power grid dispatching field knowledge graph construction method based on machine learning | |
| CN113792538B (en) | Method and device for rapidly generating operation ticket of power distribution network | |
| CN111708817A (en) | Intelligent disposal method for transformer substation monitoring information | |
| CN114282010A (en) | Power grid operation fault identification method and system based on knowledge graph and storage medium | |
| CN114529166A (en) | Power distribution network operation safety risk early warning method and system | |
| CN112906389B (en) | Fault trip discrimination method based on multi-dimensional data analysis | |
| CN112036179B (en) | Electric power plan information extraction method based on text classification and semantic frame | |
| CN113379214A (en) | Method for automatically filling and assisting decision of power grid accident information based on affair map | |
| CN112420042A (en) | Control method and device of power system | |
| CN111177323A (en) | Power failure plan unstructured data extraction and identification method based on artificial intelligence | |
| CN111061800A (en) | STATCOM transient response analysis system and method based on fault recording file | |
| CN110765986A (en) | Method for automatically auditing monitoring signals of main station of power system | |
| Shan et al. | Research on deep learning based dispatching fault disposal robot technology | |
| CN116108203A (en) | Method, system, storage medium and equipment for constructing power grid panoramic dispatching knowledge graph and managing power grid equipment | |
| CN115099232A (en) | Power grid operation knowledge model construction method for scheduling regulations and historical data | |
| CN114077835A (en) | Urban power grid dispatching operation ticket generation method |
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 |