CN115080687A - Accurate matching method for nuclear power plant work order tasks and quality defect report information - Google Patents

Accurate matching method for nuclear power plant work order tasks and quality defect report information Download PDF

Info

Publication number
CN115080687A
CN115080687A CN202210657842.9A CN202210657842A CN115080687A CN 115080687 A CN115080687 A CN 115080687A CN 202210657842 A CN202210657842 A CN 202210657842A CN 115080687 A CN115080687 A CN 115080687A
Authority
CN
China
Prior art keywords
information
quality defect
defect report
matching
work order
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
Application number
CN202210657842.9A
Other languages
Chinese (zh)
Inventor
张廉
李武平
富会佳
蔡汉坤
温庆邦
杨逗
王晓东
刘莉
李贵莲
姚昊
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
CNNC Nuclear Power Operation Management Co Ltd
China Nuclear Power Operation Technology Corp Ltd
Original Assignee
CNNC Nuclear Power Operation Management Co Ltd
China Nuclear Power Operation Technology Corp Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by CNNC Nuclear Power Operation Management Co Ltd, China Nuclear Power Operation Technology Corp Ltd filed Critical CNNC Nuclear Power Operation Management Co Ltd
Priority to CN202210657842.9A priority Critical patent/CN115080687A/en
Publication of CN115080687A publication Critical patent/CN115080687A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/205—Parsing
    • G06F40/216—Parsing using statistical methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
    • 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
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06395—Quality analysis or management
    • 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
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Health & Medical Sciences (AREA)
  • Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Educational Administration (AREA)
  • Development Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • Primary Health Care (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Probability & Statistics with Applications (AREA)
  • Testing And Monitoring For Control Systems (AREA)

Abstract

The invention particularly relates to a method for accurately matching work order tasks and quality defect report information of a nuclear power plant, which comprises the following steps: acquiring historical quality defect report information to form a quality defect report database of the nuclear power plant; taking the to-be-prepared work order task information as input information, and matching the to-be-prepared work order task information with historical quality defect report information in a nuclear power plant quality defect report database through a nuclear power plant quality defect report information accurate matching modelMatching to obtain a total matching score S of the historical quality defect report information; s is more than or equal to set W Limiting the score Into a set S of historical quality defect report information Set of scores (ii) a Pushing the count set S from high to low Set of scores Historical quality defect report information. According to the accurate matching method for the nuclear power plant work order task and the quality defect report information, the intelligent and accurate pushing of the historical similar quality defect report is realized, the searching time of maintenance workers is reduced, and the searching efficiency of the maintenance workers is improved.

Description

Accurate matching method for nuclear power plant work order tasks and quality defect report information
Technical Field
The invention relates to the technical field of nuclear power plant work order management, in particular to a method for accurately matching work order tasks and quality defect report information of a nuclear power plant.
Background
After a nuclear power plant is established in a nuclear power safety production management system, a large amount of quality defect report data (QDR) is accumulated. The quality defect report is an equipment quality abnormity report aiming at the condition that the quality of an unexpected item in the maintenance process does not meet the original design requirement, and a corrective measure must be made in time to repair the equipment or the quality of the item to enable the quality of the item to meet the design requirement. Maintenance tasks of the nuclear power plant are all carried out through work order tasks, so quality defect reports are all generated reports of object quality defects found in the process of implementing a certain work order task.
The work order task is a core object in the work control business process of the nuclear power plant, and each work needs to create the work order task (except simple maintenance). The preparation of the work order task is to form a complete and accurate work package, the work package collects a collection of files required by developing a certain maintenance task, and the work package is a necessary tool for maintenance personnel of the nuclear power plant to develop maintenance activities.
When a maintenance work order task preparer prepares a work order task, for the regular inspection, equipment maintenance and other works of equipment defects, the information such as reason analysis, processing schemes and the like in historical similar equipment quality defect reports needs to be searched for as reference, so that the maintenance worker can conveniently carry out the preparation work of a work package. However, the problems that the quality defect report is not accurately searched and the efficiency is low, and the historical quality defect report cannot be accurately pushed in time in the work order task preparation process exist at present.
Disclosure of Invention
Based on the above, it is necessary to provide a nuclear power plant work order task and quality defect report information accurate matching method for solving the problems that the existing quality defect report search is not accurate and inefficient, and the accurate pushing of the historical quality defect report cannot be performed in the work order task preparation process in time.
In order to achieve the above purpose, the invention provides the following technical scheme:
a nuclear power plant work order task and quality defect report information accurate matching method comprises the following steps:
1. acquiring historical quality defect report information to form a quality defect report database of the nuclear power plant;
2. matching the to-be-prepared work order task information with historical quality defect report information in a nuclear power plant quality defect report database by using the to-be-prepared work order task information as input information through a nuclear power plant quality defect report information accurate matching model to obtain a historical quality defect report information matching total score S;
3. s is more than or equal to set W Limiting the score Into a set S of historical quality defect report information Set of scores ；
4. Pushing the count set S from high to low Set of scores Historical quality defect report information.
Further, the input information of the work order task information to be prepared comprises field information of 'nuclear power plant', 'unit', 'equipment code', 'equipment name' and 'work order title'; the matching information of the historical quality defect report information comprises field information of 'relating to a power plant', 'QDR coding', 'QDR theme', 'unit', 'equipment coding' and 'equipment name'; the pushed historical quality defect report information display information comprises field information of 'relating to power plant', 'QDR code', 'QDR theme', 'unit', 'equipment code' and 'equipment name'.
Further, the accurate matching model of the nuclear power plant quality defect report information matches the input to-be-prepared work order task information with the historical quality defect report information based on the equipment service logic rule and the semantic similarity rule to obtain a historical quality defect report information matching total score S.
Further, when the matched field information of the nuclear power plant to be prepared work order task information is the same as the field information of the historical quality defect report information, and the field information of the nuclear power plant to be prepared is all in the model of CNP-600, CNP-1000, HPR-1000 or CPR-1000, the accurate matching model of the nuclear power plant quality defect report information matches the input work order task information to be prepared with the historical quality defect report information based on the following equipment business logic rules and semantic similarity rules to obtain a total matching score S of the historical quality defect report information:
1. when the 'equipment code' field information for matching the to-be-prepared work order task information can be extracted, the 'equipment code' field information for matching the to-be-prepared work order task information is extracted; matching the 'equipment code' field information for matching the to-be-prepared work order task information with the 'equipment code' field information of the historical quality defect report information, and calculating to obtain a historical quality defect report information equipment service logic matching score;
2. the method comprises the steps that equipment code field information for matching of to-be-prepared work order task information cannot be extracted, semantic similarity matching is carried out on the equipment name field information of the to-be-prepared work order task information and the equipment name field information of historical quality defect report information when the equipment name field information of the to-be-prepared work order task information can be matched with the equipment name field information of the historical quality defect report information, and semantic similarity matching scores of the historical quality defect report information are obtained through calculation;
3. semantic similarity matching is carried out on 'work order title' field information of the work order task information to be prepared and 'QDR theme' field information of the historical quality defect report information, and semantic similarity matching scores of the historical quality defect report information are obtained through calculation;
4. and (3) calculating the total matching score S of the historical quality defect report information, namely the matching score of the step (1) and the matching score of the step (3), or the matching score of the step (2) and the matching score of the step (3), or the matching score of the step (3).
Further, when the matched field information of the nuclear power plant of the to-be-prepared work order task information is the same as the field information of the historical quality defect report information, and the field information of the to-be-prepared work order is related to the power plant and is of a CNP-300 model, the accurate matching model of the nuclear power plant quality defect report information matches the input to-be-prepared work order task information with the historical quality defect report information based on the following equipment business logic rules and semantic similarity rules to obtain a historical quality defect report information matching total score S:
1. extracting 'equipment code' field information in 'work order title' field information of the work order task information to be prepared as 'equipment code' field information for matching the work order task information to be prepared; matching the 'equipment code' field information for matching the to-be-prepared work order task information with the 'equipment code' field information of the historical quality defect report information, and calculating to obtain the historical quality defect report information equipment industryBusiness logic match score W 8 ：
2. When the equipment code field information for matching the to-be-prepared work order task information cannot be matched with the equipment code field information of the historical quality defect report information, semantic similarity matching is carried out on the equipment name field information of the to-be-prepared work order task information and the equipment name field information of the historical quality defect report information, and the semantic similarity matching score W of the historical quality defect report information is obtained through calculation 9 (ii) a Historical quality defect report information semantic similarity matching score W 9 The highest score is h;
3. semantic similarity matching is carried out on 'work order title' field information of the work order task information to be prepared and 'QDR subject' field information of the historical quality defect report information, and semantic similarity matching score W of the historical quality defect report information is obtained through calculation 10 (ii) a Historical quality defect report information semantic similarity matching score W 10 The highest score is i;
4. calculating the total matching score S of the historical quality defect report information, which is the matching score W of the business logic of the historical quality defect report information equipment 8 + historical quality defect report information semantic similarity matching score W 10 Or historical quality defect report information semantic similarity match score W 9 + historical quality defect report information semantic similarity matching score W 10 ；h+i＝1。
Further, when the matched field information of the nuclear power plant of the to-be-prepared work order task information is the same as the field information of the historical quality defect report information, and the field information of the to-be-prepared work order is related to the power plant, and the field information of the to-be-prepared work order is the model of the CANDU6, the accurate matching model of the nuclear power plant quality defect report information matches the input to-be-prepared work order task information with the historical quality defect report information based on the following equipment business logic rule and semantic similarity rule, and the matching total score S of the historical quality defect report information is obtained:
1. when the 'equipment code' field information for matching the to-be-prepared work order task information can be extracted, the 'equipment code' field information for matching the to-be-prepared work order task information is extracted; matching the 'equipment code' field information for matching the to-be-prepared work order task information with the 'equipment code' field information of the historical quality defect report information, and calculating to obtain a historical quality defect report information equipment service logic matching score;
2. the method comprises the steps that equipment code field information for matching of to-be-prepared work order task information cannot be extracted, semantic similarity matching is carried out on the equipment name field information of the to-be-prepared work order task information and the equipment name field information of historical quality defect report information when the equipment name field information of the to-be-prepared work order task information can be matched with the equipment name field information of the historical quality defect report information, and semantic similarity matching scores of the historical quality defect report information are obtained through calculation;
3. performing semantic similarity matching on 'work order title' field information of the work order task information to be prepared and 'QDR topic' field information of the historical quality defect report information, and calculating to obtain a semantic similarity matching score of the historical quality defect report information;
4. and (3) calculating the total matching score S of the historical quality defect report information, namely the matching score of the step (1) and the matching score of the step (3), or the matching score of the step (2) and the matching score of the step (3), or the matching score of the step (3).
Further, when the matched field information of the nuclear power plant of the to-be-prepared work order task information is the same as the field information of the historical quality defect report information, and the matched field information of the to-be-prepared work order is of the VVER type, the accurate matching model of the nuclear power plant quality defect report information matches the input to-be-prepared work order task information with the historical quality defect report information based on the following equipment business logic rules and semantic similarity rules to obtain a historical quality defect report information matching total score S:
1. when the 'equipment code' field information for matching the to-be-prepared work order task information can be extracted, the 'equipment code' field information for matching the to-be-prepared work order task information is extracted; matching the 'equipment code' field information for matching the to-be-prepared work order task information with the 'equipment code' field information of the historical quality defect report information, and calculating to obtain a historical quality defect report information equipment service logic matching score;
2. the method comprises the steps that equipment code field information for matching of to-be-prepared work order task information cannot be extracted, semantic similarity matching is carried out on the equipment name field information of the to-be-prepared work order task information and the equipment name field information of historical quality defect report information when the equipment name field information of the to-be-prepared work order task information can be matched with the equipment name field information of the historical quality defect report information, and semantic similarity matching scores of the historical quality defect report information are obtained through calculation;
3. semantic similarity matching is carried out on 'work order title' field information of the work order task information to be prepared and 'QDR theme' field information of the historical quality defect report information, and semantic similarity matching scores of the historical quality defect report information are obtained through calculation;
4. and (3) calculating the total matching score S of the historical quality defect report information, namely the matching score of the step (1) and the matching score of the step (3), or the matching score of the step (2) and the matching score of the step (3), or the matching score of the step (3).
Further, when the matched field information of the nuclear power plant of the to-be-prepared work order task information is the same as the field information of the historical quality defect report information, and the matched field information of the to-be-prepared work order is in an AP1000 model, the accurate matching model of the nuclear power plant quality defect report information matches the input to-be-prepared work order task information with the historical quality defect report information based on the following equipment business logic rules and semantic similarity rules to obtain a historical quality defect report information matching total score S:
1. when the 'equipment code' field information for matching the to-be-prepared work order task information can be extracted, the 'equipment code' field information for matching the to-be-prepared work order task information is extracted; matching the 'equipment code' field information for matching the to-be-prepared work order task information with the 'equipment code' field information of the historical quality defect report information, and calculating to obtain a historical quality defect report information equipment service logic matching score;
2. the method comprises the steps that equipment code field information for matching of to-be-prepared work order task information cannot be extracted, semantic similarity matching is carried out on the equipment name field information of the to-be-prepared work order task information and the equipment name field information of historical quality defect report information when the equipment name field information of the to-be-prepared work order task information can be matched with the equipment name field information of the historical quality defect report information, and semantic similarity matching scores of the historical quality defect report information are obtained through calculation;
3. performing semantic similarity matching on 'work order title' field information of the work order task information to be prepared and 'QDR topic' field information of the historical quality defect report information, and calculating to obtain a semantic similarity matching score of the historical quality defect report information;
4. and (3) calculating the total matching score S of the historical quality defect report information, namely the matching score of the step (1) and the matching score of the step (3), or the matching score of the step (2) and the matching score of the step (3), or the matching score of the step (3).
Further, when the matched field information of the nuclear power plant of the to-be-prepared work order task information is different from the field information of the historical quality defect report information, and the field information of the nuclear power plant of the to-be-prepared work order task information belongs to the models of CANDU6, CNP-300, AP1000 or VVER, when the matched historical quality defect report information of other models is matched, the field information of the equipment code which is equivalent to the historical quality defect report information is different from the field information of the equipment code which is input to the to-be-prepared work order task information, the accurate matching model of the nuclear power plant quality defect report information matches the input to-be-prepared work order task information and the historical quality defect report information based on the following semantic similarity rule 6 to obtain a historical quality defect report information matching total score S:
performing semantic similarity matching on 'work order title' and 'equipment name' field information of the work order task information to be prepared and 'QDR subject' and 'equipment name' field information of the historical quality defect report information, and calculating to obtain a semantic similarity matching score W of the historical quality defect report information 32 (ii) a Historical quality defect report information semantic similarity matching score W 32 The highest value is ae;
calculating the total matching score S of the historical quality defect report information, namely the semantic similarity matching score W of the historical quality defect report information 32 ；
ae＝1。
Further, when the matched field information of the nuclear power plant of the to-be-prepared work order task information is different from the field information of the historical quality defect report information, and the field information of the nuclear power plant of the to-be-prepared work order task information belongs to the model of CNP-600, CNP-1000, HPR-1000 or CPR-1000, when the historical quality defect report information of the model of CANDU6, CNP-300, AP1000 or VVER is matched, the accurate matching model of the nuclear power plant quality defect report information matches the input to-be-prepared work order task information and the historical quality defect report information based on the following semantic similarity rule 7 to obtain a historical quality defect report information matching total score S:
performing semantic similarity matching on 'work order title' and 'equipment name' field information of the work order task information to be prepared and 'QDR subject' and 'equipment name' field information of the historical quality defect report information, and calculating to obtain a semantic similarity matching score W of the historical quality defect report information 33 (ii) a Historical quality defect report information semantic similarity matching score W 33 The highest value is af;
calculating a historical quality defect report information matching total score S 7 Historical quality defect report information semantic similarity matching score W 33 ；
af＝1。
Further, when the matched field information of the nuclear power plant of the to-be-prepared work order task information is different from the field information of the historical quality defect report information, the field information of the nuclear power plant of the to-be-prepared work order task information belongs to the model of CNP-600, CNP-1000, HPR-1000 or CPR-1000, and the matched model of CNP-600, CNP-1000, HPR-1000 or CPR-1000 is different from the model of the to-be-prepared work order task information, the accurate matching model of the quality defect report information of the nuclear power plant matches the input to-be-prepared work order task information with the historical quality defect report information based on the following equipment service logic rules and semantic similarity rules to obtain a historical quality defect report information matching total score S:
1. when the 'equipment code' field information for matching the to-be-prepared work order task information can be extracted, the 'equipment code' field information for matching the to-be-prepared work order task information is extracted; matching the 'equipment code' field information for matching the to-be-prepared work order task information with the 'equipment code' field information of the historical quality defect report information, and calculating to obtain a historical quality defect report information equipment service logic matching score; performing semantic similarity matching on 'work order title' field information of the work order task information to be prepared and 'QDR topic' field information of the historical quality defect report information, and calculating to obtain a semantic similarity matching score of the historical quality defect report information; calculating a historical quality defect report information matching total score S which is a historical quality defect report information equipment service logic matching score plus a historical quality defect report information semantic similarity matching score;
2. when the field information of the equipment code for matching the work order task information to be prepared cannot be extracted, semantic similarity matching is carried out on the field information of the work order title and the equipment name of the work order task information to be prepared and the field information of the QDR theme and the equipment name of the historical quality defect report information, and the semantic similarity matching score of the historical quality defect report information is obtained through calculation; and calculating the historical quality defect report information matching total score S which is the semantic similarity matching score of the historical quality defect report information.
The invention has the beneficial technical effects that:
the method for accurately matching the work order task and the quality defect report information of the nuclear power plant realizes the accurate pushing of the historical similar quality defect report information, saves the manpower and time for searching the historical similar quality defect report information, lightens the burden of a work order preparer, improves the quality and efficiency of work order task preparation, and ensures the safe and efficient implementation of various maintenance works of the nuclear power plant.
Drawings
FIG. 1 is a schematic flow chart of a method for accurately matching nuclear power plant work order tasks with quality defect report information.
Detailed Description
The invention is described in further detail below with reference to the figures and the detailed description.
The invention provides a method for accurately matching work order tasks and quality defect report information of a nuclear power plant, which comprises the following steps:
1. acquiring historical quality defect report information to form a quality defect report database of the nuclear power plant;
2. matching the to-be-prepared work order task information with historical quality defect report information in a nuclear power plant quality defect report database by using the to-be-prepared work order task information as input information through a nuclear power plant quality defect report information accurate matching model to obtain a historical quality defect report information matching total score S;
3. s is more than or equal to set W Limiting the score Into a set S of historical quality defect report information Set of scores ；
4. Pushing the credit set S in the order of scores from high to low Set of scores Historical quality defect report information.
Further, the input information of the work order task information to be prepared comprises field information of 'nuclear power plant', 'unit', 'equipment code', 'equipment name' and 'work order title'; the matching information of the historical quality defect report information comprises field information of 'relating to a power plant', 'QDR coding', 'QDR theme', 'unit', 'equipment coding' and 'equipment name'; the pushed historical quality defect report information display information comprises field information of 'relating to power plant', 'QDR code', 'QDR theme', 'unit', 'equipment code' and 'equipment name'.
Further, the accurate matching model of the nuclear power plant quality defect report information matches the input to-be-prepared work order task information with the historical quality defect report information based on the equipment service logic rule and the semantic similarity rule to obtain a historical quality defect report information matching total score S.
Further, the semantic similarity matching relates to a natural language technology, and comprises the following steps:
(1) performing word segmentation processing on input work order task information to be prepared and character description field information of historical quality defect report information through a Chinese word segmentation engine after nuclear power professional word stock optimization to respectively obtain respective word segmentation phrases;
(2) respectively calculating the word frequency vector and the sentence vector of the word segmentation phrase obtained in the step (1) based on a TF-IDF algorithm;
(3) cosine similarity calculation is carried out on the word frequency vectors and sentence vectors obtained in the step (2), and semantic similarity matching scores are obtained and output; the larger the semantic similarity matching score is, the higher the similarity is, and conversely, the lower the similarity is.
Further, when the matched field information of the nuclear power plant to be prepared for the work order task information is the same as the field information of the historical quality defect report information, which relates to the power plant (belongs to the same machine type), and the field information of the nuclear power plant to be prepared for the work order task information is the same as the field information of the historical quality defect report information, and the field information of the nuclear power plant to be prepared for the historical quality defect report information is the type of CNP-600, CNP-1000, HPR-1000 or CPR-1000, the accurate matching model of the nuclear power plant quality defect report information extracts the field information of the equipment code for matching the work order task information to be prepared based on the following equipment code rules:
the "unit number" + "system code" + "device code", the "unit number" is composed of one-digit letters, the "system code" is composed of three-digit letters, and the "device code" is composed of three-digit/four-digit numbers + two-digit/three-digit letters.
Further, referring to fig. 1, when the field information of the nuclear power plant of the matched to-be-prepared work order task information is the same as the field information of the historical quality defect report information (belonging to the same model) related to the power plant and is of the model of "CNP-600", "CNP-1000", "HPR-1000" or "CPR-1000", the accurate matching model of the nuclear power plant quality defect report information is based onMatching the input work order task information to be prepared with the historical quality defect report information according to the following equipment service logic rule 1 and semantic similarity rule 1 to obtain a historical quality defect report information matching total score S 1 ：
1. When the 'equipment code' field information for matching the to-be-prepared work order task information can be extracted, the 'equipment code' field information for matching the to-be-prepared work order task information is extracted; matching the 'equipment code' field information for matching the to-be-prepared work order task information with the 'equipment code' field information of the historical quality defect report information, and calculating to obtain a historical quality defect report information equipment service logic matching score;
2. the method comprises the steps that equipment code field information for matching of to-be-prepared work order task information cannot be extracted, semantic similarity matching is carried out on the equipment name field information of the to-be-prepared work order task information and the equipment name field information of historical quality defect report information when the equipment name field information of the to-be-prepared work order task information can be matched with the equipment name field information of the historical quality defect report information, and semantic similarity matching scores of the historical quality defect report information are obtained through calculation;
3. performing semantic similarity matching on 'work order title' field information of the work order task information to be prepared and 'QDR topic' field information of the historical quality defect report information, and calculating to obtain a semantic similarity matching score of the historical quality defect report information;
4. calculating a historical quality defect report information matching total score S 1 Matching score of step (1) plus matching score of step (3), or matching score of step (2) plus matching score of step (3), or matching score of step (3).
Further, when the matched field information of the nuclear power plant of the to-be-prepared work order task information is the same as the field information of the historical quality defect report information, wherein the field information of the nuclear power plant is related to the power plant, and the field information of the to-be-prepared work order task information belongs to the same model, and the field information of the to-be-prepared work order task information is of the model of CNP-600, CNP-1000, HPR-1000 or CPR-1000, and the field information of the to-be-prepared work order task information meets the equipment coding rule of the power plantThen, the accurate matching model of the quality defect report information of the nuclear power plant matches the input work order task information to be prepared with the historical quality defect report information to obtain a historical quality defect report information matching total score S 1 ：
1. Extracting 'equipment code' field information of the to-be-prepared work order task information as 'equipment code' field information for matching the to-be-prepared work order task information; matching the 'equipment code' field information for matching the to-be-prepared work order task information with the 'equipment code' field information of the historical quality defect report information as follows, and calculating to obtain a historical quality defect report information equipment service logic matching score W 1 ：
When the 'equipment code' field information for matching the prepared work order task information and the 'equipment code' field information of the historical quality defect report information are all the same (same equipment), calculating the service logic matching score W of the historical quality defect report information equipment 1 ＝α 1 ；
Except that the field information of the unit number is different in the field information of the equipment code for matching the job order task information and the field information of the equipment code of the historical quality defect report information, and the other field information are all the same, calculating the service logic matching score W of the historical quality defect report information equipment 1 ＝α 2 ；
Except that the 'unit number' and the intermediate digital coding field information are different in the 'equipment coding' field information for matching the to-be-prepared work order task information and the 'equipment coding' field information of the historical quality defect report information, and the other field information are all the same, calculating the historical quality defect report information equipment service logic matching score W 1 ＝α 3 ；
When the conditions are not met, calculating the service logic matching score W of the historical quality defect report information equipment 1 ＝0；
2. Semantic similarity matching is carried out on 'work order title' field information of the work order task information to be prepared and 'QDR subject' field information of the historical quality defect report information, and calculation is carried out to obtainReport information semantic similarity matching score W to historical quality defects 2 (ii) a Historical quality defect report information semantic similarity matching score W 2 The highest value is b;
3. calculating the total matching score S1 of the historical quality defect report information, namely the service logic matching score W of the historical quality defect report information equipment 1 + historical quality defect report information semantic similarity matching score W 2 ；
α 1 ＞α 2 ＞α 3 ＞0，α 1 +b＝1。
Further, when the matched field information of the nuclear power plant of the to-be-prepared work order task information is the same as the field information of the historical quality defect report information, which relates to the power plant (belongs to the same model), and the field information of the to-be-prepared work order task information is the model of CNP-600, CNP-1000, HPR-1000 or CPR-1000, the field information of the to-be-prepared work order task information does not meet the equipment coding rule of the power plant, and when the 'work order title' field information of the work order task information to be prepared contains 'equipment coding' field information meeting the equipment coding rule of the power plant, the nuclear power plant quality defect report information is accurately matched with the model, the method comprises the following steps of matching input work order task information to be prepared with historical quality defect report information to obtain a historical quality defect report information matching total score S. 1 ：
1. Extracting 'equipment code' field information in 'work order title' field information of the work order task information to be prepared, and using the 'equipment code' field information as the matching 'equipment code' field information of the work order task information to be prepared; matching the 'equipment code' field information for matching the to-be-prepared work order task information with the 'equipment code' field information of the historical quality defect report information as follows, and calculating to obtain a historical quality defect report information equipment service logic matching score W 3 ：
When the 'equipment code' field information for matching the prepared work order task information and the 'equipment code' field information of the historical quality defect report information are all the same (same equipment), calculating the service logic matching score W of the historical quality defect report information equipment 3 ＝c 1 ；
Except that the field information of the unit number is different in the field information of the equipment code for matching the job order task information and the field information of the equipment code of the historical quality defect report information, and the other field information are all the same, calculating the service logic matching score W of the historical quality defect report information equipment 3 ＝c 2 ；
Except that the 'unit number' and the intermediate digital coding field information are different in the 'equipment coding' field information for matching the to-be-prepared work order task information and the 'equipment coding' field information of the historical quality defect report information, and the other field information are all the same, calculating the historical quality defect report information equipment service logic matching score W 3 ＝c 3 ；
When the conditions are not met, calculating the service logic matching score W of the historical quality defect report information equipment 3 ＝0；
2. Semantic similarity matching is carried out on 'work order title' field information of the work order task information to be prepared and 'QDR subject' field information of the historical quality defect report information, and semantic similarity matching score W of the historical quality defect report information is obtained through calculation 4 (ii) a Historical quality defect report information semantic similarity matching score W 4 The highest value is d;
3. calculating a historical quality defect report information matching total score S 1 Reporting information device business logic match score W ═ historical quality defects 3 + historical quality defect report information semantic similarity matching score W 4 ；
c 1 ＞c 2 ＞c 3 ＞0，c 1 +d＝1。
Further, when the matched field information of the nuclear power plant of the to-be-prepared work order task information is the same as the field information of the historical quality defect report information, which relates to the power plant (belongs to the same model), and is of the models of CNP-600, CNP-1000, HPR-1000 or CPR-1000, the field information of the to-be-prepared work order task information does not meet the equipment coding rule of the power plant, and the to-be-prepared work order task information is not in accordance with the equipment coding rule of the power plantAnd matching the input to-be-prepared work order task information with the historical quality defect report information to obtain a historical quality defect report information matching total score S through the following steps 1 ：
1. Performing semantic similarity matching on the 'equipment name' field information of the to-be-prepared work order task information and the 'equipment name' field information of the historical quality defect report information, and calculating to obtain a semantic similarity matching score W of the historical quality defect report information 5 (ii) a Historical quality defect report information semantic similarity matching score W 5 The highest value is e;
2. semantic similarity matching is carried out on 'work order title' field information of the work order task information to be prepared and 'QDR subject' field information of the historical quality defect report information, and semantic similarity matching score W of the historical quality defect report information is obtained through calculation 6 (ii) a Historical quality defect report information semantic similarity matching score W 6 The highest value is f;
3. calculating the total matching score S1 of the historical quality defect report information, namely the semantic similarity matching score W of the historical quality defect report information 5 + historical quality defect report information semantic similarity matching score W 6 ；
e+f＝1。
Further, when the matched field information of the nuclear power plant of the to-be-prepared work order task information is the same as the field information of the historical quality defect report information, which relates to the power plant (belongs to the same model), and the field information of the to-be-prepared work order task information is of the model of CNP-600, CNP-1000, HPR-1000 or CPR-1000, the field information of the to-be-prepared work order task information does not satisfy the equipment coding rule of the power plant, and the field information of the to-be-prepared work order title does not satisfy the equipment coding rule of the power plantMatching the input to-be-prepared work order task information and the historical quality defect report information to obtain a historical quality defect report information matching total score S through the following steps of matching the input to-be-prepared work order task information with the accurate matching model of the nuclear power plant quality defect report information when the field information of the equipment name of the to-be-prepared work order task information cannot be matched with the field information of the equipment name of the historical quality defect report information 1 ：
1. Semantic similarity matching is carried out on 'work order title' field information of the work order task information to be prepared and 'QDR subject' field information of the historical quality defect report information, and semantic similarity matching score W of the historical quality defect report information is obtained through calculation 7 (ii) a Historical quality defect report information semantic similarity matching score W 7 The highest value is g;
2. calculating a historical quality defect report information matching total score S 1 Historical quality defect report information semantic similarity matching score W 7 ；
g＝1。
Further, when the matched field information of the nuclear power plant of the to-be-prepared work order task information is the same as the field information of the historical quality defect report information, which relates to the power plant (belongs to the same model), and is a CNP-300 model, the accurate matching model of the nuclear power plant quality defect report information extracts the field information of the equipment code for matching the to-be-prepared work order task information based on the following equipment coding rules:
the "0/1/2/3 bit number" + "1/2/3/4 bit letters" + "0/1/2 bit number" + "0/1 bit letters" + "-" + "0/1/2/3/4 bit letters" + "0/1/2/3/4/5 bit number".
Further, referring to fig. 1, when the matched "power plant related" field information of the to-be-prepared work order task information is the same as the "power plant related" field information of the historical quality defect report information (belonging to the same model) and is of the model "CNP-300", the accurate matching model of the nuclear power plant quality defect report information is based on the following equipment business logic rule 2 and semantic similarity rule 2, and the input to-be-prepared work order task information and historical quality defect report information are inputThe report information is matched to obtain the total matching score S of the report information of the historical quality defects 2 ：
1. Extracting 'equipment code' field information in 'work order title' field information of the work order task information to be prepared as 'equipment code' field information for matching the work order task information to be prepared; matching the 'equipment code' field information for matching the to-be-prepared work order task information with the 'equipment code' field information of the historical quality defect report information as follows, and calculating to obtain a historical quality defect report information equipment service logic matching score W 8 ：
When the 'equipment code' field information for matching the prepared work order task information and the 'equipment code' field information of the historical quality defect report information are all the same (same equipment), calculating the service logic matching score W of the historical quality defect report information equipment 8 ＝h；
When the conditions are not accordant, calculating the service logic matching score W of the historical quality defect report information equipment 8 ＝0；
2. When the equipment code field information for matching the to-be-prepared work order task information cannot be matched with the equipment code field information of the historical quality defect report information, semantic similarity matching is carried out on the equipment name field information of the to-be-prepared work order task information and the equipment name field information of the historical quality defect report information, and the semantic similarity matching score W of the historical quality defect report information is obtained through calculation 9 (ii) a Historical quality defect report information semantic similarity matching score W 9 The highest score is h;
3. semantic similarity matching is carried out on 'work order title' field information of the work order task information to be prepared and 'QDR subject' field information of the historical quality defect report information, and semantic similarity matching score W of the historical quality defect report information is obtained through calculation 10 (ii) a Historical quality defect report information semantic similarity matching score W 10 The highest score is i;
4. calculating a historical quality defect report information matching total score S 2 Historical quality defect reporting information device service logic match scoreValue W 8 + historical quality defect report information semantic similarity matching score W 10 Or historical quality defect report information semantic similarity match score W 9 + historical quality defect report information semantic similarity matching score W 10 ；h+i＝1。
Further, when the matched field information of the nuclear power plant of the to-be-prepared work order task information is the same as the field information of the historical quality defect report information, which relates to the power plant (belongs to the same machine type), and the field information of the historical quality defect report information is of the type of 'CANDU 6', the accurate matching model of the nuclear power plant quality defect report information extracts the field information of the 'equipment code' for matching the to-be-prepared work order task information based on the following equipment coding rules:
"set number" + "-" + "system code" + "-" + "device code", e.g., "1/2/3/4/5/6-bit letters" + "0/1/2/3/4/5-bit numbers" + "0/1-bit letters" + "0/1/2-bit numbers"; or "1/2/3/4/5/6-bit letters" + "0/1/2/3/4/5-bit numbers" + "0/1-bit letters" + "0/1/2-bit numbers" + "-" + "0/1/2/3-bit letters" + "0/1/2/3/4-bit numbers" + "0/1/2-bit letters" + "0/1/2-bit numbers"; or "1/2-bit letters" + "-" + "0/1/2-bit letters" + "0/1/2-bit numbers" + "0/1/2-bit letters" + "-" + "0/1/2/3/4-bit numbers" + "0/1/2-bit letters"; or a "1-digit" + "1-digit letter" + "1/2-digit" + "0/1/2/3-digit letter".
Further, referring to fig. 1, when the matched "nuclear power plant" field information of the to-be-prepared work order task information is the same as the "related power plant" field information of the historical quality defect report information (belonging to the same model) and both are in the "CANDU 6" model, the accurate matching model of the nuclear power plant quality defect report information matches the input to-be-prepared work order task information and the historical quality defect report information based on the following device business logic rule 3 and semantic similarity rule 3 to obtain a historical quality defect report information matching total score S 3 ：
1. When the 'equipment code' field information for matching the to-be-prepared work order task information can be extracted, the 'equipment code' field information for matching the to-be-prepared work order task information is extracted; matching the 'equipment code' field information for matching the to-be-prepared work order task information with the 'equipment code' field information of the historical quality defect report information, and calculating to obtain a historical quality defect report information equipment service logic matching score;
2. the method comprises the steps that equipment code field information for matching of to-be-prepared work order task information cannot be extracted, semantic similarity matching is carried out on the equipment name field information of the to-be-prepared work order task information and the equipment name field information of historical quality defect report information when the equipment name field information of the to-be-prepared work order task information can be matched with the equipment name field information of the historical quality defect report information, and semantic similarity matching scores of the historical quality defect report information are obtained through calculation;
3. performing semantic similarity matching on 'work order title' field information of the work order task information to be prepared and 'QDR topic' field information of the historical quality defect report information, and calculating to obtain a semantic similarity matching score of the historical quality defect report information;
4. calculating a historical quality defect report information matching total score S 3 Matching score of step (1) plus matching score of step (3), or matching score of step (2) plus matching score of step (3), or matching score of step (3).
Further, when the matched field information of the nuclear power plant to be prepared with the work order task information is the same as the field information of the historical quality defect report information, wherein the field information of the nuclear power plant to be prepared with the historical quality defect report information is related to the power plant (belongs to the same machine type), and is all in the type of CANDU6, and the field information of the equipment code of the work order task information to be prepared meets the equipment code rule of the power plant, the accurate matching model of the nuclear power plant quality defect report information matches the input work order task information to be prepared with the historical quality defect report information through the following steps to obtain the total matching score S of the historical quality defect report information 3 ：
1. Extracting 'equipment code' field information of the to-be-prepared work order task information as 'equipment code' field information for matching the to-be-prepared work order task information; matching the job order information to be prepared "Matching the equipment code field information with the equipment code field information of the historical quality defect report information as follows, and calculating to obtain the historical quality defect report information equipment service logic matching score W 11 ：
When the 'equipment code' field information for matching the prepared work order task information and the 'equipment code' field information of the historical quality defect report information are all the same (same equipment), calculating the service logic matching score W of the historical quality defect report information equipment 11 ＝j 1 ；
Except that the field information of the unit number is different in the field information of the equipment code for matching the job order task information and the field information of the equipment code of the historical quality defect report information, and the other field information are all the same, calculating the service logic matching score W of the historical quality defect report information equipment 11 ＝j 2 ；
Except that the field information of the unit number and the system code is different in the field information of the equipment code for matching the to-be-prepared work order task information and the field information of the equipment code of the historical quality defect report information, and the other field information are all the same, calculating the service logic matching score W of the historical quality defect report information equipment 11 ＝j 3 ；
When the conditions are not met, calculating the service logic matching score W of the historical quality defect report information equipment 11 ＝0；
2. Semantic similarity matching is carried out on 'work order title' field information of the work order task information to be prepared and 'QDR subject' field information of the historical quality defect report information, and semantic similarity matching score W of the historical quality defect report information is obtained through calculation 12 (ii) a Historical quality defect report information semantic similarity matching score W 12 The highest value is k;
3. calculating a historical quality defect report information matching total score S 3 Reporting information device business logic match score W ═ historical quality defects 11 + historical quality defect report information semantic similarity matching score W 12 ；
j 1 ＞j 2 ＞j 3 ＞0，j 1 +k＝1。
Further, when the matched field information of the nuclear power plant of the to-be-prepared work order task information is the same as the field information of the historical quality defect report information, which relates to the power plant (belongs to the same machine type), and the field information of the to-be-prepared work order task information is of the CANDU6 type, the equipment coding field information of the to-be-prepared work order task information does not meet the equipment coding rule of the power plant, and the equipment coding field information meeting the equipment coding rule of the power plant is contained in the field information of the work order title of the to-be-prepared work order task information, the nuclear power plant quality defect report information accurate matching model matches the input to-be-prepared work order task information with the historical quality defect report information to obtain the historical quality defect report information matching total score S 3 ：
1. Extracting 'equipment code' field information in 'work order title' field information of the work order task information to be prepared, and using the 'equipment code' field information as the matching 'equipment code' field information of the work order task information to be prepared; matching the 'equipment code' field information for matching the to-be-prepared work order task information with the 'equipment code' field information of the historical quality defect report information as follows, and calculating to obtain a historical quality defect report information equipment service logic matching score W 13 ：
When the 'equipment code' field information for matching the prepared work order task information and the 'equipment code' field information of the historical quality defect report information are all the same (same equipment), calculating the service logic matching score W of the historical quality defect report information equipment 13 ＝L 1 ；
Except that the field information of the unit number is different in the field information of the equipment code for matching the job order task information and the field information of the equipment code of the historical quality defect report information, and the other field information are all the same, calculating the service logic matching score W of the historical quality defect report information equipment 13 ＝L 2 ；
'equipment coding' field information and historical quality defect report information for matching to-be-prepared work order task informationIn the 'equipment coding' field information, except that the 'unit number' field information is different from the 'system code' field information, when all the other field information are identical, calculating historical quality defect report information equipment service logic matching score W 13 ＝L 3 ；
When the conditions are not met, calculating the service logic matching score W of the historical quality defect report information equipment 13 ＝0；
2. Semantic similarity matching is carried out on 'work order title' field information of the work order task information to be prepared and 'QDR subject' field information of the historical quality defect report information, and semantic similarity matching score W of the historical quality defect report information is obtained through calculation 14 (ii) a Historical quality defect report information semantic similarity matching score W 14 The highest value is m;
3. calculating a historical quality defect report information matching total score S 3 Reporting information appliance service logic match score W as historical quality defect 13 + historical quality defect report information semantic similarity matching score W 14 ；
L 1 ＞L 2 ＞L 3 ＞0，L 1 +m＝1。
Further, when the matched field information of the nuclear power plant to be prepared with the work order task information is the same as the field information of the historical quality defect report information, wherein the field information of the nuclear power plant to be prepared with the historical quality defect report information relates to the same power plant (belongs to the same machine type), the field information of the CANDU6 is in the CANDU6 type, the equipment code field information of the work order task information to be prepared does not satisfy the equipment code rule of the power plant, the equipment code field information of the equipment code rule of the power plant is not satisfied in the title field information of the work order to be prepared with the equipment name field information of the historical quality defect report information, the nuclear power plant quality defect report information accurate matching model matches the input work order task information to be prepared with the historical quality defect report information through the following steps, obtaining a total matching score S of the historical quality defect report information 3 ：
1. Will be ready forPreparing 'equipment name' field information of the work order task information and 'equipment name' field information of the historical quality defect report information for semantic similarity matching, and calculating to obtain a semantic similarity matching score W of the historical quality defect report information 15 (ii) a Historical quality defect report information semantic similarity matching score W 15 The highest value is n;
2. semantic similarity matching is carried out on 'work order title' field information of the work order task information to be prepared and 'QDR subject' field information of the historical quality defect report information, and semantic similarity matching score W of the historical quality defect report information is obtained through calculation 16 (ii) a Historical quality defect report information semantic similarity matching score W 16 The highest value is o;
3. calculating a historical quality defect report information matching total score S 3 Historical quality defect report information semantic similarity matching score W 15 + historical quality defect report information semantic similarity matching score W 16 ；
n+o＝1。
Further, when the matched field information of the nuclear power plant to be prepared with the work order task information is the same as the field information of the historical quality defect report information, wherein the field information of the nuclear power plant to be prepared with the historical quality defect report information relates to the same power plant (belongs to the same machine type), the field information of the CANDU6 is in the CANDU6 type, the equipment code field information of the work order task information to be prepared does not satisfy the equipment code rule of the power plant, the equipment code field information of the equipment code rule of the power plant is not satisfied in the title field information of the work order to be prepared with the equipment name field information of the historical quality defect report information, the nuclear power plant quality defect report information accurate matching model matches the input work order task information to be prepared with the historical quality defect report information through the following steps, obtaining a total matching score S of the historical quality defect report information 3 ：
1. Performing semantic meaning on 'work order title' field information of work order task information to be prepared and 'QDR subject' field information of historical quality defect report informationSimilarity matching, namely calculating to obtain a semantic similarity matching score W of the historical quality defect report information 17 (ii) a Historical quality defect report information semantic similarity matching score W 17 The highest value is p;
2. calculating a historical quality defect report information matching total score S 3 Reporting information semantic similarity matching score W as historical quality defect 17 ；
p＝1。
Further, when the matched field information of the nuclear power plant of the to-be-prepared work order task information is the same as the field information of the historical quality defect report information (belonging to the same machine type) related to the power plant and is of the VVER machine type, the accurate matching model of the nuclear power plant quality defect report information extracts the field information of the equipment code for matching the to-be-prepared work order task information based on the following equipment code rules:
"set number" + "system code" + "device code", the "set number" consisting of 1 digit or 1 digit alphabet, the "system code" consisting of 0/1 digits +3 digits +2 digits, the "device code" consisting of 2 digits +3 digits +0/1 digits alphabet.
Further, referring to fig. 1, when the matched "nuclear power plant" field information of the to-be-prepared work order task information is the same as the "related power plant" field information of the historical quality defect report information (belonging to the same model) and both are in the "VVER" model, the accurate matching model of the nuclear power plant quality defect report information matches the input to-be-prepared work order task information and the historical quality defect report information based on the following equipment business logic rule 4 and semantic similarity rule 4 to obtain a total matching score S of the historical quality defect report information 4 ：
1. When the 'equipment code' field information for matching the to-be-prepared work order task information can be extracted, the 'equipment code' field information for matching the to-be-prepared work order task information is extracted; matching the 'equipment code' field information for matching the to-be-prepared work order task information with the 'equipment code' field information of the historical quality defect report information, and calculating to obtain a historical quality defect report information equipment service logic matching score;
2. the method comprises the steps that equipment code field information for matching of to-be-prepared work order task information cannot be extracted, semantic similarity matching is carried out on the equipment name field information of the to-be-prepared work order task information and the equipment name field information of historical quality defect report information when the equipment name field information of the to-be-prepared work order task information can be matched with the equipment name field information of the historical quality defect report information, and semantic similarity matching scores of the historical quality defect report information are obtained through calculation;
3. performing semantic similarity matching on 'work order title' field information of the work order task information to be prepared and 'QDR topic' field information of the historical quality defect report information, and calculating to obtain a semantic similarity matching score of the historical quality defect report information;
4. calculating a historical quality defect report information matching total score S 4 Matching score of step (1) plus matching score of step (3), or matching score of step (2) plus matching score of step (3), or matching score of step (3).
Further, when the matched 'nuclear power plant' field information of the to-be-prepared work order task information is the same as the 'related power plant' field information of the historical quality defect report information (belongs to the same machine type) and is in the 'VVER' machine type, and the 'equipment coding' field information of the to-be-prepared work order task information meets the equipment coding rule of the power plant, the accurate matching model of the nuclear power plant quality defect report information matches the input to-be-prepared work order task information and the historical quality defect report information through the following steps to obtain the total matching score S of the historical quality defect report information 4 ：
1. Extracting 'equipment code' field information of the to-be-prepared work order task information as 'equipment code' field information for matching the to-be-prepared work order task information; matching the 'equipment code' field information for matching the to-be-prepared work order task information with the 'equipment code' field information of the historical quality defect report information as follows, and calculating to obtain a historical quality defect report information equipment service logic matching score W 18 ：
When the 'equipment code' field information for matching the prepared work order task information and the 'equipment code' field information of the historical quality defect report information are all the same (same equipment), calculating the service logic matching score W of the historical quality defect report information equipment 18 ＝q 1 ；
Except that the field information of the unit number is different in the field information of the equipment code for matching the job order task information and the field information of the equipment code of the historical quality defect report information, and the other field information are all the same, calculating the service logic matching score W of the historical quality defect report information equipment 18 ＝q 2 ；
Except that the 'unit number' and the last digital coding field information are different in the 'equipment coding' field information for matching the to-be-prepared work order task information and the 'equipment coding' field information of the historical quality defect report information, and the other field information are all the same, calculating the historical quality defect report information equipment service logic matching score W 18 ＝q 3 ；
Except that the 'unit number' and the middle digital coding field information are different in the 'equipment coding' field information for matching the to-be-prepared work order task information and the 'equipment coding' field information of the historical quality defect report information, and the other field information are all the same, calculating the historical quality defect report information equipment service logic matching score W 18 ＝q 4 ；
Except that the 'unit number', the middle digital code and the last digital code field information are different in the 'equipment code' field information for matching the to-be-prepared work order task information and the 'equipment code' field information of the historical quality defect report information, and the other field information are all the same, calculating the historical quality defect report information equipment service logic matching score W 18 ＝q 5 ；
When the conditions are not met, calculating the service logic matching score W of the historical quality defect report information equipment 18 ＝0；
2. To be prepared with work order task information "Semantic similarity matching is carried out on the ' field information of the work order title and the ' QDR subject ' field information of the historical quality defect report information, and the semantic similarity matching score W of the historical quality defect report information is obtained through calculation 19 (ii) a Historical quality defect report information semantic similarity matching score W 19 The highest value is r;
3. calculating a historical quality defect report information matching total score S 4 Reporting information device business logic match score W ═ historical quality defects 18 + historical quality defect report information semantic similarity matching score W 19 ；
q 1 ＞q 2 ＞q 3 ＞q 4 ＞q 5 ＞0，q 1 +r＝1。
Further, when the matched 'nuclear power plant' field information of the to-be-prepared work order task information is the same as the 'related power plant' field information of the historical quality defect report information (belongs to the same machine type) and is in the 'VVER' machine type, the 'equipment code' field information of the to-be-prepared work order task information does not meet the equipment code rule of the power plant, and the 'equipment code' field information meeting the equipment code rule of the power plant is contained in the 'work order title' field information of the to-be-prepared work order task information, the nuclear power plant quality defect report information accurate matching model matches the input to-be-prepared work order task information with the historical quality defect report information to obtain a historical quality defect report information matching total score S 4 ：
1. Extracting 'equipment code' field information in 'work order title' field information of the work order task information to be prepared, and using the 'equipment code' field information as the matching 'equipment code' field information of the work order task information to be prepared; matching the 'equipment code' field information for matching the to-be-prepared work order task information with the 'equipment code' field information of the historical quality defect report information as follows, and calculating to obtain a historical quality defect report information equipment service logic matching score W 20 ：
To-be-prepared work order task information matching equipment coding field information and historical quality defect report information equipment coding fieldWhen the information is all the same (same equipment), calculating the service logic matching score W of the historical quality defect report information equipment 20 ＝s 1 ；
Except that the field information of the unit number is different in the field information of the equipment code for matching the job order task information and the field information of the equipment code of the historical quality defect report information, and the other field information are all the same, calculating the service logic matching score W of the historical quality defect report information equipment 20 ＝s 2 ；
Except that the 'unit number' and the last digital coding field information are different in the 'equipment coding' field information for matching the to-be-prepared work order task information and the 'equipment coding' field information of the historical quality defect report information, and the other field information are all the same, calculating the historical quality defect report information equipment service logic matching score W 20 ＝s 3 ；
Except that the 'unit number' and the middle digital coding field information are different in the 'equipment coding' field information for matching the to-be-prepared work order task information and the 'equipment coding' field information of the historical quality defect report information, and the other field information are all the same, calculating the historical quality defect report information equipment service logic matching score W 20 ＝s 4 ；
Except that the 'unit number', the middle digital code and the last digital code field information are different in the 'equipment code' field information for matching the to-be-prepared work order task information and the 'equipment code' field information of the historical quality defect report information, and the other field information are all the same, calculating the historical quality defect report information equipment service logic matching score W 20 ＝s 5 ；
When the conditions are not met, calculating the service logic matching score W of the historical quality defect report information equipment 20 ＝0；
2. Semantic similarity matching is carried out on 'work order title' field information of the work order task information to be prepared and 'QDR subject' field information of the historical quality defect report information, and the semantic facies of the historical quality defect report information is obtained through calculationSimilarity match score W 21 (ii) a Historical quality defect report information semantic similarity matching score W 21 The highest value is t;
3. calculating a historical quality defect report information matching total score S 4 Reporting information device business logic match score W ═ historical quality defects 20 + History quality defect report information semantic similarity match score W 21 ；
s 1 ＞s 2 ＞s 3 ＞s 4 ＞s 5 ＞0，s 1 +t＝1。
Further, when the matched field information of the nuclear power plant to be prepared with the work order task information is the same as the field information of the historical quality defect report information, wherein the field information of the nuclear power plant to be prepared with the historical quality defect report information relates to the same power plant (belongs to the same machine type), the equipment code field information of the work order task information to be prepared does not satisfy the equipment code rule of the power plant, the equipment code field information of the equipment code rule of the power plant is not satisfied in the title field information of the work order to be prepared, and the equipment name field information of the work order task information to be prepared can be matched with the equipment name field information of the historical quality defect report information, the nuclear power plant quality defect report information accurate matching model matches the input work order task information to be prepared with the historical quality defect report information through the following steps, obtaining a total matching score S of the historical quality defect report information 4 ：
1. Performing semantic similarity matching on the 'equipment name' field information of the to-be-prepared work order task information and the 'equipment name' field information of the historical quality defect report information, and calculating to obtain a semantic similarity matching score W of the historical quality defect report information 22 (ii) a Historical quality defect report information semantic similarity matching score W 22 The highest value is u;
2. semantic similarity matching is carried out on 'work order title' field information of the work order task information to be prepared and 'QDR subject' field information of the historical quality defect report information, and semantic similarity matching score W of the historical quality defect report information is obtained through calculation 23 (ii) a Historical quality defect report information semantic similarity matching score W 23 The highest value is v;
3. calculating a historical quality defect report information matching total score S 4 Historical quality defect report information semantic similarity matching score W 22 + historical quality defect report information semantic similarity matching score W 23 ；
u+v＝1。
Further, when the matched field information of the nuclear power plant to be prepared with the work order task information is the same as the field information of the historical quality defect report information, wherein the field information of the nuclear power plant to be prepared with the historical quality defect report information relates to the same power plant (belongs to the same machine type), the equipment code field information of the work order task information to be prepared does not satisfy the equipment code rule of the power plant, the equipment code field information of the equipment code rule of the power plant is not satisfied in the title field information of the work order, and the equipment name field information of the work order task information to be prepared and the equipment name field information of the historical quality defect report information cannot be matched, the nuclear power plant quality defect report information accurate matching model matches the input work order task information to be prepared and the historical quality defect report information through the following steps, obtaining a total matching score S of the historical quality defect report information 4 ：
1. Semantic similarity matching is carried out on 'work order title' field information of the work order task information to be prepared and 'QDR subject' field information of the historical quality defect report information, and semantic similarity matching score W of the historical quality defect report information is obtained through calculation 24 (ii) a Historical quality defect report information semantic similarity matching score W 24 The highest value is w;
2. calculating a historical quality defect report information matching total score S 4 Historical quality defect report information semantic similarity matching score W 24 ；
w＝1。
Further, when the matched field information of the nuclear power plant of the to-be-prepared work order task information is the same as the field information of the historical quality defect report information (belonging to the same machine type) related to the power plant and is an AP1000 machine type, the accurate matching model of the nuclear power plant quality defect report information extracts the field information of the equipment code for matching the to-be-prepared work order task information based on the following equipment coding rules:
a "set number" + "-" + "location code (system code)" + "-" + "device type code" + "-" + "serial number.
Further, referring to fig. 1, when the matched field information of the nuclear power plant to be prepared work order task information is the same as the field information of the power plant related to the historical quality defect report information (belonging to the same model) and is in the model of AP1000, the accurate matching model of the nuclear power plant quality defect report information matches the input work order task information to be prepared and the historical quality defect report information based on the following equipment business logic rule 5 and semantic similarity rule 5 to obtain a total matching score S of the historical quality defect report information 5 ：
1. When the 'equipment code' field information for matching the to-be-prepared work order task information can be extracted, the 'equipment code' field information for matching the to-be-prepared work order task information is extracted; matching the field information of the equipment codes for matching the work order task information to be prepared with the field information of the equipment codes of the historical quality defect report information, and calculating to obtain a service logic matching score of the historical quality defect report information equipment;
2. when the field information of the equipment name of the to-be-prepared work order task information can be matched with the field information of the equipment name of the historical quality defect report information, semantic similarity matching is carried out on the field information of the equipment name of the to-be-prepared work order task information and the field information of the equipment name of the historical quality defect report information, and a semantic similarity matching score of the historical quality defect report information is obtained through calculation;
3. semantic similarity matching is carried out on 'work order title' field information of the work order task information to be prepared and 'QDR theme' field information of the historical quality defect report information, and semantic similarity matching scores of the historical quality defect report information are obtained through calculation;
4. calculating a historical quality defect report information matching total score S 5 Matching score of step (1) plus matching score of step (3), or matching score of step (2) plus matching score of step (3), or matching score of step (3).
Further, when the matched 'nuclear power plant' field information of the to-be-prepared work order task information is the same as the 'related power plant' field information of the historical quality defect report information (belonging to the same machine type) and is in the 'AP 1000' machine type, and the 'equipment coding' field information of the to-be-prepared work order task information meets the equipment coding rule of the power plant, the accurate matching model of the nuclear power plant quality defect report information matches the input to-be-prepared work order task information and the historical quality defect report information through the following steps to obtain the total matching score S of the historical quality defect report information 5 ：
1. Extracting 'equipment code' field information of the to-be-prepared work order task information as 'equipment code' field information for matching the to-be-prepared work order task information; matching the 'equipment code' field information for matching the to-be-prepared work order task information with the 'equipment code' field information of the historical quality defect report information as follows, and calculating to obtain a historical quality defect report information equipment service logic matching score W 25 ：
When the 'equipment code' field information for matching the prepared work order task information and the 'equipment code' field information of the historical quality defect report information are all the same (same equipment), calculating the service logic matching score W of the historical quality defect report information equipment 25 ＝x 1 ；
Except that the field information of the unit number is different in the field information of the equipment code for matching the job order task information and the field information of the equipment code of the historical quality defect report information, and the other field information are all the same, calculating the service logic matching score W of the historical quality defect report information equipment 25 ＝x 2 ；
For matching job order information to be preparedExcept that the 'unit number' field information and the 'serial number' field information in the 'equipment code' field information and the 'equipment code' field information in the historical quality defect report information are different, and other field information are all the same, calculating the historical quality defect report information equipment service logic matching score W 25 ＝x 3 ；
When the conditions are not met, calculating the service logic matching score W of the historical quality defect report information equipment 25 ＝0；
2. Semantic similarity matching is carried out on 'work order title' field information of the work order task information to be prepared and 'QDR subject' field information of the historical quality defect report information, and semantic similarity matching score W of the historical quality defect report information is obtained through calculation 26 (ii) a Historical quality defect report information semantic similarity matching score W 26 The highest value is y;
3. calculating a historical quality defect report information matching total score S 5 Reporting information device business logic match score W ═ historical quality defects 25 + historical quality defect report information semantic similarity matching score W 26 ；
x 1 ＞x 2 ＞x 3 ＞0，x 1 +y＝1。
Further, when the matched 'nuclear power plant' field information of the to-be-prepared work order task information is the same as the 'related power plant' field information of the historical quality defect report information (belongs to the same machine type) and is in the 'AP 1000' machine type, the 'equipment code' field information of the to-be-prepared work order task information does not meet the equipment code rule of the power plant, and the 'equipment code' field information meeting the equipment code rule of the power plant is contained in the 'work order title' field information of the to-be-prepared work order task information, the nuclear power plant quality defect report information accurate matching model matches the input to-be-prepared work order task information with the historical quality defect report information to obtain a historical quality defect report information matching total score S 5 ：
1. Extracting 'equipment code' in 'work order title' field information of work order task information to be prepared "The field information is used as 'equipment coding' field information for matching the to-be-prepared work order task information; matching the 'equipment code' field information for matching the to-be-prepared work order task information with the 'equipment code' field information of the historical quality defect report information as follows, and calculating to obtain a historical quality defect report information equipment service logic matching score W 27 ：
When the 'equipment code' field information for matching the prepared work order task information and the 'equipment code' field information of the historical quality defect report information are all the same (same equipment), calculating the service logic matching score W of the historical quality defect report information equipment 27 ＝z 1 ；
Except that the field information of the unit number is different in the field information of the equipment code for matching the job order task information and the field information of the equipment code of the historical quality defect report information, and the other field information are all the same, calculating the service logic matching score W of the historical quality defect report information equipment 27 ＝z 2 ；
Except that the field information of the unit number and the serial number is different in the field information of the equipment code for matching the to-be-prepared work order task information and the field information of the equipment code of the historical quality defect report information, and the other field information are all the same, calculating the service logic matching score W of the historical quality defect report information equipment 27 ＝z 3 ；
When the conditions are not met, calculating the service logic matching score W of the historical quality defect report information equipment 27 ＝0；
2. Semantic similarity matching is carried out on 'work order title' field information of the work order task information to be prepared and 'QDR subject' field information of the historical quality defect report information, and semantic similarity matching score W of the historical quality defect report information is obtained through calculation 28 (ii) a Historical quality defect report information semantic similarity matching score W 28 The highest value is aa;
3. calculating a historical quality defect report information matching total score S 5 Reporting information device business logic match score as historical quality defectW 27 + historical quality defect report information semantic similarity matching score W 28 ；
z 1 ＞z 2 ＞z 3 ＞0，z 1 +aa＝1。
Further, when the matched field information of the nuclear power plant to be prepared of the work order task information is the same as the field information of the historical quality defect report information, wherein the field information of the nuclear power plant to be prepared of the work order task information is related to the power plant (belongs to the same machine type), the field information of the equipment code of the work order task information to be prepared does not satisfy the equipment code rule of the power plant, the field information of the equipment code of the work order header of the work order task information to be prepared does not satisfy the equipment code rule of the power plant, and the field information of the equipment name of the work order task information to be prepared can be matched with the field information of the equipment name of the historical quality defect report information, the accurate matching model of the nuclear power plant quality defect report information matches the input work order task information to be prepared with the historical quality defect report information through the following steps, obtaining a total matching score S of the historical quality defect report information 5 ：
1. Performing semantic similarity matching on the 'equipment name' field information of the to-be-prepared work order task information and the 'equipment name' field information of the historical quality defect report information, and calculating to obtain a semantic similarity matching score W of the historical quality defect report information 29 (ii) a Historical quality defect report information semantic similarity matching score W 29 The highest value ab;
2. semantic similarity matching is carried out on 'work order title' field information of the work order task information to be prepared and 'QDR subject' field information of the historical quality defect report information, and semantic similarity matching score W of the historical quality defect report information is obtained through calculation 30 (ii) a Historical quality defect report information semantic similarity matching score W 30 The highest value is ac;
3. calculating a historical quality defect report information matching total score S 5 Historical quality defect report information semantic similarity matching score W 29 + historical quality defect report information semantic similarity matchingScore value W 30 ；
ab+ac＝1。
Further, when the matched field information of the nuclear power plant to be prepared of the work order task information is the same as the field information of the historical quality defect report information, wherein the field information of the nuclear power plant to be prepared of the work order task information is related to the power plant (belongs to the same machine type), the field information of the equipment code of the work order task information to be prepared does not satisfy the equipment code rule of the power plant, the field information of the equipment code of the work order header of the work order task information to be prepared does not satisfy the equipment code rule of the power plant, and the field information of the equipment name of the work order task information to be prepared is not matched with the field information of the equipment name of the historical quality defect report information, the accurate matching model of the nuclear power plant quality defect report information matches the input work order task information to be prepared with the historical quality defect report information through the following steps, obtaining a total matching score S of the historical quality defect report information 5 ：
1. Semantic similarity matching is carried out on 'work order title' field information of the work order task information to be prepared and 'QDR subject' field information of the historical quality defect report information, and semantic similarity matching score W of the historical quality defect report information is obtained through calculation 31 (ii) a Historical quality defect report information semantic similarity matching score W 31 The highest value is ad;
2. calculating a historical quality defect report information matching total score S 5 Historical quality defect report information semantic similarity matching score W 31 ；
ad＝1。
Further, referring to fig. 1, when the field information of the "nuclear power plant" of the matched to-be-prepared work order task information is different from the field information of the "power related plant" of the historical quality defect report information (not belonging to the same model), and the field information of the "nuclear power plant" of the to-be-prepared work order task information belongs to the model "CANDU 6", "CNP-300", "AP 1000", or "VVER", when the matched to the historical quality defect report information of other models, the matched to-be-prepared work order task information is equivalent to the field information of the "equipment code" of the historical quality defect report informationThe accurate matching model of the nuclear power plant quality defect report information is different from the 'equipment coding' field information of the input to-be-prepared work order task information, the input to-be-prepared work order task information is matched with the historical quality defect report information based on the following semantic similarity rule 6, and the matching total score S of the historical quality defect report information is obtained 6 ：
Performing semantic similarity matching on 'work order title' and 'equipment name' field information of the work order task information to be prepared and 'QDR subject' and 'equipment name' field information of the historical quality defect report information, and calculating to obtain a semantic similarity matching score W of the historical quality defect report information 32 (ii) a Historical quality defect report information semantic similarity matching score W 32 The highest value is ae;
calculating a historical quality defect report information matching total score S 6 Historical quality defect report information semantic similarity matching score W 32 ；
ae＝1。
Further, referring to fig. 1, when the matched field information of the nuclear power plant to be prepared for the job order task information is different from the field information of the power plant related to the historical quality defect report information (not belonging to the same model), and the field information of the nuclear power plant to be prepared for the job order task information belongs to the models of "CNP-600", "CNP-1000", "HPR-1000" and "CPR-1000", when the historical quality defect report information of the models of "CANDU 6", "CNP-300", "AP 1000" and "VVER" is matched, the accurate matching model of the nuclear power plant quality defect report information matches the input job order task information to be prepared and the historical quality defect report information based on the following semantic similarity rule 7 to obtain a historical quality defect report information matching total score S 7 ：
Performing semantic similarity matching on 'work order title' and 'equipment name' field information of the work order task information to be prepared and 'QDR subject' and 'equipment name' field information of the historical quality defect report information, and calculating to obtain a semantic similarity matching score W of the historical quality defect report information 33 (ii) a Historical quality defect reportNotice information semantic similarity matching score W 33 The highest value is af;
calculating a historical quality defect report information matching total score S 7 Historical quality defect report information semantic similarity matching score W 33 ；
af＝1。
Further, referring to fig. 1, when the matched field information of the nuclear power plant to be prepared of the work order task information is different from the field information of the historical quality defect report information, which relates to the power plant (not belonging to the same model), and the field information of the nuclear power plant to be prepared of the work order task information belongs to the model of "CNP-600", "CNP-1000", "HPR-1000" or "CPR-1000", and the matched model of the historical quality defect report information is matched with the model of the "CNP-600", "CNP-1000", "HPR-1000" or "CPR-1000" and is different from the model of the work order task information to be prepared, the accurate matching model of the nuclear power plant quality defect report information matches the input work order task information to be prepared with the historical quality defect report information based on the following equipment service logic rule 6 and semantic similarity rule 8, obtaining a total matching score S of the historical quality defect report information 8 ：
1. When the 'equipment code' field information for matching the to-be-prepared work order task information can be extracted, the 'equipment code' field information for matching the to-be-prepared work order task information is extracted; matching the field information of the equipment codes for matching the work order task information to be prepared with the field information of the equipment codes of the historical quality defect report information, and calculating to obtain a service logic matching score of the historical quality defect report information equipment; performing semantic similarity matching on 'work order title' field information of the work order task information to be prepared and 'QDR topic' field information of the historical quality defect report information, and calculating to obtain a semantic similarity matching score of the historical quality defect report information; calculating a historical quality defect report information matching total score S 8 The historical quality defect report information equipment service logic matching score + the historical quality defect report information semantic similarity matching score;
2. equipment editing for matching unable to extract work order information to be preparedWhen the field information is coded, carrying out semantic similarity matching on the field information of the 'work order title' and the 'equipment name' of the work order task information to be prepared and the 'QDR subject' and the 'equipment name' field information of the historical quality defect report information, and calculating to obtain a semantic similarity matching score of the historical quality defect report information; calculating a historical quality defect report information matching total score S 8 Reporting information semantic similarity matching score as historical quality defect.
Further, when the matched 'nuclear power plant' field information of the to-be-prepared work order task information is different from the 'power plant related' field information of the historical quality defect report information (does not belong to the same machine type), the 'nuclear power plant' field information of the to-be-prepared work order task information belongs to the 'CNP-600', 'CNP-1000', 'HPR-1000' or 'CPR-1000' machine type, the matched 'CNP-600', 'CNP-1000', 'HPR-1000' or 'CPR-1000' machine type is different from the machine type of the to-be-prepared work order task information, and the 'equipment code' field information of the to-be-prepared work order task information meets the equipment coding rule of the power plant, the nuclear power plant quality defect report information accurate matching model matches the input to-be-prepared work order task information with the historical quality defect report information through the following steps, obtaining a total matching score S of the historical quality defect report information 8 ：
1. Extracting 'equipment code' field information of the to-be-prepared work order task information as 'equipment code' field information for matching the to-be-prepared work order task information; matching the 'equipment code' field information for matching the to-be-prepared work order task information with the 'equipment code' field information of the historical quality defect report information as follows, and calculating to obtain a historical quality defect report information equipment service logic matching score W 34 ：
When the 'equipment code' field information for matching the prepared work order task information and the 'equipment code' field information of the historical quality defect report information are all the same (same equipment), calculating the service logic matching score W of the historical quality defect report information equipment 34 ＝(ag) 1 ；
Except that the field information of the unit number is different in the field information of the equipment code for matching the job order task information and the field information of the equipment code of the historical quality defect report information, and the other field information are all the same, calculating the service logic matching score W of the historical quality defect report information equipment 34 ＝(ag) 2 ；
Except that the 'unit number' and the intermediate digital coding field information are different in the 'equipment coding' field information for matching the to-be-prepared work order task information and the 'equipment coding' field information of the historical quality defect report information, and the other field information are all the same, calculating the historical quality defect report information equipment service logic matching score W 34 ＝(ag) 3 ；
When the conditions are not met, calculating the service logic matching score W of the historical quality defect report information equipment 34 ＝0；
2. Semantic similarity matching is carried out on 'work order title' field information of the work order task information to be prepared and 'QDR subject' field information of the historical quality defect report information, and semantic similarity matching score W of the historical quality defect report information is obtained through calculation 35 (ii) a Historical quality defect report information semantic similarity matching score W 35 The highest value is ah;
3. calculating a historical quality defect report information matching total score S 8 Reporting information device business logic match score W ═ historical quality defects 34 + History quality defect report information semantic similarity match score W 35 ；
(ag) 1 ＞(ag) 2 ＞(ag) 3 ＞0，(ag) 1 +ah＝1。
Further, when the matched field information of the nuclear power plant to be prepared with the work order task information is different from the field information of the historical quality defect report information, which relates to the power plant (not belonging to the same model), the field information of the nuclear power plant to be prepared with the work order task information belongs to the models of CNP-600, CNP-1000, HPR-1000 or CPR-1000, and the models of CNP-600, CNP-1000, HPR-1000 or CPR-1000 are matchedHistorical quality defect report information different from the machine type of the to-be-prepared work order task information, when the equipment code field information of the to-be-prepared work order task information does not meet the equipment code rule of the power plant, and the equipment code field information meeting the equipment code rule of the power plant exists in the work order title field information of the to-be-prepared work order task information, matching the input to-be-prepared work order task information and the historical quality defect report information to obtain a historical quality defect report information matching total score S 8 ：
1. Extracting 'equipment code' field information in 'work order title' field information of the work order task information to be prepared, and using the 'equipment code' field information as the matching 'equipment code' field information of the work order task information to be prepared; matching the 'equipment code' field information for matching the to-be-prepared work order task information with the 'equipment code' field information of the historical quality defect report information as follows, and calculating to obtain a historical quality defect report information equipment service logic matching score W 36 ：
When the 'equipment code' field information for matching the prepared work order task information and the 'equipment code' field information of the historical quality defect report information are all the same (same equipment), calculating the service logic matching score W of the historical quality defect report information equipment 36 ＝(ai) 1 ；
Except that the field information of the unit number is different in the field information of the equipment code for matching the job order task information and the field information of the equipment code of the historical quality defect report information, and the other field information are all the same, calculating the service logic matching score W of the historical quality defect report information equipment 36 ＝(ai) 2 ；
Except that the 'unit number' and the intermediate digital coding field information are different in the 'equipment coding' field information for matching the to-be-prepared work order task information and the 'equipment coding' field information of the historical quality defect report information, and the other field information are all the same, calculating the historical quality defect report information equipment service logic matching score W 36 ＝(ai) 3 ；
When the conditions are not met, calculating the service logic matching score W of the historical quality defect report information equipment 36 ＝0；
2. Semantic similarity matching is carried out on 'work order title' field information of the work order task information to be prepared and 'QDR subject' field information of the historical quality defect report information, and semantic similarity matching score W of the historical quality defect report information is obtained through calculation 37 (ii) a Historical quality defect report information semantic similarity matching score W 37 The highest value is aj;
3. calculating a historical quality defect report information matching total score S 8 Reporting information device business logic match score W ═ historical quality defects 36 + historical quality defect report information semantic similarity matching score W 37 ；
(ai) 1 ＞(ai) 2 ＞(ai) 3 ＞0，(ai) 1 +aj＝1。
Further, when the matched field information of the nuclear power plant of the to-be-prepared work order task information is different from the field information of the historical quality defect report information, which relates to the power plant (not belonging to the same model), the field information of the nuclear power plant of the to-be-prepared work order task information belongs to the models of CNP-600, CNP-1000, HPR-1000 and CPR-1000, the matched models of CNP-600, CNP-1000, HPR-1000 and CPR-1000 are different from the model of the to-be-prepared work order task information, the field information of the to-be-prepared work order task information does not satisfy the equipment coding rule of the power plant, and the field information of the work order title of the to-be-prepared work order task information does not have the field information of the equipment coding rule of the power plant, the accurate matching model of the quality defect report information of the nuclear power plant matches the input work order task information to be prepared with the historical quality defect report information to obtain a historical quality defect report information matching total score S 8 ：
1. The 'work order title' and 'equipment name' field information of the work order task information to be preparedPerforming semantic similarity matching on the information and the 'QDR subject' and 'equipment name' field information of the historical quality defect report information, and calculating to obtain a semantic similarity matching score W of the historical quality defect report information 38 (ii) a Historical quality defect report information semantic similarity matching score W 38 The highest value is ak;
2. calculating a historical quality defect report information matching total score S 8 Historical quality defect report information semantic similarity matching score W 38 ；
ak＝1。
The work order task is a special word in a nuclear power safety production management system, and is a sub task split under a work order due to professional limitation, safety measure limitation and the like. The work order task is a core object in the work control business process, and each work needs to create the work order task (except simple maintenance). The work order task information in the nuclear power safety production management system comprises task summaries, work instructions, resource requirements, documents, work licenses, safety measure requirements, spare parts, personnel, planning time, cooperative work, risk analysis, safety measures and the like.
The quality defect report is an equipment quality abnormity report aiming at the condition that the quality of an unexpected item in the maintenance process does not meet the original design requirement, and a corrective measure must be made in time to repair the equipment or the item so that the quality of the equipment or the item meets the design requirement, and the quality defect report is a quality management mode integrating corrective measure/scheme management.
The matching historical quality defect report information is also referred to as queried quality defect report information.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims (11)

1. A nuclear power plant work order task and quality defect report information accurate matching method is characterized by comprising the following steps:
step 1, obtaining historical quality defect report information to form a quality defect report database of a nuclear power plant;
step 2, taking the to-be-prepared work order task information as input information, and matching the to-be-prepared work order task information with historical quality defect report information in a nuclear power plant quality defect report database through a nuclear power plant quality defect report information accurate matching model to obtain a historical quality defect report information matching total score S;
step 3, setting S to be more than or equal to the set W Limiting the score Into a set S of historical quality defect report information Set of scores ；
Step 4, pushing the count set S from high to low Set of scores Historical quality defect report information.
2. The method for accurately matching nuclear power plant work order tasks with quality defect report information according to claim 1, wherein the input information of the work order task information to be prepared comprises field information of 'nuclear power plant', 'unit', 'equipment code', 'equipment name' and 'work order title'; the matching information of the historical quality defect report information comprises field information of 'relating to a power plant', 'QDR coding', 'QDR theme', 'unit', 'equipment coding' and 'equipment name'; the pushed historical quality defect report information display information comprises field information of 'relating to power plant', 'QDR code', 'QDR theme', 'unit', 'equipment code' and 'equipment name'.
3. The method for accurately matching the nuclear power plant work order task with the quality defect report information as claimed in claim 2, wherein the nuclear power plant quality defect report information accurate matching model matches the input work order task information to be prepared with the historical quality defect report information based on an equipment service logic rule and a semantic similarity rule to obtain a historical quality defect report information matching total score S.
4. The method for accurately matching the nuclear power plant work order task and the quality defect report information according to claim 3, wherein when the matched field information of the nuclear power plant of the to-be-prepared work order task information is the same as the field information of the power plant related to the historical quality defect report information, and the matched field information of the to-be-prepared work order task information and the historical quality defect report information are both of the models of "CNP-600", "CNP-1000", "HPR-1000" or "CPR-1000", the nuclear power plant quality defect report information accurate matching model matches the input to-be-prepared work order task information and the historical quality defect report information based on the following equipment business logic rule and semantic similarity rule to obtain a historical quality defect report information matching total score S:
step 1, extracting 'equipment code' field information for matching the work order task information to be prepared when the 'equipment code' field information for matching the work order task information to be prepared can be extracted; matching the 'equipment code' field information for matching the to-be-prepared work order task information with the 'equipment code' field information of the historical quality defect report information, and calculating to obtain a historical quality defect report information equipment service logic matching score;
step 2, the field information of the equipment code for matching the to-be-prepared work order task information cannot be extracted, when the field information of the equipment name of the to-be-prepared work order task information can be matched with the field information of the equipment name of the historical quality defect report information, semantic similarity matching is carried out on the field information of the equipment name of the to-be-prepared work order task information and the field information of the equipment name of the historical quality defect report information, and a semantic similarity matching score of the historical quality defect report information is obtained through calculation;
step 3, performing semantic similarity matching on 'work order title' field information of the work order task information to be prepared and 'QDR subject' field information of the historical quality defect report information, and calculating to obtain a semantic similarity matching score of the historical quality defect report information;
and 4, calculating the total matching score S of the historical quality defect report information, namely the matching score of the step (1) and the matching score of the step (3), or the matching score of the step (2) and the matching score of the step (3), or the matching score of the step (3).
5. The method for accurately matching the nuclear power plant work order task and the quality defect report information according to claim 3, wherein when the matched field information of the nuclear power plant of the to-be-prepared work order task information is the same as the field information of the historical quality defect report information, namely the field information of the to-be-prepared work order and the field information of the historical quality defect report information are both of a model of 'CNP-300', the accurate matching model of the nuclear power plant quality defect report information matches the input to-be-prepared work order task information and the historical quality defect report information based on the following equipment service logic rules and semantic similarity rules to obtain a historical quality defect report information matching total score S:
step 1, extracting 'equipment code' field information in 'work order title' field information of work order task information to be prepared as 'equipment code' field information for matching the work order task information to be prepared; matching the 'equipment code' field information for matching the to-be-prepared work order task information with the 'equipment code' field information of the historical quality defect report information, and calculating to obtain a historical quality defect report information equipment service logic matching score W 8 ：
Step 2, when the 'equipment code' field information for matching the to-be-prepared work order task information cannot be matched with the 'equipment code' field information of the historical quality defect report information, performing semantic similarity matching on the 'equipment name' field information of the to-be-prepared work order task information and the 'equipment name' field information of the historical quality defect report information, and calculating to obtain a semantic similarity matching score W of the historical quality defect report information 9 (ii) a Historical quality defect report information semantic similarity matching score W 9 The highest score is h;
step 3, carrying out semantic similarity matching on 'work order title' field information of the work order task information to be prepared and 'QDR subject' field information of the historical quality defect report information, and calculating to obtain semantic similarity matching of the historical quality defect report informationDistribution value W 10 (ii) a Historical quality defect report information semantic similarity matching score W 10 The highest score is i;
step 4, calculating the total matching score S of the historical quality defect report information 2 Reporting information device business logic match score W ═ historical quality defects 8 + historical quality defect report information semantic similarity matching score W 10 Or the historical quality defect report information semantic similarity matching score W 9 + historical quality defect report information semantic similarity matching score W 10 ；h+i＝1。
6. The method for accurately matching the nuclear power plant work order task and the quality defect report information according to claim 3, wherein when the matched field information of the nuclear power plant of the to-be-prepared work order task information is the same as the field information of the historical quality defect report information, namely the field information of the related power plant, and the field information of the related power plant are both models of CANDU6, the accurate matching model of the nuclear power plant quality defect report information matches the input to-be-prepared work order task information and the historical quality defect report information based on the following equipment service logic rule and semantic similarity rule to obtain the historical quality defect report information matching total score S:
step 1, extracting 'equipment code' field information for matching the work order task information to be prepared when the 'equipment code' field information for matching the work order task information to be prepared can be extracted; matching the 'equipment code' field information for matching the to-be-prepared work order task information with the 'equipment code' field information of the historical quality defect report information, and calculating to obtain a historical quality defect report information equipment service logic matching score;
step 2, the field information of the equipment code for matching the to-be-prepared work order task information cannot be extracted, when the field information of the equipment name of the to-be-prepared work order task information can be matched with the field information of the equipment name of the historical quality defect report information, semantic similarity matching is carried out on the field information of the equipment name of the to-be-prepared work order task information and the field information of the equipment name of the historical quality defect report information, and a semantic similarity matching score of the historical quality defect report information is obtained through calculation;
step 3, performing semantic similarity matching on 'work order title' field information of the work order task information to be prepared and 'QDR subject' field information of the historical quality defect report information, and calculating to obtain a semantic similarity matching score of the historical quality defect report information;
and 4, calculating the total matching score S of the historical quality defect report information, namely the matching score of the step (1) and the matching score of the step (3), or the matching score of the step (2) and the matching score of the step (3), or the matching score of the step (3).
7. The method for accurately matching the nuclear power plant work order task and the quality defect report information according to claim 3, wherein when the matched field information of the nuclear power plant of the to-be-prepared work order task information is the same as the field information of the historical quality defect report information, namely the related to power plant, and the field information of the to-be-prepared work order task information and the historical quality defect report information are both of a VVER type, the accurate matching model of the nuclear power plant quality defect report information matches the input to-be-prepared work order task information and the historical quality defect report information based on the following equipment business logic rule and semantic similarity rule to obtain a historical quality defect report information matching total score S:
step 1, extracting 'equipment code' field information for matching the work order task information to be prepared when the 'equipment code' field information for matching the work order task information to be prepared can be extracted; matching the 'equipment code' field information for matching the to-be-prepared work order task information with the 'equipment code' field information of the historical quality defect report information, and calculating to obtain a historical quality defect report information equipment service logic matching score;
step 2, the field information of the equipment code for matching the to-be-prepared work order task information cannot be extracted, when the field information of the equipment name of the to-be-prepared work order task information can be matched with the field information of the equipment name of the historical quality defect report information, semantic similarity matching is carried out on the field information of the equipment name of the to-be-prepared work order task information and the field information of the equipment name of the historical quality defect report information, and a semantic similarity matching score of the historical quality defect report information is obtained through calculation;
step 3, performing semantic similarity matching on 'work order title' field information of the work order task information to be prepared and 'QDR subject' field information of the historical quality defect report information, and calculating to obtain a semantic similarity matching score of the historical quality defect report information;
and 4, calculating the total matching score S of the historical quality defect report information, namely the matching score of the step (1) and the matching score of the step (3), or the matching score of the step (2) and the matching score of the step (3), or the matching score of the step (3).
8. The method for accurately matching the nuclear power plant work order task and the quality defect report information according to claim 3, wherein when the matched field information of the nuclear power plant of the to-be-prepared work order task information is the same as the field information of the historical quality defect report information, namely the field information related to the power plant, and the field information is the model of AP1000, the accurate matching model of the nuclear power plant quality defect report information matches the input to-be-prepared work order task information and the historical quality defect report information based on the following equipment business logic rules and semantic similarity rules to obtain the historical quality defect report information matching total score S:
step 1, extracting 'equipment code' field information for matching the work order task information to be prepared when the 'equipment code' field information for matching the work order task information to be prepared can be extracted; matching the 'equipment code' field information for matching the to-be-prepared work order task information with the 'equipment code' field information of the historical quality defect report information, and calculating to obtain a historical quality defect report information equipment service logic matching score;
step 2, the field information of the equipment code for matching the to-be-prepared work order task information cannot be extracted, when the field information of the equipment name of the to-be-prepared work order task information can be matched with the field information of the equipment name of the historical quality defect report information, semantic similarity matching is carried out on the field information of the equipment name of the to-be-prepared work order task information and the field information of the equipment name of the historical quality defect report information, and a semantic similarity matching score of the historical quality defect report information is obtained through calculation;
step 3, performing semantic similarity matching on 'work order title' field information of the work order task information to be prepared and 'QDR subject' field information of the historical quality defect report information, and calculating to obtain a semantic similarity matching score of the historical quality defect report information;
and 4, calculating the total matching score S of the historical quality defect report information, namely the matching score of the step (1) and the matching score of the step (3), or the matching score of the step (2) and the matching score of the step (3), or the matching score of the step (3).
9. The method for accurately matching the nuclear power plant work order task and the quality defect report information according to claim 3, wherein when the matched field information of the nuclear power plant of the to-be-prepared work order task information is different from the field information of the power plant related to the historical quality defect report information, and the field information of the nuclear power plant of the to-be-prepared work order task information belongs to the models of CANDU6, CNP-300, AP1000 and VVER, when the historical quality defect report information of other models is matched, the nuclear power plant quality defect report information accurate matching model matches the input to-be-prepared work order task information and the historical quality defect report information based on the following semantic similarity rules to obtain a historical quality defect report information matching total score S:
performing semantic similarity matching on 'work order title' and 'equipment name' field information of the work order task information to be prepared and 'QDR subject' and 'equipment name' field information of the historical quality defect report information, and calculating to obtain a semantic similarity matching score W of the historical quality defect report information 32 (ii) a Historical quality defect report information semantic similarity matching score W 32 The highest value is ae;
calculating the total matching score S of the historical quality defect report information, namely the semantic similarity matching score W of the historical quality defect report information 32 ；
ae＝1。
10. The method for accurately matching nuclear power plant work order tasks with quality defect report information as claimed in claim 3, the method is characterized in that when the matched field information of the nuclear power plant of the to-be-prepared work order task information is different from the field information of the historical quality defect report information, and the field information of the nuclear power plant of the to-be-prepared work order task information belongs to the model of CNP-600, CNP-1000, HPR-1000 or CPR-1000, when historical quality defect report information for "CANDU 6", "CNP-300", "AP 1000" or "VVER" models is matched, the accurate matching model of the nuclear power plant quality defect report information matches input to-be-prepared work order task information with historical quality defect report information based on the following semantic similarity rules to obtain a historical quality defect report information matching total score S:
performing semantic similarity matching on 'work order title' and 'equipment name' field information of the work order task information to be prepared and 'QDR subject' and 'equipment name' field information of the historical quality defect report information, and calculating to obtain a semantic similarity matching score W of the historical quality defect report information 33 (ii) a Historical quality defect report information semantic similarity matching score W 33 The highest value is af;
calculating the total matching score S of the historical quality defect report information, namely the semantic similarity matching score W of the historical quality defect report information 33 ；
af＝1。
11. The method for accurately matching the nuclear power plant work order task with the quality defect report information according to claim 3, wherein when the matched field information of the nuclear power plant of the to-be-prepared work order task information is different from the field information of the historical quality defect report information, and the field information of the nuclear power plant of the to-be-prepared work order task information belongs to the model of CNP-600, CNP-1000, HPR-1000 or CPR-1000, and the model of CNP-600, CNP-1000, HPR-1000 or CPR-1000 is matched and the historical quality defect report information is different from the model of the to-be-prepared work order task information, the nuclear power plant quality defect report information accurate matching model matches the input to-be-prepared work order task information with the historical quality defect report information based on the following equipment service logic rules and semantic similarity rules, obtaining a total matching score S of the historical quality defect report information:
step 1, extracting 'equipment code' field information for matching the work order task information to be prepared when the 'equipment code' field information for matching the work order task information to be prepared can be extracted; matching the 'equipment code' field information for matching the to-be-prepared work order task information with the 'equipment code' field information of the historical quality defect report information, and calculating to obtain a historical quality defect report information equipment service logic matching score; performing semantic similarity matching on 'work order title' field information of the work order task information to be prepared and 'QDR topic' field information of the historical quality defect report information, and calculating to obtain a semantic similarity matching score of the historical quality defect report information; calculating a historical quality defect report information matching total score S which is a historical quality defect report information equipment service logic matching score plus a historical quality defect report information semantic similarity matching score;
step 2, when the field information of the 'equipment code' for matching the work order task information to be prepared cannot be extracted, semantic similarity matching is carried out on the field information of the 'work order title' and the 'equipment name' of the work order task information to be prepared and the field information of the 'QDR theme' and the 'equipment name' of the historical quality defect report information, and a semantic similarity matching score of the historical quality defect report information is obtained through calculation; and calculating the historical quality defect report information matching total score S which is the semantic similarity matching score of the historical quality defect report information.
CN202210657842.9A 2022-06-10 2022-06-10 Accurate matching method for nuclear power plant work order tasks and quality defect report information Pending CN115080687A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210657842.9A CN115080687A (en) 2022-06-10 2022-06-10 Accurate matching method for nuclear power plant work order tasks and quality defect report information

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210657842.9A CN115080687A (en) 2022-06-10 2022-06-10 Accurate matching method for nuclear power plant work order tasks and quality defect report information

Publications (1)

Publication Number Publication Date
CN115080687A true CN115080687A (en) 2022-09-20

Family

ID=83251256

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210657842.9A Pending CN115080687A (en) 2022-06-10 2022-06-10 Accurate matching method for nuclear power plant work order tasks and quality defect report information

Country Status (1)

Country Link
CN (1) CN115080687A (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060235741A1 (en) * 2005-04-18 2006-10-19 Dataforensics, Llc Systems and methods for monitoring and reporting
CN113064924A (en) * 2021-03-12 2021-07-02 中核核电运行管理有限公司 Nuclear power big data experience retrieval and pushing method
CN113887936A (en) * 2021-09-29 2022-01-04 中核核电运行管理有限公司 Non-work order task management system and method based on digitization
CN114462736A (en) * 2020-11-09 2022-05-10 中核核电运行管理有限公司 Experience feedback intelligent recommendation method for nuclear power plant radiation work license application
CN114462399A (en) * 2020-11-09 2022-05-10 中核核电运行管理有限公司 Accurate matching method for quality defect report and state report of nuclear power plant

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060235741A1 (en) * 2005-04-18 2006-10-19 Dataforensics, Llc Systems and methods for monitoring and reporting
CN114462736A (en) * 2020-11-09 2022-05-10 中核核电运行管理有限公司 Experience feedback intelligent recommendation method for nuclear power plant radiation work license application
CN114462399A (en) * 2020-11-09 2022-05-10 中核核电运行管理有限公司 Accurate matching method for quality defect report and state report of nuclear power plant
CN113064924A (en) * 2021-03-12 2021-07-02 中核核电运行管理有限公司 Nuclear power big data experience retrieval and pushing method
CN113887936A (en) * 2021-09-29 2022-01-04 中核核电运行管理有限公司 Non-work order task management system and method based on digitization

Similar Documents

Publication Publication Date Title
WO2003012685A2 (en) A data quality system
CN111899090B (en) Enterprise associated risk early warning method and system
CN112000771B (en) Judicial public service-oriented sentence pair intelligent semantic matching method and device
CN109240258A (en) Vehicle failure intelligent auxiliary diagnosis method and system based on term vector
CN113157903A (en) Multi-field-oriented electric power word stock construction method
CN114462399A (en) Accurate matching method for quality defect report and state report of nuclear power plant
CN114462736A (en) Experience feedback intelligent recommendation method for nuclear power plant radiation work license application
CN113868422A (en) Multi-label inspection work order problem traceability identification method and device
CN111881258B (en) Self-learning event extraction method and application thereof
CN114462737A (en) Accurate matching method applied to nuclear power plant work order task and operation event report
CN113409001A (en) Method for controlling automatic pricing of construction engineering quantity list
CN115080687A (en) Accurate matching method for nuclear power plant work order tasks and quality defect report information
CN112036179A (en) Electric power plan information extraction method based on text classification and semantic framework
CN116611447A (en) Information extraction and semantic matching system and method based on deep learning method
CN108595415B (en) Law differentiation judgment method and device, computer equipment and storage medium
CN112395854B (en) Standard element consistency inspection method
CN113610112B (en) Auxiliary decision-making method for aircraft assembly quality defects
CN111814457A (en) Power grid engineering contract text generation method
CN110414819B (en) Work order scoring method
CN113869024A (en) Method and system for generating initial guarantee scheme of airplane
CN115098625B (en) Nuclear power plant NCR and completion report data accurate matching system and method
CN115098624A (en) Accurate matching method for NCR and external event information
CN116957369A (en) Nuclear power plant quality defect report and production non-conforming item accurate matching method
CN116842021B (en) Data dictionary standardization method, equipment and medium based on AI generation technology
CN116777148B (en) Intelligent distribution processing system for service work orders based on data analysis

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