CN-122022382-A - Knowledge-graph-based power communication network labor-monotone method and system

CN122022382ACN 122022382 ACN122022382 ACN 122022382ACN-122022382-A

Abstract

The invention relates to the technical field of power communication, in particular to a power communication network labor intensity adjustment method and system based on a knowledge graph; the method comprises the steps of collecting power communication network data, carrying out knowledge extraction on the data, constructing a power communication network knowledge graph according to the extracted data, obtaining original information of a work order to be scheduled, extracting the characteristics of the work order, matching the characteristics of the work order with work order entity nodes in the power communication network knowledge graph, mining associated information, establishing a multi-dimensional evaluation index system, generating a scheduling scheme aiming at the entity node matching data and the associated information mining data, and executing the scheduling scheme, wherein the system comprises a power communication network knowledge graph construction module, an associated information matching mining module and a scheduling scheme generation module, and realizing potential association between a mining work order and resources in the mode, thereby providing scientific and accurate decision basis for work order degree, and further solving the defects of a traditional scheduling mode.

Inventors

LI XIAOFEI
SANG TIAN
WANG JINSHENG
HE YIKANG
XU ZHEN
LIU BO
LI XIAODONG
WANG DIANDIAN

Assignees

国网北京市电力公司

Dates

Publication Date: 20260512
Application Date: 20260324

Claims (10)

1. The power communication network labor intensity adjustment method based on the knowledge graph is characterized by comprising the following steps of: collecting power communication network data, carrying out knowledge extraction on the data, and constructing a power communication network knowledge graph according to the extracted data; acquiring original information of a work order to be scheduled, extracting the characteristics of the work order, matching the characteristics of the work order with the work order entity nodes in the power communication network knowledge graph, and mining associated information; And establishing a multidimensional evaluation index system, generating a scheduling scheme aiming at entity node matching data and associated information mining data, and executing the scheduling scheme.
2. The knowledge-graph-based power communication network industrial single-tone method as claimed in claim 1, wherein in the steps of collecting power communication network data, performing knowledge extraction on the data, and constructing a power communication network knowledge graph based on the extracted data: Collecting multi-source data of an electric power communication network, and carrying out knowledge extraction on the multi-mode data; Calculating attribute similarity; and constructing a knowledge graph model, mapping the entity into nodes, mapping the relationship into edges, mapping the attribute into key value pairs, and creating the nodes and the relationship.
3. The knowledge-graph-based power communication network industrial single-node method according to claim 2, wherein in the step of collecting power communication network multi-source data and performing knowledge extraction on the multi-mode data: and according to the keyword matching extraction attribute, forming a structured knowledge segment.
4. The knowledge-graph-based power communication network industrial single-tone method according to claim 2, wherein, after the step of calculating the attribute similarity: unified data source relationship naming and complementing missing attributes.
5. The method of claim 2, wherein in the step of creating the knowledge-graph model, mapping the entities to nodes, the relationships to edges, and the attributes to key-value pairs, and creating the nodes and the relationships: and configuring an entity ID index and an attribute index, and maintaining the associated query response time.
6. The method for generating the work order single of the power communication network based on the knowledge graph according to claim 1, wherein in the steps of acquiring the original information of the work order to be scheduled, extracting the characteristics of the work order, matching the characteristics of the work order with the nodes of the work order entity in the knowledge graph of the power communication network, and mining the associated information: Inquiring the current fault of the power communication network, generating a work order, and preprocessing the work order data; extracting entity characteristics and attribute characteristics, and converting fault description in work order data into semantic vector characteristics; Preliminarily inquiring the knowledge graph according to the work order number, matching the work order features with the knowledge graph entity nodes, and outputting matching data; Starting from the matched work order nodes, traversing the relation to obtain a maintenance personnel list, associated equipment, link information and historical scheduling data; monitoring a link real-time data marking risk label, detecting personnel and equipment conflict marking resources are limited, and integrating information to form a scheduling data support set.
7. The knowledge-graph-based power communication network work order adjustment method as set forth in claim 6, wherein in the steps of inquiring about the current failure of the power communication network, generating a work order, and preprocessing work order data: And (3) cleaning redundant information and special characters in the work order data, converting the priority into a unified value, and converting the processing time limit into units.
8. The method of claim 6, wherein in the step of preliminarily inquiring the knowledge graph according to the number of the work orders, the work order features are matched with the knowledge graph entity nodes, and the matching data is output: if the repeated worksheets exist, directly associating; If the new work order is created, the work order entity node is created, the association relation with the equipment and the fault type is built based on the entity characteristics, and the attribute characteristics are assigned to the new node.
9. The knowledge-graph-based power communication network industrial personal computer method according to claim 1, wherein a multi-dimensional evaluation index system is established, a scheduling scheme is generated for entity node matching data and associated information mining data, and the steps of: Establishing a multi-dimensional evaluation index system, and generating a potential scheme according to the work order matching data and the associated mining data; Calculating efficiency, matching degree and reliability score of the potential scheme from the treatment time-efficiency fit degree and the resource response speed according to the index system, and obtaining a comprehensive score; and selecting an optimal scheme according to the comprehensive score ranking, and executing.
10. The power communication network labor intensity adjustment system based on the knowledge graph is applied to the power communication network labor intensity adjustment method based on the knowledge graph as claimed in claim 1, and is characterized by comprising a power communication network knowledge graph construction module, a correlation information matching mining module and a scheduling scheme generation module, wherein: the power communication network knowledge graph construction module is used for collecting power communication network data, carrying out knowledge extraction on the data and constructing a power communication network knowledge graph according to the extracted data; The association information matching and mining module is used for acquiring the original information of the work order to be scheduled, extracting the characteristics of the work order, matching the characteristics of the work order with the work order entity nodes in the power communication network knowledge graph, and mining the association information; the scheduling scheme generating module is used for establishing a multi-dimensional evaluation index system, generating a scheduling scheme aiming at entity node matching data and associated information mining data, and executing the scheduling scheme.

Description

Knowledge-graph-based power communication network labor-monotone method and system Technical Field The invention relates to the technical field of power communication, in particular to a power communication network labor intensity adjustment method and system based on a knowledge graph. Background The power communication network is an important infrastructure for guaranteeing safe and stable operation of the power system, and bears key tasks such as power production scheduling instruction transmission, equipment state monitoring data transmission and the like. Along with the development of the power system in the intelligent and digital directions, the scale of the power communication network is continuously enlarged, the variety of equipment is increased, and the number of work orders is also increased greatly. Currently, the work order of an electric power communication network is mainly carried out by relying on manual experience, and a dispatcher distributes the work order to maintenance personnel according to own knowledge of equipment distribution, personnel skills and fault conditions. The scheduling mode has the advantages that the fault response is not timely, and the fault response is lagged because the comprehensive grasp of the power communication network resources and the fault association relation is lacking, the fault influence range can not be rapidly positioned, and the optimal processing resources can not be found. Therefore, a potential association between the mining worksheet and the resource is provided, and a scientific and accurate decision basis is provided for the worksheet, so that the power communication network worksheet method and system for solving the defect of the traditional scheduling mode are very necessary. Disclosure of Invention The invention aims to provide a power communication network work order adjustment method and system based on a knowledge graph, which aim to achieve potential association between an excavation work order and resources and provide scientific and accurate decision basis for the work order adjustment, thereby solving the problem of insufficient traditional scheduling modes. In order to achieve the above purpose, the invention adopts a power communication network labor intensity modulation method based on a knowledge graph, which comprises the following steps: collecting power communication network data, carrying out knowledge extraction on the data, and constructing a power communication network knowledge graph according to the extracted data; acquiring original information of a work order to be scheduled, extracting the characteristics of the work order, matching the characteristics of the work order with the work order entity nodes in the power communication network knowledge graph, and mining associated information; And establishing a multidimensional evaluation index system, generating a scheduling scheme aiming at entity node matching data and associated information mining data, and executing the scheduling scheme. In the step of collecting power communication network data, performing knowledge extraction on the data, and constructing a power communication network knowledge graph according to the extracted data: Collecting multi-source data of an electric power communication network, and carrying out knowledge extraction on the multi-mode data; Calculating attribute similarity; and constructing a knowledge graph model, mapping the entity into nodes, mapping the relationship into edges, mapping the attribute into key value pairs, and creating the nodes and the relationship. Wherein, in the step of collecting the multi-source data of the power communication network and carrying out knowledge extraction on the multi-mode data: and according to the keyword matching extraction attribute, forming a structured knowledge segment. Wherein, after the step of calculating the attribute similarity: unified data source relationship naming and complementing missing attributes. Wherein, in the step of constructing a knowledge graph model, mapping the entity into nodes, mapping the relationship into edges, mapping the attribute into key value pairs, and creating the nodes and the relationships: and configuring an entity ID index and an attribute index, and maintaining the associated query response time. The method comprises the steps of acquiring original information of a work order to be scheduled, extracting the characteristics of the work order, matching the characteristics of the work order with work order entity nodes in a power communication network knowledge graph, and mining associated information: Inquiring the current fault of the power communication network, generating a work order, and preprocessing the work order data; extracting entity characteristics and attribute characteristics, and converting fault description in work order data into semantic vector characteristics; Preliminarily inquiring the knowledge graph according to the work order numbe