Power grid knowledge graph construction system

Abstract

The invention discloses a power grid knowledge graph construction system, and belongs to the technical field of power grid knowledge graphs. Comprising a central processing server, a user verification login module, a power grid fault table uploading module, a power grid fault table identification module, a power grid knowledge graph creation module, a fault statistics evaluation module, an information labeling module, a knowledge graph storage module and a knowledge graph retrieval module. The central processing server is in communication connection with the user verification login module, the power grid fault table uploading module, the power grid fault table identification module, the fault statistics evaluation module, the knowledge graph storage module and the knowledge graph retrieval module; in this way, the transformer substation power grid fault knowledge graph is automatically created.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid knowledge graphs, and in particular to a power grid knowledge graph construction system. Background Art

[0002] The power grid knowledge graph is a visualization method used to describe and display the knowledge of various aspects of the power system and their relationships.

[0003] Among many existing technologies, Chinese patent application CN111930784A discloses a method and system for constructing a knowledge graph of power grid, which includes: collecting power grid related content and organizing power grid corpus; constructing and training a natural language processing model based on the power grid corpus; extracting power grid knowledge based on the natural language processing model, and storing the extraction results in a graph structure database. It can effectively extract power grid knowledge, construct a knowledge graph in the power grid field, and provide support for subsequent knowledge graph applications.

[0004] However, this patent application cannot realize the creation of a substation power grid fault knowledge graph based on the faulty components of the substation power grid.

[0005] Based on this, the present invention designs a power grid knowledge graph construction system to solve the above problems. Summary of the invention

[0006] In view of the above-mentioned shortcomings of the prior art, the present invention provides a power grid knowledge graph construction system.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0008] A power grid knowledge graph construction system, comprising a central processing server, a user verification login module, a power grid fault table upload module, a power grid fault table identification module, a power grid knowledge graph creation module, a fault statistics evaluation module, an information annotation module, a knowledge graph storage module and a knowledge graph retrieval module;

[0009] The central processing server is in communication connection with the user verification login module, the power grid fault table upload module, the power grid fault table identification module, the fault statistics evaluation module, the knowledge graph storage module, and the knowledge graph retrieval module;

[0010] The power grid fault table identification module is communicatively connected to the power grid knowledge graph creation module and the fault statistics evaluation module, and the fault statistics evaluation module is communicatively connected to the information annotation module;

[0011] The user verification login module is used for user identity authentication login;

[0012] The power grid fault table uploading module is used to upload the power grid fault table to the central processing server, and the central processing server sends the power grid fault table to the power grid fault table identification module;

[0013] The power grid fault table identification module is used for identifying the content of the power grid fault table;

[0014] The power grid fault table records the fault data of the substation power grid within 120 days;

[0015] The power grid fault table recognition module recognizes and extracts the fault unit, power equipment type, fault component and fault type in the power grid fault table based on the natural language algorithm;

[0016] The power grid fault table identification module sends the fault unit, power equipment type and fault component to the power grid knowledge graph creation module, and the power grid fault table identification module sends the fault unit, fault component and fault type data to the fault statistics evaluation module;

[0017] The power grid knowledge graph creation module is used to create a substation power grid fault knowledge graph according to the fault unit, power equipment type and fault component; and each fault unit corresponds to a substation power grid fault knowledge graph;

[0018] The fault statistics evaluation module is used to identify the fault unit, and to collect statistics on the fault types of the same faulty component and generate annotation data;

[0019] The information annotation module is used to add the annotation data to the substation power grid fault knowledge graph;

[0020] The knowledge graph storage module is used to store the knowledge graph of substation power grid faults;

[0021] The knowledge graph retrieval module is used to consult the substation power grid fault knowledge graph.

[0022] Furthermore, the fault unit is the name of the substation.

[0023] Furthermore, the types of power equipment include primary equipment and secondary equipment.

[0024] Furthermore, the power grid knowledge graph creation module creates a substation power grid fault knowledge graph in step A:

[0025] Step A1, the power grid knowledge graph creation module determines whether the fault unit has created entity a;

[0026] Step A2: If the answer is no, a new substation power grid fault knowledge graph of the fault unit is created. The power grid knowledge graph creation module sets the fault unit as entity a, sets the power equipment type as entity b, sets the fault component as entity c, and creates an inclusion relationship U between entity a and entity b, and creates an inclusion relationship S between entity b and entity c;

[0027] Step A3, if yes, the power grid knowledge graph creation module updates the content of the substation power grid fault knowledge graph of the faulty unit stored in the knowledge graph storage module, and the power grid knowledge graph creation module determines whether the faulty component has created entity c;

[0028] If entity c has been created, the power grid knowledge graph creation module ignores the faulty component;

[0029] If entity c is not created, the power grid knowledge graph creation module sets the fault component as entity c and creates an inclusion relationship S between entity b and entity c;

[0030] Step A4: the power grid knowledge graph creation module sends the substation power grid fault knowledge graph to the knowledge graph storage module for storage.

[0031] Furthermore, the labeled data of the fault statistics evaluation module adopts step B;

[0032] Step B1, the fault statistics evaluation module identifies the fault unit, and at the same time the fault statistics evaluation module counts the number of fault types of the same fault component;

[0033] Step B2: the fault statistics evaluation module generates annotated data recording the fault type and number, and the fault statistics evaluation module sends the annotated data to the information annotating module.

[0034] Furthermore, the fault statistics evaluation module is also used to evaluate the quality level of the faulty component based on the number of fault types of the same faulty component.

[0035] Furthermore, the fault statistics evaluation module evaluates the quality level of the faulty component using step C:

[0036] Step C1, the fault statistics evaluation module identifies whether the fault type is a component fault based on a natural language algorithm;

[0037] Step C2, if yes, the fault statistics evaluation module identifies the number of fault types;

[0038] If the number is less than 2, the fault statistics evaluation module evaluates the quality level of the faulty component as excellent;

[0039] If the number is greater than or equal to 2 and less than 4, the fault statistics evaluation module evaluates the quality level of the faulty component as good;

[0040] If the number is greater than or equal to 4, the fault statistics evaluation module evaluates the quality level of the faulty component as poor;

[0041] Step C3, if not, the fault statistics evaluation module skips the evaluation;

[0042] Step C4: the fault statistics evaluation module sends the quality level of the faulty component to the central processing server.

[0043] Furthermore, the central processing server generates an evaluation report based on the quality level of the received faulty component and sends it to the user.

[0044] Furthermore, the intrinsic fault includes aging fault, conductive fault and mechanical fault.

[0045] Furthermore, the information annotation module adds annotation data using step D:

[0046] Step D1, the information annotation module determines whether there is annotated data with the same fault type as the annotated data in the knowledge graph of substation power grid faults;

[0047] Step D2, if it exists, the information annotation module adds the number of times in the annotation data to the number of times the annotation data is in the substation power grid fault knowledge graph;

[0048] Step D3: If it does not exist, the information annotation module adds the annotation data to the relationship S between the entity c and the entity b of the faulty component in the substation power grid fault knowledge graph.

[0049] Compared with the prior art, the present invention has the following beneficial effects: a knowledge graph of substation power grid faults is created through a power grid knowledge graph creation module, thereby realizing an intuitive display of power grid fault components in the substation, and a substation power grid fault knowledge graph is generated for each fault unit, thereby facilitating the query of component fault conditions in different substations;

[0050] Identify and extract the content of the power grid fault table through the power grid fault table identification module;

[0051] When the present invention is used, the fault statistics evaluation module is used to count the number of occurrences of the fault type of the same fault component in the power grid fault table, and annotated data recording the fault type and its number is generated. The annotated data is added to the substation power grid fault knowledge graph through the information annotation module, thereby intuitively reflecting the occurrence of the fault type of the fault component. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0053] Figure 1 A block diagram of a power grid knowledge graph construction system of the present invention;

[0054] Figure 2 is a schematic diagram of a power grid fault table of the present invention;

[0055] Figure 3 It is a schematic diagram of the substation power grid fault knowledge graph of the present invention.

[0056] The numbers in the figure represent:

[0057] 1. Central processing server 2. User verification login module 3. Power grid fault table upload module 4. Power grid fault table identification module 5. Power grid knowledge graph creation module 6. Fault statistics evaluation module 7. Information annotation module 8. Knowledge graph storage module 9. Knowledge graph retrieval module. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0059] Embodiment 1: In some embodiments, please refer to the drawings of the specification Figure 1-Figure 3 , a power grid knowledge graph construction system, comprising a central processing server 1, a user verification login module 2, a power grid fault table upload module 3, a power grid fault table identification module 4, a power grid knowledge graph creation module 5, a fault statistics evaluation module 6, an information annotation module 7, a knowledge graph storage module 8 and a knowledge graph retrieval module 9;

[0060] The central processing server 1 is in communication connection with the user verification login module 2, the power grid fault table upload module 3, the power grid fault table identification module 4, the fault statistics evaluation module 6, the knowledge graph storage module 8, and the knowledge graph retrieval module 9;

[0061] The power grid fault table identification module 4 is in communication connection with the power grid knowledge graph creation module 5 and the fault statistics evaluation module 6, and the fault statistics evaluation module 6 is in communication connection with the information labeling module 7;

[0062] User authentication login module 2 is used for user identity authentication login;

[0063] The power grid fault table uploading module 3 is used to upload the power grid fault table to the central processing server 1, and the central processing server 1 sends the power grid fault table to the power grid fault table identification module 4;

[0064] The power grid fault table identification module 4 is used for identifying the content of the power grid fault table;

[0065] The power grid fault table records the fault data of the substation power grid within 120 days;

[0066] The power grid fault table recognition module 4 recognizes and extracts the fault unit, power equipment type, fault component and fault type in the power grid fault table based on the natural language algorithm;

[0067] The power grid fault table identification module 4 sends the fault unit, power equipment type and fault component to the power grid knowledge graph creation module 5, and the power grid fault table identification module 4 sends the fault unit, fault component and fault type data to the fault statistics evaluation module 6;

[0068] The power grid knowledge graph creation module 5 is used to create a substation power grid fault knowledge graph according to the fault unit, power equipment type and fault component; and each fault unit corresponds to a substation power grid fault knowledge graph;

[0069] Step A of the power grid knowledge graph creation module 5 for creating a substation power grid fault knowledge graph:

[0070] Step A1, the power grid knowledge graph creation module 5 determines whether the fault unit has created entity a;

[0071] Step A2: if the answer is no, a new substation power grid fault knowledge graph of the fault unit is created. The power grid knowledge graph creation module 5 sets the fault unit to entity a, sets the power equipment type to entity b, sets the fault component to entity c, creates an inclusion relationship U between entity a and entity b, and creates an inclusion relationship S between entity b and entity c;

[0072] Step A3, if yes, the power grid knowledge graph creation module 5 updates the content of the substation power grid fault knowledge graph of the faulty unit stored in the knowledge graph storage module 8, and the power grid knowledge graph creation module 5 determines whether the faulty component has created entity c;

[0073] If entity c has been created, the power grid knowledge graph creation module 5 ignores the faulty component;

[0074] If entity c is not created, the power grid knowledge graph creation module 5 sets the fault component as entity c and creates an inclusion relationship S between entity b and entity c;

[0075] Step A4, the power grid knowledge graph creation module 5 sends the substation power grid fault knowledge graph to the knowledge graph storage module 8 for storage;

[0076] The fault statistics evaluation module 6 is used to identify the fault unit, and to collect statistics on the fault types of the same faulty component and generate annotation data;

[0077] The fault statistics evaluation module 6 is also used to evaluate the quality level of the fault component based on the number of fault types of the same fault component;

[0078] The labeling data of the fault statistics evaluation module 6 adopts step B;

[0079] Step B1, the fault statistics evaluation module 6 identifies the fault unit, and at the same time the fault statistics evaluation module 6 counts the number of fault types of the same fault component;

[0080] Step B2, the fault statistics evaluation module 6 generates annotated data recording the fault type and number, and the fault statistics evaluation module 6 sends the annotated data to the information annotating module 7;

[0081] The failure statistics evaluation module 6 evaluates the quality level of the failed component using step C:

[0082] Step C1, the fault statistics evaluation module 6 identifies whether the fault type is a component fault based on a natural language algorithm;

[0083] Step C2, if yes, the fault statistics evaluation module 6 identifies the number of fault types;

[0084] If the number is less than 2, the fault statistics evaluation module 6 evaluates the quality level of the faulty component as excellent;

[0085] If the number is greater than or equal to 2 and less than 4, the fault statistics evaluation module 6 evaluates the quality level of the faulty component as good;

[0086] If the number is greater than or equal to 4, the fault statistics evaluation module 6 evaluates the quality level of the faulty component as poor;

[0087] Step C3, if not, the fault statistics evaluation module 6 skips the evaluation;

[0088] Step C4 , the fault statistics evaluation module 6 sends the quality level of the faulty component to the central processing server 1 .

[0089] The information annotation module 7 is used to add the annotation data to the substation power grid fault knowledge graph;

[0090] The information annotation module 7 adds annotation data using step D:

[0091] Step D1, the information annotation module 7 determines whether there is annotated data with the same fault type as the annotated data in the substation power grid fault knowledge graph;

[0092] Step D2, if it exists, the information annotation module 7 adds the number of times in the annotation data to the number of times the annotation data is in the substation power grid fault knowledge graph;

[0093] Step D3, if it does not exist, the information annotation module 7 adds the annotation data to the relationship S between the entity c and the entity b of the fault component in the substation power grid fault knowledge graph.

[0094] When the present invention is used, a substation power grid fault knowledge graph is created through the power grid knowledge graph creation module 5, so as to realize the intuitive display of the power grid fault components in the substation, and each fault unit generates a substation power grid fault knowledge graph, so as to facilitate the query of component fault conditions of different substations;

[0095] The power grid fault table content is identified and extracted by the power grid fault table identification module 4;

[0096] When the present invention is used, the fault statistical evaluation module 6 is used to count the number of occurrences of the fault type of the same fault component in the power grid fault table, and generate annotation data recording the fault type and its number, and the information annotation module 7 is used to add the annotation data to the substation power grid fault knowledge map, so as to intuitively reflect the occurrence of the fault type of the fault component;

[0097] The fault statistics evaluation module 6 identifies the fault type of the fault component in the power grid fault table as self-fault, and evaluates the quality of the fault component according to the number of times the self-fault occurs, so as to facilitate the user to select a suitable component.

[0098] The central processing server 1 generates an evaluation report based on the quality level of the received faulty component and sends it to the user;

[0099] The knowledge graph storage module 8 is used for storing the knowledge graph of substation power grid faults;

[0100] The knowledge graph retrieval module 9 is used to consult the substation power grid fault knowledge graph.

[0101] The fault unit is the substation name;

[0102] Types of power equipment include primary equipment and secondary equipment;

[0103] Internal failures include aging failures, conductive failures and mechanical failures.

[0104] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A power grid knowledge graph construction system, characterized by: It comprises a central processing server (1), a user verification login module (2), a power grid fault table upload module (3), a power grid fault table identification module (4), a power grid knowledge graph creation module (5), a fault statistics evaluation module (6), an information annotation module (7), a knowledge graph storage module (8) and a knowledge graph retrieval module (9); The central processing server (1) is communicatively connected with the user verification login module (2), the power grid fault table upload module (3), the power grid fault table identification module (4), the fault statistics evaluation module (6), the knowledge graph storage module (8), and the knowledge graph retrieval module (9); The power grid fault table identification module (4) is communicatively connected to the power grid knowledge graph creation module (5) and the fault statistics evaluation module (6), and the fault statistics evaluation module (6) is communicatively connected to the information labeling module (7); The user authentication login module (2) is used for user identity authentication login; The power grid fault table uploading module (3) is used to upload the power grid fault table to the central processing server (1), and the central processing server (1) sends the power grid fault table to the power grid fault table identification module (4); The power grid fault table identification module (4) is used for identifying the content of the power grid fault table; The power grid fault table records the fault data of the substation power grid within 120 days; The power grid fault table recognition module (4) recognizes and extracts the fault unit, power equipment type, fault component and fault type in the power grid fault table based on a natural language algorithm; The power grid fault table identification module (4) sends the fault unit, the power equipment type and the fault component to the power grid knowledge graph creation module (5), and the power grid fault table identification module (4) sends the fault unit, the fault component and the fault type data to the fault statistics evaluation module (6); The power grid knowledge graph creation module (5) is used to create a substation power grid fault knowledge graph according to the fault unit, the power equipment type and the fault component; and each fault unit corresponds to a substation power grid fault knowledge graph; The fault statistics evaluation module (6) is used to identify the fault unit, and to collect statistics on the fault types of the same faulty component and generate annotation data; The information labeling module (7) is used to add the labeling data to the substation power grid fault knowledge graph; The knowledge graph storage module (8) is used to store the knowledge graph of substation power grid faults; The knowledge graph retrieval module (9) is used to retrieve the substation power grid fault knowledge graph.

2. The power grid knowledge graph construction system according to claim 1, characterized in that: The fault unit is the name of the substation.

3. The power grid knowledge graph construction system according to claim 2, characterized in that: The types of electrical equipment include primary equipment and secondary equipment.

4. The power grid knowledge graph construction system according to claim 3, characterized in that: The power grid knowledge graph creation module (5) creates a substation power grid fault knowledge graph in step A: Step A1, the power grid knowledge graph creation module (5) determines whether the fault unit has created entity a; Step A2: if the answer is no, a new substation power grid fault knowledge graph of the fault unit is created. The power grid knowledge graph creation module (5) sets the fault unit as entity a, sets the power equipment type as entity b, sets the fault component as entity c, creates an inclusion relationship U between entity a and entity b, and creates an inclusion relationship S between entity b and entity c; Step A3, if yes, the power grid knowledge graph creation module (5) updates the content of the substation power grid fault knowledge graph of the faulty unit stored in the knowledge graph storage module (8), and the power grid knowledge graph creation module (5) determines whether the faulty component has created entity c; If entity c has been created, the power grid knowledge graph creation module (5) ignores the faulty component; If entity c is not created, the power grid knowledge graph creation module (5) sets the fault component as entity c and creates an inclusion relationship S between entity b and entity c; Step A4, the power grid knowledge graph creation module (5) sends the substation power grid fault knowledge graph to the knowledge graph storage module (8) for storage.

5. The power grid knowledge graph construction system according to claim 4, characterized in that: The labeling data of the fault statistics evaluation module (6) adopts step B; Step B1, the fault statistics evaluation module (6) identifies the fault unit, and at the same time, the fault statistics evaluation module (6) counts the number of fault types of the same fault component; Step B2: the fault statistics evaluation module (6) generates annotated data recording the fault type and number of times, and the fault statistics evaluation module (6) sends the annotated data to the information annotating module (7).

6. The power grid knowledge graph construction system according to claim 5, characterized in that: The fault statistics evaluation module (6) is also used to evaluate the quality level of the fault component based on the number of fault types of the same fault component.

7. The power grid knowledge graph construction system according to claim 6, characterized in that: The fault statistics evaluation module (6) evaluates the quality level of the faulty component using step C: Step C1, the fault statistics evaluation module (6) identifies whether the fault type is a component fault based on a natural language algorithm; Step C2, if yes, the fault statistics evaluation module (6) identifies the number of fault types; If the number is less than 2, the fault statistics evaluation module (6) evaluates the quality level of the faulty component as excellent; If the number is greater than or equal to 2 and less than 4, the fault statistics evaluation module (6) evaluates the quality level of the faulty component as good; If the number is greater than or equal to 4, the fault statistics evaluation module (6) evaluates the quality level of the faulty component as poor; Step C3, if not, the fault statistics evaluation module (6) skips the evaluation; Step C4, the fault statistics evaluation module (6) sends the quality level of the above-mentioned faulty component to the central processing server (1).

8. The power grid knowledge graph construction system according to claim 7, characterized in that: The central processing server (1) generates an evaluation report based on the quality level of the received faulty component and sends it to the user.

9. The power grid knowledge graph construction system according to claim 8, characterized in that: The intrinsic faults include aging faults, conductive faults and mechanical faults.

10. The power grid knowledge graph construction system according to claim 9, characterized in that: The information annotation module (7) adds annotation data using step D: Step D1, the information annotation module (7) determines whether there is an annotation data with the same fault type as the annotated data in the substation power grid fault knowledge graph; Step D2, if it exists, the information annotation module (7) adds the number of times in the annotation data to the number of times the annotation data is in the substation power grid fault knowledge graph; Step D3, if it does not exist, the information annotation module (7) adds the annotation data to the relationship S between the entity c and the entity b of the fault component in the substation power grid fault knowledge graph.

Images