Knowledge graph construction method and system for power grid data assets

Abstract

The embodiment of the invention provides a knowledge graph construction method and system for power grid data assets, and belongs to the technical field of power grid data processing. The knowledge graph construction method comprises the following steps: checking data resources in an enterprise, and standardizing the data resources in the enterprise to ensure the consistency and comparability of data; according to the checking condition, collecting power grid data dispersed in each system from different data sources; identifying the power grid data so as to complete entity identification for power grid proper nouns; the relation between the entities is extracted; and according to the relationship between the entities and the entities, constructing a power grid data asset-oriented knowledge graph. According to the knowledge graph construction method, the knowledge graph about the power grid can be constructed, so that power grid data assets can be effectively managed and utilized, and the comprehensive analysis capability and the value mining capability of data are improved.

Description

Technical Field

[0001] This invention relates to the field of power grid data processing technology, and more specifically to a method and system for constructing a knowledge graph for power grid data assets. Background Technology

[0002] With the rapid development of information technology, emerging technologies such as big data and artificial intelligence are gradually becoming key forces driving socio-economic development. Particularly in the power industry, with the construction and operation of smart grids, a massive amount of data from multiple stages, including power generation, transmission, distribution, and consumption, is constantly accumulating. This data covers various aspects such as grid operation status, equipment health, and user electricity consumption behavior. However, effectively managing and utilizing this enormous amount of data has become a major challenge for power companies.

[0003] Traditional data management models are often limited to a single system or business department, lacking cross-system integration and sharing mechanisms. This leads to the phenomenon of "data silos," severely impacting the comprehensive analysis capabilities and value extraction of data. Therefore, it is necessary to construct a knowledge graph to effectively manage and utilize power grid data assets, thereby enhancing the comprehensive analysis and value extraction capabilities of the data. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for constructing a knowledge graph for power grid data assets. This knowledge graph construction method can build a knowledge graph about the power grid to effectively manage and utilize power grid data assets and improve the comprehensive analysis and value mining capabilities of the data.

[0005] To achieve the above objectives, embodiments of the present invention provide a method for constructing a knowledge graph for power grid data assets, the method comprising: Take stock of the company's internal data resources and standardize them to ensure data consistency and comparability; Based on the inventory, power grid data scattered across various systems were collected from different data sources; The power grid data is identified to perform entity recognition for power grid-specific terms; Complete the extraction of relationships between entities; Based on the relationships and entities between them, a knowledge graph for power grid data assets is constructed.

[0006] Optionally, data sources include data from the power generation, transmission, distribution, and consumption stages of the power grid.

[0007] Optionally, the power grid data is identified to perform entity recognition for power grid proper nouns, including: Acquire the power grid data; Identify and delete data in the power grid data that does not belong to the power grid domain. Determine whether any data is missing from the power grid data; In the case of missing data, interpolation methods are used to fill in the missing parts to obtain complete power grid data; The complete power grid data is converted into a consistent format to facilitate subsequent processing.

[0008] Optionally, the power grid data is identified to perform entity recognition for power grid proper nouns, including: Acquire the power grid data; The power grid data is segmented into words to obtain multiple words; Find the nouns in the given words; Find the combined words within the given words; The nouns and compound words are grouped into entity words to be identified.

[0009] Optionally, the power grid data is identified to perform entity recognition for power grid proper nouns, including: Obtain the initial combination of words in the power grid data; Calculate the frequency of the initial combination of terms in the power grid data; The initial combination of words that appears in the power grid data with a frequency exceeding a preset threshold is selected as the combination of words.

[0010] Optionally, the power grid data is identified to perform entity recognition for power grid proper nouns, including: Obtain the entity words to be identified; Feature extraction is performed on the words to be identified to obtain features about the words to be identified; The features are fed into a named entity recognition model to identify entity words related to the power grid field and recognize them as entities.

[0011] Optionally, perform the extraction of relationships between entities, including: Retrieve the identified entities; The entities are detected, and entities with different names but the same substance are merged into a single entity; Detect semantic associations between entities and extract the relationships between them; Multiple semantic relationships that describe entities with the same substance are merged into a single relationship in order to extract the relationships between entities.

[0012] Optionally, based on the relationships between entities and the entities themselves, a knowledge graph for power grid data assets can be constructed, including: The entities are used as nodes, and the relationships between the entities are used as edges to construct an initial knowledge graph; The edges between entities are assigned values ​​based on the number of entities and the number of semantic relationships before the merge. Based on the edge values ​​assigned between entities, edges with values ​​greater than a preset threshold are designated as priority edges to connect two nodes, thereby constructing a knowledge graph for power grid data assets.

[0013] On the other hand, the present invention also provides a knowledge graph construction system for power grid data assets, the knowledge graph construction system comprising: The data acquisition module is used to acquire power grid data; An analysis platform is used to execute a knowledge graph construction method for power grid data assets as described above, based on the power grid data.

[0014] Through the above technical solution, the present invention provides a knowledge graph construction method for power grid data assets. This method involves inventorying and standardizing internal enterprise data resources to ensure data consistency and comparability. Based on the inventory, power grid data scattered across various systems can be collected from different data sources. After obtaining the power grid data, it can be identified, and entity recognition can be performed for power grid-specific terms. Following entity recognition, relationships between entities can be extracted. Based on these relationships and the entities themselves, a knowledge graph for power grid data assets can be constructed. This knowledge graph construction method can build a knowledge graph about the power grid to effectively manage and utilize power grid data assets, enhancing the comprehensive analysis and value mining capabilities of the data.

[0015] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description section. Attached Figure Description

[0016] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart of a knowledge graph construction method for power grid data assets according to an embodiment of the present invention; Figure 2 This is a flowchart illustrating the first step of entity recognition in a knowledge graph construction method for power grid data assets according to an embodiment of the present invention. Figure 3 This is a second flowchart illustrating the completion of entity recognition in a knowledge graph construction method for power grid data assets according to an embodiment of the present invention. Figure 4 This is a third flowchart illustrating the entity recognition process in a knowledge graph construction method for power grid data assets according to an embodiment of the present invention. Figure 5 This is a flowchart illustrating the fourth step of entity recognition in a knowledge graph construction method for power grid data assets according to an embodiment of the present invention. Figure 6 This is a flowchart illustrating the entity extraction process of a knowledge graph construction method for power grid data assets according to an embodiment of the present invention. Figure 7 This is a flowchart illustrating a knowledge graph construction method for power grid data assets according to an embodiment of the present invention. Detailed Implementation

[0017] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the scope of the present invention.

[0018] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application all comply with the relevant provisions of national laws and regulations. In the embodiments of this application, certain existing industry solutions such as software, components, and models may be mentioned. These should be considered exemplary, intended only to illustrate the feasibility of implementing the technical solution of this application, and do not imply that the applicant has already used or necessarily used such solutions.

[0019] Figure 1 This is a flowchart of a knowledge graph construction method for power grid data assets according to an embodiment of the present invention. The process of this construction method in the present invention may include: In step S1, the company's internal data resources are inventoried and standardized to ensure data consistency and comparability.

[0020] In step S2, based on the inventory situation, power grid data scattered across various systems are collected from different data sources.

[0021] In step S3, the power grid data is identified to complete entity recognition for power grid proper nouns.

[0022] In step S4, the relationships between entities are extracted.

[0023] In step S5, a knowledge graph for power grid data assets is constructed based on the relationships between entities and the entities themselves.

[0024] In this invention, when constructing a knowledge graph about the power grid, an inventory of internal enterprise data resources can be conducted, and these resources can be standardized to ensure data consistency and comparability. Then, based on the inventory, power grid data scattered across various systems can be collected from different data sources. After obtaining the power grid data, it can be identified, and entity recognition can be performed for power grid-specific terms. After entity recognition, relationships between entities can be extracted. Based on these relationships and the entities themselves, a knowledge graph oriented towards power grid data assets can be constructed. This knowledge graph construction method can build a knowledge graph about the power grid to effectively manage and utilize power grid data assets, enhancing the comprehensive analysis capabilities and value mining capabilities of the data.

[0025] In one embodiment of the present invention, when collecting power grid data from different data sources that are dispersed across various systems, the data from these different sources may include data from the power generation, transmission, distribution, and consumption stages of the power grid.

[0026] In one embodiment of the present invention, such as Figure 2 As shown, the first step in completing entity recognition may include: In step S6, power grid data is acquired.

[0027] In step S7, data in the power grid data that does not belong to the power grid domain is identified and deleted.

[0028] In step S8, it is determined whether there is missing data in the power grid data.

[0029] In step S9, in the case of missing data, the missing parts are filled in by interpolation to obtain complete power grid data.

[0030] In step S10, the complete power grid data is converted into a consistent format to facilitate subsequent processing.

[0031] In this invention, when performing entity recognition, power grid data can be acquired first, and then data that does not belong to the power grid domain can be deleted. After deletion, it can be determined whether there is missing data in the deleted power grid data. If there is missing data, the missing parts can be filled in using interpolation methods, thereby obtaining complete power grid data. After obtaining complete power grid data, the format of the complete power grid data can be converted to a consistent format for subsequent processing.

[0032] In one embodiment of the present invention, such as Figure 3 As shown, the second step in entity recognition can include: In step S11, power grid data is acquired.

[0033] In step S12, the power grid data is segmented into words to obtain multiple words.

[0034] In step S13, the nouns in the words are searched.

[0035] In step S14, the combination words in the words are searched.

[0036] In step S15, nouns and combined words are grouped into entity words to be identified.

[0037] In this invention, after acquiring power grid data, the data can be segmented to obtain multiple words. Since the knowledge graph is constructed in the power grid field, there are many proper nouns related to the power grid, and many of these proper nouns are compound nouns. Therefore, it is necessary to extract these compound words and identify them as entity words to be identified. These entity words to be identified can include nouns and compound words from the power grid data.

[0038] In one embodiment of the present invention, such as Figure 4 As shown, the third step in entity recognition can include: In step S16, the initial combination of words in the power grid data is obtained.

[0039] In step S17, the frequency of the initial combination of words in the power grid data is calculated.

[0040] In step S18, initial combination words that appear more frequently in the power grid data than a preset threshold are selected as combination words.

[0041] In this invention, when acquiring combined words, some combined words may not be the desired words, therefore, it is necessary to filter the combined words. During filtering, initial combined words can be obtained from the power grid data, and then the frequency of these initial combined words in the power grid data can be calculated. After obtaining the frequency of the initial combined words, initial combined words whose frequency in the power grid data exceeds a preset threshold can be selected as the final combined words. These combined words can be merged with nouns to form entity words to be identified.

[0042] In one embodiment of the present invention, such as Figure 5 As shown, the fourth step in entity recognition may include: In step S19, the entity words to be identified are obtained.

[0043] In step S20, feature extraction is performed on the entity words to be identified to obtain features about the entity words to be identified.

[0044] In step S21, the features are fed into the named entity recognition model to identify the entity words related to the power grid field and treat them as entities.

[0045] In this invention, when performing entity recognition, the entity word to be recognized can be obtained first, and then features can be extracted from the entity word to obtain features related to the entity word. After obtaining the features, the features can be fed into a named entity recognition model, thereby recognizing the entity words related to the power grid field within the entity word to be recognized, and then treating them as entities. The named entity recognition model can be an existing entity recognition model.

[0046] In one embodiment of the present invention, such as Figure 6 As shown, the process for completing entity extraction may include: In step S22, the identified entity is obtained.

[0047] In step S23, entities are detected, and entities with different names but the same substance are merged into a single entity.

[0048] In step S24, semantic associations between entities are detected, and the relationships between them are extracted.

[0049] In step S25, multiple semantic relationships that describe entities with the same substance are merged into a single relationship to complete the extraction of relationships between entities.

[0050] In this invention, when extracting relationships between entities, the entities to be identified can be obtained first. Since there can be multiple entities, and multiple entities may have essentially the same description, entities with different names but the same substantive description can be merged into a single entity. Semantic associations between entities can be detected, and the relationships between them can be extracted. Because there can be multiple relationships between entities, and multiple relationships may describe the same substance, they can be merged. Thus, multiple semantic relationships describing entities with the same substance can be merged into a single relationship, thereby completing the extraction of relationships between entities.

[0051] In one embodiment of the present invention, such as Figure 7 As shown, the process of constructing a knowledge graph may include: In step S26, entities are used as nodes, and the relationships between entities are used as edges to construct an initial knowledge graph.

[0052] In step S27, the edges between entities are assigned values ​​based on the number of entities before merging and the number of semantic relationships before merging.

[0053] In step S28, based on the assignment of values ​​to the edges between entities, edges with values ​​greater than a preset threshold are set as preferred edges to connect two nodes, thereby constructing a knowledge graph for power grid data assets.

[0054] In this invention, after constructing an initial knowledge graph by using entities as nodes and relationships between entities as edges, the edges between entities are assigned values ​​based on the number of entities and the number of semantic relationships before merging. These values ​​can be recommended values ​​for the association between entities; the larger the assigned value, the more likely the other node will be recommended as a priority association if one of its connected nodes appears. Therefore, based on the assigned values ​​of the edges between entities, edges with values ​​greater than a preset threshold can be designated as priority recommended edges to connect two nodes, thereby constructing a knowledge graph for power grid data assets.

[0055] On the other hand, the present invention can also provide a knowledge graph construction system for power grid data assets, the knowledge graph construction system comprising: a data acquisition module and an analysis platform. The data acquisition module is used to acquire power grid data. The analysis platform is used to execute a knowledge graph construction method for power grid data assets as described above based on the power grid data.

[0056] Through the above technical solution, the present invention provides a knowledge graph construction method for power grid data assets. This method involves inventorying and standardizing internal enterprise data resources to ensure data consistency and comparability. Based on the inventory, power grid data scattered across various systems can be collected from different data sources. After obtaining the power grid data, it can be identified, and entity recognition can be performed for power grid-specific terms. Following entity recognition, relationships between entities can be extracted. Based on these relationships and the entities themselves, a knowledge graph for power grid data assets can be constructed. This knowledge graph construction method can build a knowledge graph about the power grid to effectively manage and utilize power grid data assets, enhancing the comprehensive analysis and value mining capabilities of the data.

[0057] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0058] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0059] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0060] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0061] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0062] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0063] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0064] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0065] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for constructing a knowledge graph for power grid data assets, characterized in that, The knowledge graph construction method includes: Take stock of the company's internal data resources and standardize them to ensure data consistency and comparability; Based on the inventory, power grid data scattered across various systems were collected from different data sources; The power grid data is identified to perform entity recognition for power grid-specific terms; Complete the extraction of relationships between entities; Based on the relationships and entities between them, a knowledge graph for power grid data assets is constructed.

2. The knowledge graph construction method according to claim 1, characterized in that, Data sources include data from the power generation, transmission, distribution, and consumption stages of the power grid.

3. The knowledge graph construction method according to claim 1, characterized in that, The power grid data is identified to perform entity recognition for power grid proper nouns, including: Acquire the power grid data; Identify and delete data in the power grid data that does not belong to the power grid domain. Determine whether any data is missing from the power grid data; In the case of missing data, interpolation methods are used to fill in the missing parts to obtain complete power grid data; The complete power grid data is converted into a consistent format to facilitate subsequent processing.

4. The knowledge graph construction method according to claim 1, characterized in that, The power grid data is identified to perform entity recognition for power grid proper nouns, including: Acquire the power grid data; The power grid data is segmented into words to obtain multiple words; Find the nouns in the given words; Find the combined words within the given words; The nouns and compound words are grouped into entity words to be identified.

5. The knowledge graph construction method according to claim 4, characterized in that, The power grid data is identified to perform entity recognition for power grid proper nouns, including: Obtain the initial combination of words in the power grid data; Calculate the frequency of the initial combination of terms in the power grid data; The initial combination of words that appears in the power grid data with a frequency exceeding a preset threshold is selected as the combination of words.

6. The knowledge graph construction method according to claim 5, characterized in that, The power grid data is identified to perform entity recognition for power grid proper nouns, including: Obtain the entity words to be identified; Feature extraction is performed on the words to be identified to obtain features about the words to be identified; The features are fed into a named entity recognition model to identify entity words related to the power grid field and recognize them as entities.

7. The knowledge graph construction method according to claim 6, characterized in that, Complete the extraction of relationships between entities, including: Retrieve the identified entities; The entities are detected, and entities with different names but the same substance are merged into a single entity; Detect semantic associations between entities and extract the relationships between them; Multiple semantic relationships that describe entities with the same substance are merged into a single relationship in order to extract the relationships between entities.

8. The knowledge graph construction method according to claim 7, characterized in that, Based on the relationships and entities between them, a knowledge graph for power grid data assets is constructed, including: The entities are used as nodes, and the relationships between the entities are used as edges to construct an initial knowledge graph; The edges between entities are assigned values ​​based on the number of entities and the number of semantic relationships before the merge. Based on the edge values ​​assigned between entities, edges with values ​​greater than a preset threshold are designated as priority edges to connect two nodes, thereby constructing a knowledge graph for power grid data assets.

9. A knowledge graph construction system for power grid data assets, characterized in that, The knowledge graph construction system includes: The data acquisition module is used to acquire power grid data; An analysis platform is used to execute a knowledge graph construction method for power grid data assets as described in any one of claims 1-8 based on the power grid data.

Images