Power utilization address governance method based on multi-source data fusion analysis

Abstract

The invention relates to a power utilization address management method based on multi-source data fusion analysis, which is applied to the field of power grid digital management and comprises the steps of constructing a digital address space model taking an address space as a core, accessing fresh map address data and a power grid address database and the like. Based on a set of digital address library model, according to high-quality map data and power grid address data, high-quality spatial address data is formed by utilizing mutual checking and fusion of a spatial relationship and a hierarchical relationship, a digital address library with spatial information is constructed, and a power grid user change relationship and equipment coordinate fusion analysis are accessed. According to the method, mutual checking is carried out by utilizing a power grid hierarchical relationship and an address space relationship, finally, high-quality automatic analysis and matching of the power utilization addresses are realized, and address data are strongly checked by utilizing address fence information, so that the reliability of an address automatic analysis result is further improved, and the workload of power utilization address governance is greatly reduced.

Description

Technical Field

[0001] The present invention relates to a method for managing electricity usage addresses, and in particular to a method for managing electricity usage addresses based on multi-source data fusion analysis and applied in the field of digital management of power grids. Background Art

[0002] As the core information of power customer files, the electricity address is crucial for the efficient execution of fault repair and power supply services, and is also an indispensable foundation for the digital transformation of power companies. Despite multiple rounds of special electricity address data governance, electricity address data still faces many challenges, such as outdated administrative division information, inaccurate community names, and difficulty in locating users.

[0003] Traditional electricity address management mainly focuses on the standardization of address texts, maintaining and managing address information through unified text descriptions. However, after years of management, the quality of electricity address data is still difficult to meet the growing business needs. Analyzing the reasons, there are mainly the following points: 1. With the acceleration of urbanization, the demolition and reconstruction of urban villages and rural areas have led to frequent changes in address data, and there is a lack of real-time updated address data sources; 2. The diversity of addresses is part of user habits, and the addresses are called differently in different scenarios, making it difficult to achieve unified standardization; 3. The existing electricity address texts contain a lot of ambiguous location information, such as "100 meters to the left", etc. This information is difficult to accurately diagnose through existing digital technologies, making it difficult to evaluate the effectiveness of address management.

[0004] Therefore, we propose a power consumption address management method based on multi-source data fusion analysis. Summary of the invention

[0005] In view of the above-mentioned prior art, the technical problem to be solved by the present invention is: how to improve the automatic resolution rate of electricity usage addresses and reduce the workload of manual confirmation.

[0006] To solve the above problems, the present invention provides a method for electricity address management based on multi-source data fusion analysis, comprising the following steps: S1. Construct a digital address space model with address space as the core; S2. Access the fresh map address data and power grid address data, check the spatial relationship and hierarchical relationship of the accessed data, correct the deviation data, eliminate the erroneous data, and initialize the digital address library; S3. Build an address resolution engine based on the digital address database. The address resolution engine includes address entity resolution matching service and address space query service. S4, access the grid transformer equipment coordinates, use the address space query service to analyze the transformer address information; S5, access the grid transformer box user relationship, obtain the user address under the transformer area, and use the address resolution and matching capabilities to resolve the power address coordinates; S6, calculating the power consumption address resolution coordinates and transformer coordinate distance to form the user address coordinate information under the substation area; S7, based on reasonable user address coordinate information, using address space query service, calculate the address information of the coordinates; S8. Count the power consumption address information of the transformer and make secondary corrections to the transformer address information.

[0007] In the above-mentioned electricity address management method based on multi-source data fusion analysis, high-quality automatic parsing and matching of electricity addresses can be achieved, and the workload of electricity address management can be greatly reduced.

[0008] As a further improvement of the present application, the address entity resolution and matching service is based on the address library data, a customized address entity resolution and matching service is constructed, and natural language processing technology is used to perform address segmentation and recognition.

[0009] As a further improvement of the present application, the address space query service is based on the address fence and address point data of the address library, and uses spatial analysis technology to achieve hierarchical association between arbitrary point coordinates and address entities.

[0010] As a further improvement of the present application, when calculating the distance between the electricity address resolution coordinates and the transformer coordinates in step S6, different distance thresholds are set using the urban and rural characteristics of the current address. When the calculated distance between the electricity address resolution coordinates and the transformer coordinates is greater than the set distance threshold, it is determined to be unreasonable. The meter box coordinates are obtained based on the box-household relationship, the distance between the meter box coordinates and the transformer coordinates is calculated, and whether it is reasonable is determined based on the threshold. When the calculated distance between the meter box coordinates and the transformer coordinates is also greater than the set distance threshold, it is determined to be unreasonable, and the electricity address is set to an unmatched address.

[0011] To summarize, the electricity address management method in the present application is based on a set of digital address library models. According to high-quality map data and power grid address data, it utilizes the mutual verification of spatial relationships and hierarchical relationships to integrate and form high-quality spatial address data, and constructs a digital address library with spatial information. It is connected to the power grid change-user relationship and equipment coordinate fusion analysis, and utilizes the power grid hierarchical relationship and address space relationship for mutual verification, and finally realizes high-quality automatic parsing and matching of electricity addresses, and utilizes multi-source power grid address data for mutual verification, which can avoid the problem of inaccurate address data parsing caused by a single data source. Through the address engine service capability, it realizes functions such as word splitting and matching of long address texts, and uses address fence information to strongly verify address data, which further improves the reliability of the address automatic parsing results and greatly reduces the workload of electricity address management. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 This is a method flow chart of the first implementation mode of this application; Figure 2 This is a definition diagram of a digital address space model in the first embodiment of the present application; Figure 3 This is a flowchart of address library data access fusion in the first implementation mode of this application; Figure 4 This is a flowchart of address entity matching and parsing in the first implementation mode of this application. DETAILED DESCRIPTION

[0013] Two implementation modes of the present application are described in detail below with reference to the accompanying drawings.

[0014] The first implementation method: Figure 1-4 A method for managing electricity consumption addresses based on multi-source data fusion analysis is shown, comprising the following steps: S1. Construct a digital address space model with address space as the core; The digital address space model includes information such as address fences and address points, and has the functions of unifying address entities and managing address aliases and address historical names, and pays attention to the consistency of spatial locations. For details, please refer to Figure 2 ; S2. Access the fresh map address data and power grid address data, check the spatial relationship and hierarchical relationship of the accessed data, correct the deviation data, eliminate the erroneous data, and initialize the digital address library; After the address database data is modeled, the community fence is connected, and street fences, district and county fences, city fences, and provincial fences are constructed step by step according to the hierarchical relationship to achieve full coverage of the first five levels of areas; the relationship between the community fence and the building is checked through the spatial relationship, the hierarchical relationship and spatial relationship are maintained, the deviation data is corrected, and the unreliable data is eliminated. For the specific fusion process, please refer to Figure 3 ; S3. Build an address resolution engine based on the digital address database. The address resolution engine includes address entity resolution matching service and address space query service. For the specific process, please refer to Figure 4 ; The address entity resolution and matching service is based on the address database data to build a custom address entity resolution and matching service, and uses natural language processing technology to perform address segmentation and recognition; The address space query service is based on the address fence and address point data of the address database, and uses spatial analysis technology to achieve hierarchical association between arbitrary point coordinates and address entities; S4, access the grid transformer equipment coordinates, use the address space query service to analyze the transformer address information; The coordinates of the transformer equipment corresponding to the upper-level substation of the grid user are connected, and the address information of the province, city, district, county, street, community, and district where the transformer is located is generated by calculating the spatial relationship with the address library, and the reference address information is established for the address data; S5, access the grid transformer box user relationship, obtain the user address under the transformer area, and use the address resolution and matching capabilities to resolve the power address coordinates; S6, calculating the power consumption address resolution coordinates and transformer coordinate distance to form the user address coordinate information under the substation area; When calculating the distance between the power consumption address resolution coordinates and the transformer coordinates, different distance thresholds are set using the current address urban and rural characteristics. When the calculated distance between the power consumption address resolution coordinates and the transformer coordinates is greater than the set distance threshold, it is determined to be unreasonable. The meter box coordinates are obtained according to the box-household relationship, and the distance between the meter box coordinates and the transformer coordinates is calculated. Whether it is reasonable is determined according to the threshold. When the calculated distance between the meter box coordinates and the transformer coordinates is also greater than the set distance threshold, it is determined to be unreasonable, and the power consumption address is set as an unmatched address. The above steps form the user address coordinate information under the substation area. S7, based on reasonable user address coordinate information, using address space query service, calculate the address information of the coordinates; For user coordinates whose calculated distance is less than the distance threshold, the address information of the coordinates is obtained through the address space query service to ensure the uniformity of the address entity; S8, collecting electricity consumption address information of transformers, and revising transformer address information for the second time; The user addresses under the substation where the transformer is located are classified and counted. If the proportion of user address consistency is greater than a reasonable threshold, but is inconsistent with the transformer address information, it means that the transformer address information is incorrect and the transformer address information needs to be corrected a second time to complete the automatic matching and confirmation of the electricity address.

[0015] The electricity address management method in the present application is based on a set of digital address library models. According to high-quality map data and power grid address data, spatial relationships and hierarchical relationships are mutually verified to form high-quality spatial address data, and a digital address library with spatial information is constructed. The power grid is connected to the household relationship and equipment coordinate fusion analysis, and the grid hierarchical relationship and address space relationship are mutually verified, so as to finally achieve high-quality automatic parsing and matching of electricity addresses, and use multi-source power grid address data for mutual verification, which can avoid the problem of inaccurate address data parsing caused by a single data source. Through the address engine service capability, the functions of long text word splitting and matching of addresses are realized, and the address fence information is used to strongly verify the address data, which further improves the reliability of the address automatic parsing results and greatly reduces the workload of electricity address management.

[0016] The first implementation method: In order to further clearly and completely describe the technical solution of the present application, the implementation steps of the present application are described with specific examples, as follows: Substation name: Zhonghai Phoenix Xi'an 1# Transformer Transformer coordinates: 118.75833232,32.04211123 The addresses and meter box coordinates of the 5 users in the substation area: Yu Yi: 2-1-602, No. 1 Qingliangmen Street, Gulou District, Nanjing City, Jiangsu Province, meter box coordinates 118.75953, 32.04209 Liu Er: Room 502, Unit 1, Building 2, Phase 1, Zhonghai Phoenix Xi'an, Jianye District, Nanjing, Jiangsu Province, meter box coordinates 118.75950,32.04199 Zhang San: Room 701, Unit 1, Building 3, Phase 1, Zhonghai Phoenix Xi'an, Gulou District, Nanjing, Jiangsu Province, meter box coordinates 118.75863,32.04167 Li Si: Room 302, Building 130, No. 128-138 Fenghuang West Street, Gulou District, Nanjing, Jiangsu Province, meter box coordinates 118.75908, 32.04158 Wang Wu: Room 101, Unit 1, Building 23, Huayang Jiayuan Community, Gulou District, Nanjing City, Jiangsu Province, meter box coordinates 118.75111,32.04286 Step 1: Based on the transformer coordinates, use the digital space address library to generate the address: Phase 1 of Zhonghai Phoenix Xi'an, No. 1 Qingliangmen Street, Gulou District, Nanjing City, Jiangsu Province; Step 2: According to the household-transformer relationship, parse the land address text, match the user coordinates, and calculate the distance to the transformer as follows: Yu Yi: Matching coordinates 118.75958,32.04195, distance: 118.9594 meters Liu Er: Matching coordinates 118.75958,32.04195, distance: 118.9594 meters Zhang San: Matching coordinates 118.75865, 32.04164, distance: 34.8998 meters Li Si: Matching coordinates 118.75575, 32.03923, distance: 402.3515 meters Wang Wu: matching coordinates 118.75110,32.04284, distance: 686.4824 meters; Step 3: Set the city transformer and user coordinate threshold to 350 meters. The results of each user address resolution are as follows: Yu Yi: less than the threshold, through the space query service, the electricity address is Room 602, Unit 1, Building 2, Phase 1, Zhonghai Phoenix Xi'an, Gulou District, Nanjing, Jiangsu Province Liu Er: Less than the threshold, through the space query service, the electricity address is Room 502, Unit 1, Building 2, Phase 1, Zhonghai Phoenix Xi'an, Gulou District, Nanjing, Jiangsu Province Zhang San: less than the threshold, through the space query service, the electricity address is Room 701, Unit 1, Building 3, Phase 1, Zhonghai Phoenix Xi'an, Gulou District, Nanjing, Jiangsu Province Li Si: Exceeding the threshold, the distance calculated by the meter box coordinates is 91.9551 meters. Within the threshold, the electricity address is Room 302, Building 3, Phase 1, Zhonghai Phoenix Xi'an, Gulou District, Nanjing, Jiangsu Province, through the space query service. Wang Wu: exceeds the threshold. The distance calculated by the meter box coordinates is 685.8129 meters, which still exceeds the threshold. Wang Wu's address information is unreliable. The recommended address is the transformer address, No. 1 Qingliangmen Street, Gulou District, Nanjing City, Jiangsu Province, China Overseas Phoenix Xi'an Phase 1; Step 4: The address information of 4 users under the transformer is counted, namely, Phase 1 of Zhonghai Phoenix Xi'an, No. 1 Qingliangmen Street, Gulou District, Nanjing City, Jiangsu Province. The proportion of the address information consistent with the transformer is 80%. The final conclusion is that the transformer address, the parsed addresses and coordinates of Yu Yi, Liu Er, Zhang San, and Li Si are credible, and the address of Wang Wu user is not credible. The recommended address is Phase 1 of Zhonghai Phoenix Xi'an, No. 1 Qingliangmen Street, Gulou District, Nanjing City, Jiangsu Province.

[0017] In this example, the technical features of this application are based on spatial entity resolution and matching, and combined with multiple data sources, it avoids the inaccurate matching problem caused by a single technical feature, and creatively utilizes fusion analysis techniques such as address space relationships, power grid hierarchical relationships, and text semantic processing to improve the matching degree and accuracy of electricity address resolution.

[0018] In view of current practical needs, the above-mentioned implementation mode adopted in this application is not limited to the scope of protection. Various changes made within the knowledge scope of technical personnel in this field without departing from the concept of this application still fall within the scope of protection of the present invention.

Claims

1. A method for electricity address management based on multi-source data fusion analysis, characterized in that: The following steps are involved: S1. Construct a digital address space model with address space as the core; S2. Access the fresh map address data and power grid address data, check the spatial relationship and hierarchical relationship of the accessed data, correct the deviation data, eliminate the erroneous data, and initialize the digital address library; S3. Build an address resolution engine based on the digital address database. The address resolution engine includes address entity resolution matching service and address space query service. S4, access the grid transformer equipment coordinates, use the address space query service to analyze the transformer address information; S5, access the grid transformer box user relationship, obtain the user address under the transformer area, and use the address resolution and matching capabilities to resolve the power address coordinates; S6, calculating the power consumption address resolution coordinates and transformer coordinate distance to form the user address coordinate information under the substation area; S7, based on reasonable user address coordinate information, using address space query service, calculate the address information of the coordinates; S8. Count the power consumption address information of the transformer and make secondary corrections to the transformer address information.

2. The method for electricity address management based on multi-source data fusion analysis according to claim 1 is characterized in that: The address entity resolution and matching service is based on the address database data to build a custom address entity resolution and matching service, and uses natural language processing technology to perform address segmentation and recognition.

3. The method for electricity address management based on multi-source data fusion analysis according to claim 1 is characterized in that: The address space query service is based on the address fence and address point data of the address library, and utilizes the space analysis technology to realize the hierarchical association between the coordinates of any point and the address entity.

4. The method for electricity address management based on multi-source data fusion analysis according to claim 1 is characterized in that: When calculating the distance between the electricity address resolution coordinates and the transformer coordinates in step S6, different distance thresholds are set using the urban and rural characteristics of the current address. When the calculated distance between the electricity address resolution coordinates and the transformer coordinates is greater than the set distance threshold, it is determined to be unreasonable. The meter box coordinates are obtained based on the box-household relationship, the distance between the meter box coordinates and the transformer coordinates is calculated, and whether it is reasonable is determined based on the threshold. When the calculated distance between the meter box coordinates and the transformer coordinates is also greater than the set distance threshold, it is determined to be unreasonable, and the electricity address is set as an unmatched address.

Images