A city power grid grid service system and method based on the Internet

Abstract

The present invention discloses an urban power grid service system and method based on the Internet. The system includes a data acquisition unit, a data processing unit, a power supply area work intensity assessment model construction unit, a grid intelligent division model construction unit and a grid result visualization unit; the data acquisition unit is used to obtain the first metadata in the power supply area; the data processing unit is used to process the first metadata and obtain the power supply area application data; the power supply area work intensity assessment model construction unit is used to construct a power supply area work intensity assessment model; the grid intelligent division model development unit is used to construct a grid intelligent division model; the visualization unit is used to output the fitting grid result and display it. The system and method proposed in the present invention comprehensively consider factors such as regional division, customer density, equipment scale, load characteristics, user needs, and urban road network, and can achieve technical effects of better service, more precise management, and lower cost.

Description

Technical Field

[0001] The present invention relates to the technical field of urban power grid service, and in particular to an urban power grid service system and method based on the Internet. Background Art

[0002] In order to improve the reliability of power supply, the urban area is divided into multiple small power supply areas by implementing grid gridding. When a fault occurs, it only affects the local area and will not cause power outages in the entire city, thereby improving power supply reliability and reducing power outage time for users.

[0003] However, at present, most units simply delineate grids based on administrative regions or customer scale, without considering the equipment operation quality and customer business needs in detail. Grid comprehensive service personnel are mostly grouped and configured based on the original work teams or grids according to the integrated business needs, resulting in insufficient actual staff allocation, low service efficiency, untimely demand response, and insufficient application of marketing data such as service operation and maintenance, business distribution, and customer demands, resulting in the failure to effectively integrate service resources. The quality and efficiency of urban power supply services urgently need to be improved. Summary of the invention

[0004] The purpose of the present invention is to provide an urban power grid service system and method based on the Internet to improve the quality and efficiency of urban power supply services.

[0005] To achieve the purpose of the present invention, the technical solution provided by the present invention is as follows:

[0006] First aspect

[0007] The present invention provides an urban power grid service system based on the Internet, the system comprising a data acquisition unit, a data processing unit, a power supply area work intensity assessment model construction unit, a grid intelligent division model construction unit and a grid result visualization unit;

[0008] The data acquisition unit is used to connect with the power marketing system, the power consumption information collection system, the power PMS system, and the GIS map system through the Internet, and obtain the first metadata in the power supply area therefrom;

[0009] The data processing unit is used to process the first metadata and obtain power supply area application data based on the processing result;

[0010] The power supply area work intensity assessment model construction unit is used to construct a power supply area work intensity assessment model based on the power supply area application data;

[0011] The grid intelligent partitioning model development unit is used to construct a grid intelligent partitioning model based on the first metadata combined with the output result of the power supply area work intensity assessment model;

[0012] The visualization unit is used to calculate the first metadata using the grid intelligent partitioning model, output the fitted grid result, and display the fitted grid result on the Siji map.

[0013] Second aspect

[0014] Corresponding to the above system, the present invention provides an Internet-based urban power grid service method, comprising the following steps:

[0015] Step S1: connecting with the power marketing system, the power consumption information collection system, the power PMS system, and the GIS map system through the Internet, and obtaining the first metadata in the power supply area;

[0016] Step S2: Processing the first metadata, and acquiring power supply area application data based on the processing result;

[0017] Step S3: constructing a power supply area work intensity assessment model based on the power supply area application data;

[0018] Step S4: constructing a grid intelligent partitioning model based on the first metadata combined with the output result of the power supply area work intensity assessment model;

[0019] Step S5: Calculate the first metadata using the grid intelligent partitioning model, output the grid fitting result, and display the grid fitting result on the Siji map.

[0020] Compared with the prior art, the technical effects of the present invention are as follows:

[0021] 1. The urban power grid service system and method proposed in the present invention comprehensively considers factors such as regional division, customer density, equipment scale, load characteristics, user needs, urban road network, etc., combines big data tracing analysis such as grid personnel level, service operation and maintenance quality, business distribution, and customer demands, integrates service resources, promotes comprehensive evaluation combining piece-rate quantification of work, equipment operation quality, and customer satisfaction, implements a scientific and reasonable regional and service team grid layout for urban power supply services, and achieves technical effects of better service, more refined management, and lower cost.

[0022] 2. The present invention is customer-centric and market-oriented. It combines geographic data, business data, complaint data, regional personnel and equipment configuration data, integrates multi-source and multi-dimensional data, and gives full play to the massive data processing capabilities and computing advantages of big data analysis tools. It uses data mining and analysis algorithms to carry out data quality management, correlation matching, model training and verification and other analysis work, fully explore the value of data and its relevance, and can more accurately grasp customer service needs and regional carrying capacity, plan personnel allocation in a targeted manner, and reasonably optimize grid planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A schematic diagram of the system structure provided by an embodiment of the present invention;

[0024] Figure 2 A schematic diagram of a method flow chart provided by an embodiment of the present invention;

[0025] Figure 3 It is the current work intensity distribution diagram of each service grid using existing technology;

[0026] Figure 4 It is a working intensity distribution diagram of each suggested grid using an embodiment of the present invention. DETAILED DESCRIPTION

[0027] The following is a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0028] like Figure 1 As shown, this embodiment provides an urban power grid service system based on the Internet, the system includes a data acquisition unit, a data processing unit, a power supply area work intensity assessment model construction unit, a grid intelligent division model construction unit and a grid result visualization unit;

[0029] The data acquisition unit is used to connect with the power marketing system, the power consumption information collection system, the power PMS system, and the GIS map system through the Internet, and obtain the first metadata in the power supply area therefrom;

[0030] The first metadata includes the following:

[0031] By connecting with the power marketing system, we can obtain marketing customer information, arrears information, payment information, power outage information, work order information, personnel information, power supply area information, line information, and grid division, customer management, and marketing business data that support the grid foundation;

[0032] By connecting with the electricity consumption information collection system, we can obtain customers' daily electricity consumption data, equipment collection abnormal data, and support collection of fault elimination and abnormal electricity consumption warning data;

[0033] By connecting with the power PMS system, equipment fault information data is obtained;

[0034] By connecting with the GIS map system, the transformer coordinates, user coordinates and equipment coordinates of the power supply area are obtained.

[0035] The data processing unit is used to process the first metadata and obtain power supply area application data based on the processing result;

[0036] It should be noted that by using big data analysis technologies such as AHP hierarchical analysis method, cluster analysis K-means algorithm, R / Python data crawling, etc., various heterogeneous metadata are processed, governed and preliminarily calculated to obtain indicator weighting results, address information, power supply station distance, visual position of power supply station in geographic two-dimensional space, and adjacent status between power supply service grids as power supply station application data, providing data support and auxiliary decision-making for grid layout research and formulation.

[0037] Specifically, the data processing unit includes a conversion module, a decision module, a selection module, a clustering module, an extraction module, a measurement module, a determination module and a judgment module;

[0038] The conversion module is used to convert the acquired first metadata into a set analysis format to obtain second metadata after the analysis format is converted;

[0039] Specifically, the conversion module is used as follows:

[0040] Querying a preset format template from an analysis format library, and deserializing the first metadata into key-value pair format data according to the format template;

[0041] The key-value pair format data is converted into unified indicator data, and the indicator and time dimension are aggregated to obtain the second metadata.

[0042] The decision module is used to extract decision indicators from the second metadata using the hierarchical analysis method;

[0043] Specifically, the analytic hierarchy process is a practical decision-making method for analyzing complex systems composed of numerous interrelated and mutually constrained factors. It combines qualitative analysis and quantitative analysis and is suitable for target systems with hierarchical and staggered evaluation indicators and decision-making problems whose target values ​​are difficult to describe quantitatively.

[0044] The selection module is used to weight the decision-making indicators based on the inherent rules between the indicator data and the subjective weight method;

[0045] Specifically, a subjective and objective comprehensive weighting method is adopted. This method weights the decision indicators based on the internal rules between the indicator data and the expert experience at the same time, so that the attribute weighting can achieve the unity of subjective and objective, and then make the decision result true and reliable. Among them, the objective weighting method includes the entropy weight discrimination model, the principal component analysis model, and the coefficient of variation model. The subjective weighting method is an earlier and more mature method studied by people. The advantage of the subjective weighting method is that experts can reasonably determine the ranking of the weights of each attribute based on the actual decision-making problem and the expert's own knowledge and experience, so as to avoid the situation where the attribute weight is inconsistent with the actual importance of the attribute.

[0046] Specifically, the calculation formula of the subjective weight of the decision indicator is:

[0047]

[0048] In the formula, Indicates j The full score of the decision indicator is Indicates j The subjective weight of the decision-making indicators, n Equal to the number of decision indicators.

[0049] The clustering module is used to group and cluster the weighted results and output the clustering results;

[0050] Cluster analysis is to discover the relationship between data objects in the data and group the data. The greater the similarity within the group and the greater the difference between the groups, the better the clustering effect. In this project, it is mainly used for data observation and confirmation of the scores of each indicator.

[0051] The extraction module is used to obtain address information from the second metadata according to the set rules and Python crawling technology;

[0052] Specifically, a program or script that automatically crawls World Wide Web information according to certain rules can obtain address information of communities, buildings, etc., and support the realization of grid visualization display function.

[0053] The measuring module is used to measure the distance of the power supply area based on the Euclidean distance and the second metadata to obtain the distance of the power supply area;

[0054] Specifically, the calculation principle of the Euclidean distance algorithm adopts the well-known technology.

[0055] The determination module is used to determine the visualized position of the power supply station area in the geographic two-dimensional space based on the convex polygon algorithm and the second metadata;

[0056] Specifically, for several points on a plane, a polygon can be used to "enclose" all the points in a way that passes through the vertices. According to the principle that two points determine a straight line, if the remaining points are on the same side of the straight line, then the two points are points on the convex hull, otherwise they are not, and the algorithm is exhausted until all vertices are determined. In this embodiment, the algorithm is applied to determine the visual position of the station area in the two-dimensional geographic space.

[0057] The judgment module is used to judge whether there are intersections or adjoining power supply service grids based on the second metadata, and output the judgment result.

[0058] Specifically, whether a certain polygon on a plane intersects with another plane polygon is determined by successively judging whether the vertices of a certain polygon fall inside the other polygon. If they fall inside the polygon, it means that the two polygons intersect.

[0059] To determine whether a point falls within a polygon, the ray method is used. For example, if the point is along the x-direction to negative infinity, if the number of edges crossed is odd, then the point is inside the polygon; if the number of edges crossed is even, then the point is outside the polygon.

[0060] This algorithm is used in this embodiment to determine whether there are intersections or adjoining power supply service grids, which serves as an important basis for determining whether the intelligent partitioning model has reached a relatively optimal state.

[0061] The power supply area work intensity assessment model construction unit is used to construct a power supply area work intensity assessment model based on the power supply area application data;

[0062] Specifically, the power supply area work intensity assessment model construction unit includes an acquisition module, an analysis module, a mining module, an indicator assessment module, a determination module and an optimization module;

[0063] Wherein, the acquisition module is used to acquire the power supply area application data required for model construction;

[0064] The analysis module is used to perform cluster analysis on the power supply area application data using an unsupervised learning algorithm, and classify the areas whose similarity reaches a preset standard into one category through clustering to form different work intensity groups;

[0065] The indicator evaluation module is used to extract the indicators of each dimension of the work intensity group and construct the work intensity evaluation model of the power supply area based on the indicators of each dimension;

[0066] The extracting of the dimensional indicators of the work intensity group and constructing the work intensity assessment model of the power supply area based on the dimensional indicators specifically includes the following:

[0067] Read the result data and process data of all target objects according to the group filtering instruction, and extract information of several dimensional indicators from the result data and process data, wherein the dimensional indicators include at least one of the distance from the substation to the power supply station, the total number of users, the load rate, the maximum power supply diameter, the line loss abnormality, the collection success rate, the load rate, the 24-hour success rate of the substation, the number of power outages in the substation, the number of complaints in the substation, the number of opinion work orders, and the number of fault repair service work orders in the substation;

[0068] The information of each dimensional indicator is vectorized to obtain the characteristic vector of each dimensional indicator, and a characteristic matrix representing each dimensional target is generated based on the characteristic vector;

[0069] Based on the characteristic matrix, scientific scores and weights are set for each dimensional indicator, and a power supply substation work intensity assessment model is constructed in combination with the substation service base, work difficulty, substation operation status, and substation service work orders.

[0070] The mining module is used to discover the correlation between indicators of different dimensions by combining the association rule algorithm with the different work intensity groups;

[0071] Specifically, the different work intensity groups are combined with an association rule algorithm to discover the correlation between indicators of different dimensions, which specifically includes the following:

[0072] Obtaining clustered work intensity group data, performing unified management of data representation on the work intensity group data according to evaluation indicators and indicator values, and obtaining unified work intensity group data;

[0073] Based on the FP-Growth algorithm, the unified work intensity group data is analyzed for correlation and a list of strong correlation rules is obtained;

[0074] Performing verification rule generation processing on the strong association rule list to obtain the verification rule list;

[0075] The group data reported in the verification rule list area are verified one by one using the verification rule list, and abnormal data that does not meet the verification rules is removed.

[0076] The determination module is used to formulate a subjective and objective value assignment method for the work intensity group in combination with expert knowledge to determine the weight of each dimensional indicator, and add up the indicators of each dimension to obtain the final work intensity score;

[0077] Specifically, the principal component analysis method and the entropy weight method are combined to perform weight analysis to obtain the weight results, and the weight results of the two indicators are sorted in descending order according to the weight of the "principal component analysis method".

[0078] The optimization module is used to evaluate and optimize the power supply area work intensity assessment model using the second metadata, compare the difference between the actual work intensity and the model assessment result, and make adjustments and improvements.

[0079] Specifically, after scientifically scoring and weighting each indicator, the grid manager's work intensity is comprehensively evaluated through the service base of the substation, the degree of work difficulty, the operation status of the substation, and the substation service work orders. , the specific formula is as follows:

[0080]

[0081] In the formula, They respectively represent the service base of the station, the degree of work difficulty, the operation status of the station, the service work orders of the station and the coefficient of work difficulty.

[0082] The grid intelligent partitioning model development unit is used to construct a grid intelligent partitioning model based on the first metadata combined with the output result of the power supply area work intensity assessment model;

[0083] When constructing the service grid intelligent partition model, the first step is to establish the location and geographical boundaries of the substation based on the longitude and latitude of the transformer and meter box in the substation. Apply K-means clustering and greedy algorithm, combined with the output results of the power supply substation work intensity assessment model, and based on the number of existing substation managers in the power supply station, construct the service grid intelligent partition model and output the service grid intelligent partition results: establish the corresponding relationship between the service grid and the power supply substation, form the key point coordinates of the geographical boundary of the grid unit, and the grid unit name, number of covered customers, business conditions and other information on the grid unit.

[0084] Specifically, the grid intelligent partitioning model development unit includes a loading module, a building module and a partitioning module;

[0085] The loading module is used to obtain the longitude and latitude of the transformer and meter box in the substation area in the second metadata, and establish the location and geographical boundaries of the substation area;

[0086] The building module is used to apply K-means clustering and greedy algorithm, combined with the output results of the power supply area work intensity assessment model, and build a grid intelligent division model based on the number of existing area managers of the power supply station;

[0087] Specifically, the building module is used as follows:

[0088] Use the K-means clustering algorithm to cluster the power supply areas, divide similar power supply areas into the same group, and obtain different service grids based on the clustering results;

[0089] Use the greedy algorithm to optimize the division results of the service grid, and select the optimal number of area managers through iteration;

[0090] Combined with the output results of the power supply area work intensity assessment model, the work intensity information is set as an indicator for the decision-making service grid division results;

[0091] According to the indicators of the decision-making service grid division results, combined with the number of existing substation managers and the characteristics of each power supply substation, a reasonable service grid is automatically divided, and finally a grid intelligent division model is constructed.

[0092] The division module is used to establish a corresponding relationship between the service grid and the power supply area according to the division result of the grid intelligent division model.

[0093] The visualization unit is used to calculate the first metadata using the grid intelligent partitioning model, output the fitted grid result, and display the fitted grid result on the Siji map.

[0094] Specifically, based on the template import, the transformer, the substation, the virtual meter box coordinates, etc. are realized to realize the grid display of the substation on the Siji map; in the substation fitting process, the grid-substation corresponding ownership situation, the power supply weak link display data and the grid manager work evaluation data are imported, and after the background model calculation, the fitting grid situation is output, and the overall substation grid fitting is realized through the Siji map.

[0095] like Figure 2 As shown, this embodiment provides an Internet-based urban power grid service method, including the following steps:

[0096] Step S1: connecting with the power marketing system, the power consumption information collection system, the power PMS system, and the GIS map system through the Internet, and obtaining the first metadata in the power supply area;

[0097] Step S2: Processing the first metadata, and acquiring power supply area application data based on the processing result;

[0098] Step S3: constructing a power supply area work intensity assessment model based on the power supply area application data;

[0099] Step S4: constructing a grid intelligent partitioning model based on the first metadata combined with the output result of the power supply area work intensity assessment model;

[0100] Step S5: Use the grid intelligent partitioning model to calculate the first metadata, output the fitted grid result, and display the fitted grid result on the Siji map.

[0101] Below, a power supply service center is taken as a sample unit. According to the dimensions of the geographical location of the substation, the operation status of the equipment in the substation, the nature of the customers served by the substation, the workload of 95598 in the substation, etc., the work intensity evaluation model is applied to evaluate and analyze the work intensity distribution of the current power supply service grid and the intelligent power supply service grid of the power supply station, focusing on displaying the weak links of the power supply service grid, supporting the power supply station managers to grasp the current grid division work intensity and realize lean management.

[0102] like Figure 3 As shown in the figure, from the distribution diagram of the current service grid work intensity of a power supply service center using existing technology, it is found that the current average grid work intensity index is 1208.78, with a large overall difference. Among them, the work intensity of grid number 21 is the highest, which is 2052.01; the work intensity of grid number 13 is the lowest, which is only 79.

[0103] Further analysis of the differences in work intensity among grids revealed that the substation manager of grid number 21 managed 65 substations, serving 52,486 electricity users, 74 substations with abnormal line loss, 37 substations with a collection success rate less than 100%, 10 substations with a recharge success rate less than 99%, 6 temporary power outages, 0 planned power outages, and 309 95,598 work orders of various types (119 fault reports and 126 service applications); while the substation manager of grid number 13 was only responsible for 3 substations, serving 2,046 electricity users, 9 substations with abnormal line loss, 1 substation with a collection success rate less than 100%, 0 substations with a recharge success rate less than 99%, 0 temporary and planned power outages, and 0 95,598 work orders.

[0104] From the current geographical distribution of grids in a power supply service center, it is found that the current service grid areas have a large span, the geographical space of the substations to which they belong is not concentrated, and there is room for optimization in the service areas of substation managers.

[0105] like Figure 4 As shown, from the distribution diagram of the work intensity of each recommended grid using the embodiment of the present invention, it is found that the average work intensity index of the recommended grid is 1439.59, and the overall difference is small. Among them, the work intensity of grid number 12 is relatively the highest, which is 1470.48; the work intensity of grid number 35 is relatively the lowest, which is only 1410.45.

[0106] Further analysis of the differences in work intensity among grids revealed that the substation manager of grid number 12 managed 41 substations, serving 24,178 electricity users, 27 substations with abnormal line loss, 12 substations with a collection success rate less than 100%, 4 substations with a recharge success rate below 99%, 1 temporary power outage, 7 planned power outages, and 106 95,598 work orders of various types (36 fault reports and 37 service applications); while the substation manager of grid number 35 was responsible for 32 substations, serving 21,881 electricity users, 74 substations with abnormal line loss, 15 substations with a collection success rate less than 100%, 6 substations with a recharge success rate below 99%, 6 temporary power outages, 1 planned power outage, and 110 95,598 work orders (including 38 fault repairs and 37 service applications).

[0107] There is no obvious difference in the distribution of business work between the grid with maximum work intensity and the grid with minimum work intensity. Although the 12-grid management area with maximum work intensity has 9 more areas than the 35-grid management area with minimum work intensity, the number of line loss anomalies in the 35-grid management area with minimum work intensity is more than that in the 12-grid management area with maximum work intensity. An overall review of the application distribution shows that the recommended grid division result is better, achieving a balanced effect of over-intensity work.

[0108] Finally, it should be noted that the above embodiments are only used to illustrate and explain the present invention, and are not intended to limit the present invention to the scope of the described embodiments. In addition, those skilled in the art can understand that the present invention is not limited to the above embodiments, and more variations and modifications can be made according to the teachings of the present invention, and these variations and modifications all fall within the scope of the protection claimed by the present invention.

Claims

1. An urban power grid service system based on the Internet, characterized in that: The system includes a data acquisition unit, a data processing unit, a power supply area work intensity assessment model construction unit, a grid intelligent division model construction unit and a grid result visualization unit; The data acquisition unit is used to connect with the power marketing system, the power consumption information collection system, the power PMS system, and the GIS map system through the Internet, and obtain the first metadata in the power supply area therefrom; The data processing unit is used to process the first metadata and obtain the power supply area application data based on the processing result; Wherein, the data processing unit includes a conversion module, a decision module, a selection module, a clustering module, an extraction module, a measurement module, a determination module and a judgment module; The conversion module is used to convert the acquired first metadata into a set analysis format to obtain second metadata after the analysis format is converted; The decision module is used to extract decision indicators from the second metadata using the hierarchical analysis method; The selection module is used to weight the decision indicators based on the inherent rules between the indicator data and the subjective weight method; The clustering module is used to group and cluster the weighted results and output the clustering results; The extraction module is used to obtain address information from the second metadata according to the set rules and Python crawling technology; The measuring module is used to measure the distance of the power supply area based on the Euclidean distance and the second metadata to obtain the distance of the power supply area; The determination module is used to determine the visualized position of the power supply station area in the geographic two-dimensional space based on the convex polygon algorithm and the second metadata; The judgment module is used to judge whether there are intersections or adjoining power supply service grids based on the second metadata, and output the judgment result; The power supply area work intensity assessment model construction unit is used to construct a power supply area work intensity assessment model based on the power supply area application data; The power supply area work intensity assessment model construction unit includes an acquisition module, an analysis module, a mining module, an indicator assessment module, a determination module and an optimization module; The acquisition module is used to acquire the power supply area application data required for model construction; The analysis module is used to perform cluster analysis on the power supply area application data using an unsupervised learning algorithm, and classify the areas whose similarity reaches a preset standard into one category through clustering to form different work intensity groups; The indicator evaluation module is used to extract the indicators of each dimension of the work intensity group and construct the work intensity evaluation model of the power supply area based on the indicators of each dimension; The mining module is used to discover the correlation between indicators of different dimensions by combining the association rule algorithm with the different work intensity groups; The determination module is used to formulate a subjective and objective value assignment method for the work intensity group in combination with expert knowledge to determine the weight of each dimensional indicator, and add up the indicators of each dimension to obtain the final work intensity score; The optimization module is used to evaluate and optimize the power supply area work intensity assessment model using the second metadata, compare the difference between the actual work intensity and the model assessment result, and make adjustments and improvements; The grid intelligent partitioning model development unit is used to construct a grid intelligent partitioning model based on the first metadata combined with the output result of the power supply area work intensity assessment model; The visualization unit is used to calculate the first metadata using the grid intelligent partitioning model, output the fitted grid result, and display the fitted grid result on the Siji map.

2. The Internet-based urban power grid service system according to claim 1, characterized in that: The first metadata includes the following: By connecting with the power marketing system, we can obtain marketing customer information, arrears information, payment information, power outage information, work order information, personnel information, power supply area information, line information, and grid division, customer management, and marketing business data that support the grid foundation; By connecting with the electricity consumption information collection system, we can obtain customers' daily electricity consumption data, equipment collection abnormal data, and support collection and elimination of faults and abnormal electricity consumption warning data; By connecting with the power PMS system, equipment fault information data is obtained; By connecting with the GIS map system, the transformer coordinates, user coordinates and equipment coordinates of the power supply station area are obtained.

3. The Internet-based urban power grid service system according to claim 1, characterized in that: The conversion module is specifically used as follows: Querying a preset format template from an analysis format library, and deserializing the first metadata into key-value pair format data according to the format template; The key-value pair format data is converted into unified indicator data, and the indicator and time dimension are aggregated to obtain the second metadata.

4. The Internet-based urban power grid service system according to claim 3 is characterized in that: The extracting of the dimensional indicators of the work intensity group and constructing the work intensity assessment model of the power supply area based on the dimensional indicators specifically includes the following: Read the result data and process data of all target objects according to the group filtering instruction, and extract information of several dimensional indicators from the result data and process data, wherein the dimensional indicators include at least one of the distance from the substation to the power supply station, the total number of users, the load rate, the maximum power supply diameter, the line loss abnormality, the collection success rate, the load rate, the 24-hour success rate of the substation, the number of power outages in the substation, the number of complaints in the substation, the number of opinion work orders, and the number of fault repair service work orders in the substation; The information of each dimensional indicator is vectorized to obtain the characteristic vector of each dimensional indicator, and a characteristic matrix representing each dimensional target is generated based on the characteristic vector; Based on the characteristic matrix, scientific scores and weights are set for each dimensional indicator, and a power supply substation work intensity assessment model is constructed in combination with the substation service base, work difficulty, substation operation status, and substation service work orders.

5. The Internet-based urban power grid service system according to claim 4, characterized in that: The method of combining the association rule algorithm with the different work intensity groups to discover the correlation between the indicators of different dimensions specifically includes the following: Obtaining clustered work intensity group data, performing unified management of data representation on the work intensity group data according to evaluation indicators and indicator values, and obtaining unified work intensity group data; Based on the FP-Growth algorithm, the unified work intensity group data is analyzed for correlation and a list of strong correlation rules is obtained; Performing verification rule generation processing on the strong association rule list to obtain the verification rule list; The group data reported in the verification rule list area are verified one by one using the verification rule list, and abnormal data that does not meet the verification rules is removed.

6. The Internet-based urban power grid service system according to claim 5, characterized in that: The grid intelligent partitioning model development unit includes a loading module, a building module and a partitioning module; The loading module is used to obtain the longitude and latitude of the transformer and meter box in the substation area in the second metadata, and establish the location and geographical boundaries of the substation area; The building module is used to apply K-means clustering and greedy algorithm, combined with the output results of the power supply area work intensity assessment model, and build a grid intelligent division model based on the number of existing area managers of the power supply station; The division module is used to establish a corresponding relationship between the service grid and the power supply area according to the division result of the grid intelligent division model.

7. The Internet-based urban power grid service system according to claim 6, characterized in that: The building module is specifically used as follows: Use the K-means clustering algorithm to cluster the power supply areas, divide similar power supply areas into the same group, and obtain different service grids based on the clustering results; Use the greedy algorithm to optimize the division results of the service grid, and select the optimal number of area managers through iteration; Combined with the output results of the power supply area work intensity assessment model, the work intensity information is set as an indicator for the decision-making service grid division results; According to the indicators of the decision-making service grid division results, combined with the number of existing substation managers and the characteristics of each power supply substation, a reasonable service grid is automatically divided, and finally a grid intelligent division model is constructed.

8. An urban power grid service method based on the Internet, characterized in that: The steps include: Step S1: connecting with the power marketing system, the power consumption information collection system, the power PMS system, and the GIS map system through the Internet, and obtaining the first metadata in the power supply area; Step S2: Processing the first metadata, and acquiring power supply area application data based on the processing result; The details include: Convert the acquired first metadata into a set analysis format to obtain second metadata after the analysis format conversion; Utilize analytic hierarchy process to extract decision indicators from the second metadata; Empower decision-making indicators based on the inherent laws between indicator data and subjective weighting method; Group and cluster the weighted results and output the clustering results; Obtain address information from the second metadata according to the set rules and Python crawling technology; The distance between the power supply areas is measured based on the Euclidean distance and the second metadata to obtain the distance between the power supply areas; Determine the visualized position of the power supply station area in the geographic two-dimensional space based on the convex polygon algorithm and the second metadata; The second metadata determines whether there are intersections or adjoining power supply service grids, and outputs the determination result; Step S3: constructing a power supply area work intensity assessment model based on the power supply area application data; The details include: Obtain the power supply area application data required for model construction; Use unsupervised learning algorithms to cluster the power supply area application data, and classify the areas with similarity that meet the preset standards into one category through clustering to form different work intensity groups; Extracting the dimensional indicators of the work intensity group, and constructing the work intensity assessment model of the power supply area based on the dimensional indicators; For the different work intensity groups, the association between indicators of different dimensions is discovered by combining association rule algorithms; According to the work intensity group, a subjective and objective value assignment method is formulated in combination with expert knowledge to determine the weight of each dimension indicator, and the indicators of each dimension are added together to obtain the final work intensity score; Using the second metadata to evaluate and optimize the power supply area work intensity assessment model, compare the difference between the actual work intensity and the model assessment result, and make adjustments and improvements; Step S4: constructing a grid intelligent partitioning model based on the first metadata combined with the output result of the power supply area work intensity assessment model; Step S5: Use the grid intelligent partitioning model to calculate the first metadata, output the fitted grid result, and display the fitted grid result on the Siji map.

Images