Precise portraying method for court portrait based on marketing and distribution data fusion

Abstract

The invention discloses a distribution room portrait accurate description method based on marketing and distribution data fusion, which comprises the following steps: acquiring and fusing multi-source data of an electric power distribution room, determining a mapping relationship between distribution room business and the multi-source data, and establishing a distribution room label system based on marketing and distribution data fusion; adopting an association rule algorithm introducing a fuzzy set theory to convert quantized data in the transformer area label system into qualitative features so as to realize conversion from the transformer area label system to a transformer area portrait system; and carrying out graph clustering analysis based on a louvain community detection algorithm on the transformer area portrait features in the transformer area portrait system, and generating clustered transformer area portrait features to show transformer area portrait strong association features. According to the invention, comprehensive control and optimal management of the operation state of the transformer area can be realized, and the management efficiency and the service quality of the transformer area are effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of power system substation profiling, and in particular to a method for accurately depicting substation profiling based on marketing and distribution data fusion. Background Art

[0002] With the rapid development of the power system and the diversification of user needs, the management and operation of the distribution network are facing new challenges. The marketing and distribution network data of the substation are scattered in different systems and departments, lacking an effective integration and sharing mechanism, resulting in serious information islands. In addition, the traditional substation management method is relatively extensive, lacking accurate analysis and response to equipment status, user conditions, substation characteristics, etc., which further affects the response speed and processing efficiency of the substation, and affects the customer service quality and user satisfaction. In this regard, the data fusion and analysis of substation marketing and distribution network data are particularly critical. Only with accurate data support can we achieve comprehensive control and optimized management of the substation operation status, and effectively improve the management efficiency and service quality of the substation. Summary of the invention

[0003] The purpose of the present invention is to provide a method for accurately depicting substation portraits based on the fusion of marketing and distribution data. By conducting graph clustering analysis based on the Louvain community detection algorithm, the correlation between labels is displayed, a substation label map is constructed, and labels are predicted, thereby achieving comprehensive control and optimized management of the substation operation status, effectively improving the management efficiency and service quality of the substation.

[0004] In order to achieve the above objectives, the present invention is implemented by the following technical solutions:

[0005] A method for accurately depicting a substation area image based on the fusion of distribution data includes the following steps:

[0006] Step S1: Acquire and integrate multi-source data of the power substation, determine the mapping relationship between the substation business and the multi-source data, and establish a substation label system based on the fusion of marketing and distribution data.

[0007] Step S2: using an association rule algorithm that introduces fuzzy set theory to transform the quantitative data in the substation label system into qualitative features, so as to achieve the transformation of the substation label system into a substation portrait system.

[0008] Step S3: Performing a graph clustering analysis based on the Louvain community detection algorithm on the substation portrait features in the substation portrait system to generate clustered substation portrait features to show strong correlation features of the substation portrait.

[0009] Optionally, step S1 includes: the multi-source data includes: according to the key contents and needs of each business of the power grid, the marketing data, the electricity consumption data and the distribution network equipment data of the power substation are obtained and collected from the marketing service system, the electricity consumption information collection system, the business operation center and the power supply service command center; according to the marketing data, the electricity consumption data and the distribution network equipment data indicators, the marketing and distribution data are integrated, and according to the expert experience, the mapping relationship between the substation business and the substation multi-source data is determined to construct the substation label system. The substation label system includes at least six dimensions: basic information of the substation, line loss management, business expansion services, new loads, power quality and quality services. Each dimension corresponds to a number of different detailed indicators.

[0010] Optionally, step S2 includes: step S2.1, determining the qualitative characteristics of the quantitative data of the label system based on a fuzzy evaluation algorithm.

[0011] Step S2.2: Fuzzify the quantitative data in the label system, and then calculate the support of the quantitative data in each fuzzy interval according to the membership function to determine the fuzzy frequent item set.

[0012] Step S2.3: After obtaining the fuzzy frequent item set, a strong rule is determined according to the minimum support, so as to convert the quantitative data into qualitative features, so as to realize the conversion from the substation label system to the substation portrait system.

[0013] Optionally, the step S2.1 includes: defining an original label library D for m indicators in the station area label system B Fuzzy attribute item set I:

[0014] I={I1,I2,…I m}

[0015] In the formula, I1 represents the total number of users in the area, I2 represents the line loss rate, I3 represents the number of business expansion orders, I4 represents the photovoltaic power generation, ..., I m Number of work orders;

[0016] Convert the fuzzy attribute item set I into the fuzzy attribute tag library D f The attribute item set I f ,

[0017]

[0018] In the formula, the original label library D B Each attribute in I j In the fuzzy attribute tag library D f There is q j A fuzzy attribute value is associated with it;

[0019] The subscripts represent the m indicators in the area label system, and the superscripts represent the different characteristics of the area to which each indicator can correspond. It is represented by the qth position of index m m kind of characteristics.

[0020] Optionally, the step S2.2 includes: dividing the quantized data into a plurality of fuzzy intervals and obtaining a specific membership function; calculating the support of the quantized data in each fuzzy interval according to the membership function;

[0021] For a fuzzy attribute set X, X = {x1, x2, ... x n}∈I f

[0022] In the formula, x n Represents the fuzzy attribute item set I f The sub-collection elements in ;

[0023] The support of the i-th record for X is as follows:

[0024]

[0025] Among them, the fuzzy attribute x j The value of the i-th record is Sup i (X) represents the supremum of the fuzzy attribute set X;

[0026] Fuzzy attribute set X = {x1, x2, ...x n}∈I f In the fuzzy attribute tag library D f The support in is as follows:

[0027]

[0028] In the formula, |D f | represents the fuzzy attribute tag library D f The number of elements of Sup t (X) is represented as the supremum of the t-part fuzzy attribute set X;

[0029] based on The calculated support determines the fuzzy frequent item set Y;

[0030]

[0031] Where, X n Represented as the nth fuzzy attribute set.

[0032] Optionally, step S2.3 includes: for the minimum support of each sub-item in the fuzzy frequent item set Y, selecting the maximum minimum support To determine the qualitative characteristics of quantitative data.

[0033] Optionally, the step S3 includes: step S3.1, mapping all features in the substation portrait system into a weight map, each feature corresponds to each vertex in the weight map, and each vertex is connected by a correlation degree to obtain a network diagram; the greater the correlation degree, the greater the weight and the thicker the connection line.

[0034] Step S3.2: Initialize each node in the network graph as an independent community. After obtaining the nodes of the weight graph, traverse each node in the weight graph and calculate the change in relative modularity gain of the node from the current community to the communities where all neighboring nodes are located. If the relative modularity gain is positive, merge the node from the current community into the community where the neighbor node with the largest relative modularity is located. Repeat this operation until no node joins the new community.

[0035] Step S3.3: Compress the merged communities, update each community to a new super node, set the sum of the total weights of the edges between communities as the weight of the edges between the new nodes, and the sum of the weights of all the edges in the community as the self-loop weight within the new node. At this time, a new network graph is generated and the overall modularity of the new network graph is calculated.

[0036] If the increment Q of the overall modularity is less than the set threshold, the calculation is stopped and the result is output. Otherwise, a new network diagram is generated as data input, and step S3.2 is repeated, and the modularity increment Q is calculated again until the increment Q of the overall modularity is less than the set threshold. The overall calculation is completed, and finally the clustered substation portrait features are generated to show the strong correlation characteristics of the substation portrait.

[0037] Optionally, the correlation calculation formula P(B|A) in step S3.1 is as follows:

[0038] P(B|A)=P(A∩B) / P(A)

[0039] A means that the area has feature A, and B means that the area has feature B. The probability of feature B appearing when feature A exists in the area is calculated as the correlation between the features.

[0040] The gain change calculation formula in step S3.2 is as follows:

[0041]

[0042] Among them, ∑in represents the sum of the weights of the edges within the community; ∑tot represents the sum of the weights of all edges connected to the community; k i，in represents the sum of the weights of node i when it joins community c; k iRepresents the sum of the weights of all edges connected to node i;

[0043] The overall modularity calculation formula in step S3.3 is as follows:

[0044]

[0045] Among them A ij represents the edge weight between nodes i and j; k i , k j represents the edge weights between all nodes and nodes i and j; represents the average edge weight; when nodes i and j are in the same community, σ = 1, otherwise σ = 0; m represents the total number of edges in the network; c i represents the i node in community c; c j represents the j node in community c.

[0046] On the other hand, the present invention further provides an electronic device, including a processor and a memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the method described above is implemented.

[0047] In yet another aspect, the present invention further provides a readable storage medium, wherein the readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described above is implemented.

[0048] The present invention has at least the following technical effects:

[0049] The present invention discloses a method based on the fusion of multi-source data and business in the substation area, a substation label system, etc., to determine the mapping relationship between substation area business and multi-source data, to construct a substation area label system and to carry out substation area business analysis, to introduce an algorithm based on fuzzy set theory, to soften the classification boundary of numerical attributes, to complete the transformation of quantitative data to qualitative features in the index system, thereby constructing a complete substation area portrait system; and to propose a data processing based on the Louvain community detection algorithm, to complete the association rule, to construct a substation area feature map, and to carry out a graph clustering analysis based on the community detection algorithm. The present invention can realize the comprehensive control and optimization management of the substation area operation status, and effectively improve the management efficiency and service quality of the substation area. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A flow chart of a method for accurately depicting a substation area image based on the fusion of distribution data provided by one embodiment of the present invention;

[0051] Figure 2 This is a diagram of an iterative process of the Louvain algorithm used in one embodiment of the present invention;

[0052] Figure 3A graph clustering area portrait diagram based on community detection provided by an embodiment of the present invention;

[0053] Figure 4 This is a correlation analysis diagram of station area portraits provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0054] The following is a further detailed description of a method for accurately depicting a station area portrait based on the fusion of distribution data proposed by the present invention in combination with the accompanying drawings and specific embodiments. According to the following description, the advantages and features of the present invention will be clearer. It should be noted that the accompanying drawings are in a very simplified form and use non-precise proportions, which are only used to conveniently and clearly assist in explaining the purpose of the embodiments of the present invention. In order to make the purposes, features and advantages of the present invention more obvious and easy to understand, please refer to the accompanying drawings. It should be noted that the structure, proportion, size, etc. illustrated in the drawings of this specification are only used to match the contents disclosed in the specification for people familiar with this technology to understand and read, and are not used to limit the limiting conditions for the implementation of the present invention, so they have no technical substantive significance. Any modification of the structure, change in the proportional relationship or adjustment of the size, without affecting the effects that the present invention can produce and the purposes that can be achieved, should still fall within the scope of the technical content disclosed in the present invention.

[0055] The substation management unit is the foundation for realizing the integration of the terminal of the distribution business and the deep integration of the traditional management system of distribution and dispatch. Improving the lean management level of the substation is an important long-term and continuous task, whether from the perspective of the internal management of the power company or the need to improve the external customer service capabilities. Extracting high-value information that is beneficial to efficiency improvement and management upgrade from massive substation ledgers, equipment and operation data is a necessary measure to adapt to the needs of digital transformation and business transformation of power companies.

[0056] In view of this, the present invention provides a method for accurately portraying substation portraits based on the fusion of marketing and distribution data. Based on the fusion of multi-source data and business in the substation, the substation label system, etc., the mapping relationship between the substation business and the multi-source data is determined, a substation label system is constructed and substation business analysis is carried out, an algorithm based on fuzzy set theory is introduced, the classification boundary of numerical attributes is softened, and the transformation of quantitative data to qualitative features in the indicator system is completed, so as to construct a complete substation portrait system; a community detection algorithm based on Louvain (community discovery algorithm based on modularity) is proposed to complete the data processing after the association rules, construct a substation feature map, and carry out graph clustering analysis based on the community detection algorithm, so as to realize comprehensive control and optimized management of the substation operation status, and effectively improve the management efficiency and service quality of the substation.

[0057] like Figure 1 As shown, this embodiment provides a method for accurately depicting a substation area image based on the fusion of marketing and distribution data, comprising the following steps:

[0058] Step S1: Acquire and integrate multi-source data of the power substation, determine the mapping relationship between the substation business and the multi-source data, and establish a substation label system based on the fusion of marketing and distribution data.

[0059] Step S2: using an association rule algorithm that introduces fuzzy set theory to transform the quantitative data in the substation label system into qualitative features, so as to achieve the transformation of the substation label system into a substation portrait system and realize the accurate portrayal of the substation portrait.

[0060] Step S3: Performing a graph clustering analysis based on the Louvain community detection algorithm on the substation portrait features in the substation portrait system to generate clustered substation portrait features to show strong correlation features of the substation portrait.

[0061] This embodiment can achieve comprehensive control and optimized management of the operation status of the substation through the substation portrait features, effectively improving the management efficiency and service quality of the substation.

[0062] In this embodiment, the step S1 includes: the multi-source data includes: according to the key content and needs of each power grid business, the marketing data, procurement data and distribution network equipment data of the power substation are obtained and collected from the marketing service system, the electricity consumption information collection system, the business operation center and the power supply service command center; according to the marketing data, procurement data and distribution network equipment data indicators, the marketing and distribution data are integrated, and according to the expert experience, the mapping relationship between the substation business and the substation multi-source data is determined to construct the substation label system. The substation label system includes at least six dimensions: basic information of the substation, line loss management, business expansion services, new loads, power quality and high-quality services. Each dimension corresponds to a number of different detailed indicators.

[0063] That is, analyze the label requirements of the business focus in each dimension, including attributes, values, and reasons. According to the multi-source data of the substation, extract the basic statistics and power consumption feature labels, abstract the labeled substation label system library, and more comprehensively describe the multi-dimensional characteristics of the substation.

[0064] It is understandable that the marketing data may include, for example, the area file information, the number of area users, the number of business expansion work orders, the number of appeal work orders, photovoltaic capacity, etc. obtained from the marketing service system.

[0065] The usage data may include, for example, the PV power generation, PV grid-connected power, load, etc. obtained from the power usage information collection system.

[0066] The distribution network equipment data includes, for example, the substation line loss rate and substation load rate obtained from the power supply service command center.

[0067] The specific content is shown in Table 1, which is only an example of a multi-dimensional station operation and allocation index system, and the present invention is not limited to this.

[0068] For example, the label system has different detailed indicators under the six directions. For example, basic information includes detailed indicators such as the total number of users, the number of low-voltage residential users, and the number of low-voltage non-residential users. Another example is that line loss management includes detailed indicators such as collection success rate, monthly line loss rate, and anti-theft inspection violations.

[0069] Table 1 Customer label system table for distribution area

[0070]

[0071]

[0072]

[0073] Please continue to refer to Figure 2 As shown, in this embodiment, step S2 includes:

[0074] Step S2.1: Determine the qualitative characteristics of the quantitative data of the label system based on the fuzzy evaluation algorithm.

[0075] Step S2.2: Fuzzify the quantitative data in the label system, and then calculate the support of the quantitative data in each fuzzy interval according to the membership function to determine the fuzzy frequent item set.

[0076] Step S2.3: After obtaining the fuzzy frequent item set, a strong rule is determined according to the minimum support, so as to convert the quantitative data into qualitative features, so as to realize the conversion from the substation label system to the substation portrait system.

[0077] In this embodiment, step S2.1 includes: defining an original label library D for m indicators in the station area label system B Fuzzy attribute item set I:

[0078] I={I1,I2,…I m}

[0079] In the formula, I1 represents the total number of users in the area, I2 represents the line loss rate, I3 represents the number of business expansion orders, I4 represents the photovoltaic power generation, ..., I m Number of work orders;

[0080] Convert the fuzzy attribute item set I into the fuzzy attribute tag library D f The attribute item set I f ,

[0081]

[0082] In the formula, the original label library DB Each attribute in I j In the fuzzy attribute tag library D f There is q j Fuzzy attribute values ​​are associated with it; the subscripts represent the m indicators in the area label system, and the superscripts represent the different characteristics of the area to which each indicator can correspond. It is represented by the qth position of index m m kind of characteristics.

[0083] For example, taking the total number of users in the area as an example, if I1 is in D f Where is the total number of users in the area, then Indicates a low user number area, Indicates the number of users in the area, Indicates the area with high number of users, so as to correspond the quantitative data to different area characteristics.

[0084] In this embodiment, the step S2.2 includes: dividing the quantized data into a plurality of fuzzy intervals and obtaining a specific membership function; calculating the support of the quantized data in each fuzzy interval according to the membership function;

[0085] For a fuzzy attribute set X, X = {x1, x2, ... x n}∈I f

[0086] In the formula, x n Represents the fuzzy attribute item set I f The sub-collection elements in ;

[0087] The support of the i-th record for X is as follows:

[0088]

[0089] Among them, the fuzzy attribute x j The value of the i-th record is Sup i (X) represents the supremum of the fuzzy attribute set X;

[0090] Fuzzy attribute set X = {x1, x2, ...x n}∈I f In the fuzzy attribute tag library D f The support in is as follows:

[0091]

[0092] In the formula, |D f | represents the fuzzy attribute tag library D f The number of elements of Sup t (X) is represented as the supremum of the t-part fuzzy attribute set X;

[0093] based on The calculated support determines the fuzzy frequent item set Y;

[0094]

[0095] Where, X n Represented as the nth fuzzy attribute set.

[0096] In this embodiment, step S2.3 includes: for the minimum support of each sub-item in the fuzzy frequent item set Y, select the maximum minimum support To determine the qualitative characteristics of quantitative data.

[0097] For example, taking the total number of users in the area as an example, Corresponding to low, medium and high user number areas respectively, if The highest value indicates that the area has a medium number of users.

[0098] That is, the above step S2 is to carry out the label association calculation based on the fuzzy set theory of the station area data, and calculate the association between labels in different dimensions, as shown in Table 2.

[0099] Table 2: Table of correlation of area labels (partial)

[0100]

[0101] Please continue to refer to Figure 1 As shown, in this embodiment, the step S3 carries out a graph clustering analysis based on a community detection algorithm, and measures the feature association network or graph structure in a modular way based on the Louvain algorithm. A highly modular network has dense connections between nodes within a module, but sparse connections between nodes in different modules.

[0102] The step S3 includes: step S3.1, mapping all features in the substation image system into a weight map, each feature corresponds to each vertex in the weight map, and each vertex is connected by the degree of association to obtain a network diagram; the greater the degree of association, the greater the weight and the thicker the connection.

[0103] In this embodiment or some other embodiments, the correlation calculation formula P(B|A) in step S3.1 is as follows:

[0104] P(B|A)=P(A∩B) / P(A)

[0105] A indicates that the area has feature A, and B indicates that the area has feature B. The probability of feature B appearing when feature A exists in the area is calculated as the correlation between the features.

[0106] Step S3.2: Initialize each node in the network graph as an independent community. After obtaining the nodes of the weight graph, traverse each node in the weight graph and calculate the change in relative modularity gain of the node from the current community to the communities where all neighboring nodes are located. If the relative modularity gain is positive, merge the node from the current community into the community where the neighbor node with the largest relative modularity is located. Repeat this operation until no node joins the new community.

[0107] In this embodiment, the gain change calculation formula in step S3.2 is as follows:

[0108]

[0109] Among them, ∑in represents the sum of the weights of the edges within the community; ∑tot represents the sum of the weights of all edges connected to the community; k i，in represents the sum of the weights of node i when it joins community c; k i Represents the sum of the weights of all edges connected to node i.

[0110] like Figure 2 As shown, step S3.3, compress the merged community, update each community to a new super node, set the sum of the total weights of the edges between the communities as the weight of the edges between the new nodes, and the sum of the weights of all the edges in the community as the self-loop weight within the new node. At this time, a new network graph is generated, and the overall modularity of the new network graph is calculated.

[0111] If the increment Q of the overall modularity is less than the set threshold, the calculation is stopped and the result is output. Otherwise, a new network diagram is generated as data input, and step S3.2 is repeated, and the modularity increment Q is calculated again until the increment Q of the overall modularity is less than the set threshold. The overall calculation is completed, and finally the clustered substation portrait features are generated to show the strong correlation characteristics of the substation portrait.

[0112] In this embodiment, the overall modularity calculation formula in step S3.3 is as follows:

[0113]

[0114] Among them A ij represents the edge weight between nodes i and j; k i , k j represents the edge weights between all nodes and nodes i and j; represents the average edge weight; when nodes i and j are in the same community, σ = 1, otherwise σ = 0; m represents the total number of edges in the network; c i represents the i node in community c; c j represents the j node in community c.

[0115] like Figure 3 As shown in the figure, when the Louvain threshold is finally selected as 1, the aggregated / clustered area labels are generated, indicating that there is a strong correlation / strong association relationship between the area labels of this type, and the correlation relationship between the typical features of the areas in the region can be understood.

[0116] That is, step S3 measures the network or graph structure in a modular way based on the Louvain algorithm to measure the strength of the network being divided into modules. A highly modular network has dense connections between nodes within a module, but sparse connections between nodes in different modules.

[0117] like Figure 4 As shown, based on the result of step S3, the future trend changes of some substations can be predicted through the strong correlation between the substation labels, and the specific substation labels can be used for analysis and prediction to determine the probability of situations that will occur in the substation in the future.

[0118] This embodiment further provides an electronic device, including a processor and a memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the method described above is implemented.

[0119] This embodiment further provides a readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the method described above is implemented.

[0120] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0121] It should be noted that the devices and methods disclosed in the embodiments of this article can also be implemented in other ways. The device implementation described above is only schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of this article. In this regard, each box in the flowchart or block diagram can represent a part of a module, program or code, and the module, program segment or part of the code contains one or more executable instructions for implementing the specified logical function, and the module, program segment or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented by a dedicated hardware-based system for performing a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0122] In addition, the functional modules in the various embodiments of this document may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0123] Although the content of the present invention has been described in detail through the above preferred embodiments, it should be appreciated that the above description should not be considered as a limitation of the present invention. After reading the above content, it will be apparent to those skilled in the art that various modifications and substitutions of the present invention will occur. Therefore, the protection scope of the present invention should be limited by the appended claims.

Claims

1. A method for accurately depicting the image of a substation area based on the fusion of distribution data, characterized in that , including the following steps: Step S1: Acquire and integrate multi-source data of the power substation, determine the mapping relationship between substation business and multi-source data, and establish a substation label system based on the fusion of marketing and distribution data; Step S2: using an association rule algorithm that introduces fuzzy set theory to transform the quantitative data in the station area label system into qualitative features, so as to achieve the transformation of the station area label system into a station area portrait system; Step S3: Performing a graph clustering analysis based on the Louvain community detection algorithm on the substation portrait features in the substation portrait system to generate clustered substation portrait features to show strong correlation features of the substation portrait.

2. The method for accurately depicting a station area image based on the fusion of distribution data according to claim 1, characterized in that , The step S1 includes: the multi-source data includes: acquiring and collecting the marketing data, usage and procurement data and distribution network equipment data of the power substation from the marketing service system, the power consumption information collection system, the business operation center and the power supply service command center according to the key contents and needs of each business of the power grid; integrating the marketing and distribution data according to the marketing data, usage and procurement data and distribution network equipment data indicators, and determining the mapping relationship between the substation business and the multi-source data of the substation according to the expert experience, so as to construct the substation label system; The substation label system includes at least six dimensions: basic information of the substation, line loss management, business expansion services, new loads, power quality and quality services; Each dimension includes several different detailed indicators.

3. The method for accurately depicting a station area image based on the fusion of distribution data as claimed in claim 1 is characterized in that , Step S2 includes: Step S2.1, determining the qualitative characteristics of the quantitative data of the label system based on the fuzzy evaluation algorithm; Step S2.2, fuzzifying the quantitative data in the label system, and then calculating the support of the quantitative data in each fuzzy interval according to the membership function to determine the fuzzy frequent item set; Step S2.3: After obtaining the fuzzy frequent item set, a strong rule is determined according to the minimum support, so as to convert the quantitative data into qualitative features, so as to realize the conversion from the substation label system to the substation portrait system.

4. The method for accurately depicting a station area image based on the fusion of distribution data according to claim 1 is characterized in that , The step S2.1 comprises: Define the original label library D for the m indicators in the area label system B Fuzzy attribute item set I: I={I1,I2,…I m } In the formula, I1 represents the total number of users in the area, I2 represents the line loss rate, I3 represents the number of business expansion orders, I4 represents the photovoltaic power generation, ..., I m Number of work orders; Convert the fuzzy attribute item set I into the fuzzy attribute tag library D f The attribute item set I f , In the formula, the original label library D B Each attribute in I j In the fuzzy attribute tag library D f There is q j A fuzzy attribute value is associated with it; The subscripts represent the m indicators in the area label system, and the superscripts represent the different characteristics of the area to which each indicator can correspond. It is represented by the qth position of index m m kind of characteristics.

5. The method for accurately depicting a station area image based on the fusion of distribution data according to claim 1 is characterized in that , The step S2.2 includes: dividing the quantized data into a plurality of fuzzy intervals and obtaining a specific membership function; calculating the support of the quantized data in each fuzzy interval according to the membership function; For a fuzzy attribute set X, X = {x1, x2, ... x n }∈I f In the formula, x n Represents the fuzzy attribute item set I f The sub-collection elements in ; The support of the i-th record for X is as follows: Among them, the fuzzy attribute x j The value of the i-th record is Sup i (X) represents the supremum of the fuzzy attribute set X; Fuzzy attribute set X = {x1, x2, ...x n }∈I f In the fuzzy attribute tag library D f The support in is as follows: In the formula, |D f | represents the fuzzy attribute tag library D f The number of elements of Sup t (X) is represented as the supremum of the t-part fuzzy attribute set X; based on The calculated support determines the fuzzy frequent item set Y; Where, X n Represented as the nth fuzzy attribute set.

6. The method for accurately depicting a station area image based on the fusion of distribution data according to claim 1, characterized in that , The step S2.3 includes: for the minimum support of each sub-item in the fuzzy frequent item set Y, selecting the maximum minimum support To determine the qualitative characteristics of quantitative data.

7. The method for accurately depicting a station area image based on the fusion of distribution data as claimed in claim 1 is characterized in that , The step S3 comprises: Step S3.1, map all features in the area portrait system into a weight map, each feature corresponds to each vertex in the weight map, and each vertex is connected by the correlation degree to obtain a network map; the greater the correlation degree, the greater the weight and the thicker the connection line; Step S3.2: Initialize each node in the network graph as an independent community. After obtaining the nodes of the weight graph, traverse each node in the weight graph and calculate the relative modularity gain change of the node from the current community to the communities where all neighboring nodes are located. If the relative modularity gain is positive, merge the node from the current community to the community where the neighboring node with the largest relative modularity is located. Repeat this operation until no node is added to the new community. Step S3.3: Compress the merged communities, update each community to a new super node, set the sum of the total weights of the edges between communities as the weight of the edges between the new nodes, and the sum of the weights of all the edges in the community as the self-loop weight within the new node. At this time, a new network graph is generated, and the overall modularity of the new network graph is calculated; If the increment Q of the overall modularity is less than the set threshold, the calculation is stopped and the result is output. Otherwise, a new network diagram is generated as data input, and step S3.2 is repeated, and the modularity increment Q is calculated again until the increment Q of the overall modularity is less than the set threshold. The overall calculation is completed, and finally the clustered substation portrait features are generated to show the strong correlation characteristics of the substation portrait.

8. The method for accurately depicting a station area image based on the fusion of distribution data as claimed in claim 7 is characterized in that , The correlation calculation formula P(B|A) in step S3.1 is as follows: P(B|A)=P(A∩B) / P(A) A means that the area has feature A, and B means that the area has feature B. The probability of feature B appearing when feature A exists in the area is calculated as the correlation between the features. The gain change calculation formula in step S3.2 is as follows: Where ∑in represents the sum of the weights of the edges within the community; ∑tot represents the sum of the weights of all edges connected to the community; k i，in represents the sum of the weights of node i when it joins community c; k i Represents the sum of the weights of all edges connected to node i; The overall modularity calculation formula in step S3.3 is as follows: Among them A ij represents the edge weight between nodes i and j; k i , k j represents the edge weights between all nodes and nodes i and j; represents the average edge weight; when nodes i and j are in the same community, σ = 1, otherwise σ = 0; m represents the total number of edges in the network; c i represents the i node in community c; c j represents the j node in community c.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the method according to any one of claims 1 to 8 is implemented.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images