Electric power material relation graph drawing and demand prediction method and system based on entropy value

Abstract

The invention relates to an entropy-based electric power material relation graph drawing and demand prediction method and system, and the method comprises the following steps: collecting electric power material data in a project set, and carrying out the graph structuring, thereby obtaining an initial material relation graph; based on the initial material relation graph, adopting a matrix expression method for quantification, and further adopting an associated material grouping algorithm for associated material grouping; calculating an entropy value of the quantized initial material relationship map based on the associated material grouping result, and eliminating noise points based on a maximum entropy noise reduction principle to obtain a final material relationship map; and predicting a material demand interval based on the material relation graph. Compared with the prior art, the method has the advantages of improving the drawing speed and quality of the relation graph and the like.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power materials, and in particular to a method and system for drawing an entropy-based electric power material relationship map and forecasting demand. Background Art

[0002] The material relationship map is a new technical tool adopted by power companies to improve material management, which can provide technical support for scenarios such as material demand forecasting. At present, the research and patents on the mapping technology related to the domestic power industry are all centered on the optimization of the analysis algorithm of material relationships. However, there is no targeted research and patent on how to improve the accuracy of sample data and ensure that the speed and quality of mapping are not affected by data noise.

[0003] Patent application CN118193749A discloses a method and device for associating power data elements. The method collects power data elements to form a data set to be associated and processed; by frequently processing the data set to be associated and processed, the associated frequent item sets and corresponding association relationships are given; the method described in the patent is applicable to the analysis of the power industry, including material relationships, but the content is only the collection, clustering and linking of association relationship sample data, and does not involve data noise cleaning related content. Patent application CN118193749A discloses a method and system for automatic relationship recognition based on deep learning. The method collects power system knowledge graph data, including entities and their relationships, converts the knowledge graph data into a graph data format, trains a multi-level graph neural network model based on historical power system knowledge graph data, and predicts the relationship type between knowledge graph entities. The content of this method is mainly the disassembly, combination and reconstruction between different relationship graphs. There is no targeted method involved in the accuracy judgment and cleaning of sample data.

[0004] In summary, there is a need for an automated data cleaning method to address the problem of sample data accuracy, improve sample data accuracy, and ensure the speed and quality of map drawing. Summary of the invention

[0005] The purpose of the present invention is to provide an automatic noise reduction entropy-based power material relationship map drawing and demand forecasting method and system.

[0006] The purpose of the present invention can be achieved by the following technical solutions:

[0007] A method for drawing a power material relationship map and predicting demand based on entropy value comprises the following steps:

[0008] Collect the power material data in the project, structure it into a graph, and obtain the initial material relationship graph;

[0009] Quantify the initial material relationship graph using the matrix expression method, and further group the associated materials using the associated material grouping algorithm;

[0010] Calculate the entropy value of the quantified initial material relationship graph based on the grouping results of the associated materials, and eliminate the noise points based on the principle of maximum entropy reduction and noise reduction to obtain the final material relationship graph;

[0011] Predict the material demand quantity interval based on the material relationship graph.

[0012] Furthermore, the steps of graph structuring include:

[0013] Convert the power material data into vertex functions and edge functions to form an initial material relationship graph, where one material in the power material data corresponds to one graph vertex, and the relative demand between two materials corresponds to the graph edge.

[0014] Furthermore, the expression of the vertex function is:

[0015]

[0016] In the formula, V(x) is the vertex function of material x, which is a mapping of the demand frequency of material x and reflects the absolute demand of the project for material x. 0 < V(x) ≤ 1. When V(x) = 1, material x is an essential material for the entire project set P; N(P x ) is the number of items of project P that use material x x , and N(P) is the number of items in the project set;

[0017] The expression of the edge function is:

[0018]

[0019] In the formula, E(x, y) is the edge function between material x and material y, which is a mapping of the demand correlation between material x and material y; N(P y|x ) is the number of items of P y|x , P y|x is the project that uses material y among the projects that use material x; N(P) is the number of items in the project set.

[0020] Furthermore, the steps of quantification using the matrix expression method include:

[0021] Construct the mapping from the vertex function V(x) to the demand vector where D n =(d1, d2,..., d i ,..., d n ) is the demand relationship vector, and d i is the i-th item of material x iThe demand frequency V(x i ), n is the number of material types covered by the project set P;

[0022] Construct a mapping from edge function E(x, y) to the association matrix Complete the quantization process, where R n×n is the association matrix, the element r in row i and column j is i，j =E(x i , x j ), 1≤i≤n, 1≤j≤n, and r i，i =E(x i , x i )=1.

[0023] Furthermore, the step of grouping related materials includes:

[0024] Construction material x i Prerequisite material mapping Based on the prerequisite material mapping Traverse the association matrix R n×n , filter the column number whose element is 1 to find the material x i Prerequisite materials x j , where the prerequisite material mapping For all items with material x i A collection of materials with direct associations;

[0025] Based on the prerequisite material mapping Constructing a Map Traverse the association matrix R n×n The i-th row and j-th column of the matrix are obtained by finding all column numbers j that satisfy R(i, j) = R(j, i) = 1}. i Supporting materials x j ,Right now:

[0026]

[0027] Group the complementary materials into one group, and repeat the above steps to complete the grouping of all materials.

[0028] Furthermore, the calculation expression of the entropy value is:

[0029]

[0030] In the formula, H is the entropy value, which reflects the concentration of related material groups, m is the number of related material groups, Group the i-th associated material, x1, x2, …, x NCovering materials for item set P, N is the number of materials.

[0031] Furthermore, the step of obtaining the final material relationship map includes:

[0032] 1) Determine whether the entropy value is zero. If so, it indicates that no noise reduction is required, and the quantized initial material relationship map is used as the final material relationship map. If not, it indicates that noise reduction is required, and the next step is executed:

[0033] 2) For the item set P in the quantified initial material relationship map, delete the jth item to form a subset P -j , calculate the subset P -j The entropy value H(P -j ), and repeat this step to obtain the entropy values ​​of all subsets;

[0034] 3) deleting the item with the largest entropy value among the entropy values ​​of all the subsets;

[0035] 4) Calculate whether the entropy reduction of the item set P exceeds the threshold. If so, end the noise reduction operation and obtain the final material relationship map. If not, repeat the iterative steps 1)-4) according to the item set P after entropy reduction until the end to obtain the final material relationship map, where the calculation expression of the entropy reduction of the item set P is:

[0036] Entropy reduction = H(P)-max{H(P -j )}

[0037] Where H(P) is the entropy value of the item set P.

[0038] Furthermore, the step of predicting the material demand range includes:

[0039] Determine the quantity relationship type between material requirements based on the material relationship map;

[0040] The demand quantity interval of each material is calculated according to the quantity relationship type to obtain the material demand quantity interval.

[0041] Furthermore, the quantitative relationship types include interval-type quantitative relationships, formula-type quantitative relationships and proportion-type quantitative relationships.

[0042] The present invention also provides an entropy-based power material relationship map drawing and demand forecasting system, comprising:

[0043] Graph structuring module: used to collect power material data, perform graph structuring, and obtain the initial material relationship map;

[0044] Quantification and grouping module: used to quantify based on the initial material relationship map using a matrix expression method, and further group related materials using a related material grouping algorithm;

[0045] Entropy analysis module: used to calculate the entropy value of each associated material group, and remove noise points based on the maximum entropy reduction principle to obtain the final material relationship map;

[0046] Prediction module: used to predict the material demand based on the material relationship map and the determined quantity relationship type.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] (1) Automated sample data noise reduction: The identification and cleaning of data noise points are fully automated, reducing the drawbacks of traditional data cleaning, which has high labor intensity and cannot eliminate subjective experience bias.

[0049] (2) Applicable to any type of power materials: Entropy, as a dimensionless measurement, measures the regularity of the sample content. As long as the regularity of the noise data is obviously different, this method can be applied without being restricted by specific projects and material types.

[0050] (3) Entropy reduction as a project management indicator: The reduction in entropy reflects the accuracy of sample data and can therefore be used as a reverse indicator to evaluate the standardization of sample project management.

[0051] (4) Material demand range: The material demand range is predicted based on the quantity relationship type between materials determined by the material relationship map to improve the prediction accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a schematic diagram of the method flow of the present invention. DETAILED DESCRIPTION

[0053] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. This embodiment is implemented based on the technical solution of the present invention, and provides a detailed implementation method and specific operation process, but the protection scope of the present invention is not limited to the following embodiments.

[0054] Example 1

[0055] This embodiment provides a method for drawing an entropy-based electricity material relationship map and demand forecasting, which aims to achieve automatic cleaning and optimization of electricity material data and improve the accuracy of material demand forecasting through entropy analysis technology. The basic principle of entropy analysis is to use the contrast of data regularity to distinguish normal data from noise data. As a dimensionless measurement, entropy measures the regularity of sample connotation and is not limited by specific projects and material scales. The technical path for generating material relationship maps is divided into five steps in total, which are carried out along the path of graph data collection, graph structure definition, graph matrix mapping, graph sample denoising, and graph quantitative analysis. Specifically, Figure 1 As shown in Figure 1 , the method includes the following steps:

[0056] (1) Graph data collection

[0057] The purpose of graph data collection is to obtain the input data required for analysis. As the basis for the entire analysis and research, the selection of the scope of the input data is very important. In this project, typical distribution network projects in the past three years are used as the sample domain, and only the projects that have completed final accounts are collected. The purchase orders include all-caliber batch bidding, agreement inventory allocation, and e-commerce procurement. After the historical data is collected, preliminary cleaning work is carried out to remove blank values and outliers.

[0058] (2) Graph structure definition

[0059] The structure of the material relationship graph is used to specify the underlying logic of the internal laws of materials. The basic content is to construct graph vertices and connecting edges. One graph vertex corresponds to one material, and any two vertices are connected to form a set of graph edges. When there are n materials in the whole domain, the relationship graph corresponds to n vertices and permutation number x of one-way edges. For the project set P, and two materials x and y, let the number of items in the project set be N(P), the projects using material x be P y , and the projects using material y be P

[0060] Vertex function V(x): The vertex function is a mapping of the demand frequency of a single material, reflecting the absolute demand of the project for the material. The expression of the vertex function Obviously, 0 < V(x) ≤ 1, and when V(x) = 1, material x is an essential material for the entire project set P.

[0061] Edge function E(x, y): The edge function is a mapping of the demand correlation between two materials, reflecting the relative demand between the two materials. Denote the projects that use material x and also use material y as P y|x , and the expression of the edge function Obviously, 0 < E(x, y) ≤ 1.

[0062] (3) Graph matrix mapping

[0063] Using the definition rules of the graph structure, convert the massive samples into vertex functions and edge functions, completing the first step from unstructured data to structured data. However, it still cannot be directly processed quantitatively by a computer. Therefore, a quantitative expression form of the relationship graph needs to be designed, and here the matrix expression method is adopted.

[0064] For the n materials x1, x1... x covered by the project set P n , define the demand relationship vector D of the materials n = (d1, d2,..., dn ), d i is the i-th item x i The demand frequency V(x i ), thus constructing a mapping from vertex function to required vector Define the material association matrix R n×n , the element r in row i and column j i，j =E(x i , x j ), 1≤i≤n, 1≤j≤n, and r i，i =E(x i , x i )=1. This constructs the mapping from edge function to association matrix

[0065] Demand relationship vector D n And the correlation matrix R n×n The introduction of solves the problem of quantitative expression of relationship graphs. The quantitative analysis of association relationships is transformed from an abstract graph structure into a logical operation that can be accepted by computers. According to the definition of association relationships, an algorithm for grouping related materials is designed. For the prerequisite material, record material x i Prerequisite material mapping Just need to traverse the association matrix R n×n The i-th row of the filter element is 1. For all items with material x i A collection of materials with direct associations;

[0066] To solve for material x i Supporting material group, design mapping The same traversal algorithm is used, and it is mandatory According to the transitivity of the matching relationship, Obviously That is, the supporting material grouping of mutually supporting materials must be the same.

[0067] Finally, repeat the above steps to complete the grouping of all materials.

[0068] (4) Image sample denoising

[0069] First, construct the entropy value of the association graph. The entropy value reflects the degree of disorder of a system. In the material relationship graph, it is used to reflect the discreteness of material grouping. Assume that the project set P covers materials x1, x2, ..., x N . The associated materials are grouped as And there is Defining Entropy in yes The number of materials in the group, N is the number of materials. There must be So H≥0. The more concentrated the grouping of related materials is, the smaller the entropy value is, and the more dispersed the grouping is, the larger the entropy value is. When and only when all materials are classified into one group, the entropy value drops to zero. The maximum entropy reduction principle, for two item sets P1 and P2, if Then H(P1)≤H(P2). Eliminating noise points will inevitably lead to entropy reduction, but different noise points have different entropy reduction ranges, and the noise points with the largest entropy reduction should be eliminated first. The specific algorithm is as follows:

[0070] Step 1: Subset entropy comparison: For the current item set P, delete the jth item to form the subset P. -j , horizontal comparison H(P -j );

[0071] Step 2 Maximum Entropy Reduction Path Search: For the largest H(P -i ), P -i =max{H(P -j )}, delete the i-th item and repeat step 1;

[0072] Step 3 Threshold trigger: Entropy reduction H(P)-max{H(P -j )} ends when the threshold is exceeded.

[0073] (5) Graph Quantitative Analysis

[0074] First, determine the quantity relationship type between material requirements based on the material relationship map; calculate the demand interval of each material based on the quantity relationship type to obtain the material demand interval. The quantity relationship types include interval quantity relationship, formula quantity relationship and ratio quantity relationship.

[0075] Interval quantitative relationship: It is difficult to find a suitable engineering characteristic factor for the quantitative relationship, so the confidence interval estimation method is adopted. The confidence level is α, and the confidence interval estimate of the mean demand is in is the t-quantile with n-1 degrees of freedom.

[0076] Formula-based quantitative relationship: The quantitative relationship can introduce engineering characteristic factors, and the sample demand is recorded as Y = (y1, y2, ..., y n ) T , engineering characteristic factor Establish a linear equation Y = βX + ε, and the coefficient β = (β0, β1, ..., β m ) T , solve the linear equation with unknown coefficient β=(X TX) -1 X T Y. The characteristic factor of the new project is X n+1 , the demand forecast interval is

[0077] The implementation method of the present invention is computer program development, deployment and application, the development programming language is Python, the library package Numpy multidimensional array library package, Matplotlib data visualization, Pandas data analysis library, Scikit-learn machine learning are imported. Necessary data structures and technologies include: (1) ndarray class, including various matrix operation functions, supporting matrix dot multiplication and star multiplication, adaptive broadcast mechanism, easy implementation of correlation matrix solution, and reduced development workload; (2) JIT real-time compilation technology, so that the Numpy library package developed based on C language has a computing speed close to that of compiled voice; (3) Network library, supporting various types of graphs, built-in shortest path and connectivity detection algorithms, supporting calculation of clustering coefficients, and analyzing local clustering structures of graphs.

[0078] Example 2

[0079] This embodiment provides an entropy-based power material relationship map drawing and demand forecasting system, including:

[0080] Graph structuring module: used to collect power material data, perform graph structuring, and obtain the initial material relationship map;

[0081] Quantification and grouping module: used to quantify based on the initial material relationship map using a matrix expression method, and further group related materials using a related material grouping algorithm;

[0082] Entropy analysis module: used to calculate the entropy value of each associated material group, and remove noise points based on the maximum entropy reduction principle to obtain the final material relationship map;

[0083] Prediction module: used to predict the material demand based on the material relationship map and the determined quantity relationship type.

[0084] The rest is the same as in Example 1.

[0085] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0086] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The schemes in the embodiments of the present invention may be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0087] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0088] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0089] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0090] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0091] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for drawing a power material relationship map and forecasting demand based on entropy, characterized in that: The following steps are involved: Collect the power material data in the project, structure it into a graph, and obtain the initial material relationship graph; Based on the initial material relationship map, a matrix expression method is used for quantification, and an associated material grouping algorithm is further used to group associated materials; The entropy value of the quantified initial material relationship map is calculated based on the grouping results of the associated materials, and the noise points are removed based on the maximum entropy reduction and noise reduction principle to obtain the final material relationship map; Based on the material relationship map, the material demand range is predicted.

2. The method for drawing a power material relationship map and forecasting demand based on entropy value according to claim 1, characterized in that: The step of performing graph structuring includes: The power material data is converted into vertex functions and edge functions to form an initial material relationship graph, wherein one material in the power material data corresponds to one graph vertex, and the relative demand of two materials corresponds to a graph edge.

3. The method for drawing a power material relationship map and predicting demand based on entropy value according to claim 2 is characterized in that: The expression of the vertex function is: Wherein, V(x) is the vertex function of material x, which is a mapping of the demand frequency of material x and reflects the absolute demand of the project for material x. 0 < V(x) ≤ 1. When V(x) = 1, material x is an essential material for the entire project set P; N(P x ) is the number of items of project P that use material x x , and N(P) is the number of items in the project set; The expression of the edge function is: Where E(x,y) is the edge function between material x and material y, which is the mapping of the demand correlation between material x and material y; N(P y|x ) is P y|x The number of items, P y|x A project that uses material x also uses material y; N(P) is the number of items in the project set.

4. The method for drawing a power material relationship map and forecasting demand based on entropy value according to claim 2 is characterized in that: The step of quantifying by matrix expression method comprises: Construct a mapping from the vertex function V(x) to the required vector Where D n =(d1,d2,…,d i ,…,d n ) is the demand relationship vector, d i is the i-th item x i The demand frequency V(x i ), n is the number of material types covered by the project set P; Construct a mapping from edge function E(x,y) to the association matrix Complete the quantization process, where R n×n is the association matrix, the element r in row i and column j is i,j =E(x i ,x j ), 1≤i≤n, 1≤j≤n, and r i,i =E(x i ,x i )=1.

5. The method for drawing a power material relationship map and forecasting demand based on entropy value according to claim 4 is characterized in that: The step of grouping associated materials comprises: Construction material x i Prerequisite material mapping Based on the prerequisite material mapping Traverse the association matrix R n×n , filter the column number whose element is 1 to find the material x i Prerequisite materials x j , where the prerequisite material mapping For all items with material x i A collection of materials with direct associations; Based on the prerequisite material mapping Constructing a Map Traverse the association matrix R n×n The i-th row and j-th column of the matrix are obtained by finding all column numbers j that satisfy R(i,j)=R(j,i)=1}. i Supporting materials x j ,Right now: Group the complementary materials into one group, and repeat the above steps to complete the grouping of all materials.

6. The method for drawing a power material relationship map and forecasting demand based on entropy value according to claim 1, characterized in that: The calculation expression of the entropy value is: In the formula, H is the entropy value, which reflects the concentration of related material groups, m is the number of related material groups, Group the i-th associated material, x1,x2,…,x N Covering materials for item set P, N is the number of materials.

7. The method for drawing a power material relationship map and forecasting demand based on entropy value according to claim 1, characterized in that: The steps of obtaining the final material relationship map include: 1) Determine whether the entropy value is zero. If so, it indicates that no noise reduction is required, and the quantized initial material relationship map is used as the final material relationship map. If not, it indicates that noise reduction is required, and the next step is executed: 2) For the item set P in the quantified initial material relationship map, delete the jth item to form a subset P -j , calculate the subset P -j The entropy value H(P -j ), and repeat this step to obtain the entropy values ​​of all subsets; 3) deleting the item with the largest entropy value among the entropy values ​​of all the subsets; 4) Calculate whether the entropy reduction of the item set P exceeds the threshold. If so, end the noise reduction operation and obtain the final material relationship map. If not, repeat the iterative steps 1)-4) according to the item set P after entropy reduction until the end to obtain the final material relationship map, where the calculation expression of the entropy reduction of the item set P is: Entropy reduction = H(P)-max{H(P -j )} Where H(P) is the entropy value of the item set P.

8. The method for drawing a power material relationship map and forecasting demand based on entropy value according to claim 1, characterized in that: The step of predicting the material demand range includes: Determine the quantity relationship type between material requirements based on the material relationship map; The demand quantity interval of each material is calculated according to the quantity relationship type to obtain the material demand quantity interval.

9. The method for drawing a power material relationship map and forecasting demand based on entropy value according to claim 8, characterized in that: The quantitative relationship types include interval-type quantitative relationships, formula-type quantitative relationships and proportion-type quantitative relationships.

10. An entropy-based power material relationship mapping and demand forecasting system, characterized in that: include: Graph structuring module: used to collect power material data, perform graph structuring, and obtain the initial material relationship map; Quantification and grouping module: used to quantify based on the initial material relationship map using a matrix expression method, and further group related materials using a related material grouping algorithm; Entropy analysis module: used to calculate the entropy value of each associated material group, and remove noise points based on the maximum entropy reduction principle to obtain the final material relationship map; Prediction module: used to predict the material demand based on the material relationship map and the determined quantity relationship type.

Images