Intelligent electricity price matching and checking method based on graph neural network and related device

Abstract

The invention relates to the technical field of power management, in particular to an intelligent electricity price matching and checking method based on a graph neural network and a related device, and the method comprises the steps: obtaining electricity consumption data of all users, carrying out the data processing of the electricity consumption data of all users, and obtaining graph structure data; according to the graph structure data, the graph neural network model is established, the complex relation of user power consumption data can be effectively modeled, the similarity and difference between users can be captured, the users with abnormal electricity prices can be quickly and accurately identified, the risk of false report and missing report can be reduced, and the user experience can be improved along with the increase of the number of the users and the change of power consumption behaviors. New data distribution is adapted through continuous learning and optimization, the accuracy of checking is kept, the intelligent level of electricity price checking is further improved, and the challenges of electricity market reform and user requirements are met. The problem that in the prior art, the matching between the actual electricity utilization condition and the electricity price recorded in a system file is poor is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of power management, and in particular to an intelligent electricity price matching and verification method based on a graph neural network and a related device. Background Art

[0002] Electricity price implementation and electricity price verification are two important links in the operation of the power market. Together, they ensure the fair, just and efficient operation of the power market. Electricity price implementation refers to the process by which power companies calculate and collect electricity charges from power users based on the electricity price policies formulated by the national or local governments. The accuracy of electricity price implementation is directly related to the economic benefits of power companies and the rights and interests of power users. Electricity price verification refers to the process of comprehensive inspection and verification of electricity price implementation, aiming to ensure the accurate implementation of electricity price policies and fair competition in the power market. Electricity price implementation and electricity price verification are interdependent and mutually reinforcing. Electricity price implementation is the premise and basis of electricity price verification. Only by ensuring the accuracy and compliance of electricity price implementation can effective electricity price verification be carried out. Electricity price verification is the supervision and guarantee of electricity price implementation. Through verification, problems and risks in electricity price implementation can be discovered, and rectification and treatment can be carried out in a timely manner to ensure the accurate implementation of electricity price policies and fair competition in the power market.

[0003] At present, the method of manually checking the implementation of electricity prices on a household basis is mainly relied on. It is not only inefficient and inaccurate, but also cannot be adjusted dynamically. It cannot respond to the dynamic changes of users' electricity consumption behavior in a timely manner, and it is difficult to match the dynamic changes and diversified needs of users' electricity consumption behavior. Therefore, in order to improve the efficiency and accuracy of electricity price verification, intelligent means have become an inevitable choice. With the deepening of the market-oriented reform of the power industry, the construction of a new digital and intelligent electricity fee accounting business system has become an important topic. The accurate implementation of electricity prices not only directly affects the economic benefits of power companies, but also is related to the fairness of the market and the satisfaction of users. Therefore, improving the accuracy of electricity price execution and effectively verifying it has become one of the key tasks of the State Grid Marketing Department.

[0004] However, in actual operation, due to the dynamic changes in the nature of user electricity consumption over time, or due to unreasonable electricity price schemes selected during application, ordinary matching algorithms have great limitations for complex electricity user data, and it is often difficult to accurately capture key information in electricity user data, which affects the accuracy and reliability of the verification results, resulting in the actual electricity consumption situation not being consistent with the electricity price recorded in the system archives. If such problems are not discovered and handled in a timely manner, they may have a negative impact on the company's capital control and the scientific nature of electricity price management. Summary of the invention

[0005] In view of the problem in the prior art that actual electricity consumption is poorly matched with the electricity price recorded in the system archives, the present invention provides an intelligent electricity price matching and verification method and related devices based on graph neural network.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions: The present invention provides a smart electricity price matching and verification method based on graph neural network, comprising: Obtain electricity consumption data of all users; Process the electricity consumption data of all users to obtain graph structure data; According to the graph structure data, a graph neural network model is established; The graph neural network model is used to verify the implementation of user electricity prices in the current system archive, and abnormal users are marked to complete electricity price matching and verification.

[0007] Optionally, the electricity consumption data of all users include electricity consumption categories of all users, user electricity consumption and market electricity prices.

[0008] Furthermore, the method of processing the electricity consumption data of all users to obtain graph structure data is as follows: Classify the electricity consumption data of all users and obtain the electricity consumption data set of each category of users; Normalize each feature in the electricity consumption data set of each type of user to obtain a normalized user feature matrix; According to the normalized user feature matrix, the graph structure data is obtained.

[0009] Furthermore, the method of normalizing each feature in the power consumption data set of each type of user to obtain a normalized user feature matrix is:

[0010] The normalized user feature matrix is:

[0011] in, Indicates user In the Features of the dimensions; is the number of dimensions of the feature; is the normalized user feature; N The number of users of a certain type; is the normalized user feature matrix.

[0012] Furthermore, according to the normalized user feature matrix, the method for obtaining graph structure data is: According to the normalized user feature matrix, define the user node set and the electricity price node set; Obtain edge weights based on the user node set and the electricity price node set; According to the edge weights, the user-electricity price graph and the adjacency matrix of the user-electricity price graph are obtained to complete the acquisition of graph structure data.

[0013] Furthermore, according to the graph structure data, the method of establishing the graph neural network model is: Using graph structure data as input, the feature vector of each layer of the neural network model is updated to obtain the feature vector of the user's electricity consumption behavior and electricity price adaptability; Define the electricity price matching function, match the characteristic vectors of user electricity consumption behavior and electricity price adaptability with the predefined electricity price category, obtain the minimum loss function of the electricity price matching function, and complete the establishment of the graph neural network model.

[0014] Furthermore, the method of using the graph neural network model to check the user electricity price execution status in the current system archive and mark abnormal users to complete electricity price matching and verification is: Use graph neural network models to obtain predicted electricity prices; When conducting the verification, the predicted electricity price is compared with the actual electricity price to determine whether there is any abnormality in the electricity price; If the electricity price is abnormal, the predicted electricity price of the user with the abnormal electricity price and the predicted electricity price of the neighboring users of the user with the abnormal electricity price are obtained; An abnormality score is obtained based on the predicted electricity price of the user with abnormal electricity price and the predicted electricity prices of neighboring users of the user with abnormal electricity price, and it is determined whether the electricity price execution of the user with abnormal electricity price is abnormal.

[0015] The present invention also provides an intelligent electricity price matching and verification system based on graph neural network, comprising: Electricity consumption data acquisition module: used to obtain electricity consumption data of all users; Graph structure data acquisition module: used to process the electricity consumption data of all users and obtain graph structure data; Graph neural network model building module: used to build a graph neural network model based on graph structure data; Electricity price matching and verification module: used to use the graph neural network model to verify the implementation of user electricity prices in the current system archive, and mark abnormal users to complete electricity price matching and verification.

[0016] A terminal device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0017] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0018] Compared with the prior art, the present invention has the following beneficial effects: The present invention provides an intelligent electricity price matching and verification method based on graph neural network. The method obtains graph structure data by acquiring electricity consumption data of all users and performing data processing on the electricity consumption data of all users. The graph structure data can intuitively reflect the electricity consumption behavior relationship between users and provide a solid foundation for subsequent model establishment. By establishing a graph neural network model based on the graph structure data and analyzing the graph structure data, the advantages of graph neural networks (GNNs) in processing graph structure data can be utilized. GNNs can effectively model the complex relationship between users' electricity consumption data and capture the similarities and differences between users. It can not only quickly and accurately identify users with abnormal electricity prices and reduce the risks of false alarms and missed alarms, but also can adapt to new data distribution through continuous learning and optimization as the number of users increases and electricity consumption behavior changes, maintain the accuracy of verification, further improve the intelligence level of electricity price verification, and meet the challenges of power market reform and user needs.

[0019] The electricity consumption data of all users includes the electricity consumption categories and electricity consumption of all users. By representing information such as users, electricity consumption behaviors and market electricity prices as a graph structure, GNNs can comprehensively consider multiple factors and improve the accuracy and efficiency of electricity price matching.

[0020] In the method of processing the electricity consumption data of all users and obtaining graph structure data, the electricity consumption data of all users are classified and the electricity consumption data set of each type of user is obtained; the purpose is to classify users according to certain standards (such as electricity consumption behavior, region, electricity consumption category, etc.) for subsequent processing, which helps to better understand the differences between user groups and provide a basis for subsequent graph structure construction. By normalizing each feature in the electricity consumption data set of each type of user, a normalized user feature matrix is ​​obtained; data with different dimensions or different value ranges are converted to the same scale for comparison and analysis. In the electricity consumption data, the value ranges of different features may vary greatly. Normalization can eliminate such differences, making the model more stable when processing data. Finally, according to the normalized user feature matrix, the graph structure data is obtained. The normalized user feature matrix provides standardized data input for the subsequent graph structure construction, which helps to improve the accuracy and efficiency of the model, and can eliminate the noise and differences in the user electricity consumption data, making the model more stable and accurate when processing data. The normalized user feature matrix is ​​converted into graph structure data. Graph structured data consists of nodes and edges, where nodes can represent users and edges can represent relationships between users (such as similarity, association, etc.). The construction of graph structured data is the key to the application of GNNs models because it can capture complex relationships between users and provide rich information input for the model.

[0021] In the method of obtaining graph structure data according to the normalized user feature matrix, a user node set and an electricity price node set are defined according to the normalized user feature matrix; in this step, each row (or each column, depending on the specific representation of the data) in the normalized user feature matrix is ​​regarded as a user node, thereby constructing a user node set. At the same time, an electricity price node set is defined according to the electricity price category or specific electricity price data. Then, the weight of the edge is obtained according to the user node set and the electricity price node set. The weight of the edge reflects the strength or similarity of the relationship between the user node and the electricity price node, which can be obtained by calculating the similarity, distance or other measurement indicators between the user characteristics and the electricity price characteristics. The larger the weight, the stronger the correlation between the user and the specific electricity price. Finally, according to the edge weights, the user-electricity price graph and the adjacency matrix of the user-electricity price graph are obtained to complete the acquisition of graph structure data. The user-electricity price graph is constructed using the user node set, the electricity price node set and the edge weights. In this graph, the user nodes and the electricity price nodes are connected by weighted edges. According to the structure of the graph, the corresponding adjacency matrix is ​​generated. The adjacency matrix is ​​a two-dimensional array, in which the value of the element represents the connection relationship between the nodes in the graph (that is, the weight of the edge). The introduction of graph structure data enables the model to understand the relationship between users and electricity prices more comprehensively, thereby enhancing the model's expressive power. The edge weight reflects the correlation between users and electricity prices. In the electricity price matching and verification tasks, this correlation is crucial for predicting users' electricity price choices. By accurately calculating the edge weights and constructing the user-electricity price graph, the model can more accurately predict users' electricity price behavior, thereby improving the accuracy of the prediction.

[0022] In the method of establishing a graph neural network model based on graph structure data, the graph structure data is used as input to update the feature vector of each layer node of the neural network model to obtain the feature vector of the user's electricity consumption behavior and electricity price adaptability. The graph structure data contains rich user information and relationship networks. This information is crucial for training the graph neural network model. By using this information, the model can learn a wider range of user electricity consumption behaviors and electricity price patterns. Define the electricity price matching function, match the feature vectors of the user's electricity consumption behavior and electricity price adaptability with the predefined electricity price category, obtain the minimum loss function of the electricity price matching function, and complete the establishment of the graph neural network model. By minimizing the loss function during the training process, the graph neural network model can continuously optimize its weights and parameters, thereby enhancing the generalization ability of the model so that it can be applied to a wider range of electricity price matching scenarios. In the GNNs model, node features are transmitted and updated through the edges in the graph structure. In each layer, node features are aggregated and updated according to the features of their neighbor nodes and the weights of the edges. This information transmission mechanism enables the model to capture the complex relationships in the graph structure and generate more expressive node feature representations. By updating node features layer by layer, the GNNs model can gradually extract deep information in the graph structure, which helps the model to more accurately predict the user's electricity price selection behavior, thereby improving the prediction accuracy. At the same time, it can realize the rapid processing of large-scale graph structure data and further improve computing efficiency.

[0023] In the method of using the graph neural network model to check the user electricity price execution in the current system archive, and marking the abnormal users to complete the electricity price matching and verification, the most suitable electricity price type is obtained by matching the feature vector of each user in the graph neural network model with the predefined electricity price category; this data-driven matching method can capture more subtle user characteristics and electricity consumption behavior differences compared to traditional manual judgment or simple rule matching, thereby improving the accuracy of electricity price matching. When verifying, the most suitable electricity price type is compared with the actual electricity price to determine whether the electricity price is abnormal; the graph neural network model is used to automatically verify the electricity price, reducing manual intervention and improving the verification efficiency. At the same time, by predicting the electricity price through the model and comparing it with the actual electricity price, potential electricity price anomalies can be intelligently identified, reducing the risk of human error. When an abnormal electricity price is found, the method not only focuses on the predicted electricity price of the abnormal user itself, but also considers the predicted electricity price of its neighboring users. This analysis method based on the graph structure can capture the correlation and mutual influence between users, so as to more accurately determine whether the abnormal electricity price really exists, and avoid misjudgment caused by abnormal data of a single user. The anomaly score is calculated based on the predicted electricity price of the abnormal user and the predicted electricity price of its neighboring users, providing a quantitative basis for determining whether there is an anomaly in the execution of electricity prices. This quantitative method makes the anomaly determination more objective and explainable, which is helpful for subsequent analysis and processing. By accurately identifying and marking users with abnormal electricity prices, this method helps maintain the fairness and transparency of the electricity market. For power companies, this helps to promptly detect and deal with potential electricity price violations and ensure the normal operation of the electricity market; for users, this can enhance their trust and satisfaction with electricity price policies.

[0024] The present invention also provides an intelligent electricity price matching and verification system based on graph neural network. Through the setting of electricity data acquisition module, graph structure data acquisition module, graph neural network model building module and electricity price matching and verification module, the collection and processing of a large number of user electricity data are realized, and then the graph structure data is constructed. The graph neural network model is constructed according to the graph structure data to realize automatic matching and verification of electricity prices. Compared with the traditional electricity price matching strategy based on static rules or simple models, the system can dynamically learn the characteristics of user electricity data and adjust the electricity price matching strategy according to these characteristics. This dynamic optimization capability enables the system to respond to market changes more flexibly. By using the graph neural network model, the system can realize accurate verification of the execution of user electricity prices in the current system archives and automatically mark abnormal users. This precise and intelligent verification method not only improves the efficiency of electricity price management, but also reduces the risk of human errors, providing a strong guarantee for the electricity price management of power companies. The system achieves comprehensive optimization of electricity price management through automation and intelligence, from data collection, processing, modeling to verification, which not only reduces the manpower and time costs of electricity price management, but also improves the accuracy and scientificity of electricity price management. The system provides new ideas for technological innovation in the power industry and provides strong support for the upgrading and transformation of related industries. With the continuous advancement of technology and the expansion of application scenarios, the intelligent electricity price matching and verification system based on graph neural network is expected to play an important role in more fields.

[0025] The present invention also provides a terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program. The device has a simple structure, low modification cost, and small resource occupation.

[0026] A computer-readable storage medium stores a computer program, wherein the computer program implements the steps of the above method when executed by a processor. The storage medium has good portability and strong versatility. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 This is a schematic diagram of an intelligent electricity price matching and verification method based on graph neural network of the present invention.

[0028] Figure 2 This is a schematic diagram of the implementation process of an intelligent electricity price matching and verification method based on graph neural network of the present invention.

[0029] Figure 3 This is a structural schematic diagram of an intelligent electricity price matching and verification system based on graph neural network of the present invention. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below 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 should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] The present invention is further described in detail below in conjunction with specific embodiments, which are intended to explain the present invention rather than to limit it.

[0033] See also Figure 1 and Figure 2 The present invention provides a smart electricity price matching and verification method based on graph neural network, comprising: S1: Obtain electricity consumption data of all users; the electricity consumption data of all users includes the electricity consumption categories and electricity consumption of all users. By representing information such as users, electricity consumption behaviors and market electricity prices as a graph structure, GNNs can comprehensively consider multiple factors and improve the accuracy and efficiency of electricity price matching.

[0034] S2: Process the electricity consumption data of all users to obtain graph structure data. The specific method is as follows: Classify the electricity consumption data of all users and obtain the electricity consumption data set of each category of users: divide the known monthly electricity consumption data set of users according to different electricity consumption categories. Assuming there are N users, the classified electricity consumption data set of a certain category of users is: ;in, Indicates user In the Characteristics of each dimension, such as monthly electricity consumption, peak-to-valley ratio, etc. is the number of dimensions of the feature; Normalize each feature in the electricity consumption data set of each type of user to obtain the normalized user feature matrix:

[0035] The normalized user feature matrix is:

[0036] in, Indicates user In the Features of the dimensions; is the number of dimensions of the feature; is the normalized user feature; N The number of users of a certain type; is the normalized user feature matrix.

[0037] According to the normalized user feature matrix, obtain the graph structure data: According to the normalized user feature matrix, the user node set is defined as ,in Indicates user Node; define the electricity price node set ,in Indicates electricity price scheme; According to the user node set and the electricity price node set, get the edge weight:

[0038] in, Is a user The eigenvector of It is an electricity price plan The eigenvector of According to the edge weights, the user-electricity price graph and the adjacency matrix of the user-electricity price graph are obtained to complete the acquisition of the graph structure data: You can choose cosine similarity, Euclidean distance and other methods to build a user-price map:

[0039] in, is a node set; is an edge set, is the weight threshold.

[0040] Adjacency Matrix of a Graph It is expressed as:

[0041] S3: Build a graph neural network model based on graph structure data, specifically: Using graph structure data as input, the feature vector of each layer of the neural network model is updated to obtain the feature vector of the user's electricity consumption behavior and electricity price adaptability: GNNs can model through the characteristics of graph structure data, comprehensively considering the similarities between users and the impact of different factors on electricity price matching. Information is transmitted through the adjacency relationship of nodes, and the features of nodes are continuously updated during the multi-layer propagation process. The feature of each node is represented as a vector, which contains information such as the user's electricity consumption behavior, industry classification, and transformer capacity. The initial feature vector of each user It can include basic information of users, such as industry classification, power consumption and transformer capacity. user nodes, a feature matrix To represent the initial features of all user nodes:

[0042] in, is the dimension of each node feature. This matrix contains the initial features of each user; In each layer of the graph neural network, the features of the nodes are updated according to the information of their neighboring nodes. The characteristics of the layer nodes are , then in The feature update formula of the layer is:

[0043] in: Indicates User in layer The eigenvector of Indicates user The set of neighbor nodes of is the adjacency matrix The elements in represent nodes With Node The strength of the relationship between It is The weight matrix of the layer is used for feature transformation; is the activation function, and the linear rectifier unit is used to increase the nonlinearity of the network.

[0044] The feature update formula of this layer shows how each node updates its own features based on the information of its neighboring nodes. This information propagation mechanism will be carried out layer by layer in the graph neural network, gradually capturing the complex relationships between users; After multi-layer information transmission of node features through the graph neural network, each node will eventually learn a feature vector representing the user's electricity consumption behavior and electricity price adaptability. in, is the number of layers in the network. This feature vector contains the complex association information between users and electricity prices.

[0045] Define the electricity price matching function, match the characteristic vectors of user electricity consumption behavior and electricity price adaptability with the predefined electricity price category, obtain the minimum loss function of the electricity price matching function, and complete the establishment of the graph neural network model: In order to determine the most appropriate electricity price matching strategy, the final feature vector of each user can be matched with the predefined electricity price category. electricity price categories, define an electricity price matching function , maps the user's final feature vector to the most appropriate electricity price category. The specific formula is:

[0046] in, is the weight matrix of electricity price matching, which represents the relationship between each electricity price category and user characteristics; is the bias term; Given the user The most suitable type of electricity price; Through this electricity price matching function, the system can dynamically match the most suitable electricity price type according to each user's electricity consumption behavior and characteristics; Electricity price matching loss function training: In order to optimize the electricity price matching accuracy of the graph neural network, the electricity price matching loss function is defined to measure the accuracy of the model's prediction of electricity prices. The commonly used loss function is the cross-entropy loss (Cross-EntropyLoss), and the formula is as follows:

[0047] in, Is a user The actual electricity price category (one-hot encoding), Indicates user Belongs to category ,otherwise ; Is the user predicted by the model Belongs to the electricity price category The probability of ; is the number of electricity rate categories.

[0048] By minimizing the loss function, the graph neural network can continuously adjust its parameters and , in order to improve the accuracy of electricity price matching. The graph neural network learns the similarities between users and accurately matches the most suitable electricity price based on these similarities and user characteristics. This process not only improves the efficiency of electricity price matching, but also takes into account the dynamic changes of user behavior.

[0049] S4: Use the graph neural network model to check the user electricity price execution status in the current system archive, mark abnormal users, and complete electricity price matching and verification. Specifically: for users , the actual electricity price recorded by the system is , while the electricity price predicted by the graph neural network is , then the electricity price error It can be expressed as:

[0050] in, Is a user The actual electricity prices recorded in the system; It is the predicted electricity price obtained through the graph neural network model; Is a user The price error represents the difference between the actual price and the predicted price. Greater than or equal to the set threshold ,Right now , it is considered that there is an abnormality in the execution of the user's electricity price, and further detection and adjustment are needed.

[0051] The next step of electricity price verification is anomaly detection, that is, to determine which users have problems with electricity price execution. If there is an abnormality in electricity price, the predicted electricity price of the user with abnormal electricity price and the predicted electricity price of the neighboring users of the user with abnormal electricity price are obtained; by analyzing the user The relationship between the electricity price error of its neighbor users can be calculated using the anomaly detection function of the graph neural network to calculate the anomaly score of each user. Is a user The neighbor node set of user The anomaly detection score (Anomaly Score) can be calculated by the following formula:

[0052] in, Is a user Forecasted electricity prices; Neighbor user Forecasted electricity prices; Is a user The set of neighbor nodes of Is a user The anomaly detection score of The greater the difference between the electricity price of the user and the electricity price of the neighboring user, the higher the anomaly score, indicating that the user There may be a problem with electricity prices. If the anomaly score Greater than or equal to the preset threshold ,Right now , then determine the user There are abnormalities in the implementation of electricity prices.

[0053] Finally, for users who are judged to be abnormal The system will give adjustment suggestions based on the electricity price forecast results of its historical electricity consumption data. Assuming that the electricity price forecasted by the historical electricity consumption data is , then the weighted average of historical electricity consumption data can be used to provide users with Provide adjusted electricity price recommendations.

[0054] Adjusted electricity prices It can be expressed as:

[0055] in: is the proposed adjusted electricity price; Is a user The number of historical power consumption nodes; It is an electricity price forecast based on historical electricity consumption.

[0056] In this way, the adjusted electricity price can comprehensively consider the electricity consumption behavior and electricity price implementation of historical electricity consumption data, thereby achieving a more scientific and reasonable electricity price adjustment.

[0057] Electricity price verification and anomaly detection can not only detect abnormal users, but also provide corresponding electricity price adjustment suggestions. The feedback process includes the following steps: Abnormal user list generation: Generate a list of all abnormal users and provide an abnormal detection score and electricity price adjustment suggestions for each user.

[0058] Adjustment confirmation and implementation: The relevant departments (such as the power marketing department) confirm the electricity price adjustment proposal and adjust the electricity prices for abnormal users.

[0059] Feedback and optimization: The system conducts feedback learning on the graph neural network model based on the adjusted electricity price results, and continuously optimizes the accuracy of electricity price matching and anomaly detection. Through this optimization process, the system can improve the accuracy of electricity price verification and gradually improve the intelligent level of electricity price management.

[0060] Through the price verification and anomaly detection of graph neural networks, the system can accurately detect problems in the implementation of user electricity prices and provide reasonable suggestions for price adjustments. This process not only improves the efficiency of price verification, but also optimizes the scientificity and accuracy of price management through deep learning technology, thereby helping power grid companies to achieve intelligent and precise price management, and promote the fairness of orderly electricity use and user satisfaction.

[0061] See also Figure 3 The present invention provides an intelligent electricity price matching and verification system based on graph neural network, comprising: Electricity consumption data acquisition module: used to obtain electricity consumption data of all users; Graph structure data acquisition module: used to process the electricity consumption data of all users and obtain graph structure data; Graph neural network model building module: used to build a graph neural network model based on graph structure data; Electricity price matching and verification module: used to use the graph neural network model to verify the implementation of user electricity prices in the current system archive, and mark abnormal users to complete electricity price matching and verification.

[0062] The system collects and processes a large amount of user electricity data through the settings of electricity data acquisition module, graph structure data acquisition module, graph neural network model building module and electricity price matching and verification module, and then constructs graph structure data. According to the graph structure data, the graph neural network model is constructed to realize automatic matching and verification of electricity prices. Compared with the traditional electricity price matching strategy based on static rules or simple models, the system can dynamically learn the characteristics of user electricity data and adjust the electricity price matching strategy according to these characteristics. This dynamic optimization capability enables the system to respond to market changes more flexibly. By using the graph neural network model, the system can realize accurate verification of the user electricity price execution in the current system archive and automatically mark abnormal users. This precise and intelligent verification method not only improves the efficiency of electricity price management, but also reduces the risk of human error, providing a strong guarantee for the electricity price management of power companies. The system realizes the comprehensive optimization of electricity price management from data collection, processing, modeling to verification through automation and intelligence, which not only reduces the manpower cost and time cost of electricity price management, but also improves the accuracy and scientificity of electricity price management. The system provides new ideas for technological innovation in the power industry and also provides strong support for the upgrading and transformation of related industries. With the continuous advancement of technology and the expansion of application scenarios, the intelligent electricity price matching and verification system based on graph neural networks is expected to play an important role in more fields.

[0063] The present invention provides a terminal device including: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above-mentioned method embodiments are implemented. Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned device embodiments are implemented.

[0064] The computer program may be divided into one or more modules / units, and the one or more modules / units are stored in the memory and executed by the processor to accomplish the present invention.

[0065] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0066] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0067] The memory may be used to store the computer programs and / or modules, and the processor implements various functions of the terminal device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory.

[0068] If the module / unit integrated in the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0069] In summary, the present invention provides an intelligent electricity price matching and verification method and related devices based on graph neural networks. By using graph neural networks (GNNs) to model the complex relationship between user electricity consumption data and electricity prices, the similarities and differences between users are accurately captured, and the accuracy of electricity price matching is improved. Compared with traditional manual verification or simple algorithms, GNNs can better handle complex electricity price execution situations, avoid errors and omissions in manual verification, and improve the accuracy of electricity price execution. Through the dynamic optimization capability of GNNs, the electricity price matching strategy is adjusted in real time to ensure the scientificity and timeliness of electricity price execution, automatically adapt to changes in the electricity market and fluctuations in user electricity demand, and improve the flexibility and timeliness of electricity price management. The anomaly detection function based on graph neural networks can identify anomalies in electricity price execution in real time. By calculating the difference between the user's electricity price and the electricity price based on historical electricity consumption data, electricity price problems can be quickly located, reducing manual intervention. For abnormal users, GNNs can accurately mark and automatically generate adjustment suggestions to ensure the fairness and rationality of electricity prices. At the same time, through automated data processing and intelligent analysis, the need for manual intervention is greatly reduced, labor costs are reduced, work efficiency is improved, and the overall operational efficiency of power companies is improved.

[0070] The above description is only a preferred embodiment of the present invention and is not intended to impose any limitation on the technical solution of the present invention. Those skilled in the art should understand that, without departing from the spirit and principles of the present invention, the technical solution can also be subjected to several simple modifications and substitutions, and these modifications and substitutions are also within the scope of protection covered by the claims.

Claims

1. A smart electricity price matching and verification method based on graph neural network, characterized in that: include: Obtain electricity consumption data of all users; Process the electricity consumption data of all users to obtain graph structure data; According to the graph structure data, a graph neural network model is established; The graph neural network model is used to verify the implementation of user electricity prices in the current system archive, and abnormal users are marked to complete electricity price matching and verification.

2. The intelligent electricity price matching and verification method based on graph neural network according to claim 1 is characterized in that: The electricity consumption data of all users include electricity consumption categories, electricity consumption of all users and market electricity prices.

3. The intelligent electricity price matching and verification method based on graph neural network according to claim 1 is characterized in that: The method of processing the electricity consumption data of all users to obtain graph structure data is as follows: Classify the electricity consumption data of all users and obtain the electricity consumption data set of each category of users; Normalize each feature in the electricity consumption data set of each type of user to obtain a normalized user feature matrix; According to the normalized user feature matrix, the graph structure data is obtained.

4. The intelligent electricity price matching and verification method based on graph neural network according to claim 3 is characterized in that: The method of normalizing each feature in each type of user power consumption data set to obtain a normalized user feature matrix is: The normalized user feature matrix is: in, Indicates user In the Features of the dimensions; is the number of dimensions of the feature; is the normalized user feature; N The number of users of a certain type; is the normalized user feature matrix.

5. The intelligent electricity price matching and verification method based on graph neural network according to claim 3 is characterized in that: According to the normalized user feature matrix, the method for obtaining graph structure data is: According to the normalized user feature matrix, define the user node set and the electricity price node set; Obtain edge weights based on the user node set and the electricity price node set; According to the edge weights, the user-electricity price graph and the adjacency matrix of the user-electricity price graph are obtained to complete the acquisition of graph structure data.

6. The intelligent electricity price matching and verification method based on graph neural network according to claim 1 is characterized in that: According to the graph structure data, the method of establishing the graph neural network model is: Using graph structure data as input, the feature vector of each layer of the neural network model is updated to obtain the feature vector of the user's electricity consumption behavior and electricity price adaptability; Define the electricity price matching function, match the characteristic vectors of user electricity consumption behavior and electricity price adaptability with the predefined electricity price category, obtain the minimum loss function of the electricity price matching function, and complete the establishment of the graph neural network model.

7. The intelligent electricity price matching and verification method based on graph neural network according to claim 1 is characterized in that: The method of using the graph neural network model to check the user electricity price execution status in the current system archive and mark abnormal users to complete electricity price matching and verification is as follows: Use graph neural network models to obtain predicted electricity prices; When conducting the verification, the predicted electricity price is compared with the actual electricity price to determine whether there is any abnormality in the electricity price; If the electricity price is abnormal, the predicted electricity price of the user with the abnormal electricity price and the predicted electricity price of the neighboring users of the user with the abnormal electricity price are obtained; An abnormality score is obtained based on the predicted electricity price of the user with abnormal electricity price and the predicted electricity prices of neighboring users of the user with abnormal electricity price, and it is determined whether the electricity price execution of the user with abnormal electricity price is abnormal.

8. An intelligent electricity price matching and verification system based on graph neural network, characterized in that: include: Electricity consumption data acquisition module: used to obtain electricity consumption data of all users; Graph structure data acquisition module: used to process the electricity consumption data of all users and obtain graph structure data; Graph neural network model building module: used to build a graph neural network model based on graph structure data; Electricity price matching and verification module: used to use the graph neural network model to verify the implementation of user electricity prices in the current system archive, and mark abnormal users to complete electricity price matching and verification.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images