Electricity market transaction information management system

Abstract

The application discloses a power sale market transaction information management system and relates to the technical field of power retail information management.The system comprises a data gathering and storage module, a user portrait construction module, a dynamic settlement engine, a rule base and configuration center and a bill generation and traceability module.The data gathering and storage module is used for acquiring and storing actual power consumption data of users in a preset time granularity from an external power grid metering system.The user portrait construction module is connected with the data gathering and storage module.The dynamic settlement engine is connected with the data gathering and storage module and the user portrait construction module.The rule base and configuration center are used in a parameterized and formulated form.The settlement accounting core is configured to be triggered at a settlement period.The bill generation and traceability module is connected with the dynamic settlement engine.The system collects and analyzes user power consumption and transaction behavior data, generates a quantitative portrait and maps the portrait to an N-dimensional settlement judgment space as a structural factor, realizes adaptive division and differentiated settlement strategy matching, supports flexible pricing and personalized services.

Description

Technical Field

[0001] This invention relates to the field of power information management, and in particular to a power sales market transaction information management system. Background Technology

[0002] With the deepening of my country's power system reform, the electricity retail market is gradually developing towards multi-entity competition and multi-level transactions, and electricity users are playing an increasingly proactive and diversified role in the market. To support users in conducting transaction declarations, settlements, and other activities, traditional information management systems are typically built around fixed metering data collection and static rule execution, with an overall architecture primarily based on centralized processing and standardized processes. These systems mainly implement settlement rules through embedded code, lacking deep modeling support for differences in user behavior. Furthermore, they struggle to quickly adapt to the flexible needs of market rule adjustments and changes in trading mechanisms, and are gradually failing to meet the refined management goals of retail-side business under the new circumstances.

[0003] Existing technologies suffer from significant shortcomings in terms of system flexibility and intelligence. On the one hand, once settlement rules are fixed, they lack configurability; adjustments require modification of underlying program code, easily leading to business interruptions and operational risks. On the other hand, users' actual electricity consumption behavior and market trading preferences are not structurally incorporated into the settlement judgment process, making it impossible to implement targeted strategies. Furthermore, most current systems lack traceability of the settlement process, and the presentation of billing data is opaque, making it difficult for users to understand the cost formation path, thus affecting market transparency and user trust. Therefore, there is an urgent need for a transaction information management technology that integrates user behavior modeling, dynamic rule configuration, and full-process traceability of settlement to meet the high-frequency, differentiated, and auditable operational requirements of the electricity retail market. Summary of the Invention

[0004] To address the aforementioned problems in the existing technology, the purpose of this invention is to provide an electricity sales market transaction information management system, and the specific technical solution adopted is as follows: The data aggregation and storage module is used to acquire and store actual electricity consumption metering data of users in preset time granularity from external power grid metering systems, and to acquire and store users' historical transaction declaration data from the trading platform.

[0005] The user profile building module is connected to the data aggregation and storage module. It is configured to generate a set of quantified, multi-dimensional user profile tags for each electricity user based on the actual electricity metering data and historical transaction declaration data, using a preset profile modeling algorithm. These tags represent the user's inherent electricity consumption behavior and transaction preferences.

[0006] A dynamic settlement engine, connected to both the data aggregation and storage module and the user profile construction module, comprises: The rule base and configuration center are used to define and store a set of settlement rules in a parameterized and formulaic form, which can be edited and version-managed by authorized users.

[0007] The settlement and accounting core is configured to dynamically call the settlement rule set in the rule base and configuration center when the settlement cycle is triggered, and perform settlement operations by combining the actual electricity metering data and the user profile tags.

[0008] The bill generation and traceability module is connected to the dynamic settlement engine and is used to format the settlement result into a settlement bill and attach data traceability information to the key expense items in the bill.

[0009] Preferably, the user profile construction module performs statistical algorithm analysis on the load time series composed of the actual electricity metering data to extract load factor, peak-valley difference and volatility indicators, thereby generating electricity behavior tags that characterize the user's electricity consumption characteristics; and generates transaction preference tags that characterize the user's market participation strategy by analyzing the difference series between the bid price and the average market transaction price in the historical transaction declaration data.

[0010] The rule base and configuration center in the dynamic settlement engine provide a graphical management interface. The graphical management interface is configured to allow authorized users to create, edit, version control, enable, or disable rules in the settlement rule set without modifying the core program code of the system.

[0011] Preferably, the rule base and the settlement rule set stored in the configuration center constitute an N-dimensional settlement decision space. ,in: This represents the number of settlement influencing factors; the settlement status of any user within the settlement period is represented as a state vector. Each component Indicates the first related to settlement The key factors include at least user profile factors, market status factors, and contract performance factors. The settlement determination space It is automatically divided into several non-overlapping subspaces. It meets the following conditions: , in, This indicates the number of subspaces created; each subspace Internally bound unique settlement operator It defines the settlement calculation logic corresponding to the subspace.

[0012] During the settlement process, the system constructs the current user's state vector. And project it into the decision space. In this process, determine the subspace to which it belongs. Then call the corresponding settlement operator. The final cost is calculated as follows: ,in, This indicates the settlement fees for this period. For subspace The bound settlement function.

[0013] The bill generation and traceability module adds data traceability information to any expense item in the settlement bill. The data traceability information is a structured calculation path record, wherein: the path record consists of a set of data elements, which are divided into: original input elements, which are indivisible initial data; and derived result elements, which are the results generated by applying calculation operators to one or more other data elements.

[0014] Each derived result element is permanently linked to the data elements on which its computation depends and the version number of the operator used, thus forming a hierarchical, unidirectional computational dependency chain. Each dependency chain starts from one or more original input elements and eventually converges to the derived result element as the final cost item.

[0015] Preferably, the settlement and accounting core in the dynamic settlement engine, and the user profile tags output by the user profile construction module during the settlement operation, constitute the state vector. The key components determine the topological structure of the subspaces within the N-dimensional settlement and determination space; Based on the user's profile tags, a matching spatial partitioning scheme is loaded, and then the user's state vector is projected into it; the user profile structurally reshapes the entire settlement decision space, so that user groups with different profile characteristics follow essentially different settlement decision logics.

[0016] Preferably, the management system executes a management method, including the following steps: Step S1: Obtain and structure the historical electricity metering data and historical transaction declaration data of electricity users as the basic dataset for subsequent analysis.

[0017] Step S2: Invoke the preset profile modeling algorithm to perform in-depth analysis on the basic dataset and generate a set of quantified, multi-dimensional user profile labels for each electricity user, representing their inherent electricity consumption behavior and transaction preferences.

[0018] Step S3: Through the configurable rule definition interface, the complex settlement logic is abstracted and solidified into an N-dimensional settlement decision space. The settlement decision space is defined by the internal subspace topology partitioning, boundary functions and settlement operators bound to each subspace, forming an independently manageable set of settlement rules.

[0019] Step S4: During the settlement period, based on the user's real-time status data and the user profile generated in step S2, the corresponding hypercube rules are loaded from the rule set in step S3 and applied to perform settlement calculations and generate a final settlement bill containing data traceability information in the form of a settlement traceability dependency linked list.

[0020] Preferably, the step S2, which involves performing deep analysis on the basic dataset to generate quantified profile labels, includes the following sub-steps: Step S201: Extract a set of high-dimensional features from the basic dataset. The high-dimensional features characterize the periodicity, stability and abruptness of the user's electricity consumption pattern.

[0021] Step S202: Input the high-dimensional features into a pre-trained unsupervised learning model for revealing the intrinsic structure of the data, and map the high-dimensional feature vectors to a low-dimensional latent space that can characterize their core features.

[0022] Step S203: Based on the coordinate position of the high-dimensional feature vector in the low-dimensional latent space, a final quantized user profile label that can be directly interpreted by a machine is generated through a preset normalization or mapping function.

[0023] Preferably, the step of constructing the N-dimensional settlement determination space in step S3 includes: In step S301, the authorized user interactively selects N key factors as orthogonal coordinate axes of the settlement determination space from the available parameter pool containing user profiles, market status and contract performance parameters through a graphical interface.

[0024] Step S302: Based on the distribution characteristics of state vectors in historical data, a spatial clustering algorithm is applied to automatically divide the N-dimensional space into multiple data clusters, where each data cluster constitutes an initial subspace, thereby generating the topological structure of the space.

[0025] Step S303: For adjacent subspaces, a classification model algorithm is applied to fit a decision boundary function with nonlinear characteristics that can distinguish these subspaces.

[0026] Step S304: For each subspace enclosed by the boundary function, configure and bind a specific settlement operator that defines the settlement logic of that region.

[0027] Preferably, the dynamic settlement and traceability step in step S4 includes the following specific method for performing settlement calculations: Step S401: Construct a state vector by combining user profile tags, market status parameters, and contract performance data into a multi-dimensional state vector.

[0028] Step S402, Spatial positioning and operator selection: Project the state vector into a preset N-dimensional settlement judgment space, locate its subspace, and select the settlement operator bound to it.

[0029] Step S403: Execute the operator and record the path, apply the selected settlement operator to perform calculations, obtain the settlement result, and simultaneously generate a settlement traceability dependency chain list that records this complete calculation process; Step S404: Generate an invoice. The calculation result and the settlement traceability dependency chain are used as data traceability information and aggregated together to generate the final invoice.

[0030] Preferably, the settlement operator in step S403 is a function entity with a version identifier, including: when executing the settlement operator, recording the operator version identifier and the input state vector used, and synchronously writing the record as structured metadata into the settlement traceability dependency chain.

[0031] Compared to existing technologies, the advantages of this invention are as follows: By constructing deep user profiles, a dynamically configurable settlement engine, and refined data traceability, this invention fundamentally solves the problems of rigid rules, limited services, and opaque billing in traditional power trading management. Its core lies in the fact that the system not only builds quantitative profiles for users based on their electricity consumption and trading behavior, but also innovatively uses this profile as a structural factor to reshape the settlement logic, driving the adaptive division of the N-dimensional settlement judgment space. This automatically matches differentiated settlement strategies to user groups with different characteristics, truly achieving free and intelligent pricing. Simultaneously, its visualized rule configuration and end-to-end data traceability greatly improve business agility and settlement transparency, constructing a new paradigm for efficient, intelligent, and reliable power retail transaction management. Attached Figure Description

[0032] Figure 1 This is a schematic block diagram of the system comprising the management modules of the present invention.

[0033] Figure 2 This is a schematic diagram showing the distribution of user profiles in the three-dimensional decision space according to an embodiment of the present invention.

[0034] Figure 3 This is an exemplary flowchart of the management method of the present invention.

[0035] Figure 4This is an exemplary flowchart of the steps for generating quantitative profile tags according to the present invention.

[0036] The icons are labeled as follows: Data aggregation and storage module - 101; User profile building module - 102; Dynamic settlement engine - 103; Bill generation and traceability module - 104; Rule base and configuration center - 103a; Settlement and accounting core - 103b. Detailed Implementation

[0037] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following detailed description, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of the electricity sales market transaction information management system proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0038] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0039] The present invention will be further described below with reference to specific embodiments.

[0040] This invention addresses the specific scenario of transaction information processing and settlement management in the electricity retail market. It is applicable to market environments with diverse electricity consumers, varied transaction models, and complex dynamic settlement rules, encompassing businesses such as direct power purchase by large users, agency transactions by power sales companies, distributed energy aggregation, demand response, and cross-regional collaborative settlement. In this scenario, electricity consumption and transaction behaviors are significantly differentiated. Existing single settlement rules struggle to balance refinement and fairness, user transaction strategies and contract performance are difficult to quantify, and frequent price fluctuations and policy adjustments lead to delayed rule updates and high risks. Furthermore, the settlement process lacks transparency due to multiple data source access and multi-system integration. This invention achieves personalized, traceable, and highly flexible settlement management in the electricity retail market through multi-dimensional user profile modeling, N-dimensional settlement judgment space mapping, dynamic rule base management, and a full-link bill traceability mechanism. Example

[0041] like Figure 1 The diagram shown illustrates the system module structure of an electricity market transaction information management system according to an embodiment of the present invention, including: The data aggregation and storage module 101 is used to acquire and store the user's actual electricity consumption metering data in preset time granularity from the external power grid metering system, and to acquire and store the user's historical transaction declaration data from the trading platform.

[0042] Specifically, this module connects the grid-side metering system and the electricity market-side transaction reporting platform through a data acquisition subunit, extracts data according to a set cycle, and stores the processed data in a time-series database and a structured relational database through data cleaning and standardization processes.

[0043] This module also includes metadata management functions, which are used to model and associate data indexes with information such as user identifiers, meter IDs, transaction accounts, and contract numbers.

[0044] The user profile building module 102 is connected to the data aggregation and storage module 101. It is configured to generate a set of quantified, multi-dimensional user profile tags for each electricity user based on actual electricity metering data and historical transaction declaration data, using a preset profile modeling algorithm. These tags represent the user's inherent electricity consumption behavior and transaction preferences.

[0045] Specifically, this module is based on an unsupervised learning modeling framework and uses methods such as clustering, PCA dimensionality reduction, and feature selection to construct the modeling process, supporting separate deployment of training and inference.

[0046] This module contains a user profile tag repository, which can be accessed and managed by user ID and profile version. User profile tags are recorded in JSON format and provide API call services.

[0047] The dynamic settlement engine 103 is connected to both the data aggregation and storage module 101 and the user profile building module 102. The dynamic settlement engine 103 includes: The rule base and configuration center 103a is used to define and store a set of settlement rules that can be edited and version-managed by authorized users in a parameterized and formulaic form.

[0048] It should be noted that in this embodiment, the rules are stored in JSON-LD or DSL format, which allows for version control, online activation and rollback, ensuring that rule changes are controllable.

[0049] The settlement operator executor is based on a function parsing engine, which supports runtime parsing and execution of expressions, ensuring that the system can update rules without downtime.

[0050] The settlement accounting core 103b is configured to dynamically call the settlement rule set that is in effect in the rule base and configuration center 103a when the settlement cycle is triggered, and perform settlement operations in combination with actual electricity metering data and user profiles; The bill generation and traceability module 104 is connected to the dynamic settlement engine 103 and is used to format the settlement result into a settlement bill and attach data traceability information to the key expense items in the bill.

[0051] The user profile building module 102 uses statistical algorithms to analyze the load time series composed of actual electricity metering data, extracts load factor, peak-valley difference and volatility indicators, and generates electricity behavior tags that characterize the user's electricity consumption characteristics; it also analyzes the difference series between the bid price and the average market transaction price in the historical transaction declaration data to generate transaction preference tags that characterize the user's market participation strategy.

[0052] like Figure 2 The diagram shown is a simulation of the data segmentation by the user profile construction module 102 in this embodiment. Referring to the table below, the basic judgments for obtaining user profiles based on different indicators are given:

[0053] The rule base and configuration center 103a in the dynamic settlement engine 103 provide a graphical management interface. The graphical management interface is configured to allow authorized users to create, edit, version control, enable or disable rules in the settlement rule set without modifying the core program code of the system.

[0054] The settlement rule set stored in the rule base and configuration center 103a is an N-dimensional settlement decision space. , A three-dimensional space with N=3 can be constructed, where the three dimensions are composed of the user's load rate, peak-to-valley difference rate, and price deviation, respectively, where: This represents the number of settlement influencing factors; the settlement status of any user within the settlement period is represented as a state vector. Each component Indicates the first related to settlement For example, for user User002, the state vector within a settlement cycle can be calculated as x=(0.45,0.88,15.8).

[0055] Key factors include at least user profile factors, market status factors, and contract performance factors.

[0056] Settlement Judgment Space It is automatically divided into several non-overlapping subspaces. It meets the following conditions: , in, This indicates the number of subspaces created; each subspace Internally bound unique settlement operator It defines the settlement calculation logic corresponding to the subspace; for example, space S can be divided into subspaces. (Stable base load type) and (Peak fluctuation type), etc. Among them, subspace The boundary can be defined as (LF < 0.5 and PVR > 0.8), and its bound settlement operator This is a punitive time-of-use pricing model.

[0057] During the settlement process, the system constructs the current user's state vector. And project it into the decision space. In this process, determine the subspace to which it belongs. Then call the corresponding settlement operator. The final cost is calculated as follows: ,in, This indicates the settlement fees for this period. For subspace The bound settlement function; taking the user User002 as an example, its state vector x=(0.45,0.88,15.8) satisfies the boundary conditions of subspace S2, therefore the system will automatically call the settlement operator. This is used to calculate the final electricity bill. Here, Fee represents the settlement fee for this period. For subspace The bound settlement function calls the user's original metering data (such as peak and off-peak electricity consumption) for calculation when it is executed.

[0058] The bill generation and traceability module 104 adds data traceability information to any expense item in the settlement bill. The data traceability information is a structured calculation path record, wherein: the path record consists of a set of data elements, which are divided into: original input elements, which are indivisible initial data; and derived result elements, which are the results generated by applying a calculation operator to one or more other data elements.

[0059] Each derived result element is permanently linked to the data elements on which its computation depends and the version number of the operator used, thus forming a hierarchical, unidirectional computational dependency chain. Each dependency chain begins with one or more original input elements and eventually converges to the derived result element as the final cost item.

[0060] The settlement and accounting core 103b in the dynamic settlement engine 103, and the user profile tags output by the user profile construction module 102 during settlement operations, constitute the state vector. The key component determines the topological structure of the subspace partitioning within the N-dimensional settlement and determination space.

[0061] Based on the user's profile tags, a matching spatial partitioning scheme is loaded, and then the user's state vector is projected into it; the user profile structurally reshapes the entire settlement decision space, so that user groups with different profile characteristics follow essentially different settlement decision logics.

[0062] like Figure 3 The diagram shown is an exemplary flowchart of a transaction information management method provided in this embodiment, including the following steps: Step S1: Obtain and structure the historical electricity metering data and historical transaction declaration data of electricity users as the basic dataset for subsequent analysis.

[0063] Step S101: Collect historical data of the specified user group over the past 12 calendar months from the electricity marketing system and automatic meter reading system.

[0064] Step S102 involves cleaning and aligning the collected data to form a structured basic dataset. This dataset includes data for each user. The data consists of two parts: Electricity metering data: load sequences with a 15-minute time granularity. .

[0065] Historical transaction data: The sequence of electricity prices declared by users in each market transaction. .

[0066] Step S103, ensure and Strict alignment on timestamps is required for correlation analysis.

[0067] Step S2: Invoke the preset profile modeling algorithm to perform in-depth analysis on the basic dataset and generate a set of quantified, multi-dimensional user profile labels for each electricity user, representing their inherent electricity consumption behavior and transaction preferences.

[0068] At this stage, the system will analyze the user's load sequence. The system extracts indicators characterizing the periodicity, stability, and abrupt changes in users' electricity consumption patterns. Specifically, it calculates users' load factor (LF) and peak-valley ratio (PVR); and analyzes users' historical transaction data. By comparing with the average transaction price in the same period, indicators representing its market participation strategy are extracted, mainly for calculating the price deviation.

[0069] like Figure 4 As shown, step S2, which involves deep analysis of the base dataset to generate quantified profile labels, includes the following sub-steps: Step S201: Extract a set of high-dimensional features from the basic dataset. The high-dimensional features characterize the periodicity, stability and abruptness of the user's electricity consumption pattern.

[0070] Step S202 involves inputting high-dimensional features into a pre-trained unsupervised learning model used to reveal the intrinsic structure of the data, and mapping the high-dimensional feature vectors to a low-dimensional latent space that can characterize their core properties.

[0071] Step S203: Based on the coordinate position of the high-dimensional feature vector in the low-dimensional latent space, the final quantized user profile label that can be directly interpreted by the machine is generated through a preset normalization or mapping function.

[0072] Step S3: Through the configurable rule definition interface, the complex settlement logic is abstracted and solidified into an N-dimensional settlement decision space. The settlement decision space is defined by the internal subspace topology partitioning, boundary functions and settlement operators bound to each subspace, forming an independently manageable set of settlement rules.

[0073] The steps in step S3 to construct the N-dimensional settlement decision space include: In step S301, the authorized user interactively selects N key factors as orthogonal coordinate axes for the settlement determination space from an available parameter pool containing user profiles, market status, and contract performance parameters via a graphical interface. In this embodiment, the authorized user selects the load factor (LF), peak-valley ratio (PVR), and bid deviation (BD) as the coordinate axes constituting the three-dimensional settlement determination space.

[0074] Step S302: Based on the distribution characteristics of state vectors in historical data, a spatial clustering algorithm is applied to automatically divide the N-dimensional space into multiple data clusters, where each data cluster constitutes an initial subspace, thereby generating the topological structure of the space; as mentioned above. Figure 2 As shown in the figure, “Distribution of User Profiles in 3D Decision Space”, this step can clearly identify several naturally existing user clusters such as “Stable Baseload Type” and “Peak Fluctuation Type”, and each cluster is an initial subspace.

[0075] Step S303: For adjacent subspaces, apply a classification model algorithm to fit a decision boundary function with nonlinear characteristics that can distinguish these subspaces. Step S304: For each subspace enclosed by the boundary function, configure and bind a specific settlement operator that defines the settlement logic of that region.

[0076] Step S4: During the settlement period, based on the user's real-time status data and the user profile generated in step S2, the corresponding hypercube rules are loaded from the rule set in step S3 and applied to perform settlement calculations and generate a final settlement bill containing data traceability information in the form of a settlement traceability dependency linked list.

[0077] The specific methods for performing settlement calculations in the dynamic settlement and traceability step S4 include: Step S401: Construct a state vector by combining the user's profile tags, market status parameters, and contract performance data into a multi-dimensional state vector. For example, at the end of the settlement period, the system constructs a real-time state vector x=(0.45,0.88,15.8) for user User002 for the current period.

[0078] Step S402, Spatial positioning and operator selection: The state vector is projected into a preset N-dimensional settlement decision space, its subspace is located, and the settlement operator bound to it is selected; the system matches the vector x=(0.45,0.88,15.8) with the boundaries of each subspace and finds that it completely falls into the subspace. Within the range of (peak fluctuation type), therefore automatically select with Bound settlement operators .

[0079] Step S403: Execute the operator and record the path; apply the selected settlement operator to perform calculations, obtain the settlement result, and simultaneously generate a settlement traceability dependency linked list recording this complete calculation process; system call. (Punishment-based time-of-use pricing model) Substitutes the raw data such as User002's peak and off-peak electricity consumption into the calculation to obtain the final fee Fee. Simultaneously, it generates a (state vector x, subspace)... Operator The tracing path for information such as the final cost (Fee).

[0080] Step S404: Generate an invoice. The calculation results and the settlement traceability dependency chain list are used as data traceability information and aggregated together to generate the final invoice.

[0081] The settlement operator in step S403 is a function entity with a version identifier. The method includes: when executing the settlement operator, recording the version identifier of the operator used and the input state vector, and synchronously writing the record as structured metadata into the settlement traceability dependency chain.

[0082] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. An electricity sales market transaction information management system, characterized in that, include: The data aggregation and storage module (101) is used to acquire and store the actual electricity consumption metering data of users in a preset time granularity from the external power grid metering system, and to acquire and store the historical transaction declaration data of users from the trading platform. The user profile building module (102) is connected to the data aggregation and storage module (101). It is configured to generate a set of quantified, multi-dimensional user profile tags for each electricity user based on the actual electricity metering data and historical transaction declaration data through a preset profile modeling algorithm. A dynamic settlement engine (103) is connected to both the data aggregation and storage module (101) and the user profile construction module (102). The dynamic settlement engine (103) includes: The rule base and configuration center (103a) is used to define and store a set of settlement rules that can be edited and version-managed by authorized users in a parameterized and formulaic form; The settlement accounting core (103b) is configured to dynamically call the settlement rule set in the rule base and configuration center (103a) when the settlement cycle is triggered, and perform settlement operations in combination with the actual electricity metering data and the user profile tags; The bill generation and traceability module (104) is connected to the dynamic settlement engine (103) and is used to format the settlement result into a settlement bill and add data traceability information to the key expense items in the bill.

2. The electricity sales market transaction information management system according to claim 1, characterized in that: The user profile construction module (102) performs statistical algorithm analysis on the load time series composed of the actual electricity metering data to extract load rate, peak-valley difference and volatility indicators, thereby generating electricity behavior labels that characterize the user's electricity consumption characteristics; and generates transaction preference labels that characterize the user's market participation strategy by analyzing the difference series between the declared price and the average market transaction price in the historical transaction declaration data.

3. The electricity sales market transaction information management system according to claim 1, characterized in that: The rule base and configuration center (103a) in the dynamic settlement engine (103) provide a graphical management interface. The graphical management interface is configured to allow authorized users to create, edit, version control, enable, or disable rules in the settlement rule set without modifying the core program code of the system.

4. The electricity sales market transaction information management system according to claim 3, characterized in that: The settlement rule set stored in the rule base and configuration center (103a) is an N-dimensional settlement decision space. ,in: This represents the number of settlement influencing factors; the settlement status of any user within the settlement period is represented as a state vector. Each component Indicates the first related to settlement The key factors include at least user profile factors, market status factors, and contract performance factors. The settlement determination space It is automatically divided into several non-overlapping subspaces. It meets the following conditions: ， in, This indicates the number of subspaces created; each subspace Internally bound unique settlement operator It defines the settlement calculation logic corresponding to this subspace; During the settlement process, the system constructs the current user's state vector. And project it into the decision space. In this process, determine the subspace to which it belongs. Then call the corresponding settlement operator. The final cost is calculated as follows: ,in, This indicates the settlement fees for this period. For subspace Bound settlement function; The bill generation and traceability module (104) adds data traceability information to any expense item in the settlement bill. The data traceability information is a structured calculation path record, wherein: the path record consists of a set of data elements, which are divided into: original input elements, which are indivisible initial data; and derived result elements, which are the results generated by applying calculation operators to one or more other data elements. Each derived result element is permanently linked to the data elements on which its computation depends and the version number of the operator used, thus forming a hierarchical, unidirectional computational dependency chain. Each dependency chain starts from one or more original input elements and eventually converges to the derived result element as the final cost item.

5. The electricity sales market transaction information management system according to claim 4, characterized in that: The settlement calculation core (103b) in the dynamic settlement engine (103) and the user profile tags output by the user profile construction module (102) during the settlement operation constitute the state vector. The key components determine the topological structure of the subspaces within the N-dimensional settlement and determination space; Based on the user's profile tags, load the matching spatial partitioning scheme, and then project the user's state vector into it; User profiling structurally reshapes the entire settlement decision space, causing user groups with different profile characteristics to follow essentially different settlement decision logics.

6. The electricity market transaction information management system according to claim 1, characterized in that: It also includes a management method comprising the following steps: Step S1: Obtain and structure the historical electricity metering data and historical transaction declaration data of electricity users as the basic dataset for subsequent analysis; Step S2: Invoke the preset profile modeling algorithm to perform in-depth analysis on the basic dataset and generate a set of quantified, multi-dimensional user profile labels for each electricity user, representing their inherent electricity consumption behavior and transaction preferences. Step S3: Through the configurable rule definition interface, the complex settlement logic is abstracted and solidified into an N-dimensional settlement decision space. The settlement decision space is defined by the internal subspace topology partitioning, boundary functions and settlement operators bound to each subspace, forming an independently manageable set of settlement rules. Step S4: During the settlement period, based on the user's real-time status data and the user profile generated in step S2, the corresponding hypercube rules are loaded from the rule set in step S3 and applied to perform settlement calculations and generate a final settlement bill containing data traceability information in the form of a settlement traceability dependency linked list.

7. The electricity market transaction information management system according to claim 6, characterized in that: The step S2, which involves performing in-depth analysis on the basic dataset to generate quantitative profile labels, includes the following sub-steps: Step S201: Extract a set of high-dimensional features from the basic dataset. The high-dimensional features characterize the periodicity, stability and abruptness of the user's electricity consumption pattern. Step S202: Input the high-dimensional features into a pre-trained unsupervised learning model for revealing the intrinsic structure of the data, and map the high-dimensional feature vectors to a low-dimensional latent space that can characterize their core features. Step S203: Based on the coordinate position of the high-dimensional feature vector in the low-dimensional latent space, a final quantized user profile label that can be directly interpreted by a machine is generated through a preset normalization or mapping function.

8. The electricity market transaction information management system according to claim 6, characterized in that: The step of constructing the N-dimensional settlement determination space in step S3 includes: Step S301: Authorized users interactively select N key factors as orthogonal coordinate axes of the settlement determination space from the available parameter pool containing user profiles, market status and contract performance parameters through a graphical interface. Step S302: Based on the distribution characteristics of state vectors in historical data, a spatial clustering algorithm is applied to automatically divide the N-dimensional space into multiple data clusters, where each data cluster constitutes an initial subspace, thereby generating the topological structure of the space. Step S303: For adjacent subspaces, apply a classification model algorithm to fit a decision boundary function with nonlinear characteristics that can distinguish these subspaces. Step S304: For each subspace enclosed by the boundary function, configure and bind a specific settlement operator that defines the settlement logic of that region.

9. The electricity sales market transaction information management system according to claim 6, characterized in that: The specific method for performing settlement calculations in the dynamic settlement and traceability step S4 includes: Step S401: Construct a state vector by combining user profile tags, market status parameters, and contract performance data into a multi-dimensional state vector. Step S402, Spatial positioning and operator selection: Project the state vector into the preset N-dimensional settlement judgment space, locate its subspace, and select the settlement operator bound to it. Step S403: Execute the operator and record the path, apply the selected settlement operator to perform calculations, obtain the settlement result, and simultaneously generate a settlement traceability dependency chain list that records this complete calculation process; Step S404: Generate an invoice. The calculation result and the settlement traceability dependency chain are used as data traceability information and aggregated together to generate the final invoice.

10. The electricity sales market transaction information management system according to claim 6, characterized in that: The settlement operator mentioned in step S403 is a function entity with a version identifier, including: when executing the settlement operator, recording the operator version identifier and the input state vector used, and synchronously writing the record as structured metadata into the settlement traceability dependency chain list.

Images