Automatic checking method, system and equipment for premium electricity charge in green electricity transaction environment and medium

Abstract

The invention discloses an automatic checking method, system, equipment and medium for green electricity transaction environment premium electric charge, and relates to the technical field of electric charge checking, which comprises the steps of collecting and preprocessing environment premium electric charge data, constructing a checking rule base based on settlement requirements and integrating a rule engine, checking transaction in real time, and performing feature extraction on the data. And performing hierarchical matching with a rule base, evaluating consistency, generating an evaluation vector, automatically identifying abnormity, comparing payment data based on an evaluation result, checking the difference between a theoretical value and an actual value, feeding back the result in real time, automatically generating a report and triggering early warning. According to the method, a closed-loop system in which the rule engine, dynamic evaluation and difference checking are combined is constructed, so that full-process automation and intelligentization from data verification, anomaly recognition to payment risk interception of the premium electric charge in the green electricity environment are realized, and the settlement efficiency and the risk management and control capability are improved while the fund safety is guaranteed.

Description

Technical Field

[0001] This invention relates to the field of electricity bill verification technology, specifically to an automatic verification method, system, equipment, and medium for premium electricity charges in green electricity trading environments. Background Technology

[0002] The environmental premium for green electricity refers to the extra cost that consumers are willing to pay to support the development of green electricity. This cost is usually used to subsidize renewable energy power generation companies to encourage more green electricity production. In the process of green electricity trading, the calculation of the environmental premium involves multiple stages, including electricity production, trading, and consumption. The data volume is large, the process is complex, and manual verification is inefficient and prone to errors. Therefore, a method for verifying the premium has emerged. This method mainly uses big data, cloud computing, blockchain and other technologies to collect, process and analyze the premium data, as well as coordinate with multiple trading parties, thereby achieving automatic verification of electricity charges. This can improve the efficiency and accuracy of data processing and reduce transaction costs. However, existing technologies still have the following drawbacks: First, existing methods for verifying premium electricity charges may only collect partial electricity charge data, lacking systematicity and comprehensiveness. Data preprocessing may be missing or simplistic, affecting the accuracy of subsequent verification. Second, existing methods for verifying premium electricity charges may have relatively simple and fixed rules, making it difficult to adapt to complex and ever-changing transaction scenarios. Furthermore, they lack real-time verification mechanisms, making it impossible to promptly identify and correct problems during transaction settlement. Third, existing methods for verifying premium electricity charges may not extract electricity charge-related information in a detailed and comprehensive manner, focusing only on some key information and easily overlooking important details that affect the verification results, leading to inaccurate matching. They may also only perform simple rule matching, lacking further analysis and evaluation of the matching results, making it difficult to identify and eliminate abnormal data, which may result in inaccurate verification results. Summary of the Invention

[0003] In view of the above-mentioned existing problems, the present invention provides an automatic verification method, system, equipment and medium for premium electricity charges in green electricity trading environment, in order to solve the problems of low verification accuracy, difficulty in adapting to complex and ever-changing trading scenarios, lack of real-time verification mechanism, inability to detect and correct problems in a timely manner during the transaction settlement process, inaccurate matching, difficulty in identifying and excluding abnormal data, and thus inaccurate verification results in the existing technology.

[0004] To address the aforementioned technical issues, an automatic verification method for premium electricity charges in green electricity trading is proposed, including: The system collects environmental premium electricity charge information data, preprocesses the data, and constructs a verification rule base based on transaction settlement needs. This verification rule base is integrated into the transaction settlement rule engine for real-time verification and rule execution of each transaction settlement. Feature extraction is performed on the preprocessed environmental premium electricity charge information data to identify key features. These extracted features are then matched hierarchically with the verification rule base to assess data consistency. The rule matching results are aggregated to generate a unified evaluation vector, which is then used for dynamic evaluation to automatically identify and eliminate abnormal data. Based on the dynamic evaluation results, comparative analysis is performed on environmental premium electricity charge payment data. The difference between theoretical and actual values ​​is calculated to verify whether the payment meets the acceptance criteria. The verification results of the environmental premium electricity charge are fed back in real-time, automatically generating reports and triggering early warning mechanisms.

[0005] As a preferred embodiment of the automatic verification method for premium electricity charges in the green electricity trading environment described in this invention, the preprocessing of information data includes: cleaning the collected information data, identifying and processing outliers and missing data, verifying the cleaned data, and converting the verified data into a unified format and unit. The transformed data is integrated, relationships are established between different data tables, and the integrated data is labeled with classification tags and semantic information to obtain a standardized dataset.

[0006] As a preferred embodiment of the automatic verification method for premium electricity charges in the green electricity trading environment described in this invention, the construction of the verification rule base includes defining rule types based on each type of requirement in the transaction settlement process, and classifying the rules according to their functions and scope of application. Write rules for each type of rule to obtain executable verification logic, and then enter the written rules into the rule base and assign a unique identifier to each rule. The rule base is divided into functional layers to establish logical relationships between rules at different levels. The layered rules are then deployed to the rule engine for automatic execution.

[0007] As a preferred embodiment of the automatic verification method for premium electricity charges in the green electricity trading environment described in this invention, the feature extraction includes: identifying feature dimensions from preprocessed information data and determining the categories of key information to be extracted; For each feature dimension, feature localization is performed to locate the matching data field from the original data, and feature parsing is performed on the located feature data to extract structured feature information; The parsed features are classified and organized according to feature type. The classified features are then matched hierarchically with the rule base to compare features against rules.

[0008] As a preferred embodiment of the automatic verification method for premium electricity charges in green electricity trading environment described in this invention, the aggregation process includes: generating a rule matching vector; aggregating the rule matching results at each level into a vector form; performing dynamic evaluation; assigning weights to each coefficient in the vector; calculating a verification evaluation index through weighted summation; comparing the verification evaluation index with a preset verification threshold; if the verification evaluation index is greater than or equal to the threshold, it is determined to meet the standard and the process continues; otherwise, the transaction is terminated and manual approval is triggered; anomaly identification is performed based on the matching results; the anomaly level is located through multi-dimensional correlation analysis; and anomaly cause tags are automatically generated. The dynamic evaluation based on the evaluation vector includes assigning a weight coefficient to each matching coefficient in the rule matching vector, calculating a verification evaluation index through weighted summation, and comparing the verification evaluation index with a preset verification threshold. The calculation formula is expressed as follows: in, To verify the evaluation index, , , and These are the weighting coefficients for rules at different levels. D is the basic matching coefficient, and D is the dynamic matching coefficient. For compliance matching coefficient, The operation matching coefficient is μ, and the preset verification threshold is μ. If A ≥ μ, the payment review process continues if the verification standard is met. If A < μ, the transaction process is terminated and manual approval is triggered if the verification standard is not met. The anomaly level is located based on the rule matching results. The anomaly characteristics are investigated through multi-dimensional correlation analysis, including comparing the matching of the remaining data in the same transaction batch, tracing historical transaction records, and automatically generating anomaly reason tags by combining conflict rules in the business rule base.

[0009] As a preferred embodiment of the automatic verification method for environmental premium electricity fees in green electricity trading according to the present invention, the comparative analysis includes: calculating the theoretical environmental premium electricity fee based on the environmental premium electricity fee payment data; comparing the calculated theoretical environmental premium electricity fee with the actual environmental premium electricity fee to be paid; when the absolute value of the difference between the two is greater than a preset difference threshold, the environmental premium electricity fee payment is determined to be unsuccessful, the payment process is immediately stopped, the payment status is updated to payment freeze, an anomaly list is generated, and manual review of the payment amount is triggered; when the absolute value of the difference is less than or equal to the preset difference threshold, the environmental premium electricity fee payment is determined to be successful, and the normal settlement process is triggered. The formula for calculating the theoretical environmental premium electricity tariff premium is expressed as follows: in, The theoretical environmental premium for electricity pricing, For electricity consumption, The benchmark electricity price, This represents the premium percentage.

[0010] As a preferred embodiment of the automatic verification method for premium electricity charges in the green electricity trading environment described in this invention, the real-time feedback includes: automatically generating a verification report based on the verification process and verification results, asynchronously pushing the verification results to the user terminal, and issuing warnings for abnormal verification results, triggering manual review prompts. When the environmental premium electricity charge information data does not meet the verification standards or the environmental premium electricity charge payment does not meet the payment approval standards, an early warning prompt for abnormal verification results is automatically triggered, an environmental premium electricity charge anomaly detection report is generated, and sent to the user terminal along with the anomaly list for early warning feedback.

[0011] The beneficial effects of this preferred technical solution are that by automatically generating reports, asynchronously pushing results, issuing early warnings of anomalies, and triggering manual review, it ensures that users and maintenance personnel have the right to know about the system status and transaction results, and establishes a risk emergency response mechanism to ensure that any anomalies can be detected, reported, and handled in a timely manner, thereby minimizing the economic losses and risks that may be caused by delayed processing.

[0012] As a preferred embodiment of the automatic verification system for premium electricity charges in the green electricity trading environment described in this invention, it is characterized by including an information collection module, a rule base construction module, an information matching and analysis module, an information verification and detection module, a payment verification module, and a verification result feedback module.

[0013] The information collection module is used to automatically collect information data related to environmental premium electricity charges through the API interface and preprocess the collected raw data.

[0014] The rule base construction module is used to systematically divide the rules into four types: basic rules, dynamic rules, compliance rules, and operational rules by collecting the verification requirements in the transaction settlement process. The rule base is also layered into a basic layer, a dynamic layer, a compliance layer, and an operational layer. After the rules are written and entered, they are deployed and integrated into the rule engine of the transaction settlement system to perform real-time and automated verification of each transaction settlement data.

[0015] The information matching and analysis module is used to perform deep feature extraction on the preprocessed data, extracting key feature information from four dimensions: contract terms, electricity volume, green certificates, and finance. The extracted features are then matched with the matching standards at the matching level in the rule base, and the basic matching coefficient, dynamic matching coefficient, compliance matching coefficient, and operational matching coefficient are calculated to provide a quantitative matching basis for comprehensive evaluation.

[0016] The information verification and detection module is used to aggregate the matching coefficients at each level to generate a unified rule matching vector. By assigning weights to each coefficient, it calculates a comprehensive verification evaluation index, compares the verification evaluation index with a preset verification threshold, dynamically determines whether the current transaction data meets the verification standards, and automatically locates the abnormal level for data that does not meet the standards. Combining multi-dimensional correlation analysis and business conflict rules, it identifies and marks abnormal data, triggers a manual approval process, and eliminates risks.

[0017] The payment verification module is used to calculate the theoretical environmental premium electricity fee based on the electricity consumption, benchmark electricity price and premium ratio, and compare the theoretical value with the actual payment amount. When the difference between the two exceeds the preset difference threshold, the payment is determined to be unsuccessful, the payment status is immediately frozen, an abnormal list is generated and manual review is triggered. When the difference is within the allowable range, the payment is determined to be successful and the normal settlement process is triggered.

[0018] The verification result feedback module is used to automatically generate verification reports and push the results asynchronously to the user terminal. For any abnormalities found during the verification, it will issue early warning information in a timely manner and trigger manual review prompts.

[0019] A computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of a method for automatically verifying premium electricity charges in green electricity trading environments.

[0020] A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of the method for automatically verifying the premium electricity charges in the green electricity trading environment are disclosed.

[0021] The beneficial effects of this invention are as follows: This invention constructs a standardized dataset through data preprocessing, laying an accurate and reliable data foundation for subsequent verification; by integrating a hierarchical rule base and rule engine, it achieves comprehensive coverage and real-time dynamic verification of complex transaction scenarios, significantly improving the system's adaptability and response speed; through multi-dimensional feature extraction and hierarchical matching, the verification work is deepened from surface information comparison to deep association analysis based on business semantics, greatly improving the intelligence and accuracy of verification; and by utilizing the aggregation and quantitative evaluation model of rule matching vectors, objective and comprehensive automated decision-making and accurate anomaly location are achieved, effectively avoiding human error; through independent comparison and verification of theoretical values ​​and actual payments, erroneous payments are prevented, and through real-time feedback and early warning mechanisms, timely risk detection and efficient handling are ensured. Attached Figure Description

[0022] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart illustrating the overall process of an automatic verification method for premium electricity charges in a green electricity trading environment, as provided in one embodiment of the present invention.

[0024] Figure 2 This is a schematic diagram of the environmental premium electricity fee verification process for an automatic verification method for green electricity trading provided in an embodiment of the present invention.

[0025] Figure 3 The flowchart shows the system scheme of an automatic verification system for premium electricity charges in green electricity trading environment provided in one embodiment of the present invention. Detailed Implementation

[0026] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0027] Example 1, referring to Figure 1 As an embodiment of the present invention, an automatic verification method for premium electricity charges in green electricity trading environments is provided, including: S100: Collects environmental premium electricity charge information data, preprocesses the information data, builds a verification rule base based on transaction settlement needs, and integrates the verification rule base into the transaction settlement rule engine to perform real-time verification and rule execution for each transaction settlement.

[0028] S200: Extract features from the preprocessed environmental premium electricity charge information data, identify key feature information, perform hierarchical matching between the extracted features and the verification rule base, evaluate data consistency, aggregate the rule matching results to generate a unified evaluation vector, and perform dynamic evaluation based on the evaluation vector to automatically identify and exclude abnormal data.

[0029] S300: Based on dynamic assessment results, it compares and analyzes environmental premium electricity payment data, verifies whether the payment meets the standards by calculating the difference between theoretical and actual values, and provides real-time feedback on the verification results of environmental premium electricity charges, automatically generating reports and triggering early warning mechanisms.

[0030] It should be noted that by building an integrated rule engine, the modularization and automated execution of settlement logic have been achieved, significantly improving settlement efficiency and flexibility. Furthermore, through feature extraction and a dynamic evaluation mechanism based on evaluation vectors, accurate identification and intelligent screening of abnormal data have been achieved. By verifying the difference between theoretical and actual values, a fund security defense line has been established, ensuring payment accuracy and fund security, and comprehensively improving the automation level and risk control capabilities of green electricity transaction settlement.

[0031] Example 2, refer to Figure 1 and Figure 2 This is a second embodiment of the present invention, which provides an automatic verification method for premium electricity charges in green electricity trading environments, including: In step S100, the collection of environmental premium electricity charge information data includes steps S101~S102: S101: The power trading system, carbon trading platform and financial system automatically import data into the computer terminal through the API interface to access and obtain information on environmental premium electricity charges in real time. S102: Automatically synchronize data from the power trading system, carbon trading platform, and financial system according to preset time intervals, and integrate and classify the synchronized data according to transaction IDs.

[0032] Furthermore, in this embodiment of the application, the preprocessing of information data in step S100 includes data cleaning, data verification, data transformation, data integration, and data labeling, specifically including steps S111 to S115: S111: Data cleaning includes using the 3σ principle and the isolated forest algorithm to identify and correct outliers (such as electricity price mutation points), using linear interpolation or XGBoost models to fill missing data (such as electricity loss due to sensor failure), and deleting invalid samples with high missing rates.

[0033] S112: Data verification includes ensuring data consistency based on logical rules (such as wind power carbon emission factor <0.2kgCO2 / kWh) and multi-source cross-comparison (grid metering data vs. enterprise declaration data).

[0034] S113: Data transformation includes standardizing the electricity price and carbon emission factor dimensions using Z-score, processing the power generation type classification variable using unique thermal coding, and splitting the timestamp into year / month / day fields to support time series analysis.

[0035] S114: Data integration includes merging multi-table data on electricity consumption, electricity price, and enterprise information using primary key-foreign key relationships, and calculating the regional premium electricity rate average using a weighted average formula, expressed as follows: in, Let i be the unit price of the environmental premium electricity charge for the i-th record. This represents the regional average premium electricity price. Let i be the electricity level corresponding to the i-th record, where i is the record index.

[0036] S115: By using supervised learning to label whether transactions involve the transfer of green certificates across provinces, high-quality structured data can be provided for subsequent electricity price forecasting and carbon emission reduction strategies.

[0037] In an optional implementation, step S100, the preprocessing of the information data further includes: performing data cleaning, identifying outliers using predefined threshold rules, and filling missing data with the mean or median; performing data verification, comparing statistical distribution characteristics with historical data for consistency checks; performing data transformation, adjusting the data range using the min-max standardization method, and labeling categorical variables; performing data integration, merging multi-source data based on similarity matching using data fusion technology; and performing data labeling, automatically adding categorization labels based on business rule conditions.

[0038] In another optional implementation, in step S100, the preprocessing of the information data may further include: data cleaning, identifying and processing outliers through a data quality rule engine, and filling missing data using a moving average method; data verification, performing multi-dimensional verification through a business rule engine; data transformation, unifying values ​​using a decimal scaling method, and encoding categorical variables with ordinal numbers; data integration, performing data association and aggregation through star schema or snowflake schema modeling; and data labeling, labeling transaction types based on heuristic rules.

[0039] In this embodiment of the application, step S100, the construction of the verification rule base includes steps S121 to S125: S121: Define rule types, and classify rules into basic rules, dynamic rules, compliance rules, and operational rules according to transaction settlement requirements; S122: Write rules and design specific logic for each rule type. For example, basic rules include electricity, amount and time verification, dynamic rules include premium unit price calculation and carbon price linkage, compliance rules include green certificate, contract and policy compliance, and operation rules include permissions, logs and process control. S123: Enter rules, store the written rules in the rule base, and assign a unique identifier to each rule; S124: Implement rule layering, organizing the rule base into a basic layer, dynamic layer, compliance layer, and operational layer to clarify the logical relationships between rules; S125: Deploy the verification rule base to the rule engine, integrate the rules into the transaction settlement system, and perform automated rule execution and real-time verification.

[0040] In an optional implementation, step S100, the construction of the verification rule base further includes defining rule types, using a predefined rule template library, such as verification templates and calculation templates, writing rules, generating rule logic by configuring template parameters, entering rules, storing the instantiated rules in the rule base, layering rules, organizing them according to business domains such as transaction layer, financial layer and compliance layer, deploying them to the rule engine, and using a lightweight engine to implement rule execution.

[0041] In another optional implementation, in step S100, the construction of the verification rule base may further include defining rule types, automatically extracting rule categories from policy documents and contract texts, using natural language processing technology to write rules, automatically generating rule logic by parsing text content, entering rules, automatically storing rules in the rule base, automatically classifying rules into different levels based on rule semantics, deploying them to the rule engine, and supporting dynamic rule updates and execution.

[0042] Furthermore, in step S124, A1: The basic layer includes electricity verification rules, amount verification rules, and time verification rules. The electricity verification rules are used to determine whether the traded electricity volume is within the contractually agreed-upon range. If it exceeds the limit, it is marked as abnormal. This is done by comparing the traded electricity volume in the power trading system with the upper limit of the contracted electricity volume in the contract management system. When the traded electricity volume is found to be greater than the upper limit of the contracted electricity volume, it is determined to be an electricity verification abnormality and marked as abnormal. The amount verification rules are used to determine whether the premium electricity fee is within a reasonable fluctuation range. If it exceeds the range, manual review is required. This is done by comparing and analyzing the premium electricity fee in the financial system with the historical average electricity fee in the historical transaction database. When the premium electricity fee exceeds the fluctuation range of the historical average price, i.e. ,in, For premium electricity charges, Historical average price If the transaction time does not meet the preset fluctuation threshold, it is judged as an anomaly in the premium electricity fee verification and marked as a potential anomaly. The time verification rule is used to determine whether the transaction time is within the contract validity period and the green certificate validity period. By comparing the transaction time with the contract validity period and the green certificate validity period, if the transaction time exceeds the contract validity period or the transaction time is longer than the green certificate validity period, then... or ,in, For trading hours, The effective date of the contract. The contract expiration date. If the green certificate is not valid, the current transaction will be deemed invalid.

[0043] A2: The dynamic layer includes the premium unit price calculation rules and the carbon price linkage rules. The premium unit price calculation rules calculate the premium unit price based on the carbon price adjustment coefficient analyzed from the carbon trading platform. The formula for calculating the carbon price adjustment coefficient is expressed as follows: in, Based on the current carbon price, As a benchmark carbon price, To adjust the factor, This is the carbon price adjustment factor; The formula for calculating the premium unit price is as follows: in, The benchmark electricity price, This is the premium percentage. This is a premium unit price; The carbon price linkage rule is used to automatically adjust the premium unit price and issue an early warning when a large fluctuation in carbon price is detected. When the carbon price fluctuation is detected to be greater than the preset carbon price fluctuation threshold, the premium unit price is recalculated and an early warning is pushed to the business department.

[0044] A3: The compliance layer includes rules on the validity of green certificates, rules on contract terms, and rules on policy compliance. Rules on the validity of green certificates are used to verify that green certificates are unique and within their validity period. If a green certificate ID is in the list of used green certificates or the validity period of a green certificate is less than the transaction time, it is determined to be an invalid green certificate. Rules on contract terms are used to verify that the transaction terms are completely consistent with the contract. If the transaction terms are inconsistent with the terms agreed in the contract (such as the premium ratio and payment method), an abnormal mechanism is triggered. Rules on policy compliance are used to detect whether the premium electricity fee is compliant. If the premium electricity fee is not listed separately or the carbon emission reduction contribution of the premium electricity fee is not marked, it is determined to be non-compliant.

[0045] A4: The operation layer includes permission verification rules and operation log rules. Permission verification rules are used to verify that only authorized users can modify key parameters. When the user role is not an authorized role and the user attempts to modify the premium ratio, the operation is intercepted and logged. Operation log rules are used to verify whether the key operation logs are completely recorded. When the key operation logs are missing user ID, operation time, and operation content, the operation is judged as abnormal.

[0046] In this embodiment of the application, in step S200, the feature extraction includes steps S201 to S205: S201: Identify feature dimensions and determine transaction contract terms, electricity volume, green certificate information, and financial information as key dimensions; The extracted contract features include contract number, contract type, contracting parties, effective date, expiration date, and premium clause; the extracted electricity information includes the traded electricity volume, metering time, electricity unit, and electricity source; the extracted green certificate information includes green certificate number, green certificate validity period, green certificate type, and associated electricity volume; and the extracted financial information includes transaction amount, premium amount, benchmark electricity price, carbon price linkage coefficient, payment method, and invoice information.

[0047] S202: Perform feature localization to locate target fields from multi-source data such as contract texts, electricity metering systems, green certificate platforms, and financial systems; The target fields are located from multiple sources of data, including contract texts, electricity metering systems, green certificate registration platforms, and financial systems. Among them, the contract clause features are extracted from PDFs / scanned documents using NLP entity recognition technology (such as the BERT model) to extract structured information such as contract number, contracting parties, and effective date. The numerical value in the premium clause ("premium of 0.05 yuan / kWh") is then parsed using regular expressions.

[0048] S203: Perform feature analysis, use natural language processing technology to extract structural information such as contract number and premium clause from contract documents, use ETL tools to clean and transform electricity data, call API to verify green certificate information, and parse financial data through a rules engine; Electricity information features rely on ETL tools to clean metering system data, unify electricity units (e.g., MWh to kWh), and associate them with enterprise information tables to label power generation type codes, verifying whether the metering time is within the contract validity period; green certificate feature extraction requires calling the national green certificate platform API to verify the validity of the number, and associating the electricity table with the transaction ID to ensure that the associated electricity does not exceed the total amount of green certificates issued.

[0049] S204: Perform feature classification, and group the parsed features into contract features, electricity features, green certificate features and financial features according to their types; Financial features are matched with transaction amounts in invoice information and system records through a rule engine. The theoretical value is dynamically calculated using the formula: Premium Amount = Transaction Electricity × (Benchmark Electricity Price + Carbon Price Linkage Coefficient × Carbon Price) - Benchmark Electricity Fee. The data consistency is verified by comparing the theoretical value with the declared value, forming a complete dataset containing four types of features: contract, electricity, green certificate, and financial features.

[0050] S205: Perform hierarchical matching, matching and analyzing the categorized features with the basic layer, dynamic layer, compliance layer, and operation layer of the rule base; By performing matching analysis between features and the base layer, a basic matching coefficient is calculated to verify whether the most basic information regarding environmental premium electricity charges is consistent. The specific calculation formula is as follows: in, Based on the matching coefficient, This is the set of basic information features extracted from the contract number and green certificate number. This refers to the set of basic information rules in the rule base. By matching features with the dynamic layer, a dynamic matching coefficient is calculated to monitor the changes in electricity consumption and financial information related to the environmental premium electricity charge over time. The specific calculation formula is as follows: Where D is the dynamic matching coefficient. The extracted power information feature set, This is a dynamic set of rules for the corresponding battery information in the rule base. For the extracted set of financial information features, This is the set of dynamic rules for corresponding financial information in the rule base; By matching features with the compliance layer, a compliance matching coefficient is calculated, and the contract terms of the environmental premium electricity fee and green certificates are checked sequentially. The specific calculation is expressed as follows: in, For compliance matching coefficient, The extracted set of contract terms information features, This is the set of contract compliance rules in the rule base. The extracted green certificate information feature set, This is the set of compliance rules for the corresponding green certificate information in the rule base; By matching features with the operational layer, an operational matching coefficient is calculated to monitor the payment methods and invoice information in the actual operation of environmental premium electricity charges. The specific calculation formula is as follows: in, For the operation matching coefficient, This is the set of operational layer information features extracted (such as payment methods and invoice information). This refers to the set of rules for the corresponding operation layer in the rule base.

[0051] In an optional implementation, in step S200, the feature extraction further includes identifying feature dimensions, determining four key dimensions, locating fields through predefined data mapping rules, extracting features from text and data using regular expressions and string processing techniques, merging features into corresponding categories based on rule conditions, and directly matching features with the rule layer using simple logic.

[0052] In another optional implementation, in step S200, the feature extraction may further include identifying feature dimensions, automatically learning feature dimensions from the original data through a neural network, locating key data fields using an attention mechanism, parsing all features simultaneously through a deep learning model, directly generating feature categories from the model output, and calculating and matching the similarity between the feature vector and the rule vector.

[0053] Furthermore, in this embodiment of the application, in step S200, the polymerization process includes steps S211 to S213: S211: Generate rule matching vectors, which aggregate the rule matching results at each level into a vector form, including basic matching coefficients, dynamic matching coefficients, compliance matching coefficients, and operational matching coefficients. Each coefficient is obtained by calculating the intersection ratio between the feature set and the rule set.

[0054] S212: Perform dynamic evaluation, assign weights to each coefficient in the vector, calculate the verification evaluation index by weighted summation, and compare the index with the preset verification threshold. If the index is greater than or equal to the threshold, it is determined to meet the standard and the process continues; otherwise, the transaction is terminated and manual approval is triggered. The dynamic evaluation based on the evaluation vector includes assigning a weight coefficient to each matching coefficient in the rule matching vector, calculating a verification evaluation index through weighted summation, and comparing the verification evaluation index with a preset verification threshold. The calculation formula is expressed as follows: in, To verify the evaluation index, , , and These are the weighting coefficients for rules at different levels. D is the basic matching coefficient, and D is the dynamic matching coefficient. For compliance matching coefficient, is the operation matching coefficient, and μ is the preset verification threshold.

[0055] S213: Based on the matching results, anomaly identification is performed, the anomaly level is located through multi-dimensional correlation analysis, and anomaly cause labels are automatically generated; If A ≥ μ, the payment review process continues if the verification standard is met. If A < μ, the transaction process is terminated and manual approval is triggered if the verification standard is not met. The anomaly level is located based on the rule matching results. The anomaly characteristics are investigated through multi-dimensional correlation analysis, including comparing the matching of the remaining data in the same transaction batch, tracing historical transaction records, and automatically generating anomaly reason tags by combining conflict rules in the business rule base.

[0056] In an optional implementation, in step S200, the aggregation process further includes generating a rule matching vector, which also includes four coefficients, calculated by simple ratio, performing dynamic evaluation, directly calculating the evaluation index by weighted average of the coefficients, and comparing it with a threshold, and identifying anomalies based on individual rule violations.

[0057] In another optional implementation, in step S200, the aggregation process may further include generating a rule matching vector, using the matching result as a feature input to a classification model for dynamic evaluation, using the classification model to output a compliance probability and comparing it with a threshold, and anomaly identification is achieved through model confidence and historical data backtracking.

[0058] In step S300, the comparative analysis includes calculating the theoretical environmental premium electricity fee based on relevant data of the environmental premium electricity fee payment, including payment amount, payment time, electricity consumption, electricity unit price, and environmental premium standard. The calculated theoretical environmental premium electricity fee is then compared with the actual environmental premium electricity fee to be paid. If the absolute value of the difference is greater than a preset difference threshold ε, the environmental premium electricity fee payment is deemed unsuccessful, the payment process is immediately stopped, the payment status is updated to payment freeze, an exception list is generated, and manual review of the payment amount is triggered. If the absolute value of the difference is less than or equal to ε, the environmental premium electricity fee payment is deemed successful, and the normal settlement process is triggered. The formula for calculating the theoretical environmental premium electricity tariff premium is expressed as follows: in, The theoretical environmental premium for electricity pricing, For electricity consumption, The benchmark electricity price, This represents the premium percentage.

[0059] Furthermore, the real-time feedback includes automatically generating a verification report based on the verification process and results, asynchronously pushing the verification results to the user terminal, and issuing warnings for abnormal verification results, triggering manual review prompts. When the environmental premium electricity charge information data does not meet the verification standards or the environmental premium electricity charge payment does not meet the payment approval standards, an early warning prompt for abnormal verification results is automatically triggered, an environmental premium electricity charge anomaly detection report is generated, and sent to the user terminal along with the anomaly list for early warning feedback.

[0060] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

[0061] Example 3, referring to Figure 3 This is the third embodiment of the present invention, which provides an automatic verification system for premium electricity charges in green electricity trading environments, including an information collection module, a rule base construction module, an information matching and analysis module, an information verification and detection module, a payment verification module, and a verification result feedback module.

[0062] The information collection module is used to automatically collect information data related to environmental premium electricity charges through the API interface and preprocess the collected raw data.

[0063] The rule base construction module is used to systematically divide the rules into four types: basic rules, dynamic rules, compliance rules, and operational rules by collecting the verification requirements in the transaction settlement process. The rule base is also layered into a basic layer, a dynamic layer, a compliance layer, and an operational layer. After the rules are written and entered, they are deployed and integrated into the rule engine of the transaction settlement system to perform real-time and automated verification of each transaction settlement data.

[0064] The information matching and analysis module is used to perform deep feature extraction on the preprocessed data, extracting key feature information from four dimensions: contract terms, electricity volume, green certificates, and finance. The extracted features are then matched with the matching standards at the matching level in the rule base, and the basic matching coefficient, dynamic matching coefficient, compliance matching coefficient, and operational matching coefficient are calculated to provide a quantitative matching basis for comprehensive evaluation.

[0065] The information verification and detection module is used to aggregate the matching coefficients at each level to generate a unified rule matching vector. By assigning weights to each coefficient, it calculates a comprehensive verification evaluation index, compares the verification evaluation index with a preset verification threshold, dynamically determines whether the current transaction data meets the verification standards, and automatically locates the abnormal level for data that does not meet the standards. Combining multi-dimensional correlation analysis and business conflict rules, it identifies and marks abnormal data, triggers a manual approval process, and eliminates risks.

[0066] The payment verification module is used to calculate the theoretical environmental premium electricity fee based on the electricity consumption, benchmark electricity price and premium ratio, and compare the theoretical value with the actual payment amount. When the difference between the two exceeds the preset difference threshold, the payment is determined to be unsuccessful, the payment status is immediately frozen, an abnormal list is generated and manual review is triggered. When the difference is within the allowable range, the payment is determined to be successful and the normal settlement process is triggered.

[0067] The verification result feedback module is used to automatically generate verification reports and push the results asynchronously to the user terminal. For any abnormalities found during the verification, it will issue early warning information in a timely manner and trigger manual review prompts.

[0068] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

[0069] Example 4, the fourth embodiment of the present invention, differs from the previous three embodiments in that: If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0070] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0071] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0072] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

Claims

1. An automatic verification method for premium electricity charges in green electricity trading environments, characterized by: include, Collect environmental premium electricity fee information data, preprocess the information data, build a verification rule base based on transaction settlement needs, and integrate the verification rule base into the transaction settlement rule engine to perform real-time verification and rule execution for each transaction settlement; Feature extraction is performed on the preprocessed environmental premium electricity fee information data to identify key feature information. The extracted features are then matched hierarchically with the verification rule base to assess data consistency. The rule matching results are aggregated to generate a unified evaluation vector. Dynamic evaluation is then performed based on the evaluation vector to automatically identify and exclude abnormal data. Based on the dynamic assessment results, the environmental premium electricity fee payment data is compared and analyzed. The difference between the theoretical value and the actual value is calculated to verify whether the payment meets the pass standard. The verification results of the environmental premium electricity fee are fed back in real time, and reports are automatically generated and early warning mechanisms are triggered.

2. The automatic verification method for green electricity trading environment premium charges as described in claim 1, characterized in that: The preprocessing of information data includes cleaning the collected information data, identifying and processing outliers and missing data, verifying the cleaned data, and converting the verified data into a unified format and unit. The transformed data is integrated, relationships are established between different data tables, and the integrated data is labeled with classification tags and semantic information to obtain a standardized dataset.

3. The automatic verification method for green electricity trading environment premium electricity fees as described in claim 2, characterized in that: The construction of the verification rule base includes defining rule types based on each type of requirement in the transaction settlement process, and classifying the rules according to their functions and scope of application. Write rules for each type of rule to obtain executable verification logic, and then enter the written rules into the rule base and assign a unique identifier to each rule. The rule base is divided into functional layers to establish logical relationships between rules at different levels. The layered rules are then deployed to the rule engine for automatic execution.

4. The automatic verification method for premium electricity charges in green electricity trading as described in claim 3, characterized in that: The feature extraction includes identifying feature dimensions from the preprocessed information data and determining the categories of key information to be extracted; For each feature dimension, feature localization is performed to locate the matching data field from the original data, and feature parsing is performed on the located feature data to extract structured feature information; The parsed features are classified and organized according to feature type. The classified features are then matched hierarchically with the rule base to compare features against rules.

5. The automatic verification method for premium electricity charges in green electricity trading as described in claim 4, characterized in that: The aggregation process includes: generating a rule matching vector; aggregating the rule matching results at each level into a vector form; performing dynamic evaluation; assigning weights to each coefficient in the vector; calculating a verification evaluation index through weighted summation; comparing the verification evaluation index with a preset verification threshold; if the verification evaluation index is greater than or equal to the threshold, it is determined that the standard is met and the process continues; otherwise, the transaction is terminated and manual approval is triggered; and anomaly identification is performed based on the matching results, the anomaly level is located through multi-dimensional correlation analysis, and anomaly cause tags are automatically generated. The dynamic evaluation based on the evaluation vector includes assigning a weight coefficient to each matching coefficient in the rule matching vector, calculating a verification evaluation index through weighted summation, and comparing the verification evaluation index with a preset verification threshold. The calculation formula is expressed as follows: in, To verify the evaluation index, , , and These are the weighting coefficients for rules at different levels. D is the basic matching coefficient, and D is the dynamic matching coefficient. For compliance matching coefficient, The operation matching coefficient is μ, and the preset verification threshold is μ. If A ≥ μ, the payment review process continues if the verification standard is met. If A < μ, the transaction process is terminated and manual approval is triggered if the verification standard is not met. The anomaly level is located based on the rule matching results. The anomaly characteristics are investigated through multi-dimensional correlation analysis, including comparing the matching of the remaining data in the same transaction batch, tracing historical transaction records, and automatically generating anomaly reason tags by combining conflict rules in the business rule base.

6. The automatic verification method for premium electricity charges in green electricity trading as described in claim 5, characterized in that: The comparative analysis includes calculating the theoretical environmental premium electricity charge based on the environmental premium electricity charge payment data, comparing the calculated theoretical environmental premium electricity charge with the actual environmental premium electricity charge to be paid, and determining that the environmental premium electricity charge payment is not approved when the absolute value of the difference is greater than a preset difference threshold, immediately stopping the payment process, updating the payment status to payment freeze, generating an exception list, and triggering manual review of the payment amount; and determining that the environmental premium electricity charge payment is approved when the absolute value of the difference is less than or equal to the preset difference threshold, triggering the normal settlement process. The formula for calculating the theoretical environmental premium electricity tariff premium is expressed as follows: in, The theoretical environmental premium for electricity pricing. For electricity consumption, The benchmark electricity price, This represents the premium percentage.

7. The automatic verification method for premium electricity charges in green electricity trading as described in claim 6, characterized in that: The real-time feedback includes automatically generating a verification report based on the verification process and verification results, asynchronously pushing the verification results to the user terminal, and issuing warnings for abnormal verification results, triggering manual review prompts. When the environmental premium electricity charge information data does not meet the verification standards or the environmental premium electricity charge payment does not meet the payment approval standards, an early warning prompt for abnormal verification results is automatically triggered, an environmental premium electricity charge anomaly detection report is generated, and sent to the user terminal along with the anomaly list for early warning feedback.

8. An automatic verification system for green electricity trading environment premium charges, employing the automatic verification method for green electricity trading environment premium charges as described in any one of claims 1 to 7, characterized in that, It includes an information collection module, a rule base construction module, an information matching and analysis module, an information verification and detection module, a payment verification module, and a verification result feedback module; The information collection module is used to automatically collect information data related to environmental premium electricity charges through the API interface and preprocess the collected raw data. The rule base construction module is used to collect the verification requirements in the transaction settlement process, systematically divide the rules into four types: basic rules, dynamic rules, compliance rules and operation rules, and layer the rule base into basic layer, dynamic layer, compliance layer and operation layer. After the rules are written and entered, the rules are deployed and integrated into the rule engine of the transaction settlement system to perform real-time and automated verification of each transaction settlement data. The information matching and analysis module is used to perform deep feature extraction on the preprocessed data, extract key feature information from four dimensions: contract terms, electricity volume, green certificates, and finance, match the extracted features with the matching level verification standards in the rule base, and calculate the basic matching coefficient, dynamic matching coefficient, compliance matching coefficient, and operation matching coefficient to provide a quantitative matching basis for comprehensive evaluation. The information verification and detection module is used to aggregate the matching coefficients at each level to generate a unified rule matching vector. By assigning weights to each coefficient, it calculates a comprehensive verification evaluation index, compares the verification evaluation index with a preset verification threshold, dynamically determines whether the current transaction data meets the verification standards, and automatically locates the abnormal level for data that does not meet the standards. Combining multi-dimensional correlation analysis and business conflict rules, it identifies and marks abnormal data, triggers a manual approval process, and eliminates risks. The payment verification module is used to calculate the theoretical environmental premium electricity fee based on the electricity consumption, benchmark electricity price and premium ratio, and compare the theoretical value with the actual payment amount. When the difference between the two exceeds the preset difference threshold, the payment is determined to be unsuccessful, the payment status is immediately frozen, an abnormal list is generated and manual review is triggered. When the difference is within the allowable range, the payment is determined to be successful and the normal settlement process is triggered. The verification result feedback module is used to automatically generate verification reports and push the results asynchronously to the user terminal. For any abnormalities found during the verification, it will issue early warning information in a timely manner and trigger manual review prompts.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the automatic verification method for the green electricity trading environment premium electricity fee as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the automatic verification method for the green electricity trading environment premium electricity fee as described in any one of claims 1 to 7.

Images