Intelligent management and control and risk early warning system for whole process of green certificate issuing

Abstract

The invention relates to the technical field of intelligent management of energy information, in particular to an intelligent management and control and risk early-warning system for a whole process of issuing a green certificate, and the system comprises a green certificate information collection module, an information detection and management module, an information risk early-warning module and an intelligent auditing and decision-making module. Obtaining green certificate multi-source information through a green certificate information acquisition module, and processing the green certificate multi-source information based on a missing information checking and filling mechanism to obtain a green certificate issuing information base; constructing a green certificate issuing information detection system in the information detection and management module, obtaining an information reference index analysis result according to the system and an information base, and outputting a green certificate issuing target information set; a green certificate issuing risk assessment mechanism is set in the information risk early warning module, and scoring results of different risk factors are obtained in combination with the target information set; and the intelligent auditing and decision-making module simulates and monitors the green certificate issuing process based on the information set and the scoring result. According to the invention, risk control and early warning of the whole green certificate issuing process are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent management of energy information, and specifically to an intelligent control and risk warning system for the whole process of green certificate issuance. Background Art

[0002] The national green certificate issuance and trading system issues green certificates based on the information of power grid enterprises and the data of power trading institutions to ensure the effective operation of the issuance work for renewable energy power generation projects. However, when the existing green certificate issuance system collects data from multiple parties such as power generation enterprises, power grid companies, and government platforms, it is difficult to achieve the synchronization and consistency of data from different sources. At the same time, the information processing efficiency of the system is relatively low, mostly relying on manual filling, resulting in a high error rate and low work efficiency of the system. On the other hand, the existing system cannot quantitatively evaluate the potential risks in the green certificate issuance process, and cannot give timely warnings and interventions when risks occur. The issuance process is opaque and lacks intelligent simulation and safety monitoring functions, which is likely to lead to operation errors and affect the work efficiency and fairness of the issuance task.

[0003] In order to solve the problems and deficiencies of the existing technology, it is necessary to upgrade the information processing method, improve the risk assessment and warning mechanism, and increase intelligent monitoring technology, which is beneficial to realizing the intelligence, precision, and high efficiency of the whole process of green certificate issuance, so as to ensure the effective operation and sustainable development of renewable energy projects. Summary of the Invention

[0004] In view of the deficiencies of existing methods and the requirements of practical applications, in order to achieve the comprehensive collection and intelligent analysis of green certificate issuance information, as well as the real-time early warning and quantitative assessment of potential risks in the green certificate issuance process. On the one hand, the present invention provides a full-process intelligent control and risk early warning system for green certificate issuance. The above system includes: a green certificate information collection module, an information detection and management module, an information risk early warning module, and an intelligent review and decision-making module; obtaining multi-source information of green certificates through the green certificate information collection module, and processing the multi-source information of green certificates based on the missing information inspection and filling mechanism in the green certificate information collection module to obtain a green certificate issuance information database; constructing a green certificate issuance information detection system in the information detection and management module, obtaining an information reference index analysis result according to the green certificate issuance information detection system and the green certificate issuance information database, and the information detection and management module outputs a set of green certificate issuance target information according to the information reference index analysis result; setting a green certificate issuance risk assessment mechanism in the information risk early warning module, and the information risk early warning module obtains a scoring result of different risk factors according to the green certificate issuance risk assessment mechanism and the set of green certificate issuance target information; the intelligent review and decision-making module performs visual simulation and safety monitoring on the green certificate issuance process based on the set of green certificate issuance target information and the scoring result to achieve intelligent control and risk early warning of the full process of green certificate issuance. The present invention increases the modular design and the application of intelligent technologies, which helps to ensure the efficiency, safety and compliance of the full process of green certificate issuance.

[0005] Optionally, the processing of the multi-source information of green certificates based on the missing information inspection and filling mechanism in the green certificate information collection module to obtain a green certificate issuance information database includes: constructing a missing information inspection and filling mechanism in the green certificate information collection module according to the historical information of the green certificate issuance system; using the missing information detection model in the missing information inspection and filling mechanism to detect the multi-source information of green certificates to obtain a missing information detection result; the missing information inspection and filling mechanism analyzes the data missing probability of different data subsets in the multi-source information of green certificates according to the missing information detection result; obtaining data filling results of different data subsets based on the supplementary information prediction model in the missing information inspection and filling mechanism and the data missing probability; the green certificate information collection module fills and processes different data subsets in the multi-source information of green certificates in combination with the missing information detection result and the data filling result to obtain a green certificate issuance information database.

[0006] The present invention combines methods such as automated detection, probability analysis and dynamic filling, which is beneficial to ensuring the integrity, accuracy and availability of the green certificate issuance information database.

[0007] Optionally, the full-process intelligent control and risk early warning system for green certificate issuance further includes: The missing information detection model satisfies the following relationship: Among them, represents the missing information detection model, represents in the data is not missing, represents in the data is missing; The probability of data missing satisfies the following relationship: Among them, represents the data missing probability of different data subsets, represents the amount of missing data in different data subsets, represents the total amount of data in different data subsets; The supplementary information prediction model satisfies the following relationship: Among them, represents the data filling value of different data subsets, represents the generative adversarial network function, represents the data subset after removing the missing values , represents the parameter related to the data missing mechanism, represents the data missing probability of different data subsets.

[0008] The present invention realizes the effective analysis and dynamic monitoring of the green certificate issuance information database through mathematical modeling and intelligent algorithms.

[0009] Optionally, constructing a green certificate issuance information detection system in the information detection and management module includes: setting information reference indicators in the green certificate issuance information detection system, where the information reference indicators include data transmission reference indicators, data feature reference indicators, and business information reference indicators; constructing a green certificate issuance information detection system in the information detection and management module based on the data transmission reference indicators, the data feature reference indicators, and the business information reference indicators. The present invention combines data transmission, data features, and business information indicators, and the above multi-dimensional indicators help to achieve the effectiveness of data management and system operation mode.

[0010] Optionally, the information reference index analysis result obtained based on the green certificate issuance information detection system and the green certificate issuance information database includes: establishing a data transmission analysis model, a data feature analysis model, and a business information analysis model in the green certificate issuance information detection system; obtaining the transmission detection results of different data subsets according to the data transmission analysis model and the green certificate issuance information database; obtaining the feature information inspection results of different data subsets by using the data feature analysis model and the green certificate issuance information database; obtaining the business information inspection results of different data subsets based on the business information analysis model and the green certificate issuance information database; and combining the transmission detection results, the feature information inspection results, and the business information inspection results to obtain the information reference index analysis result. The present invention designs an analysis model for multi-dimensional reference indexes, which helps to quickly analyze and warn of the risks of system data and business.

[0011] Optionally, the data transmission analysis model satisfies the following relationship: Wherein, represents the transmission detection results of different data subsets, represents the total number of sub-blocks of different data subsets of, represents the check sensitivity index of the key data block, represents the data value of the i-th sub-block, represents the modulus, represents the modulo operation symbol; The data feature analysis model satisfies the following relationship: Wherein, represents the feature information of different data subsets, represents the prior value of different data subsets, represents the number of feature types of different data subsets, represents the -th type of feature mean vector in different data subsets, represents the mean vector of all types of features in different data subsets, represents the dispersion degree matrix of different data subsets; The business information analysis model includes an amount verification function, a date verification function, a time verification function, and an inventory verification function, and respectively satisfies the following relationships: The amount verification function satisfies the following relationship: Wherein, represents the amount verification result, represents the order amount, Represents the price of the goods in the order, Represents the quantity of the goods in the order, Indicates that the amount verification result is qualified, Indicates that the amount verification result is unqualified; The date verification function satisfies the following relationship: Among them, Represents the date verification result, Represents the end date of the order, Represents the start date of the order, Indicates that the date verification result is qualified, Indicates that the date verification result is unqualified; The time verification function satisfies the following relationship: Among them, Represents the time verification result, Indicates that the time verification is qualified, Indicates that the time verification is unqualified, Indicates that the time verification result is qualified, Indicates that the time verification result is unqualified; The inventory verification function satisfies the following relationship: Among them, Represents the inventory verification result, Represents the inbound quantity, Represents the outbound quantity, Represents the current inventory level, Indicates that the inventory verification result is qualified, Indicates that the inventory verification result is unqualified.

[0012] The present invention designs the verification function through logical rules, providing automated and intelligent detection and verification technical support for the entire process of green certificate issuance.

[0013] Optionally, the information detection and management module outputs a green certificate issuance target information set according to the analysis result of the information reference index, including: the information detection and management module detects and manages different data subsets in the green certificate issuance information database based on the conveying detection result, the feature information verification result, and the service information verification result, and outputs a green certificate issuance target information set. The present invention integrates the verification results in three dimensions of transmission, features, and services, which can further ensure the integrity, accuracy, and consistency of the green certificate issuance data.

[0014] Optionally, a risk assessment mechanism for green certificate issuance is set in the information risk warning module. The information risk warning module obtains the scoring results of different risk factors based on the risk assessment mechanism for green certificate issuance and the green certificate issuance target information set, including: setting risk assessment factors and risk assessment indicators in the risk assessment mechanism for green certificate issuance; establishing a risk assessment matrix, a risk assessment result optimization model, and a weight assignment model in the risk assessment mechanism for green certificate issuance based on the risk assessment factors and the risk assessment indicators; and obtaining the scoring results of different risk factors by combining the risk assessment matrix, the risk assessment result optimization model, the weight assignment model, and the green certificate issuance target information set. The present invention constructs an evaluation system through risk assessment factors and indicators, converts risk factors into quantifiable scoring results, and provides technical support for green certificate issuance management and risk level assessment.

[0015] Optionally, the risk assessment matrix satisfies the following relationship: Wherein, represents the risk assessment matrix in the risk assessment mechanism for green certificate issuance, represents the risk assessment factors in the risk assessment matrix, represents the risk assessment indicators in the risk assessment matrix, represents the th risk assessment factor relative to the th risk assessment indicator; The risk assessment result optimization model satisfies the following relationship: Wherein, represents the after normalization, represents the constant value corresponding to the risk assessment result optimization model, represents the th risk assessment factor relative to the th risk assessment indicator; represents the minimum risk score in the risk assessment matrix, represents the maximum risk score in the risk assessment matrix; The weight assignment model satisfies the following relationship: Wherein, represents the weight coefficient corresponding to the th risk assessment factor, represents the after normalization, represents the entropy value of the th risk assessment factor, represents the total risk score of all risk assessment factors.

[0016] The matrix calculation, normalization, and weight assignment of the present invention can improve the intelligent control of the entire process of green certificate issuance and are conducive to the effective implementation of the risk warning system.

[0017] Optionally, the intelligent review and decision-making module performs visual simulation and security monitoring on the green certificate issuance process based on the green certificate issuance target information set and the scoring results to achieve intelligent control and risk warning for the entire process of green certificate issuance, including: adding an encryption protection subsystem and a risk assessment security threshold in the intelligent review and decision-making module; the intelligent review and decision-making module uses the encryption protection subsystem to encrypt and protect the green certificate issuance target information set and the scoring results; the intelligent review and decision-making module performs visual simulation and real-time monitoring on the green certificate issuance process based on the risk assessment security threshold, the encrypted green certificate issuance target information set, and the scoring results.

[0018] The encryption protection method and risk threshold technology of the present invention work together to help achieve the safe and effective management of the entire process of green certificate issuance, further improving the compliance, security, and practicality of the intelligent control and risk warning system. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is the flowchart of the intelligent control and risk warning system for the entire process of green certificate issuance of the present invention; Figure 2 is the structural diagram of the intelligent control and risk warning system for the entire process of green certificate issuance of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0020] Specific embodiments of the present invention will be described in detail below. It should be noted that the embodiments described here are only for illustrative purposes and are not used to limit the present invention. In the following description, a large number of specific details are set forth in order to provide a thorough understanding of the present invention. However, it is obvious to those of ordinary skill in the art that the present invention does not have to be implemented with these specific details. In other instances, well-known circuits, software, or methods are not specifically described to avoid obscuring the present invention.

[0021] Throughout the specification, references to "an embodiment", "embodiments", "an example" or "examples" mean that a particular feature, structure, or characteristic described in connection with the embodiment or example is included in at least one embodiment of the present invention. Thus, the phrases "in an embodiment", "in embodiments", "an example" or "examples" appearing throughout the specification do not necessarily all refer to the same embodiment or example. Furthermore, the particular features, structures, or characteristics may be combined in any suitable combination and / or sub-combination in one or more embodiments or examples. In addition, those of ordinary skill in the art should understand that the diagrams provided herein are for illustrative purposes only and are not necessarily drawn to scale.

[0022] Please refer to Figure 1 , in order to achieve the effective management and scientific operation of different stages of green certificate data collection, analysis, early warning and decision-making, and further ensure the comprehensive analysis and risk control of green certificate issuance information. The present invention provides a full-process intelligent control and risk early warning system for green certificate issuance. The above system includes the following steps: In the full-process intelligent control and risk early warning system for green certificate issuance, there are provided: a green certificate information collection module, an information detection and management module, an information risk early warning module, and an intelligent review and decision-making module.

[0023] S1. Obtain multi-source information of green certificates through the green certificate information collection module, and process the multi-source information of green certificates based on the missing information inspection and filling mechanism in the green certificate information collection module to obtain a green certificate issuance information database. The specific implementation steps and related content are as follows: The multi-source information of green certificates is obtained through the green certificate information collection module.

[0024] In this embodiment, the green certificate information collection module adopts a distributed data collection architecture method, which has high integration and flexibility. The green certificate information collection module constructs an all-round and multi-level data collection network by integrating API interfaces, Internet of Things sensors, and blockchain deposit nodes, and can collect and obtain green certificate data from different sources such as green certificate issuers, trading platforms, and certification agencies in real time, and reasonably verify cross-chain information based on the immutable characteristics of the blockchain, which can ensure the security and credibility of the multi-source information of green certificates in the system.

[0025] In terms of data processing, the green certificate information collection module adopts a streaming computing framework to preprocess the massive multi-source green certificate data collected in real time, effectively improving the processing efficiency and accuracy of system data. At the same time, combined with natural language processing technology, it deeply analyzes the policy texts in the information and extracts key information, providing data support for subsequent risk warning and security monitoring. In addition, the module also uses knowledge graph technology to associate and integrate the whole life cycle information of green certificates (including issuance, trading, use, etc.) to construct a clearly structured and traceable information network.

[0026] Furthermore, the green certificate information collection module also has the data access ability. It not only supports accessing real-time data of renewable energy power generation projects (such as power generation, equipment status, environmental parameters, etc.) to realize real-time monitoring and warning of the operation status of different projects, but also supports accessing historical archive data (such as project filing information, grid connection records, etc.), providing data support for the whole life cycle management of green certificate projects. At the same time, the module supports multi-source data access and can seamlessly connect with multiple data sources such as power grid companies, power generation enterprises, and third-party monitoring agencies to realize the sharing and collaboration of system green certificate issuance data.

[0027] In order to effectively obtain and utilize green certificate data from multiple parties such as power enterprises, power grid companies, and trading platforms to form a unified green certificate issuance data pool, in this embodiment, a missing information inspection and filling mechanism is constructed in the green certificate information collection module based on the historical information of the green certificate issuance system.

[0028] During the data collection and processing process, aiming at the missing problems in the data set, considering the multi-source green certificate information and historical data obtained comprehensively, and based on data characteristics and business scenarios, the green certificate data is filled to make the filled data fit the real situation. In the embodiment, a filling strategy based on the data mean principle is adopted, that is, the average value of valid numerical values in a specific data set is used to fill the missing data, which helps to ensure the reliability and effectiveness of the data processing results.

[0029] To ensure the scientificity and accuracy of the data processing results, in the embodiment, m different data collection sources are set based on the data sources of multi-source green certificate information. The data collected from each source has unique characteristics and attributes. Furthermore, the system classifies the multi-source green certificate information according to the data collection sources to form m groups of green certificate data subsets that are independent of each other and related to each other. The original system data set is obtained by integrating the m groups of data , which is presented in the form of an ordered tuple and satisfies the following relational expression: Among them, represents the system green certificate data set, (1, 2, …, m) represent the data groups (subset of green certificate data) corresponding to different data acquisition sources respectively.

[0030] First, use the missing information detection model in the missing information detection and filling mechanism to detect the multi-source green certificate information, and obtain the missing information detection result.

[0031] In the embodiment, the subset of green certificate data has a data variable matrix with a dimension of To effectively identify the missing information in the matrix, a data missing detection model adapted to it is constructed, and this model is used to detect the multi-source green certificate information. In this process, the missing information detection model follows specific logical relationships and operation rules, and specifically satisfies the following relationships: Among them, represents the missing information detection model, represents in the data is not missing, represents in the data is missing.

[0032] The data subset in the multi-source green certificate information is a data variable matrix of dimension, and the matrix contains data information and characteristic attributes from different sources. Among them, represents the number of rows of the matrix, represents the number of columns of the matrix. Each element in the matrix represents the data information and characteristic value at a specific position on.

[0033] The missing information detection model is used to judge whether the data at position in the matrix is missing. By specific logical relationships and operation rules, each element in the matrix is checked, and a binary value is returned, thereby detecting whether the data information at different positions is missing.

[0034] In the model output, 1 indicates that the data is not missing, and 0 indicates that the data is missing. The model encodes the data missing status in binary. When the model judges that the data at a certain position exists and is valid, it outputs 1; when the model judges that the data at that position is missing or invalid, it outputs 0.

[0035] Based on the detection results of the missing information detection model, the data missing situations and characteristic attributes of different data subsets can be identified. In an optional embodiment. A subset may show a phenomenon of large-scale data missing within a specific time period due to technical failures in the data acquisition link; while another subset may have characteristics such as random and scattered data missing due to the diversity of data sources.

[0036] Then, based on the missing information detection results, the missing information inspection and filling mechanism analyzes the data missing probabilities of different data subsets in the multi-source information of green certificates.

[0037] The missing information inspection and filling mechanism can effectively guarantee data integrity and accuracy. After analyzing the data missing situation in each data subset, it calculates the data missing probabilities of different data subsets based on the above analysis results. The data missing probability not only reflects the current data missing situation but also provides data support and decision-making basis for subsequent data filling strategies.

[0038] The above data missing probability needs to satisfy the following relationship: where, represents the data missing probability of different data subsets, represents the amount of missing data in different data subsets, represents the total amount of data in different data subsets; The data missing probability of different data subsets reflects the degree of missing of relevant information in different data subsets.

[0039] For the amount of missing data in different data subsets, it is necessary to traverse each data subset and count the number of all missing data. The larger the amount of missing data, the more missing data there is in the data subset.

[0040] The total amount of data in different data subsets is the statistics of the number of all data (including valid data and missing data) in the data subset, which further reflects the scale size and information acquisition situation of different data subsets.

[0041] Calculating the data missing probabilities of different data subsets in the multi-source information of green certificates can intuitively compare the data missing situations of each subset and provide a reference basis for subsequent data filling and information quality assessment.

[0042] Immediately afterwards, based on the supplementary information prediction model and data missing probability in the missing information inspection and filling mechanism, the data filling results of different data subsets are obtained.

[0043] After calculating the data missing probability, it is necessary to use the supplementary information prediction model to generate the corresponding information filling results for different data subsets. In the embodiment, the data missing probabilities of different data subsets are fully combined, and at the same time, the internal relationships of different data sets are deeply explored, including but not limited to data characteristics, distributions, correlations, etc., as well as various parameters closely related to the missing mechanism. The above parameters cover the noise level in the data acquisition process, the reliability factors of data storage, the packet loss rate of data transmission, etc.

[0044] Furthermore, a generative adversarial network is introduced. The generative adversarial network mainly consists of a generator and a discriminator. The generator is responsible for generating missing data supplementary samples similar to the real data, while the discriminator distinguishes between the generated samples and the real samples. Through the above adversarial training method, the generator continuously optimizes its own generation ability, making the generated samples closer and closer to the real data. During the model training process, the data missing probabilities, dataset information, and related parameters of different data subsets are used as inputs. After iterative training of the generative adversarial network, a supplementary information prediction model is finally obtained, thereby obtaining the data filling results of different data subsets.

[0045] The supplementary information prediction model in the embodiment satisfies the following relationship: Wherein, represents the data filling value of different data subsets, represents the generative adversarial network function, represents the data subset after removing the missing values , represents the parameters related to the data missing mechanism, represents the data missing probabilities of different data subsets.

[0046] The data filling value of different data subsets refers to the data filling value of different data subsets calculated by the supplementary information prediction model during the data processing. Based on this, the integrity of the data can be restored as much as possible, enabling the filled data subset to play a better role in subsequent analysis and applications.

[0047] The generative adversarial network function can generate new data samples according to the input data. The data subset after removing the missing values in the supplementary information prediction model is used as the input, and the generative adversarial network and the distribution characteristics of the data are utilized to generate filling values similar to the real data.

[0048] The data subset after removing the missing values refers to that when calculating the data filling value, in order to avoid the interference of the missing values on the model training and prediction, it is necessary to remove the missing values in the original data subset to obtain the data subset after removing the missing values.

[0049] The parameters related to the data missing mechanism are a comprehensive parameter that covers various factors related to the data missing mechanism. The above factors will affect the probability and pattern of data missing, thereby affecting the data filling value. During the data filling process, the parameter acts as a regulating factor and interacts with the generative adversarial network function and the data subset after removing the missing values, affecting the final data filling value.

[0050] Finally, the green certificate information collection module performs filling processing on different data subsets in the multi-source information of green certificates by combining the missing information detection results and data filling results, and obtains the green certificate issuance information database.

[0051] Based on the data filling values calculated from different data subsets, targeted supplementation and filling operations are performed on each data subset from different data sources. After completing a series of filling tasks, the original system data set after data supplementation is obtained. Each data subset in the above data set is optimized and improved, and then the green certificate issuance information database of the embodiment is obtained, and it satisfies the following mathematical relationship: Among them, represents the data set after filling processing, represents each data subset after filling processing.

[0052] Through the green certificate information collection module and the missing detection and filling mechanism, the data information can be dynamically and flexibly adjusted according to the actual situation. It can not only effectively improve the accuracy of the missing information detection model, but also timely discover the missing problems in different data sources, enhance the robustness of the green certificate information collection module, and enable it to maintain stable and reliable performance in the face of various complex data situations. Finally, after a series of optimizations and improvements, a higher-quality data set is obtained, that is, the green certificate issuance information database, which provides a data basis for subsequent data analysis and applications.

[0053] Furthermore, the method for obtaining the green certificate issuance information database in this embodiment is only an optional condition of the present invention. In one or some other embodiments, the method for obtaining the green certificate issuance information database can be adjusted according to the operation situation of the green certificate information collection module and the multi-source information collection requirements of green certificates, so as to ensure that the system can efficiently and accurately collect the required data. In the face of complex and changeable green certificate scenarios, it can quickly adapt to the environmental situation and improve the overall performance and practicability of the system.

[0054] S2. Construct a green certificate issuance information detection system in the information detection and management module, and obtain the information reference index analysis result according to the green certificate issuance information detection system and the green certificate issuance information database. The above information detection and management module outputs the green certificate issuance target information set according to the information reference index analysis result. The specific implementation content is as follows: First, a green certificate issuance information detection system is constructed in the information detection and management module.

[0055] Set the information reference indicators in the green certificate issuance information detection system. In the embodiment, the information reference indicators mainly include data transmission reference indicators, data feature reference indicators, and business information reference indicators; and based on the data transmission reference indicators, data feature reference indicators, and business information reference indicators, a green certificate issuance information detection system is constructed in the information detection and management module.

[0056] In all aspects such as storage, transmission, and processing of multi-source green certificate data, problems such as data loss, errors, or inconsistencies may occur. Through effective information detection and management, relevant problems can be discovered and corrected in a timely manner, thereby ensuring the accuracy and integrity of multi-source green certificate data. In order to construct a green certificate issuance information detection system in the information detection and management module, it is necessary to preset the information reference indicators of this system. The information reference indicators set in the embodiment mainly include data transmission reference indicators, data feature reference indicators, and business information reference indicators.

[0057] Based on the above data transmission reference indicators, data feature reference indicators, and business information reference indicators, a complete green certificate issuance information detection system is established. This system will comprehensively detect and manage various types of information in the process of green certificate issuance around the above core indicators.

[0058] Take the above reference indicators as an important reference basis for the green certificate issuance information detection system to evaluate the quality status of multi-source green certificate data in aspects such as transmission, feature performance, and business association. Through real-time monitoring and analysis of the indicators, data anomalies can be discovered in a timely manner, and corresponding measures can be taken for processing, thereby ensuring the quality and reliability of multi-source green certificate data and providing data support for green certificate issuance and scientific control.

[0059] Then, obtain the analysis results of the information reference indicators according to the green certificate issuance information detection system and the green certificate issuance information database.

[0060] In order to analyze the information characteristics, distribution laws, and correlation relationships in the green certificate issuance data, and further analyze the information conditions and change trends of different green certificate data, in the embodiment, based on the information reference indicator information in the green certificate issuance information detection system and the information database, a data transmission analysis model, a data feature analysis model, and a business information analysis model are established in the green certificate issuance information detection system.

[0061] In an optional embodiment, based on the data transmission analysis model and the green certificate issuance information database, the transmission information of different data subsets is detected, and the transmission detection results of different data subsets are obtained.

[0062] Based on the green certificate issuance information database, different data subsets are processed by data block division, and the data subsets to be verified are divided into n sub-blocks, and the data value of each sub-block is denoted as , 。

[0063] The sub - block division rule needs to be divided by a fixed length (such as byte - level, record - level), or reasonably divided by logical units (such as data table fields, message protocol segments). At the same time, based on the detection requirements of the conveyed information, a fixed value is taken for the modulus to limit the range of the information verification result, and then the data subset to be verified is pre - processed to ensure that its value range is within the range, which can ensure the stability and consistency of the verification result.

[0064] The above - mentioned data conveyance analysis model satisfies the following relationship: Among them, represents the conveyance detection result of different data subsets, represents different data subsets of the total number of sub - blocks, represents the verification sensitivity index of the key data block, represents the data value of the i - th sub - block, represents the modulus, represents the modulo operation symbol; The conveyance detection result of the data subset refers to the integrity verification result of different data subsets during the transmission process. The reference values of the data sending end and the receiving system are compared to determine whether the transmission information of green certificate data from different sources is complete and correct.

[0065] The data subset to be verified contains multiple groups and logical units. The n divided sub - blocks are verified one by one, and each sub - block independently participates in the verification calculation, which can avoid the overall verification failure caused by a single sub - block error and can improve the error - location ability of the analysis model.

[0066] The verification sensitivity index of the key data block can reflect the importance of different sub - blocks in data transmission. The higher the above - mentioned index, the stronger the verification sensitivity and the higher the weight of the key fields. By assigning higher weights to important fields (such as green certificate numbers, electricity quantity data) through the verification sensitivity index of the key data block, the accuracy of key green certificate information is further guaranteed.

[0067] The data values of different sub - blocks refer to the actual data of different sub - blocks in the data subset.

[0068] Through block processing, weight design and modulus constraint, the data conveyance analysis model realizes the verification and efficient verification of green certificate data transmission, significantly improves data integrity, security and credibility, and enables the full - process intelligent control and risk warning system of green certificate issuance to have better performance.

[0069] In an optional embodiment, the feature information test results of different data subsets are obtained by using a data feature analysis model and a green certificate issuance information database.

[0070] First, feature extraction and comparison are performed on green certificate information from different sources based on the green certificate issuance information database. By using the data feature analysis model and combining the metadata (such as data structure and field definition) in the green certificate issuance information database, the feature information of different data subsets is extracted. Furthermore, the data feature attributes from different sources or time points can be compared one by one to identify the difference points in information features.

[0071] A data feature analysis model is constructed based on the data source, timestamp, and associated attributes of the data subset, satisfying the following relationship: Where, represents the feature information of different data subsets, represents the prior value of different data subsets, represents the number of feature types of different data subsets, represents the th class feature mean vector in different data subsets, represents the mean vector of all types of features in different data subsets, represents the dispersion degree matrix of different data subsets; The feature information of different data subsets comprehensively reflects the degree of feature differences in the data subsets and is the reference basis for data feature information classification and comparison.

[0072] The prior value of a data subset refers to the weight or occurrence probability of the subset in the overall data, which is used to adjust the contribution degree of feature differences. If the data volume of a certain subset is small, its prior value will be low, thereby reducing the impact on the overall feature differences.

[0073] The number of feature types refers to the number of feature dimensions involved in the calculation in the data subset. If it means that there are 5 types of features in the data subset participating in the subsequent information analysis and verification calculation.

[0074] The mean vector of different types of features in the data subset reflects the central tendency of the subset in different types of features.

[0075] The mean vector of all feature types in the data subset is the reference value for information comparison and can be used to measure the deviation degree of the mean value of each type of feature from the overall mean value.

[0076] The dispersion matrix of the data subset can quantify the dispersion of the data within the subset, such as variance and standard deviation, which is used to adjust the weights of feature differences. Based on the above dispersion adjustment, the feature differences are weighted so that the feature differences of the subsets with lower dispersion contribute more.

[0077] Based on each feature in the data subset, calculate the difference between its mean vector and the overall mean vector, which reflects the degree of deviation of the feature in the subset.

[0078] The data feature analysis model combines feature differences, dispersion, and prior values, providing quantitative indicators for the feature analysis of data subsets, and is applicable to data quality assessment and anomaly detection in scenarios such as green certificate issuance and energy monitoring.

[0079] Subsequently, a feature information verification mechanism is set based on the feature information of different data subsets, the green certificate feature reference information, and the fitness function, and satisfies the following relationship; def compare_records(record1, record2): differences = {} for key in record1.keys(): if record1[key] != record2[key]: differences[key] = (record1[key], record2[key]) return difference In the embodiment, based on the data feature analysis model and the feature information verification mechanism, a comparative analysis is performed on the feature reference indicators of green certificate data from different sources in the system, and the feature information verification results of different data subsets are obtained.

[0080] In an optional embodiment, the business information verification results of different data subsets are obtained based on the business information analysis model and the green certificate issuance information database. The above business information analysis model mainly includes an amount verification function, a date verification function, a time verification function, and an inventory verification function, and each function follows specific logical relationships and preset business rule correspondences.

[0081] The business information analysis model conducts verification and analysis on the amount, date, time, and inventory information in business data respectively, and each function strictly follows the logical relationship matching the business rules. Among them, the amount verification function can verify the amount value in the data according to the upper and lower limits of the amount and currency type and other rules set by the business scenario; the date verification function checks the format and logical correctness of the date data according to the standard date format and the requirements of the business time sequence; the inventory verification function verifies the inventory data to ensure the reasonableness of the inventory quantity and inventory status, so as to ensure the accuracy and reliability of the output results of the business information analysis model.

[0082] The amount verification function satisfies the following relationship: Among them, represents the amount verification result, represents the order amount, represents the price of the order goods, represents the quantity of the order goods, represents that the amount verification result is qualified, represents that the amount verification result is unqualified; The amount verification result is a binary variable, which is used to represent the verification result of the order amount. When its value is 1, it means that the amount verification result is qualified, that is, the order amount is consistent with the amount calculated according to the commodity price and quantity; when its value is 0, it means that the amount verification result is unqualified, that is, the order amount is inconsistent with the calculated amount.

[0083] The date verification function satisfies the following relationship: Among them, represents the date verification result, represents the order end date, represents the order start date, represents that the date verification result is qualified, represents that the date verification result is unqualified; The date verification result is a binary variable, which is used to represent the verification result of the order date. When its value is 1, it means that the date verification result is qualified, that is, the order end date is not earlier than the order start date; when its value is 0, it means that the date verification result is unqualified, that is, the order end date is earlier than the order start date.

[0084] In the actual business scenario, the order end date represents the deadline date when the activities, services, or commodity deliveries involved in the order end.

[0085] The order start date involves the specific date when the activities, services, or commodity deliveries start.

[0086] The time verification function satisfies the following relationship: Among them, represents the time verification result, represents that the time verification is qualified, represents that the time verification is unqualified, represents that the time verification result is qualified, represents that the time verification result is unqualified; The time verification result is a binary variable, which is used to represent the final result of the time verification. It is presented in numerical form, where 1 represents that the time verification result is qualified and 0 represents that the time verification result is unqualified. In the business system, this result will be used as an important basis for judging whether the time data conforms to the business rules.

[0087] Use regular expressions to match the format and the built-in time parsing function of the programming language to analyze the value and False value in the time verification function, and satisfy the following relationship: from datetime import datetime def validate_format(date_str, fmt="%Y-%m-%d"): try: datetime.strptime(date_str, fmt) return True except ValueError: return False In the logical judgment of time verification, when the input time data meets the pre-set time rules, the function will return the True value, which means that the time data meets the business requirements in terms of format, range, logical order, etc.

[0088] When the input time data does not meet the pre-set time rules, the function will return the False value, indicating that there are problems with the time data, which may be format errors, out-of-range business time, time logic conflicts, etc.

[0089] The inventory verification function satisfies the following relationship: Among them, represents the inventory verification result, represents the inbound quantity, represents the outbound quantity, represents the current inventory, represents that the inventory verification result is qualified, Indicates that the inventory verification result is unqualified.

[0090] The inventory verification result is a binary variable used to represent the final result of the inventory verification. When its value is 1, it indicates that the inventory verification result is qualified, that is, the relationship between the incoming quantity, outgoing quantity, and current inventory quantity conforms to the business logic; when its value is 0, it indicates that the inventory verification result is unqualified, that is, there is an error in the relationship between the green certificate data.

[0091] Furthermore, the information reference index analysis result is obtained by combining the conveying detection result, characteristic information inspection result, and business information inspection result.

[0092] In the embodiment, the information detection and management module detects and manages different data subsets in the green certificate issuance information database based on the conveying detection result, characteristic information inspection result, and business information inspection result, and then can output the green certificate issuance target information set.

[0093] Based on the conveying detection result, characteristic information inspection result, and business information inspection result, the information detection and management module uses specific algorithms and rules to perform data quality detection and information management on different data subsets in the green certificate issuance information database, analyzes and processes the data subsets, and finally outputs the green certificate issuance target information set that meets the business requirements.

[0094] The green certificate information from different sources in the green certificate issuance information database passes through the analysis of each detection index of the green certificate issuance information detection system in turn. If all indicators meet the preset standards, the green certificate information will smoothly enter the green certificate issuance process; if it is found that there are non-compliant situations during the detection process, the system will automatically trigger the manual review mechanism or data correction process to ensure the accuracy and integrity of the relevant green certificate information. After a series of processing procedures, a high-quality green certificate issuance target information set can be obtained.

[0095] Furthermore, the establishment of the green certificate issuance information detection system in this embodiment is only an optional condition of the present invention. In one or some other embodiments, the establishment of the green certificate issuance information detection system can be optimized and adjusted according to the actual situation of the green certificate issuance information and the information detection and management requirements, so as to more accurately detect the problems of green certificate information from different sources, improve the accuracy of the detection results, and further ensure the fairness of the green certificate issuance.

[0096] S3. A green certificate issuance risk assessment mechanism is set in the information risk warning module. The above information risk warning module obtains the scoring results of different risk factors based on the green certificate issuance risk assessment mechanism and the green certificate issuance target information set. The specific implementation content is as follows: First, based on the green certificate issuance conditions and historical information, specific risk assessment factors and risk assessment indicators are set within the framework of the green certificate issuance risk assessment mechanism.

[0097] Risk assessment factors refer to the objective risk factors for green certificate issuance, and the specific content is as follows: Data quality risk: The green certificate issuance process has high requirements for the accuracy and integrity of data such as power production and consumption. Data errors or tampering will directly undermine the fairness and effectiveness of green certificate issuance, leading to doubts in the market about the issuance results.

[0098] Policy compliance risk: Green certificate issuance must strictly comply with the constraints of national and local policies and regulations. The frequency of policy adjustments and deviations in the implementation process will result in compliance loopholes in the issuance process, affecting the legality and authority of the issuance work.

[0099] Market operation risk: The imbalance between supply and demand in the green certificate market, drastic price fluctuations, and trading violations will have a negative impact on the issuance efficiency, reduce the market's confidence in green certificate issuance, and hinder the healthy development of the market.

[0100] Risk assessment indicators refer to the objective risk indicators for green certificate issuance, and the specific content is as follows: Data completeness indicator: Evaluate the coverage of the data required for issuance in the links of power production, transmission, and consumption to ensure the comprehensiveness and systematicness of data for different projects.

[0101] Data coordination indicator: Examine the consistency and matching degree between data from different sources (such as grid enterprises and power generation enterprises), identify data conflicts and contradictions, and ensure the accuracy and reliability of green certificate data from different sources.

[0102] Data timeliness indicator: Measure the matching degree between the update frequency of green certificate data for different projects and the real-time requirements of green certificate issuance, and avoid decision-making mistakes in issuance due to data lag.

[0103] Data security risk indicator: Evaluate the possibility of illegal modification or forgery of different green certificate data, and use technical means and systems to ensure the security of system data.

[0104] Policy stability indicator: Statistically analyze the adjustment frequency of green certificate-related policies, analyze the impact of policy changes on the stability of issuance, and provide reference for subsequent policy formulation.

[0105] Policy implementation uniformity indicator: Compare the implementation of policies in different regions or institutions, identify implementation differences and problems, and promote the unified implementation of the green certificate issuance system and policies.

[0106] Compliance review effectiveness indicator: Statistics on the proportion of issuance applications rejected due to non-compliance with policies, reflecting the compliance level of the issuance process, and promptly discovering and correcting violations.

[0107] Market supply and demand matching degree indicator: Analyze the matching degree between the number of different issued green certificates and market demand, and avoid the impact of supply-demand imbalance on the stable operation of the market.

[0108] Price fluctuation monitoring indicator: Monitor the fluctuation of green certificate trading prices, evaluate the impact of price fluctuations on the market, and provide data support for market supervision.

[0109] Market trading compliance indicator: Statistics on the occurrence frequency of violations such as false trading and market manipulation of green certificate data from different sources, which is conducive to the supervision of market trading and maintaining a fair competition environment in the market.

[0110] Then, based on the above risk assessment factors and risk assessment indicator information, a risk assessment matrix, a risk assessment result optimization model, and a weight allocation model are established in the green certificate issuance risk assessment mechanism.

[0111] According to the above content, the risk assessment factors and risk assessment indicators are further set. In the embodiment, there are x objective risk factors and y objective risk indicators. Based on this, a scientific scoring method is used to quantitatively score each objective risk factor on each objective risk indicator, so as to construct an evaluation matrix with a clear structure and numerical characteristics.

[0112] The above risk assessment matrix satisfies the following relationship: Among them, represents the risk assessment matrix in the green certificate issuance risk assessment mechanism, represents risk assessment factors in the risk assessment matrix, represents risk assessment indicators in the risk assessment matrix, represents the th risk assessment factor relative to the th risk assessment indicator's risk score value; Among them, the risk score value satisfies a certain relationship .

[0113] Based on the objective risk factors of green certificate issuance, it can be known that the risk assessment factors in the risk assessment matrix mainly include data quality risk, policy compliance risk, and market operation risk.

[0114] The The risk assessment indicators mainly include data completeness indicators, data collaboration indicators, data timeliness indicators, data security risk indicators, policy stability indicators, policy implementation unity indicators, compliance review efficiency indicators, market supply and demand matching indicators, price fluctuation monitoring indicators, and market transaction compliance indicators.

[0115] The above evaluation matrix needs to strictly follow specific mathematical logical relationships to achieve the quantitative characterization and comprehensive evaluation of objective risk factors in the objective risk index system.

[0116] In the risk assessment process of green certificate issuance, since the risk score values covered by the green certificate data risk assessment matrix have heterogeneous characteristics, that is, there are different dimensions and value ranges, in order to ensure the objectivity and comparability of the assessment results, it is necessary to perform normalization processing on it. In the embodiment, a risk assessment result optimization model is established by combining the normalization processing method and mathematical mapping rules.

[0117] The above risk assessment result optimization model satisfies the following relationship: Among them, represents after normalization processing, represents the constant value corresponding to the risk assessment result optimization model, represents the th risk assessment factor relative to the th risk assessment indicator's risk score value, represents the minimum risk score in the risk assessment matrix, represents the maximum risk score in the risk assessment matrix; Based on the risk assessment result optimization model, the original risk score value is transformed into a dimensionless relative value, which is uniformly mapped to the interval, so as to eliminate the scale difference between the original score results and provide standardized data support for subsequent green certificate issuance risk analysis and decision-making.

[0118] Analyze and match the weight coefficients of different objective risk factors according to the optimized risk score results. After completing the optimization process of the risk score results, in the embodiment, the comprehensive weighting method is used to systematically analyze the weight coefficients of different objective risk factors.

[0119] In the embodiment, a corresponding weight distribution model is established and satisfies the following relationship: Among them, represents the th risk assessment factor's corresponding weight coefficient, represents , represents the entropy value of the th risk assessment factor, and represents the total risk score of all risk assessment factors.

[0120] The above weight assignment model satisfies the relevant constraint conditions, which can ensure that each weight coefficient can accurately represent the relative influence relationship of the corresponding objective risk factor in the risk assessment.

[0121] The weight coefficients corresponding to different risk assessment factors reflect the importance of the risk assessment factor in the entire risk assessment system. The larger the weight coefficient, the greater the impact of the factor on the overall risk assessment result; the smaller the weight coefficient, the relatively smaller the impact. Through the weight coefficient, the contribution degree of each risk assessment factor to the risk can be quantified, so as to more accurately evaluate the overall risk level.

[0122] In the process of risk assessment, different risk assessment factors have different dimensions and value ranges. Directly using the original data for calculation will lead to inaccurate results. Normalization processing can convert data with different dimensions and value ranges into a unified standard scale, making each risk assessment factor comparable.

[0123] The entropy values of different risk assessment factors can measure the uncertainty or chaos degree of relevant information. In risk assessment, the entropy value reflects the dispersion degree and information volume of the risk assessment factor. The larger the entropy value, the more dispersed the values of the risk assessment factor, the more uncertain the information provided, and the relatively smaller its impact on the risk assessment result; the smaller the entropy value, the more concentrated the values of the risk assessment factor, the more certain the information provided, and the relatively larger its impact on the risk assessment result. In the embodiment, the information volume of the risk assessment factor can be quantified by calculating the entropy value, so as to give appropriate weights to different factors in the weight assignment.

[0124] Summing the risk score values after normalizing all risk assessment factors can ensure that the sum of all weight coefficients is 1, making the weight assignment result have normalization and comparability, and making the weight coefficients of each risk assessment factor can intuitively reflect its relative importance in the overall risk assessment.

[0125] Immediately afterwards, combined with the risk assessment matrix, the risk assessment result optimization model, the weight assignment model and the green certificate issuance target information set, the scoring results of different risk factors are obtained.

[0126] The intelligent control and risk warning system for the whole process of green certificate issuance also includes intelligent integration technical methods, which integrate the risk assessment matrix, the risk assessment result optimization model, the weight distribution model and the green certificate issuance target information set. By constructing a comprehensive analysis framework, cross-validation and joint operation are carried out on each model and information set, so as to quantify the scores of different risk factors. Furthermore, for green certificate data from different sources, multi-dimensional risk analysis technology is adopted to carefully evaluate the data quality risk, policy compliance risk and market operation risk, and calculate the risk score results of various risks respectively, providing a scientific basis and information foundation for the intelligent control and risk warning of green certificate data.

[0127] Furthermore, the scoring method of the green certificate issuance risk factors in this embodiment is only an optional condition of the present invention. In one or some other embodiments, the scoring method of the green certificate issuance risk factors can be adjusted according to the operation requirements of the green certificate issuance risk assessment mechanism and the actual situation of green certificate issuance. During the green certificate issuance risk assessment process, various complex and changeable application scenarios will be faced. Adjusting the scoring method can ensure the accuracy and effectiveness of the risk factor scoring results.

[0128] S4. The intelligent review and decision-making module conducts visual simulation and safety monitoring on the green certificate issuance process based on the green certificate issuance target information set and the scoring results, so as to realize the intelligent control and risk warning of the whole process of green certificate issuance. The specific implementation content is as follows: Based on the green certificate issuance target information set and the scoring results, the intelligent review and decision-making module combines visualization technology and safety monitoring means to conduct all-round and multi-level simulation and monitoring on the green certificate issuance process, which is conducive to realizing the intelligent control and risk warning of the whole process of green certificate issuance.

[0129] In the intelligent review and decision-making module, an encryption protection subsystem and risk assessment safety threshold information are introduced.

[0130] The intelligent review and decision-making module uses the encryption protection subsystem to encrypt the green certificate issuance target information set and the scoring results by using encryption algorithms, generating an encrypted information set and scoring data, further ensuring the security of the system database during transmission and storage, reducing security risks such as data leakage and tampering, and helping to protect the interests of relevant parties in green certificate issuance.

[0131] Big data analysis and risk assessment models are used to set reasonable threshold ranges for each risk indicator. When a risk indicator exceeds the threshold, the system can automatically trigger and send a warning signal to notify relevant personnel in a timely manner, enabling potential problems affecting green certificate issuance to be discovered in advance and gaining time for taking countermeasures, which is conducive to reducing risk losses.

[0132] Based on the risk assessment security threshold, the intelligent review and decision-making module combines the encrypted green certificate issuance target information set and the scoring results to visually monitor the green certificate issuance process, realizing visual simulation and real-time dynamic monitoring. Through visualization technology, the progress of the issuance process can be intuitively understood, abnormal situations can be detected in a timely manner, and decisions can be made, improving management efficiency and the scientific nature of decision-making.

[0133] Set the system risk threshold. By mainly using big data analysis and risk assessment models, a reasonable threshold range is set for each risk indicator. When the risk indicator exceeds the threshold, the intelligent review and decision-making module can automatically trigger and send a warning signal, and notify relevant personnel in a timely manner.

[0134] Based on the multi-dimensional risk assessment security threshold system, use visualization technology to simulate and present the green certificate issuance process in real time, analyze and display the issuance process from multiple dimensions, and be able to comprehensively understand the operation status of the process, providing a basis for optimizing the process.

[0135] Based on the multi-dimensional risk assessment security threshold system, the intelligent review and decision-making module combines the encrypted green certificate issuance target information set and the scoring results, and uses visualization technology to simulate and present the green certificate issuance process in real time.

[0136] The intelligent review and decision-making module strengthens the data traceability and auditing functions. Establish a perfect data traceability mechanism in the system, and use technical means such as blockchain to ensure the immutability and traceability of green certificate issuance data. At the same time, regularly carry out third-party auditing work to comprehensively review the green certificate issuance process to ensure the accuracy and compliance of the data.

[0137] The intelligent review and decision-making module optimizes the warning strategy function. According to market changes and policy updates, combined with machine learning and artificial intelligence technologies, the risk assessment indicators and warning analysis rules are adjusted and optimized in real time to improve the accuracy and timeliness of the system risk warning.

[0138] The intelligent review and decision-making module can realize the intelligence, automation and transparency of the green certificate issuance work, improve the issuance efficiency, reduce the risk of human intervention, and provide strong technical support for the sustainable development of the renewable energy industry.

[0139] Based on the green certificate issuance target information set and the scoring results, the intelligent review and decision-making module combines visualization technology and security monitoring means to simulate and monitor the green certificate issuance process in an all-round and multi-level manner. It can deeply understand each link of the issuance process from multiple angles and levels, discover potential problems in a timely manner, and contribute to the intelligent control of the entire green certificate issuance process. At the same time, the module can realize the intelligence and automation of the green certificate issuance work, reduce manual intervention, avoid errors and delays caused by human factors, ensure the fairness, impartiality and openness of the green certificate issuance work, improve the issuance efficiency, and shorten the issuance cycle.

[0140] Please refer to Figure 2 , in an optional embodiment, the present invention also provides a system for intelligent control and risk warning of the entire process of green certificate issuance. The above system includes a green certificate information collection module, an information detection and management module, an information risk warning module, and an intelligent review and decision-making module. The above green certificate information collection module, information detection and management module, information risk warning module, and intelligent review and decision-making module are interconnected to implement the specific steps of the related embodiments of the system for intelligent control and risk warning of the entire process of green certificate issuance provided by the present invention. The system for intelligent control and risk warning of the entire process of green certificate issuance of the present invention has a complete structure, is objective and stable, and improves the overall applicability and practical application ability of the present invention.

[0141] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the various embodiments of the present invention, and they should all be covered by the scope of the claims and the description of the present invention.

Claims

1. An intelligent control and risk warning system for the whole process of green certificate issuance, characterized in that, The intelligent control and risk warning system for the whole process of green certificate issuance includes: a green certificate information collection module, an information detection and management module, an information risk warning module, and an intelligent review and decision-making module; The multi-source information of the green certificate is obtained through the green certificate information collection module, and the multi-source information of the green certificate is processed based on the missing information inspection and filling mechanism in the green certificate information collection module to obtain a green certificate issuance information database; A green certificate issuance information detection system is constructed in the information detection and management module, and an information reference index analysis result is obtained according to the green certificate issuance information detection system and the green certificate issuance information database. The information detection and management module outputs a green certificate issuance target information set according to the information reference index analysis result; A green certificate issuance risk assessment mechanism is set in the information risk warning module, and the information risk warning module obtains the scoring results of different risk factors according to the green certificate issuance risk assessment mechanism and the green certificate issuance target information set; The intelligent review and decision-making module performs visual simulation and safety monitoring on the green certificate issuance process based on the green certificate issuance target information set and the scoring results to realize the intelligent control and risk warning of the whole process of green certificate issuance.

2. The full-process intelligent control and risk warning system for green certificate issuance according to claim 1, characterized in that, The process of processing the multi-source information of the green certificate based on the missing information inspection and filling mechanism in the green certificate information collection module to obtain a green certificate issuance information database includes: Construct a missing information inspection and filling mechanism in the green certificate information collection module according to the historical information of the green certificate issuance system; Use the missing information detection model in the missing information inspection and filling mechanism to detect the multi-source information of the green certificate to obtain a missing information detection result; The missing information inspection and filling mechanism analyzes the data missing probability of different data subsets in the multi-source information of the green certificate according to the missing information detection result; Obtain the data filling results of different data subsets based on the supplementary information prediction model in the missing information inspection and filling mechanism and the data missing probability; The green certificate information collection module combines the missing information detection result and the data filling result to perform filling processing on different data subsets in the multi-source information of the green certificate to obtain a green certificate issuance information database.

3. The intelligent control and risk warning system for the whole process of green certificate issuance according to claim 2, characterized in that, The intelligent control and risk warning system for the whole process of green certificate issuance further includes: The missing information detection model satisfies the following relationship: Among them, represents the missing information detection model, represents in the data is not missing, represents in the data is missing; The data missing probability satisfies the following relationship: Among them, represents the data missing probability of different data subsets, represents the amount of data missing in different data subsets, represents the total amount of data in different data subsets; The supplementary information prediction model satisfies the following relationship: Among them, represents the data filling value of different data subsets, represents the generative adversarial network function, represents the data subset after removing the missing values , represents the parameters related to the data missing mechanism, represents the data missing probability of different data subsets.

4. The intelligent control and risk warning system for the whole process of green certificate issuance according to claim 1, characterized in that, The construction of a green certificate issuance information detection system in the information detection and management module includes: Set the information reference indexes in the green certificate issuance information detection system, and the information reference indexes include data transmission reference indexes, data feature reference indexes, and business information reference indexes; Construct a green certificate issuance information detection system in the information detection and management module based on the data transmission reference index, the data feature reference index, and the business information reference index.

5. The full-process intelligent control and risk warning system for green certificate issuance according to claim 4, characterized in that The obtaining of the information reference index analysis result according to the green certificate issuance information detection system and the green certificate issuance information database includes: Establish a data transmission analysis model, a data feature analysis model, and a business information analysis model in the green certificate issuance information detection system; Obtain the transportation detection results of different data subsets according to the data transportation analysis model and the green certificate issuance information database; Obtain the feature information inspection results of different data subsets by using the data feature analysis model and the green certificate issuance information database; Obtain the business information inspection results of different data subsets based on the business information analysis model and the green certificate issuance information database; Combine the transportation detection results, the feature information inspection results, and the business information inspection results to obtain the analysis results of information reference indicators.

6. The intelligent control and risk warning system for the whole process of green certificate issuance according to claim 5, characterized in that The data transportation analysis model satisfies the following relationship: Among them, represents the transportation detection results of different data subsets, represents different data subsets of the total number of sub-blocks, represents the check sensitivity index of the key data block, represents the data value of the i-th sub-block, represents the modulus, represents the modulo operation symbol; The data feature analysis model satisfies the following relationship: Among them, represents the characteristic information of different data subsets, represents the prior values of different data subsets, represents the number of characteristic types of different data subsets, represents the mean vector of the \(i\)-th type of characteristics in different data subsets, represents the mean vector of all types of characteristics in different data subsets, represents the dispersion matrix of different data subsets; The business information analysis model includes an amount verification function, a date verification function, a time verification function, and an inventory verification function, and respectively satisfies the following relationships: The amount verification function satisfies the following relationship: Among them, represents the amount verification result, represents the order amount, represents the price of the order goods, represents the quantity of the order goods, indicates that the amount verification result is qualified, indicates that the amount verification result is unqualified; The date verification function satisfies the following relationship: Among them, represents the date verification result, represents the order end date, represents the order start date, indicates that the date verification result is qualified, indicates that the date verification result is unqualified; The time verification function satisfies the following relationship: Among them, represents the time verification result, indicating that the time verification is qualified, indicating that the time verification is unqualified, indicating that the time verification result is qualified, indicating that the time verification result is unqualified; The inventory verification function satisfies the following relationship: Among them, represents the inventory verification result, represents the incoming quantity, represents the outgoing quantity, represents the current inventory level, represents that the inventory verification result is qualified, represents that the inventory verification result is unqualified.

7. The intelligent control and risk warning system for the whole process of green certificate issuance according to claim 5, characterized in that, The information detection and management module outputs a green certificate issuance target information set according to the analysis results of the information reference indicators, including: The information detection and management module detects and manages different data subsets in the green certificate issuance information database based on the transportation detection results, the feature information inspection results, and the business information inspection results, and outputs a green certificate issuance target information set.

8. The intelligent control and risk warning system for the whole process of green certificate issuance according to claim 1, characterized in that Set up a green certificate issuance risk assessment mechanism in the information risk warning module. The information risk warning module obtains the scoring results of different risk factors based on the green certificate issuance risk assessment mechanism and the green certificate issuance target information set, including: Set risk assessment factors and risk assessment indicators in the green certificate issuance risk assessment mechanism; Establish a risk assessment matrix, a risk assessment result optimization model, and a weight assignment model in the green certificate issuance risk assessment mechanism based on the risk assessment factors and the risk assessment indicators; Combine the risk assessment matrix, the risk assessment result optimization model, the weight assignment model, and the green certificate issuance target information set to obtain the scoring results of different risk factors.

9. The intelligent control and risk warning system for the whole process of green certificate issuance according to claim 8, wherein, The risk assessment matrix satisfies the following relationship: Among them, represents the risk assessment matrix in the green certificate issuance risk assessment mechanism, represents the risk assessment factors in the risk assessment matrix, represents the risk assessment indicators in the risk assessment matrix, represents the th risk assessment factor relative to the th risk assessment indicator's risk score value; The risk assessment result optimization model satisfies the following relationship: Among them, represents the after normalization processing, represents the constant value corresponding to the risk assessment result optimization model, represents the th risk assessment factor relative to the th risk assessment index's risk score value, represents the minimum risk score value in the risk assessment matrix, represents the maximum risk score value in the risk assessment matrix; The weight assignment model satisfies the following relationship: Among them, represents the weight coefficient corresponding to the th risk assessment factor, represents the after normalization, represents the entropy value of the th risk assessment factor, represents the total risk score of all risk assessment factors.

10. The intelligent control and risk warning system for the whole process of green certificate issuance according to claim 8, characterized in that The intelligent review and decision-making module performs visual simulation and safety monitoring on the green certificate issuance process based on the green certificate issuance target information set and the scoring results to achieve intelligent control and risk warning for the entire process of green certificate issuance, including: Add an encryption protection subsystem and a risk assessment safety threshold in the intelligent review and decision-making module; The intelligent review and decision-making module uses the encryption protection subsystem to encrypt and protect the green certificate issuance target information set and the scoring results; The intelligent review and decision-making module performs visual simulation and real-time monitoring on the green certificate issuance process based on the risk assessment safety threshold, the encrypted green certificate issuance target information set, and the scoring results.

Images