Carbon trading market data compliance inspection system based on multi-party verification

Abstract

The present invention relates to the field of carbon trading technology, and in particular to a carbon trading market data compliance inspection system based on multi-party verification, comprising: a carbon trading data collection module: collecting carbon trading data in a carbon trading market; a data verification module: used for multi-party verification of the collected carbon trading data, and using the independent environment database and verification logic of each verification party to check the data compliance; a hybrid trust scoring module: building a multi-layer trust scoring mechanism based on time dynamics between multiple verification parties; a verification result evaluation module: generating a final verification evaluation result based on the verification results of multiple verification parties combined with the trust score; a data storage module; the present invention avoids the adverse effects of long-term score accumulation on new verification parties through a time decay function, and combines with score abnormal behavior detection to timely identify score abnormalities, thereby reducing the effects of subjective deviations or malicious behaviors of verification parties on the final verification results.

Description

Technical Field

[0001] The present invention relates to the field of carbon trading technology, and in particular to a carbon trading market data compliance checking system based on multi-party verification. Background Art

[0002] As an important means of emission reduction, the carbon emission trading market has been gradually promoted and applied around the world. The carbon trading market encourages enterprises to reduce carbon emissions by pricing and trading carbon emission rights. However, the existing carbon trading market faces the following technical challenges in its operation:

[0003] The authenticity and compliance of carbon trading data (such as carbon emission data, transaction records, carbon credit certificates, etc.) are key to the normal operation of the carbon trading market. At present, the collection and verification of carbon trading data usually rely on a single institution or centralized platform, which has the following problems:

[0004] Data may be falsified, tampered with, or omitted, affecting the fairness and transparency of the market;

[0005] The lack of authority of a single verifier may result in low credibility of the verification results;

[0006] The lack of a dynamic, multi-level compliance review mechanism makes it difficult to detect and handle abnormal data in a timely manner.

[0007] In the existing technology, the verification process of carbon trading data generally relies on manual or static rules, with low verification efficiency and difficulty in adapting to complex trading scenarios. When the complexity of different verification tasks and the capabilities of the verifier do not match, it is easy to cause deviations in the verification results. The verifier's scoring mechanism lacks dynamic adjustment capabilities and cannot effectively distinguish the influence of high-credibility and low-credibility verifiers. Summary of the invention

[0008] The present invention provides a carbon trading market data compliance checking system based on multi-party verification.

[0009] The carbon trading market data compliance inspection system based on multi-party verification includes:

[0010] Carbon trading data collection module: used to collect carbon trading data in the carbon trading market. Carbon trading data includes carbon emission data, transaction records, carbon credit certificates, and market transaction price data;

[0011] Data verification module: used to conduct multi-party verification of the collected carbon trading data. The verifiers include carbon trading platforms, regulatory agencies and third-party auditing agencies. The independent environmental database and verification logic of each verifier are used to check the data compliance.

[0012] Hybrid trust scoring module: Constructs a multi-layer trust scoring mechanism based on time dynamics among multiple verifiers; the multi-layer trust scoring mechanism combines the time decay function with context information to dynamically adjust the trust score of the verifier to avoid the disadvantageous effect of long-term score accumulation on new verifiers;

[0013] Verification result evaluation module: generates the final verification evaluation result based on the verification results of multiple verifiers and the trust score;

[0014] Data storage module: stores carbon trading data and verification and assessment results, and the storage is written into the blockchain through smart contracts.

[0015] Optionally, the carbon trading data collection module specifically includes:

[0016] Carbon emission data collection unit: collects carbon dioxide emission data in real time through a sensor network deployed at the emission nodes of carbon emission enterprises. The sensor network is connected to the edge computing device to filter and compress the collected raw data;

[0017] Transaction record collection unit: obtains transaction data through the carbon trading platform's application program interface, including information on the transaction initiator and recipient, transaction volume, transaction time and transaction method;

[0018] Carbon credit certificate collection unit: by establishing a data connection channel with the certification body, obtain the carbon credit certificate of the carbon emission enterprise, including the certificate number, validity period, certification body information and enterprise emission reduction quota, and associate the carbon credit certificate data with the transaction record for storage;

[0019] Market transaction price data collection unit: through real-time access to the price data interface of the carbon trading market, obtain the current market carbon trading price fluctuation information, including average price, transaction volume and increase or decrease.

[0020] Optionally, the independent environmental database in the data verification module includes local historical transaction records, regional emission standards, policies and regulations, and industry benchmarks to verify the consistency, authenticity, and compliance of the allocated carbon transactions;

[0021] The verification logic includes:

[0022] The carbon trading platform verifies the integrity and accuracy of transaction records and market transaction price data;

[0023] Regulators verify the compliance of carbon emission data and carbon credit certificates;

[0024] Third-party auditors cross-check all verification results to identify potential violations.

[0025] Optionally, the hybrid trust scoring module specifically includes:

[0026] Trust score initialization unit: Initializes the basic trust score for each verifier. The initial score is determined based on the verifier's qualification information and historical verification records.

[0027] Time dynamic score adjustment unit: dynamically adjusts the trust score of the verifier based on the time decay function to ensure that the impact of historical scores on the current trust gradually weakens, avoiding the adverse impact of long-term score accumulation on new verifiers;

[0028] Context information fusion unit: takes the complexity of the specific verification task in which the verifier participates and the consistency of the verification result with the verification results of other verifiers as context information, obtains the context correction value, and dynamically adjusts the trust score in the dynamic score adjustment unit. For high-complexity verification tasks, if the verification result is consistent with other high-credibility verifiers, the score weight is appropriately increased.

[0029] Optionally, the time-dynamic score adjustment unit dynamically adjusts the trust score of the verifier based on the time decay function and further adds score upper and lower limit constraints, which are expressed as:

[0030] ,in, is the trust score at the current time, is the initial score, is the time decay factor, is the time interval since the last score adjustment, is the context modifier, is the dynamic adjustment factor of the context, These are the upper and lower limits of the score to avoid scoring too high or too low.

[0031] Optionally, the context information fusion unit comprehensively analyzes the complexity of the task and the consistency of the verification results, and corrects the score. The context correction value Calculated as:

[0032] ,in, is the context modifier, It is an indicator of task complexity. The more complex the task, the greater its impact on the score (the value range is 0 to 1). is the consistency of the verification results, calculating the matching degree between the current verification result and the results of other highly trusted verification parties (the value range is 1 to 1, positive values ​​indicate high consistency, and negative values ​​indicate inconsistency). It is a weight coefficient that reflects the relative importance of complexity and consistency and needs to be adjusted according to the actual scenario.

[0033] Optionally, the hybrid trust scoring module further includes an abnormal scoring behavior detection unit, which detects abnormal scoring behaviors in real time in combination with a clustering algorithm, and the abnormal scoring behaviors include:

[0034] The verifier's score fluctuates abnormally (the score drops or rises sharply in a short period of time);

[0035] The verifier's score is significantly mismatched with the difficulty of the verification task, and the judgment is calculated based on the matching degree between the verifier's score and the difficulty of the verification task;

[0036] Based on the abnormal scoring behavior, the comprehensive abnormal score A is obtained, and the trust score at the current time is adjusted again. .

[0037] Optionally, the verification party score fluctuates abnormally The time series change rate based on the rating is expressed as:

[0038] ,in, is the score of the previous scoring cycle. is the time interval of the scoring cycle, defining the threshold of the scoring change rate ,like Mark as abnormal score fluctuation, the threshold can be set according to the score upper and lower limits or historical fluctuation statistics;

[0039] The matching degree between the verification party score and the verification task difficulty is calculated as:

[0040] ,in, Defined as the match between the score and the task complexity, is the current trust score, is the task complexity index, is the ideal value of matching (1), if ,but (No exception); if it exceeds the range, it will be calculated proportionally, with a maximum value of 1.

[0041] Optionally, the comprehensive abnormality score Calculated by weighted summation: ,in, is the final comprehensive anomaly score, ranging from 0 to 1. The closer it is to 1, the more serious the anomaly.

[0042] Based on the comprehensive abnormality score Adjusting Trust Score : ,in, is the updated trust score, is the raw trust score, is the comprehensive abnormality score The impact coefficient reflects the degree of punishment of the comprehensive anomaly on the trust score, and its value range is 0 to 1.

[0043] Optionally, the verification result evaluation module specifically includes weighted integration of the verification results submitted by multiple verifiers, where the integration weight is determined by the trust score of each verifier. Confirm and verify the evaluation results Calculated as:

[0044] ,in, is the final verification evaluation result, Is the verifier Trust score, Is the verifier Submitted verification results, is the number of validators participating in the verification.

[0045] Beneficial effects of the present invention:

[0046] The present invention introduces a multi-layer trust scoring mechanism based on time dynamics, dynamically adjusts the trust score according to the qualifications, historical verification performance and contextual information of the verifier, ensures that the scoring process is fair and flexible, avoids the adverse impact of long-term score accumulation on new verifiers through the time decay function, and combines with score abnormal behavior detection to timely identify score anomalies and reduce the impact of subjective bias or malicious behavior of the verifier on the final verification result. The time decay function ensures that the impact of historical scores is gradually weakened to ensure the real-time nature of the scoring. The score is dynamically adjusted in combination with contextual information (such as task complexity and verification result consistency), enhances the adaptability of the verifier in complex tasks and the positive impact of the consistency of high-trust verifiers on the score. The abnormal scoring behavior detection unit identifies abnormal scoring behavior through abnormal score fluctuations and task difficulty mismatches. The comprehensive abnormal score is used to further adjust the trust score of the verifier and suppress the adverse impact of low-trust verifiers on the results.

[0047] The present invention generates the final verification evaluation result through a weighted integration mechanism of trust scores. The results of each verifier are assigned different weights according to their trust scores. The results of high-scoring verifiers have a greater impact on the final results, and the interference of low-scoring verifiers is significantly reduced. The matching analysis between the verifier scores and the task difficulty further suppresses the adverse effects of low-scoring verifiers in high-complexity tasks, ensuring that the results rely more on the professional judgment of highly trusted verifiers. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0049] Figure 1 A schematic diagram of system function modules according to an embodiment of the present invention;

[0050] Figure 2 Schematic diagram of a hybrid trust scoring module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0051] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0052] It should be noted that the references to "one embodiment", "embodiment", "exemplary embodiments", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0053] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0054] like Figure 1-Figure 2 As shown in the figure, the carbon trading market data compliance inspection system based on multi-party verification includes:

[0055] Carbon trading data collection module: used to collect carbon trading data in the carbon trading market. Carbon trading data includes carbon emission data, transaction records, carbon credit certificates, and market transaction price data;

[0056] Data verification module: used to conduct multi-party verification of the collected carbon trading data. The verifiers include carbon trading platforms, regulatory agencies and third-party auditing agencies. The independent environmental database and verification logic of each verifier are used to check the data compliance.

[0057] Hybrid Trust Scoring Module: Constructs a multi-layer trust scoring mechanism based on time dynamics between multiple verifiers. The multi-layer trust scoring mechanism combines the time decay function with context information to dynamically adjust the trust score of the verifier to avoid the disadvantageous impact of long-term score accumulation on new verifiers.

[0058] Verification result evaluation module: generates the final verification evaluation result based on the verification results of multiple verifiers and the trust score;

[0059] Data storage module: stores carbon trading data and verification and assessment results. The data is written into the blockchain through smart contracts to ensure the data is tamper-proof and facilitate subsequent auditing and tracing.

[0060] The steps to write to the blockchain are as follows:

[0061] After the verification result evaluation module completes the analysis, all data is packaged into a parameter format that conforms to the smart contract structure;

[0062] Calling smart contracts: Using the storage function provided by smart contracts to write data through blockchain transactions;

[0063] Blockchain verification: Blockchain nodes verify the legitimacy of transactions and write data into the distributed ledger;

[0064] Storage completed: After the data is uploaded to the chain, a unique transaction hash or block ID is generated for subsequent tracing.

[0065] The carbon trading data collection module specifically includes:

[0066] Carbon emission data collection unit: Through the sensor network deployed at the emission nodes of carbon emission enterprises, the emission data of carbon dioxide and other greenhouse gases are collected in real time. The sensor network is connected to the edge computing device to filter and compress the collected raw data;

[0067] Transaction record collection unit: obtains transaction data through the carbon trading platform's application program interface, including information on the transaction initiator and recipient, transaction volume, transaction time and transaction method;

[0068] Carbon credit certificate collection unit: by establishing a data connection channel with the certification body, obtain the carbon credit certificate of the carbon emission enterprise, including the certificate number, validity period, certification body information and enterprise emission reduction quota, and associate the carbon credit certificate data with the transaction record for storage;

[0069] Market transaction price data collection unit: through real-time access to the price data interface of the carbon trading market, obtain the current market carbon trading price fluctuation information, including average price, transaction volume and increase or decrease.

[0070] The independent environmental database in the data verification module includes local historical transaction records, regional emission standards, policies and regulations, and industry benchmarks to verify the consistency, authenticity, and compliance of allocated carbon transactions;

[0071] The validation logic includes:

[0072] The carbon trading platform verifies the integrity and accuracy of transaction records and market transaction price data;

[0073] Regulators verify the compliance of carbon emission data and carbon credit certificates;

[0074] Third-party auditors cross-check all verification results to identify potential violations.

[0075] The hybrid trust scoring module specifically includes:

[0076] Trust score initialization unit: Initializes the basic trust score for each verifier. The initial score is determined based on the verifier's qualification information and historical verification records.

[0077] The basis for initializing the basic trust score is as follows:

[0078] Qualification Information:

[0079] Certification level: The industry certification of the verifier. The more authoritative it is, the higher the initial score will be.

[0080] Business experience: The verifier’s operating time in the carbon trading market and the number of projects it has participated in. The more experience it has, the higher the score.

[0081] Historical verification records:

[0082] Accuracy: The consistency ratio between past verification results and the results of other highly trusted verification parties. The higher the accuracy, the higher the score.

[0083] Stability: Validators with smaller historical score fluctuations and that maintain a high level over a long period of time will receive higher scores.

[0084] Violation record: If the verifier has a record of being questioned or having problems found during the review, its initial score will be penalized and reduced.

[0085] Based on the expert scoring, the above factors of each verifier are scored one by one, and the final sum is used to form the initial score. The deviation of the initial score of each verifier should be controlled within a small range to avoid unfairness. Therefore, the score range of each factor of the initial score is controlled in [0,0.1].

[0086] Time dynamic score adjustment unit: dynamically adjusts the trust score of the verifier based on the time decay function to ensure that the impact of historical scores on the current trust gradually weakens, avoiding the adverse impact of long-term score accumulation on new verifiers;

[0087] Context information fusion unit: takes the complexity of the specific verification task in which the verifier participates and the consistency of the verification result with the verification results of other verifiers as context information, obtains the context correction value, and dynamically adjusts the trust score in the dynamic score adjustment unit. For high-complexity verification tasks, if the verification result is consistent with other high-credibility verifiers, the score weight is appropriately increased.

[0088] The trust score of the verifier is dynamically adjusted based on the time decay function in the time dynamic score adjustment unit, and the upper and lower limit constraints of the score are added, which are expressed as:

[0089] ,in, is the trust score at the current time, is the initial score, is the time decay factor, is the time interval since the last score adjustment, is the context correction value, is the dynamic adjustment factor of the context, These are the upper and lower limits of the score to avoid scoring too high or too low.

[0090] The context information fusion unit comprehensively analyzes the task complexity, verifies the consistency of the results, and corrects the scores and context correction values. Calculated as:

[0091] ,in, is the context correction value, It is an indicator of task complexity. The more complex the task, the greater its impact on the score (the value range is 0 to 1). is the consistency of the verification results, calculating the matching degree between the current verification result and the results of other highly trusted verification parties (the value range is 1 to 1, positive values ​​indicate high consistency, and negative values ​​indicate inconsistency). It is a weight coefficient that reflects the relative importance of complexity and consistency and needs to be adjusted according to the actual scenario.

[0092] Task complexity index The calculation is based on the data type and transaction size, and is defined as follows:

[0093] ,in, Assign values ​​according to data type complexity, for example:

[0094] Carbon emission data (high complexity): assigned a value of 0.9;

[0095] Transaction records (medium complexity): assigned a value of 0.7;

[0096] Market price data (low complexity): assigned a value of 0.5;

[0097] Normalized according to the transaction size, the larger the transaction size, the higher the complexity, and the value range is 0.5 (small scale) to 1.0 (super large scale).

[0098] Verify result consistency The calculation of is based on the matching degree of the verification results between the verifier and other highly trusted verifiers, which is defined as follows: ,in, is the number of records where the verification results of the verifier are consistent with those of other highly trusted verifiers. Is the total number of verification records, value range:

[0099] : Completely consistent, all results are consistent with the high-trust verification party;

[0100] : Completely inconsistent, all results are opposite to those of the high-confidence verifier;

[0101] : Partially consistent, with a match degree of 50%.

[0102] The hybrid trust scoring module also includes an abnormal scoring behavior detection unit. The abnormal scoring behavior detection unit combines a clustering algorithm to detect abnormal scoring behaviors in real time. The abnormal scoring behaviors include:

[0103] The verifier's score fluctuates abnormally (the score drops or rises sharply in a short period of time);

[0104] The verifier's score is significantly mismatched with the difficulty of the verification task, and the judgment is calculated based on the matching degree between the verifier's score and the difficulty of the verification task;

[0105] Based on the abnormal scoring behavior, the comprehensive abnormal score A is obtained, and the trust score at the current time is adjusted again. .

[0106] Abnormal fluctuations in the verifier's score The time series change rate based on the rating is expressed as:

[0107] ,in, is the score of the previous scoring cycle. is the time interval of the scoring cycle, defining the threshold of the scoring change rate ,like Mark as abnormal score fluctuation, the threshold can be set according to the score upper and lower limits or historical fluctuation statistics;

[0108] The matching degree between the verifier score and the verification task difficulty is calculated as:

[0109] ,in, Defined as the match between the score and the task complexity, is the current trust score, is the task complexity index, is the ideal value of matching (1), if ,but (No exception); if it exceeds the range, it will be calculated proportionally, with a maximum value of 1.

[0110] Comprehensive abnormality score Calculated by weighted summation: ,in, is the final comprehensive anomaly score, ranging from 0 to 1. The closer it is to 1, the more serious the anomaly.

[0111] Based on the comprehensive abnormality score Adjusting Trust Score : ,in, is the updated trust score, is the raw trust score, is the comprehensive abnormality score The impact coefficient reflects the degree of punishment of the comprehensive anomaly on the trust score, and its value range is 0 to 1.

[0112] The verification result evaluation module specifically includes weighted integration of the verification results submitted by multiple verifiers, and the integration weight is determined by the trust score of each verifier. Confirm and verify the evaluation results Calculated as:

[0113] ,in, is the final verification evaluation result, Is the verifier Trust score, Is the verifier Submitted verification results, is the number of validators participating in the verification.

[0114] Verification results of each verifier is assigned a weight determined by the trust score of the validator Decide.

[0115] molecular: Represents the sum of weighted verification results of all verifiers.

[0116] Denominator: It is the sum of the trust scores and is used for normalization so that the final verification result has a unified standard under different verifier score weights.

[0117] Combine the verification and evaluation results submitted by multiple verifiers into a unified , through trust score The weighting gives verifiers with higher trust scores greater influence and reduces the interference of verifiers with low trust scores on the final result.

[0118] Results and significance:

[0119] If the high-scoring verifiers agree that the data check is compliant, but the low-scoring verifiers give conflicting results, then Closer to the results of high-scoring verifiers;

[0120] If all validators have a balanced score, will approach the ordinary weighted average result;

[0121] When the verifier's score is significantly mismatched with the difficulty of the verification task, the verification results of low-scoring verifiers may have large errors due to their low trust scores. If these verifiers participate in high-complexity tasks, the weight of their results on Rfinal will be suppressed.

[0122] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0123] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. The carbon trading market data compliance inspection system based on multi-party verification is characterized by: include: Carbon trading data collection module: used to collect carbon trading data in the carbon trading market. Carbon trading data includes carbon emission data, transaction records, carbon credit certificates, and market transaction price data; Data verification module: used to conduct multi-party verification of the collected carbon trading data. The verifiers include carbon trading platforms, regulatory agencies and third-party auditing agencies. The independent environmental database and verification logic of each verifier are used to check the data compliance. Hybrid trust scoring module: Constructs a multi-layer trust scoring mechanism based on time dynamics among multiple verifiers; the multi-layer trust scoring mechanism combines the time decay function with context information to dynamically adjust the trust score of the verifier to avoid the disadvantageous effect of long-term score accumulation on new verifiers; Verification result evaluation module: generates the final verification evaluation result based on the verification results of multiple verifiers and the trust score; Data storage module: stores carbon trading data and verification and assessment results, and the storage is written into the blockchain through smart contracts.

2. The carbon trading market data compliance inspection system based on multi-party verification according to claim 1 is characterized in that: The carbon trading data collection module specifically includes: Carbon emission data collection unit: collects carbon dioxide emission data in real time through a sensor network deployed at the emission nodes of carbon emission enterprises. The sensor network is connected to the edge computing device to filter and compress the collected raw data; Transaction record collection unit: obtains transaction data through the carbon trading platform's application program interface, including information on the transaction initiator and recipient, transaction volume, transaction time and transaction method; Carbon credit certificate collection unit: by establishing a data connection channel with the certification body, obtain the carbon credit certificate of the carbon emission enterprise, including the certificate number, validity period, certification body information and enterprise emission reduction quota, and associate the carbon credit certificate data with the transaction record for storage; Market transaction price data collection unit: through real-time access to the price data interface of the carbon trading market, obtain the current market carbon trading price fluctuation information, including average price, transaction volume and increase or decrease.

3. The carbon trading market data compliance inspection system based on multi-party verification according to claim 1 is characterized in that: The independent environmental database in the data verification module includes local historical transaction records, regional emission standards, policies and regulations, and industry benchmarks to verify the consistency, authenticity, and compliance of the allocated carbon transactions; The verification logic includes: The carbon trading platform verifies the integrity and accuracy of transaction records and market transaction price data; Regulators verify the compliance of carbon emission data and carbon credit certificates; Third-party auditors cross-check all verification results to identify potential violations.

4. The carbon trading market data compliance inspection system based on multi-party verification according to claim 1 is characterized in that: The hybrid trust scoring module specifically includes: Trust score initialization unit: Initializes the basic trust score for each verifier. The initial score is determined based on the verifier's qualification information and historical verification records. Time dynamic score adjustment unit: dynamically adjusts the trust score of the verifier based on the time decay function to ensure that the impact of historical scores on the current trust gradually weakens, avoiding the adverse impact of long-term score accumulation on new verifiers; Context information fusion unit: takes the complexity of the specific verification task in which the verifier participates and the consistency of the verification result with the verification results of other verifiers as context information, obtains the context correction value, and dynamically adjusts the trust score in the dynamic score adjustment unit.

5. The carbon trading market data compliance inspection system based on multi-party verification according to claim 4 is characterized in that: The time-dynamic score adjustment unit dynamically adjusts the trust score of the verifier based on the time decay function and also adds the upper and lower limit constraints of the score, which are expressed as: ,in, is the trust score at the current time, is the initial score, is the time decay factor, is the time interval since the last score adjustment, is the context modifier, is the dynamic adjustment factor of the context, are the upper and lower limits of the score.

6. The carbon trading market data compliance inspection system based on multi-party verification according to claim 5 is characterized in that: The context information fusion unit comprehensively analyzes the task complexity, verifies the consistency of the results, and corrects the score. The context correction value Calculated as: ,in, is the context modifier, is the task complexity index, Is to verify the consistency of the results, is the weight coefficient.

7. The carbon trading market data compliance inspection system based on multi-party verification according to claim 5 is characterized in that: The hybrid trust scoring module further includes an abnormal scoring behavior detection unit, which detects abnormal scoring behaviors in real time in combination with a clustering algorithm. The abnormal scoring behaviors include: The verifier's score fluctuates abnormally; The verifier's score does not match the difficulty of the verification task. The judgment is based on the matching degree between the verifier's score and the difficulty of the verification task. Based on the abnormal scoring behavior, a comprehensive abnormal score A is obtained, and the trust score at the current time is adjusted again. .

8. The carbon trading market data compliance inspection system based on multi-party verification according to claim 7 is characterized in that: The verifier's score fluctuates abnormally The time series change rate based on the rating is expressed as: ,in, is the score of the previous scoring cycle. is the time interval of the scoring cycle, defining the threshold of the scoring change rate ,like Marked as abnormal score fluctuation; The matching degree between the verification party score and the verification task difficulty is calculated as: ,in, Defined as the match between the score and the task complexity, is the current trust score, is the task complexity index, is the ideal value for matching.

9. The carbon trading market data compliance inspection system based on multi-party verification according to claim 8 is characterized in that: The combined abnormality score Calculated by weighted summation: ,in, is the final comprehensive abnormality score; Based on the comprehensive abnormality score Adjusting Trust Score : ,in, is the updated trust score, is the raw trust score, is the comprehensive abnormality score The influence coefficient of .

10. The carbon trading market data compliance inspection system based on multi-party verification according to claim 9 is characterized in that: The verification result evaluation module specifically includes weighted integration of the verification results submitted by multiple verifiers, where the integration weight is determined by the trust score of each verifier. Confirm and verify the evaluation results Calculated as: ,in, is the final verification evaluation result, Is the verifier Trust score, Is the verifier Submitted verification results, is the number of validators participating in the verification.

Images