Carbon sink measurement and monitoring system and method based on blockchain

Abstract

The present application discloses a carbon sink measurement and monitoring system and method based on blockchain, which processes the basic carbon sink data extracted from the blockchain network through an artificial intelligence-based data processing and analysis algorithm to extract the driving load characterization information between the vehicle mileage and the cargo load, and capture the road condition characterization information, and then use the significant interactive fusion representation between the driving load characteristics and the road condition characteristics to generate a reasonable estimation interval of hydrogen consumption. Furthermore, the actual extracted hydrogen consumption is compared with the reasonable estimation interval of the hydrogen consumption to determine whether the hydrogen consumption is within the reasonable estimation interval of the hydrogen consumption, so as to determine whether there is a risk of data tampering. In this way, more intelligent carbon sink measurement and monitoring can be achieved, which helps to ensure the authenticity and integrity of carbon sink data, so that drivers can obtain carbon reduction points based on their carbon reduction performance in actual work.

Description

Technical Field

[0001] The present application relates to the field of intelligent monitoring, and more specifically, to a blockchain-based carbon sink measurement and monitoring system and method. Background Art

[0002] As global awareness of environmental protection increases, the monitoring and management of carbon emissions has become increasingly important. Traditionally, the tracking and reporting of carbon emissions mostly rely on manual records, paper documents or centralized database systems. However, these methods have a series of problems, such as data tampering, lack of transparency, and difficulty in verifying the authenticity and integrity of data. In addition, centralized systems also have the risk of single point failures, and when failures occur, the operation of the entire system may be affected. And centralized systems are often less efficient when coordinating between different stakeholders.

[0003] Therefore, an optimized carbon emission tracking and measurement solution is desired. Summary of the invention

[0004] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides a carbon sink measurement monitoring system and method based on blockchain, which processes the carbon sink basic data extracted from the blockchain network through an artificial intelligence-based data processing and analysis algorithm to extract the driving load characterization information between the vehicle mileage and the cargo load, and capture the road condition characterization information, and then use the significant interactive fusion representation between the driving load characteristics and the road condition characteristics to generate a reasonable estimation interval of hydrogen consumption. Furthermore, the actual extracted hydrogen consumption is compared with the reasonable estimation interval of the hydrogen consumption to determine whether the hydrogen consumption is within the reasonable estimation interval of the hydrogen consumption, so as to determine whether there is a risk of data tampering. In this way, data anomaly detection can be performed on these carbon sink basic data in an automated manner, so as to calculate carbon reduction points when there is no abnormal carbon sink basic data. In this way, more intelligent carbon sink measurement monitoring can be achieved, which helps to ensure the authenticity and integrity of carbon sink data, so that drivers can obtain carbon reduction points based on their carbon reduction performance in actual work.

[0005] According to one aspect of the present application, a blockchain-based carbon sink measurement and monitoring method is provided, which includes:

[0006] The user uploads the basic carbon sink data to the blockchain network, wherein the basic carbon sink data includes vehicle mileage, hydrogen consumption, cargo load and road condition data;

[0007] Extracting the carbon sink basic data from the blockchain network;

[0008] Performing data anomaly detection on the carbon sink basic data to obtain a detection result, wherein the detection result is used to indicate whether there is a risk of data tampering;

[0009] In response to the detection result indicating that there is no risk of data tampering, carbon reduction credits are calculated based on the carbon sink basic data.

[0010] According to another aspect of the present application, a blockchain-based carbon sink measurement and monitoring system is provided, which includes:

[0011] A carbon sink basic data uploading module is used for users to upload carbon sink basic data to the blockchain network, wherein the carbon sink basic data includes vehicle mileage, hydrogen consumption, cargo load and road condition data;

[0012] A carbon sink basic data extraction module, used to extract the carbon sink basic data from the blockchain network;

[0013] A data anomaly detection module, used to perform data anomaly detection on the carbon sink basic data to obtain a detection result, wherein the detection result is used to indicate whether there is a risk of data tampering;

[0014] A carbon reduction credit calculation module is used to calculate carbon reduction credits based on the carbon sink basic data in response to the detection result indicating that there is no risk of data tampering.

[0015] Compared with the prior art, the present application provides a carbon sink measurement and monitoring system and method based on blockchain, which processes the carbon sink basic data extracted from the blockchain network through an artificial intelligence-based data processing and analysis algorithm to extract the driving load characterization information between the vehicle mileage and the cargo load, and capture the road condition characterization information, and then use the significant interactive fusion representation between the driving load characteristics and the road condition characteristics to generate a reasonable estimation interval of hydrogen consumption. Furthermore, the actual extracted hydrogen consumption is compared with the reasonable estimation interval of the hydrogen consumption to determine whether the hydrogen consumption is within the reasonable estimation interval of the hydrogen consumption, so as to determine whether there is a risk of data tampering. In this way, data anomaly detection can be performed on these carbon sink basic data in an automated manner, so as to calculate carbon reduction points when there is no abnormal carbon sink basic data. In this way, more intelligent carbon sink measurement and monitoring can be achieved, which helps to ensure the authenticity and integrity of carbon sink data, so that drivers can obtain carbon reduction points based on their carbon reduction performance in actual work. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0017] Figure 1 It is a flowchart of a carbon sink measurement and monitoring method based on blockchain according to an embodiment of the present application;

[0018] Figure 2 A schematic diagram of data flow of a blockchain-based carbon sink measurement and monitoring method according to an embodiment of the present application;

[0019] Figure 3 This is a flowchart of sub-step S3 of the blockchain-based carbon sink measurement and monitoring method according to an embodiment of the present application;

[0020] Figure 4 It is a block diagram of a blockchain-based carbon sink measurement and monitoring system according to an embodiment of the present application. DETAILED DESCRIPTION

[0021] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0022] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0023] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules can be used and run on the user terminal and / or server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0024] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. Meanwhile, other operations may also be added to these processes, or a certain step or several steps of operations may be removed from these processes.

[0025] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0026] In recent years, with the development of blockchain technology, it has begun to be applied to the tracking and reporting of carbon emissions. As a distributed ledger technology, blockchain has the characteristics of decentralization, high transparency, and data immutability, which is very suitable for solving the problems existing in the traditional carbon emission tracking and reporting mechanism mentioned above. By storing the basic data of carbon sinks on the blockchain, the transparency and tamper-proofness of the data can be ensured, thereby enhancing trust.

[0027] Specifically, in the operation scenario of hydrogen energy vehicles, the on-board terminal on the vehicle will automatically collect basic carbon sink data related to carbon emissions, such as vehicle mileage, hydrogen consumption, cargo load, and road condition information. These data will then be uploaded to the blockchain network. The use of blockchain technology can not only ensure the security and reliability of data, but also automate data processing and calculate carbon reduction points through smart contracts and other means. In other words, carbon reduction points are obtained based on the driver's carbon reduction performance in actual work, and these carbon reduction points will be updated in real time on the driver's side.

[0028] Based on this, in the technical solution of this application, a blockchain-based carbon sink measurement and monitoring method is proposed. Figure 1 This is a flowchart of a blockchain-based carbon sink measurement and monitoring method according to an embodiment of the present application. Figure 2 Schematic diagram of data flow of the blockchain-based carbon sink measurement and monitoring method according to an embodiment of the present application. Figure 1 and Figure 2 As shown, according to the blockchain-based carbon sink measurement and monitoring method of the embodiment of the present application, the steps include: S1, the user uploads the carbon sink basic data to the blockchain network, wherein the carbon sink basic data includes vehicle mileage, hydrogen consumption, cargo load and road condition data; S2, extracts the carbon sink basic data from the blockchain network; S3, performs data anomaly detection on the carbon sink basic data to obtain a detection result, and the detection result is used to indicate whether there is a risk of data tampering; S4, in response to the detection result that there is no risk of data tampering, calculates carbon reduction points based on the carbon sink basic data.

[0029] In particular, in S1, the user uploads the basic carbon sink data to the blockchain network, wherein the basic carbon sink data includes vehicle mileage, hydrogen consumption, cargo load and road condition data. It should be understood that the vehicle mileage, hydrogen consumption, cargo load and road condition data in the basic carbon sink data play an important role in carbon emission monitoring and management. For example: mileage directly affects the carbon emissions of the vehicle. By recording the mileage, the total carbon emissions of the vehicle in a specific time period can be more accurately calculated; hydrogen consumption is an important parameter for calculating the carbon emissions of the vehicle; and cargo load affects the energy consumption and carbon emissions of the vehicle. The energy consumption and carbon emissions of heavy-loaded vehicles are usually higher, so recording the cargo load helps to calculate carbon emissions more accurately; in addition, road condition data (such as road congestion, slope, road quality, etc.) affect the energy consumption and carbon emissions of the vehicle. By recording road condition data, carbon emissions under different road conditions can be calculated more accurately. In particular, by uploading the basic data of carbon sinks to the blockchain network, the data can be made transparent, reliable, tamper-proof and dynamically managed, which can promote the accurate calculation of carbon footprint and the healthy development of the carbon trading market, and promote the realization of environmental protection and sustainable development goals.

[0030] In particular, the S2 extracts the carbon sink basic data from the blockchain network, wherein the carbon sink basic data includes vehicle mileage, hydrogen consumption, cargo load and road condition data.

[0031] In particular, S3 performs data anomaly detection on the carbon sink basic data to obtain a detection result, and the detection result is used to indicate whether there is a risk of data tampering. It should be understood that in the above-mentioned carbon sink measurement and monitoring process, in order to ensure the quality of the data, it is also necessary to perform anomaly detection on the carbon sink basic data extracted from the blockchain network. It should be understood that in the carbon trading market, carbon sink data is directly related to the company's carbon emission quota and the corresponding economic benefits. If inaccurate or tampered data is allowed to enter the system, it may lead to fraud and damage the fairness and effectiveness of the market. In other words, only accurate data can correctly reflect the actual effect of carbon sink activities, thereby supporting effective carbon emission management and decision-making. Data anomaly detection can help identify possible errors or abnormal data points, thereby ensuring that the carbon sink basic data is reliable and has not been tampered with, which is conducive to ensuring the accuracy and reliability of carbon sink measurement. In a specific example of the present application, such as Figure 3As shown, the S3 includes: S31, embedding the vehicle mileage and the cargo load to obtain a vehicle mileage embedded coding vector and a cargo load embedded coding vector respectively; S32, cascading the vehicle mileage embedded coding vector and the cargo load embedded coding vector to obtain a driving load cascade feature vector; S33, fully connecting the road condition data to obtain a road condition fully connected coding vector; S34, performing inter-feature significant guided interactive fusion on the driving load cascade feature vector and the road condition fully connected coding vector to obtain a driving load-road condition state significant interactive fusion representation; S35, based on the driving load-road condition state significant interactive fusion representation, determining a reasonable estimation interval of hydrogen consumption, and judging whether the hydrogen consumption is within the reasonable estimation interval of hydrogen consumption to determine whether there is a risk of data tampering.

[0032] Specifically, the S31 embeds and codes the vehicle mileage and the cargo load respectively to obtain a vehicle mileage embedding coding vector and a cargo load embedding coding vector. More specifically, in the technical solution of the present application, first, the vehicle mileage is embedded and coded using a mileage embedding coding matrix to obtain a vehicle mileage embedding coding vector, and the cargo load is embedded and coded using a cargo load embedding coding matrix to obtain a cargo load embedding coding vector. That is, in the technical solution of the present application, the intrinsic structure of the vehicle mileage and the cargo load is learned through embedding coding to extract the key features of the vehicle mileage and the cargo load.

[0033] Specifically, in S32, the vehicle mileage embedded coding vector and the cargo load embedded coding vector are cascaded to obtain a driving load cascade feature vector. Since mileage and cargo load are respectively one of the important factors affecting hydrogen consumption, these two data can reflect the load conditions of the vehicle. Based on this, the vehicle mileage embedded coding vector and the cargo load embedded coding vector are further cascaded to obtain a driving load cascade feature vector. By cascading, the vehicle mileage embedded coding semantics and the cargo load embedded coding semantics can be fused to form a new feature representation of the vehicle's driving load, which is helpful for the subsequent estimation of the reasonable range of hydrogen consumption and the detection of data tampering risks.

[0034] Specifically, the S33 performs full-connection encoding on the road condition data to obtain a road condition fully-connected encoding vector. More specifically, in the technical solution of the present application, a road condition feature extractor based on a multi-layer perceptron model is used to perform full-connection encoding on the road condition data to obtain the road condition fully-connected encoding vector. It should be understood that road condition data contains various types of information, such as road type, traffic flow, weather conditions, etc. The road condition feature extractor of the multi-layer perceptron model can map these data of different dimensions and different ranges into a common space, and capture the fully-connected correlation feature representation between these different road condition data through fully-connected encoding, providing a basis for subsequent hydrogen consumption estimation and reasonable hydrogen consumption interval estimation.

[0035] Specifically, the S34 performs inter-feature significant guided interactive fusion on the driving load cascade feature vector and the road condition fully connected encoding vector to obtain a driving load-road condition state significant interactive fusion representation. It should be understood that when driving a vehicle, there is a complex interaction between the driving load (such as mileage and load) and the road condition (such as road type, traffic conditions, etc.). These factors jointly affect the energy consumption of the vehicle, especially the consumption of hydrogen fuel. Considering that the driving load cascade feature vector contains the embedded coding cascade representation semantics related to the driving load, the road condition fully connected encoding vector contains the multi-dimensional fully connected associated feature representation semantics of the road condition state. The feature representations of the driving load and road condition data each carry important information about hydrogen consumption, and the interaction between them is more complicated. For example, the same mileage may have different hydrogen consumption under different road conditions. Based on this, in order to be able to interactively fuse the significant key semantic information of the feature representation information of the two, so as to have a deeper understanding of the complex interaction between driving load (i.e., vehicle mileage and cargo load) and road conditions, so as to generate an enhanced and more discriminative feature representation, and provide a basis for subsequent hydrogen consumption estimation and data anomaly detection tasks, in the technical solution of the present application, the driving load cascade feature vector and the road condition fully connected encoding vector are further interactively fused with significant guided features to obtain the driving load-road condition state significant interactive fusion representation.

[0036] Specifically, first, the driving load cascade feature vector and the road condition fully connected coding vector are subjected to joint implicit feature analysis and activation processing to obtain driving load-road condition state condition features. In particular, the specific process includes: firstly inputting the driving load cascade feature vector and the road condition fully connected coding vector into the joint implicit feature capture network to obtain the driving load-road condition state joint implicit feature vector; that is, by inputting the driving load cascade feature vector and the road condition fully connected coding vector into the joint implicit feature capture network, a driving load-road condition state joint implicit feature vector can be generated. This new vector not only contains the original driving load feature representation information and the road condition state feature representation information, but also captures the intrinsic connection between the driving load and the road condition state, thereby generating a richer and more discriminative driving load-road condition state joint implicit feature representation. Subsequently, the driving load-road condition state joint implicit feature vector is subjected to feature activation based on the Sigmoid function to obtain the driving load-road condition state condition feature vector as the driving load-road condition state condition feature. Here, the driving load-road condition state joint implicit feature vector is activated by using the Sigmoid function, which can amplify the most critical parts for describing the comprehensive conditions of the driving load-road condition state, while suppressing irrelevant noise information. This ensures that the model focuses on the more important features for hydrogen consumption estimation and data anomaly detection tasks. Among them, the driving load cascade feature vector and the road condition fully connected encoding vector are input into the joint implicit feature capture network to obtain the driving load-road condition state joint implicit feature vector, including: adding the driving load cascade feature vector and the road condition fully connected encoding vector by position point, multiplying the obtained driving load-road condition state sum vector with the weight matrix, and then adding it with the bias vector by position to obtain the driving load-road condition state joint interaction vector; using the tanh function to process the driving load-road condition state joint interaction vector to obtain the driving load-road condition state joint implicit feature vector.

[0037] Furthermore, taking the driving load-road condition condition feature as condition information, the driving load cascade feature vector and the road condition fully connected coding vector are subjected to feature interactive fusion to obtain the driving load-road condition state significant interactive fusion representation. In particular, the specific process includes: first calculating the driving load contribution of the driving load cascade feature vector relative to the driving load-road condition state condition feature vector; calculating the road condition state contribution of the road condition fully connected coding vector relative to the driving load-road condition state condition feature vector; by calculating the contribution of the driving load cascade feature vector and the road condition fully connected coding vector respectively relative to the driving load-road condition state condition feature vector, the importance of the respective feature representations of the driving load and the road condition state to the conditional association semantic representation can be determined to obtain the driving load contribution and the road condition state contribution. Through such an evaluation, the system can identify which features are more important for the final feature representation and for the subsequent hydrogen consumption estimation and data tampering identification tasks. Then, the driving load contribution and the road condition contribution are normalized, and the normalized driving load contribution and the normalized road condition contribution are used to weighted modulate the driving load cascade feature vector and the road condition fully connected coding vector to obtain the modulated driving load cascade feature vector and the modulated road condition fully connected coding vector; by normalizing the driving load contribution and the road condition contribution, and adjusting the original driving load cascade feature vector and the road condition fully connected coding vector accordingly, it can be ensured that the more important driving load features and road condition features occupy a greater weight in the final feature representation. This helps the model better understand and process driving load information and road condition information, and interact and fuse the semantic representation information of the two. Finally, the modulated driving load cascade feature vector is used as a query vector, the modulated road condition fully connected encoding vector is used as a key vector, and the driving load-road condition state condition feature vector is used as a value vector. The modulated driving load cascade feature vector, the modulated road condition fully connected encoding vector, and the driving load-road condition state condition feature vector are input into the feature inter-significant guided interaction module based on the converter structure to obtain the driving load-road condition state significant interactive fusion representation vector as the driving load-road condition state significant interactive fusion representation. That is, the modulated feature vector is interactively fused through the feature inter-significant guided interaction module based on the converter structure. Specifically, the modulated driving load cascade feature vector is used as a query vector, the modulated road condition fully connected encoding vector is used as a key vector, and the driving load-road condition state condition feature vector is used as a value vector. These features are fused through the converter structure to generate a driving load-road condition state significant interactive fusion representation vector as the driving load-road condition state significant interactive fusion representation.This adaptive feature fusion method enables the model to examine the complex correlation and interaction between driving load features and road condition features from multiple perspectives, and to discover the most valuable information flow path. In particular, by performing semantic feature joint significant fusion processing on the driving load cascade feature vector and the road condition fully connected encoding vector, the joint significant key features and potential relationships between driving load and road condition can be fused, which enhances the expression ability of semantic association features with higher relevance to subsequent data anomaly recognition and detection tasks, and reduces the interference of irrelevant information, thereby providing a basis for subsequent hydrogen consumption estimation and data tampering risk detection, which is crucial to improving the accuracy of generating reasonable hydrogen consumption estimation intervals.

[0038] Among them, calculating the driving load contribution of the driving load cascade characteristic vector relative to the driving load-road condition state condition characteristic vector includes: calculating the positional division of the driving load cascade characteristic vector and the driving load-road condition state condition characteristic vector to obtain a driving load contribution vector; calculating the logarithmic function value with base two of the absolute value of each eigenvalue of the driving load contribution vector to obtain a driving load contribution logarithmic vector; calculating the positional dot product of the driving load cascade characteristic vector and the driving load contribution logarithmic vector, and performing positional multiplication on the obtained dot product vector to obtain a driving load contribution value; calculating an exponential function with the natural constant e as the base and the driving load contribution value as the exponent to obtain the driving load contribution degree.

[0039] More specifically, the driving load contribution and the road condition state contribution are normalized, and the normalized driving load contribution and the normalized road condition state contribution are used to perform weighted modulation on the driving load cascade feature vector and the road condition fully connected coding vector to obtain a modulated driving load cascade feature vector and a modulated road condition fully connected coding vector, including: calculating the sum of the driving load contribution and the road condition state contribution to obtain a total sum of driving load-road condition state semantic contributions; dividing the driving load contribution and the road condition state contribution by the total sum of driving load-road condition state semantic contributions respectively to obtain the normalized driving load contribution and the normalized road condition state contribution; performing position point multiplication of the driving load cascade feature vector and the normalized driving load contribution to obtain the modulated driving load cascade feature vector; performing position point multiplication of the road condition fully connected coding vector and the normalized road condition state contribution to obtain the modulated road condition fully connected coding vector.

[0040] More specifically, the modulated driving load cascade feature vector is used as a query vector, the modulated road condition fully connected encoding vector is used as a key vector, and the driving load-road condition state condition feature vector is used as a value vector. The modulated driving load cascade feature vector, the modulated road condition fully connected encoding vector, and the driving load-road condition state condition feature vector are input into a feature-to-feature significant guided interaction module based on a converter structure to obtain a driving load-road condition state significant interaction fusion representation vector as the driving load-road condition state significant interaction fusion representation, including: the modulated driving load cascade feature vector is combined with The transposed vector of the modulated road condition fully connected coding vector is vector-multiplied, and the obtained modulated driving load-road condition state association matrix is ​​divided by the square root of the length of the modulated road condition fully connected coding vector by position to obtain the modulated driving load-road condition state association scaling matrix; the modulated driving load-road condition state association scaling matrix is ​​activated using a softmax function, and the obtained modulated driving load-road condition state association scaling activation matrix is ​​multiplied by the driving load-road condition state conditional feature vector to obtain the driving load-road condition state significant interaction fusion representation vector.

[0041] In summary, in the above embodiment, the driving load cascade feature vector and the road condition fully connected encoding vector are subjected to inter-feature significant guided interactive fusion to obtain a driving load-road condition state significant interactive fusion representation, including: the driving load cascade feature vector and the road condition fully connected encoding vector are subjected to inter-feature significant guided interactive fusion to obtain a driving load-road condition state significant interactive fusion representation using the following semantic feature interactive fusion formula; wherein the semantic feature interactive fusion formula is:

[0042]

[0043] in, and are the driving load cascade feature vector and the road condition fully connected encoding vector respectively, To add by location, and are the weight matrix and bias vector respectively, for function, is the driving load-road condition joint implicit feature vector, for function, represents the driving load-road condition characteristic vector, is the characteristic value of each position in the driving load cascade characteristic vector, is the feature value of each position in the road condition fully connected encoding vector, is the characteristic value of each position in the driving load-road condition characteristic vector, is the number of eigenvalues ​​in the driving load cascade feature vector and the road condition fully connected encoding vector, represents the logarithmic function value with base 2, represents an exponential function with the natural constant e as the base, is the driving load contribution, Contribution to road condition status, and They are the normalized driving load contribution and the normalized road condition contribution, and They are the modulated driving load cascade feature vector and the modulated road condition fully connected encoding vector. yes The transposed vector of yes Length, represents vector multiplication, yes function, It is the driving load-road condition state significant interaction fusion representation vector.

[0044] Specifically, the S35 determines the reasonable estimation interval of hydrogen consumption based on the significant interactive fusion representation of the driving load-road condition state, and judges whether the hydrogen consumption is in the reasonable estimation interval of hydrogen consumption to determine whether there is a risk of data tampering. In a specific example of the present application, the driving load-road condition state significant interactive fusion representation vector is input into the decoder-based hydrogen consumption estimation module to obtain the reasonable estimation interval of hydrogen consumption; that is, the significant interactive fusion features between the driving load feature representation and the road condition feature representation are used for decoding regression to estimate hydrogen consumption, thereby generating a reasonable estimation interval of hydrogen consumption. Further, it is judged whether the hydrogen consumption is in the reasonable estimation interval of hydrogen consumption to determine whether there is a risk of data tampering. In a specific example, if the actual hydrogen consumption falls within the reasonable estimation interval, it is considered that the data has not been tampered with, and the carbon reduction credit calculation can continue; if the actual hydrogen consumption exceeds the reasonable estimation interval, there may be a risk of data tampering, which requires further investigation and processing. In this way, data anomalies can be detected in these carbon sink basic data in an automated way, so that carbon reduction credits can be calculated when there are no abnormal carbon sink basic data. In this way, more intelligent carbon sink measurement and monitoring can be achieved, which helps to ensure the authenticity and integrity of carbon sink data, so that drivers can obtain carbon reduction credits based on their actual carbon reduction performance at work. In particular, carbon reduction credits are an incentive mechanism designed to encourage the reduction of carbon emissions and promote environmental protection and sustainable development.

[0045] Preferably, inputting the driving load-road condition state significant interaction fusion representation vector into a decoder-based hydrogen consumption estimation module to obtain a reasonable hydrogen consumption estimation interval includes:

[0046] Based on the correlation value and distance value of the eigenvalue of the driving load-road condition state significant interaction fusion representation vector, a driving load-road condition state significant interaction fusion correlation response matrix and a driving load-road condition state significant interaction fusion distance response matrix are determined, namely:

[0047]

[0048] in , is the driving load-road condition state significant interaction fusion correlation response matrix, is the driving load-road condition state significant interaction fusion distance response matrix;

[0049] Performing matrix multiplication of the driving load-road condition state significant interaction fusion representation vector and the driving load-road condition state significant interaction fusion association response matrix to obtain a driving load-road condition state significant interaction fusion association response vector;

[0050] Matrix-multiplying the driving load-road condition state significant interaction fusion distance response matrix with the transposed vector of the driving load-road condition state significant interaction fusion representation vector to obtain a driving load-road condition state significant interaction fusion distance response vector;

[0051] After performing dot multiplication on the driving load-road condition state significant interaction fusion association response matrix and the driving load-road condition state significant interaction fusion distance response matrix, perform matrix multiplication on the transposed vector of the driving load-road condition state significant interaction fusion representation vector to obtain a data quality report-quality rule query logic bias vector;

[0052] The driving load-road condition state significant interaction fusion associated response vector, the driving load-road condition state significant interaction fusion distance response vector and the data quality report-quality rule query logic bias vector are added to obtain an optimized driving load-road condition state significant interaction fusion representation vector; and

[0053] The optimized driving load-road condition significant interaction fusion representation vector is input into a decoder-based hydrogen consumption estimation module to obtain a reasonable estimation interval of hydrogen consumption.

[0054] Here, the optimized driving load-road condition state significant interaction fusion representation vector It is expressed as:

[0055]

[0056] exist ,and In the case of:

[0057]

[0058]

[0059] in, is the driving load-road condition state significant interaction fusion representation vector, represents the transposed vector of the driving load-road condition state significant interaction fusion representation vector, is a response vector obtained by adding the driving load-road condition state significant interaction fusion associated response vector and the driving load-road condition state significant interaction fusion distance response vector. is the data quality report-quality rule query logic bias vector, represents the field of real numbers, Indicates point addition, represents matrix multiplication, represents dot product, It is the optimized driving load-road condition state significant interaction fusion representation vector.

[0060] That is, when the driving load cascade feature vector represents the joint coding features of vehicle mileage and cargo load, and the road condition fully connected coding vector represents the fully connected features of road condition data, when performing significant guided interaction between features with joint implicit features as conditional information, heterogeneous data and their corresponding coding mode differences will also cause the implicit conditional joint distribution to become sparse, resulting in large-scale simple repetitions based on significant guided interactions between features, affecting the semantic logical dependency of the interactive fusion and reducing the accuracy of the decoding results based on the semantic distribution.

[0061] Therefore, by using the self-correlation matrix and self-distance matrix of the driving load-road condition state significant interaction fusion representation vector as the statistical reference-free distribution response framework of the driving load-road condition state significant interaction fusion representation vector, the simple repetition of feature distribution is avoided based on the retrieval-enhanced reverse response construction of the driving load-road condition state significant interaction fusion representation vector, and the surface combination mapping is avoided by ensuring the intrinsic mapping logic of the driving load-road condition state significant interaction fusion representation vector based on the retrieval-response context, so as to achieve the logical dependency mapping of the driving load-road condition state significant interaction fusion representation vector to the decoding target domain while maintaining the intuitive response correlation, thereby improving the accuracy of the reasonable estimation interval of hydrogen consumption obtained by the driving load-road condition state significant interaction fusion representation vector input to the decoder-based hydrogen consumption estimation module. Furthermore, the actual extracted hydrogen consumption is compared with the reasonable estimation interval of hydrogen consumption to determine whether the hydrogen consumption is within the reasonable estimation interval of hydrogen consumption, so as to determine whether there is a risk of data tampering.

[0062] In particular, in S4, in response to the detection result that there is no risk of data tampering, the carbon reduction credits are calculated based on the carbon sink basic data. In a specific example, the weighted sum of each data in the carbon sink basic data is calculated, and the weighted weights of the vehicle mileage, hydrogen consumption, cargo load and road condition data are first calculated, and then the weighted sum is calculated to obtain the carbon reduction credits.

[0063] In summary, the carbon sink measurement and monitoring method based on blockchain according to the embodiment of the present application is explained, which processes the carbon sink basic data extracted from the blockchain network through an artificial intelligence-based data processing and analysis algorithm to extract the driving load characterization information between the vehicle mileage and the cargo load, and capture the road condition characterization information, and then use the significant interaction and fusion between the driving load characteristics and the road condition characteristics to generate a reasonable estimation interval of hydrogen consumption. Furthermore, the actual extracted hydrogen consumption is compared with the reasonable estimation interval of the hydrogen consumption to determine whether the hydrogen consumption is within the reasonable estimation interval of the hydrogen consumption, so as to determine whether there is a risk of data tampering. In this way, data anomaly detection can be performed on these carbon sink basic data in an automated manner, so as to calculate carbon reduction points when there is no abnormal carbon sink basic data. In this way, more intelligent carbon sink measurement and monitoring can be achieved, which helps to ensure the authenticity and integrity of carbon sink data, so that drivers can obtain carbon reduction points based on their carbon reduction performance in actual work.

[0064] Furthermore, a blockchain-based carbon sink measurement and monitoring system is also provided.

[0065] Figure 4FIG. 1 is a block diagram of a carbon sink measurement and monitoring system based on blockchain according to an embodiment of the present application. Figure 4 As shown, according to the blockchain-based carbon sink measurement and monitoring system 300 of the embodiment of the present application, it includes: a carbon sink basic data uploading module 310, which is used by the user to upload the carbon sink basic data to the blockchain network, wherein the carbon sink basic data includes vehicle mileage, hydrogen consumption, cargo load and road condition data; a carbon sink basic data extraction module 320, which is used to extract the carbon sink basic data from the blockchain network; a data anomaly detection module 330, which is used to perform data anomaly detection on the carbon sink basic data to obtain a detection result, and the detection result is used to indicate whether there is a risk of data tampering; a carbon reduction credit calculation module 340, which is used to calculate carbon reduction credits based on the carbon sink basic data in response to the detection result that there is no risk of data tampering.

[0066] As described above, the carbon sink measurement and monitoring system 300 based on blockchain according to the embodiment of the present application can be implemented in various wireless terminals, such as a server with a carbon sink measurement and monitoring algorithm based on blockchain. In one possible implementation, the carbon sink measurement and monitoring system 300 based on blockchain according to the embodiment of the present application can be integrated into the wireless terminal as a software module and / or a hardware module. For example, the carbon sink measurement and monitoring system 300 based on blockchain can be a software module in the operating system of the wireless terminal, or it can be an application developed for the wireless terminal; of course, the carbon sink measurement and monitoring system 300 based on blockchain can also be one of the many hardware modules of the wireless terminal.

[0067] Alternatively, in another example, the blockchain-based carbon sink measurement and monitoring system 300 and the wireless terminal may also be separate devices, and the blockchain-based carbon sink measurement and monitoring system 300 may be connected to the wireless terminal via a wired and / or wireless network and transmit interactive information in accordance with an agreed data format.

[0068] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A carbon sink measurement and monitoring method based on blockchain, characterized in that: include: The user uploads the basic carbon sink data to the blockchain network, wherein the basic carbon sink data includes vehicle mileage, hydrogen consumption, cargo load and road condition data; Extracting the carbon sink basic data from the blockchain network; Performing data anomaly detection on the carbon sink basic data to obtain a detection result, wherein the detection result is used to indicate whether there is a risk of data tampering; In response to the detection result indicating that there is no risk of data tampering, calculating carbon reduction credits based on the carbon sink basic data; Wherein, the carbon sink basic data is subjected to data anomaly detection to obtain a detection result, and the detection result is used to indicate whether there is a risk of data tampering, including: Embedding the vehicle mileage and the cargo load to obtain a vehicle mileage embedded coding vector and a cargo load embedded coding vector respectively; Cascading the vehicle mileage embedding coding vector and the cargo load embedding coding vector to obtain a cascaded driving load feature vector; Performing full-connection encoding on the road condition data to obtain a road condition full-connection encoding vector; The driving load cascade feature vector and the road condition fully connected coding vector are subjected to significant guided interactive fusion between features to obtain a driving load-road condition state significant interactive fusion representation, including: performing joint implicit feature analysis and activation processing on the driving load cascade feature vector and the road condition fully connected coding vector to obtain a driving load-road condition state condition feature; taking the driving load-road condition state condition feature as conditional information, performing feature interactive fusion on the driving load cascade feature vector and the road condition fully connected coding vector to obtain a driving load-road condition state significant interactive fusion representation; Determine a reasonable estimation interval of hydrogen consumption based on the significant interactive fusion representation of the driving load and road condition, and judge whether the hydrogen consumption is within the reasonable estimation interval of hydrogen consumption to determine whether there is a risk of data tampering; Among them, taking the driving load-road condition condition feature as condition information, performing feature interactive fusion on the driving load cascade feature vector and the road condition fully connected encoding vector to obtain the driving load-road condition state significant interactive fusion representation, including: Calculating the driving load contribution of the driving load cascade characteristic vector relative to the driving load-road condition state condition characteristic vector; Calculating the road condition state contribution of the road condition fully connected encoding vector relative to the driving load-road condition state condition feature vector; Normalizing the driving load contribution and the road condition contribution, and using the normalized driving load contribution and the normalized road condition contribution to perform weighted modulation on the driving load cascade feature vector and the road condition fully connected coding vector to obtain a modulated driving load cascade feature vector and a modulated road condition fully connected coding vector; Taking the modulated driving load cascade feature vector as the query vector, the modulated road condition fully connected coding vector as the key vector and the driving load-road condition state condition feature vector as the value vector, the modulated driving load cascade feature vector, the modulated road condition fully connected coding vector and the driving load-road condition state condition feature vector are input into a feature-to-feature significant guided interaction module based on a converter structure to obtain a driving load-road condition state significant interaction fusion representation vector as the driving load-road condition state significant interaction fusion representation.

2. The carbon sink measurement and monitoring method based on blockchain according to claim 1 is characterized in that: The vehicle mileage and the cargo load are respectively embedded and coded to obtain a vehicle mileage embedded coding vector and a cargo load embedded coding vector, including: Using a mileage embedding coding matrix to embed the vehicle mileage to obtain the vehicle mileage embedding coding vector; The cargo load weight is embedded and encoded using a cargo load embedding coding matrix to obtain the cargo load embedding coding vector.

3. The carbon sink measurement and monitoring method based on blockchain according to claim 2 is characterized in that: The road condition data is fully connected encoded to obtain a road condition fully connected encoding vector, including: using a road condition feature extractor based on a multi-layer perceptron model to fully connect the road condition data to obtain the road condition fully connected encoding vector.

4. The carbon sink measurement and monitoring method based on blockchain according to claim 3 is characterized in that: Performing joint implicit feature analysis and activation processing on the driving load cascade feature vector and the road condition fully connected encoding vector to obtain driving load-road condition state condition features, including: Inputting the driving load cascade feature vector and the road condition fully connected encoding vector into a joint implicit feature capture network to obtain a driving load-road condition state joint implicit feature vector; The driving load-road condition state joint implicit feature vector is subjected to feature activation based on a Sigmoid function to obtain a driving load-road condition state condition feature vector as the driving load-road condition state condition feature.

5. The blockchain-based carbon sink measurement and monitoring method according to claim 4 is characterized in that: Inputting the driving load cascade feature vector and the road condition fully connected encoding vector into a joint implicit feature capture network to obtain a driving load-road condition state joint implicit feature vector, including: After adding the driving load cascade feature vector and the road condition fully connected encoding vector by position point, the obtained driving load-road condition state sum vector is multiplied by the weight matrix and then added by position with the bias vector to obtain the driving load-road condition state joint interaction vector; The driving load-road condition state joint interaction vector is processed using a tanh function to obtain the driving load-road condition state joint implicit feature vector.

6. The blockchain-based carbon sink measurement and monitoring method according to claim 5 is characterized in that: Calculating the driving load contribution of the driving load cascade feature vector relative to the driving load-road condition state condition feature vector includes: Calculating the positional division of the driving load cascade feature vector and the driving load-road condition state condition feature vector to obtain a driving load contribution vector; Calculating a logarithmic function value with base 2 of the absolute value of each eigenvalue of the travel load contribution vector to obtain a travel load contribution logarithmic vector; Calculating the point product of the driving load cascade feature vector and the driving load contribution logarithm vector, and performing point-by-point multiplication on the obtained point product vector to obtain the driving load contribution value; An exponential function with the natural constant e as the base and the driving load contribution value as the exponent is calculated to obtain the driving load contribution degree.

7. The blockchain-based carbon sink measurement and monitoring method according to claim 6 is characterized in that: Based on the significant interactive fusion representation of the driving load and road condition, determining a reasonable estimation interval of hydrogen consumption, and judging whether the hydrogen consumption is within the reasonable estimation interval of hydrogen consumption to determine whether there is a risk of data tampering, including: Inputting the driving load-road condition state significant interaction fusion representation vector into a decoder-based hydrogen consumption estimation module to obtain a reasonable estimation interval of the hydrogen consumption; It is determined whether the hydrogen consumption is within the reasonable estimation range of the hydrogen consumption to determine whether there is a risk of data tampering.

8. A blockchain-based carbon sink measurement and monitoring system according to the blockchain-based carbon sink measurement and monitoring method according to claim 1, characterized in that: include: A carbon sink basic data uploading module is used for users to upload carbon sink basic data to the blockchain network, wherein the carbon sink basic data includes vehicle mileage, hydrogen consumption, cargo load and road condition data; A carbon sink basic data extraction module, used to extract the carbon sink basic data from the blockchain network; A data anomaly detection module, used to perform data anomaly detection on the carbon sink basic data to obtain a detection result, wherein the detection result is used to indicate whether there is a risk of data tampering; A carbon reduction credit calculation module is used to calculate carbon reduction credits based on the carbon sink basic data in response to the detection result indicating that there is no risk of data tampering.

Images