Carbon emission monitoring method and device based on block chain, equipment, medium and product
By constructing a space and time graph topology in the blockchain carbon emission monitoring method, and performing joint graph Fourier transformation and filtering, the problem of inaccurate judgment of carbon emission abnormalities in the existing technology is solved, and more efficient carbon emissions are achieved Abnormal monitoring.
Patent Information
- Application Number
- CN202411070424.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-05
- Publication Date
- 2024-11-22
AI Technical Summary
The existing blockchain-based carbon emission monitoring method only considers the spatial dimension and fails to effectively comprehensively consider the trend changes in corporate carbon emissions in time, resulting in the accuracy of judging abnormal carbon emissions.
By mapping the company's carbon emission signals to each vertex of the graph topology, a spatial graph topology structure and a time graph topology structure are constructed, a joint graph Fourier transform is performed, a graph low-pass filter is constructed, and carbon emissions are combined with the space-time graph topology structure. The signal is filtered to determine the companies with abnormal carbon emissions, and to store abnormal information through the blockchain.
The accuracy of carbon emission abnormality monitoring is improved, and by comprehensively considering changes in time and space dimensions, a more accurate judgment of carbon emission abnormality is achieved.
Smart Images

Figure CN119006008A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of carbon emissions, and in particular to a blockchain-based carbon emissions monitoring method, a blockchain-based carbon emissions monitoring device, a blockchain-based carbon emissions monitoring equipment, a storage medium, and a computer program product. Background Art
[0002] In the process of global industrialization and urbanization, carbon emissions continue to grow, leading to the intensification of environmental problems such as greenhouse effect, extreme weather and sea level rise, posing a threat to the ecosystem. Therefore, accurate monitoring and positioning of carbon emission anomalies are crucial for governments and companies to adopt effective emission reduction strategies. It not only helps companies understand whether their carbon emissions are abnormal, but also assists the government in more refined management and control, providing the necessary data support for the formulation of emission reduction strategies.
[0003] However, the existing blockchain-based carbon emission monitoring methods only consider feature extraction in the spatial dimension, and do not comprehensively consider the temporal trend changes of corporate carbon emissions, which leads to the low accuracy of judging carbon emission anomalies.
[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention
[0005] The main purpose of this application is to provide a blockchain-based carbon emission monitoring method, a blockchain-based carbon emission monitoring device, a blockchain-based carbon emission monitoring equipment, a storage medium and a computer program product, aiming to solve the technical problem of inaccurate abnormal carbon emission monitoring.
[0006] To achieve the above objectives, this application proposes a carbon emission monitoring method based on blockchain, the method comprising:
[0007] Mapping the carbon emission signal of the enterprise to each vertex of the graph topology to obtain the spatial graph topology structure and the temporal graph topology structure of the carbon emission signal;
[0008] By performing a joint graph Fourier transform of the spatial dimension and the temporal dimension on the carbon emission signal based on the spatial graph topology structure and the temporal graph topology structure, the carbon emission signal is mapped to a graph frequency domain, and a graph low-pass filter is constructed based on the carbon emission signal in the graph frequency domain;
[0009] Combining the spatial graph topology structure and the temporal graph topology structure to obtain a temporal-spatial graph topology structure of the carbon emission signal;
[0010] The carbon emission signal is filtered by the graph low-pass filter and the space-time graph topological structure, and enterprises with abnormal carbon emissions are determined based on the carbon emission signals before and after filtering, and the carbon emission anomaly information of the enterprises with abnormal carbon emissions is stored through blockchain.
[0011] In one embodiment, the spatial graph topology structure includes a spatial graph adjacency matrix, and the matrix elements represent the first correlation between the two enterprises in space; before the step of mapping the carbon emission signals of the enterprises to the vertices of the graph topology to obtain the spatial graph topology structure and the time graph topology structure of the carbon emission signals, the step includes:
[0012] Acquire the enterprise type and enterprise scale of the enterprise, and the weight factors of the enterprise type and the enterprise scale respectively affecting the first correlation;
[0013] The first correlation is calculated based on the enterprise type, the enterprise scale and the respective weight factors.
[0014] In one embodiment, the time graph topology structure includes a time graph adjacency matrix, and the matrix elements represent the second correlation between the two enterprises in time; before the step of mapping the carbon emission signals of the enterprises to each vertex of the graph topology to obtain the spatial graph topology structure and the time graph topology structure of the carbon emission signals, the step includes:
[0015] Obtain the number of enterprises and the number of time nodes for collecting carbon emission data, as well as the time interval between two consecutive carbon emission data collections;
[0016] The second correlation is calculated based on the number of enterprises, the number of time nodes, and the time interval.
[0017] In one embodiment, the step of determining the enterprise with abnormal carbon emissions according to the carbon emission signals before and after filtering includes:
[0018] Obtaining the total variation of the carbon emission signal before and after filtering, and calculating the total variation ratio of the carbon emission signal before and after filtering;
[0019] According to the comparison result of the total variation ratio of the graph and the judgment threshold, the enterprises with abnormal carbon emissions are determined.
[0020] In one embodiment, before the step of mapping the carbon emission signal of the enterprise to each vertex of the graph topology to obtain the spatial graph topology structure and the temporal graph topology structure of the carbon emission signal, the following steps are included:
[0021] Constructing an optimization problem; wherein the optimization problem is to maximize the accuracy of a decision threshold, and the decision threshold is used to determine enterprises with abnormal carbon emissions based on carbon emission signals before and after filtering;
[0022] By optimizing the optimization problem, the optimal solution of the target parameters in the blockchain-based carbon emission monitoring method is obtained; wherein the target parameters include the weight factors of the enterprise type and enterprise scale that affect the first spatial correlation between the two enterprises, the time interval between two adjacent carbon emission data collections, and the judgment threshold.
[0023] In one embodiment, the step of optimizing the optimization problem to obtain the optimal solution of the target parameters in the blockchain-based carbon emission monitoring method includes:
[0024] Initializing the target parameters in the blockchain-based carbon emission monitoring method, obtaining an initial solution to the optimization problem, and calculating the accuracy of the decision threshold under the initial solution;
[0025] Generate a temporary solution to the optimization problem through random perturbations, and calculate the accuracy of the decision threshold under the temporary solution and the accuracy increment of the current temporary solution;
[0026] If the accuracy increment is greater than zero, the provisional solution is received, and the number of times the optimal solution has not been updated is set to zero; if the accuracy increment is less than or equal to zero, the provisional solution is received according to a preset criterion, and the number of times the optimal solution has not been updated is incremented by one;
[0027] If the number of times the optimal solution has not been updated is less than the preset maximum number of times the optimal solution has not been updated, returning to the step of generating a temporary solution to the optimization problem by random perturbation until the number of times the optimal solution has not been updated is greater than or equal to the preset maximum number of times the optimal solution has not been updated;
[0028] If the number of times the optimal solution has not been updated is greater than or equal to the preset maximum number of times the non-optimal solution has not been updated, then when the current temperature is less than the termination temperature, the latest temporary solution is output as the optimal solution; when the current temperature is greater than or equal to the termination temperature, the number of times the optimal solution has not been updated is set to zero and the current temperature is lowered, and the process returns to the step of generating a temporary solution to the optimization problem through random perturbations.
[0029] In addition, to achieve the above purpose, the present application also proposes a blockchain-based carbon emission monitoring device, which includes:
[0030] A mapping module, used to map the carbon emission signal of the enterprise to each vertex of the graph topology to obtain the spatial graph topology structure and the temporal graph topology structure of the carbon emission signal;
[0031] A construction module, used to perform a joint graph Fourier transform of the spatial dimension and the temporal dimension on the carbon emission signal based on the spatial graph topology structure and the temporal graph topology structure, map the carbon emission signal to a graph frequency domain, and construct a graph low-pass filter based on the carbon emission signal in the graph frequency domain;
[0032] A combining module, used for combining the spatial graph topology structure and the temporal graph topology structure to obtain the temporal-spatial graph topology structure of the carbon emission signal and the temporal-spatial graph signal of the temporal-spatial graph topology structure;
[0033] The determination module is used to filter the carbon emission signal through the graph low-pass filter and the space-time graph topological structure, determine the enterprises with abnormal carbon emissions according to the carbon emission signals before and after filtering, and store the abnormal carbon emission information of the enterprises with abnormal carbon emissions through blockchain.
[0034] In addition, to achieve the above-mentioned objectives, the present application also proposes a blockchain-based carbon emission monitoring device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the blockchain-based carbon emission monitoring method as described above.
[0035] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the blockchain-based carbon emission monitoring method as described above are implemented.
[0036] In addition, to achieve the above-mentioned objectives, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the blockchain-based carbon emission monitoring method as described above.
[0037] One or more technical solutions proposed in this application have at least the following technical effects:
[0038] In this application, taking into account the trend changes in corporate carbon emissions over time, a new feature extraction of corporate carbon emissions over time is added, and the carbon emission signals of the enterprises are mapped to each vertex of the graph topology to obtain the spatial graph topology structure and the temporal graph topology structure of the carbon emission signals. The changes in carbon emissions in the time dimension and the spatial dimension are further considered comprehensively. Based on the spatial graph topology structure and the temporal graph topology structure, the carbon emission signal is subjected to a joint graph Fourier transform of the spatial dimension and the temporal dimension, and the carbon emission signal is mapped to the graph frequency domain. A graph low-pass filter is constructed based on the carbon emission signal in the graph frequency domain. At the same time, the spatial graph topology structure and the temporal graph topology structure are combined to obtain the spatiotemporal graph topology of the carbon emission signal. Finally, the spatiotemporal graph signal is filtered by the graph low-pass filter and the spatiotemporal graph topology structure. The enterprises with carbon emission anomalies are determined according to the spatiotemporal graph signals before and after filtering, and the carbon emission anomaly information of the enterprises with carbon emission anomalies is stored through the blockchain. Therefore, compared with the existing blockchain-based carbon emission monitoring method that only considers the spatial dimension, by comprehensively considering the trend changes in corporate carbon emissions in time and space, a comprehensive analysis from these two dimensions can be performed to more accurately determine carbon emission abnormal nodes and achieve accurate carbon emission abnormality monitoring. BRIEF DESCRIPTION OF THE DRAWINGS
[0039] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0041] Figure 1 A flowchart of the first embodiment of the carbon emission monitoring method based on blockchain provided in this application;
[0042] Figure 2 A schematic diagram of a system model provided for the first embodiment of the carbon emission monitoring method based on blockchain of this application;
[0043] Figure 3 A schematic diagram of the obfuscation model provided for Example 2 of the blockchain-based carbon emission monitoring method of this application;
[0044] Figure 4 A schematic diagram of the improved simulated annealing algorithm flow chart provided for the second embodiment of the blockchain-based carbon emission monitoring method of this application;
[0045] Figure 5 This is a schematic diagram of the module structure of a blockchain-based carbon emission monitoring device according to an embodiment of the present application;
[0046] Figure 6 This is a schematic diagram of the device structure of the hardware operating environment involved in the blockchain-based carbon emission monitoring method in the embodiment of the present application.
[0047] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0048] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.
[0049] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device that can realize the above functions.
[0050] Based on this, the present application embodiment provides a carbon emission monitoring method based on blockchain, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the blockchain-based carbon emission monitoring method of this application.
[0051] In this embodiment, the blockchain-based carbon emission monitoring method includes steps S10 to S30:
[0052] Step S10, mapping the carbon emission signal of the enterprise to each vertex of the graph topology to obtain the spatial graph topology structure and the temporal graph topology structure of the carbon emission signal;
[0053] In one embodiment, referring to Figure 2 , the system model is mainly divided into three layers: carbon emission data acquisition layer, information processing layer and data storage layer. It should be noted that in order to achieve green development, enterprises in cities usually show agglomeration characteristics, that is, there is a certain concentration trend in the spatial distribution of enterprises, and adjacent enterprises have similar corporate attributes. In the era of smart Internet of Things, the carbon emission data of each enterprise can be regarded as an interconnected network topology. This topology is composed of different enterprises in the city, not only for a certain type of enterprise, but can be applied to most enterprises. Therefore, for example, you can use Figure 2 The graph topology shown is used to describe the carbon emission data of enterprises in the city.
[0054] In one embodiment, each enterprise in the city collects raw data through sensors, and combines the industry carbon emission factor library and energy consumption conversion system library to pre-process the raw data to obtain standardized carbon emission data, thereby avoiding the problems of inaccurate and high cost of manual data collection. i(i=1, 2, ..., N) at time h (j=1, 2, ..., M) the pre-processed carbon emission data is X i,j , combining the carbon emission data of each enterprise, the carbon emission signal is expressed as X∈R N×M In this matrix, the number of rows N represents the number of enterprises, and the number of columns M represents the number of time nodes for collecting carbon emission data.
[0055] In a feasible implementation manner, the spatial graph topological structure includes a spatial graph adjacency matrix, and the matrix elements represent the first spatial correlation between the two enterprises; before step S10, the following steps are included:
[0056] Acquire the enterprise type and enterprise scale of the enterprise, and the weight factors of the enterprise type and the enterprise scale respectively affecting the first correlation;
[0057] The first correlation is calculated based on the enterprise type, the enterprise scale and the respective weight factors.
[0058] In one embodiment, if Figure 2 As shown, the obtained carbon emission signal X is mapped to each vertex of the graph topology, vertex v i On behalf of the enterprise, s =(v0, v1, ..., v N-1 ) T Represents a set of vertices, and the value on the vertex represents the carbon emission data generated at a certain moment. m and v n The weight between Indicates the strength of correlation between two vertices. A large weight means a strong correlation between the two vertices, that is, the stronger the correlation between the enterprises. The carbon emission data of two enterprises with strong correlation are often similar. If the carbon emission data gap is large, it indicates that there is abnormal data. In this way, the spatial distribution characteristics of enterprises are used to capture whether the carbon emission signal is abnormal.
[0059] It should be noted that the correlation between enterprises can be defined according to the type and size of the enterprise. The type of enterprise reflects the business field or industry that the enterprise is mainly engaged in. In one embodiment, in order to clearly describe the type of enterprise, the enterprise v i The type is denoted as b i =[b i,1 , b i,2 , ..., b i,n ] T , where element b i,θ (θ=1,2,...,n) indicates whether the enterprise belongs to the θ type, b i,θ =1 means it belongs to θ type, b i,θ = 0, it does not belong to the θ type. For example: Enterprise vi The type is represented as [1, 0, 1, 0, 1] T , which means it is engaged in business of categories 1, 3 and 5; in addition, enterprise v i The scale of express.
[0060] In one embodiment, for the carbon emission signal X, only its spatial dimension is concerned and the time is fixed, which can be expressed as signal s=(s0, s1, ..., s N-1 ) T = X[:, M], using the spatial graph topology G s =(v s , E s , A s ) represents the signal s, where v s =(v0, v1, ..., V N-1 ) T The vertex set representing the graph signal, each vertex represents an enterprise, and the vertex value represents the carbon emission signal value of each enterprise; the edges between vertices reflect the correlation between enterprises. A represents a set of edges. In one embodiment, if there is an edge between two vertices, the element is represented by 1, and if there is no edge between two vertices, the element is represented by 0; A s (A s ∈R N×N ) represents the spatial graph adjacency matrix, whose elements Represents the vertex V m and v n The first correlation between , is defined as:
[0061]
[0062] Among them, L m,n The size of L affects the correlation between vertices. m,n The larger the value, the greater the gap between enterprises and the smaller the correlation, which can be calculated based on the vertex v m and v n It is defined by the type and size of the representative enterprise and is expressed as:
[0063]
[0064] Among them, the weight factors of the impact of enterprise type and scale on correlation are expressed as α and β respectively.
[0065] In a feasible implementation manner, the time graph topology structure includes a time graph adjacency matrix, and the matrix elements represent the second correlation between the two enterprises in time; before step S10, it includes:
[0066] Obtain the number of enterprises and the number of time nodes for collecting carbon emission data, as well as the time interval between two consecutive carbon emission data collections;
[0067] The second correlation is calculated based on the number of enterprises, the number of time nodes, and the time interval.
[0068] In one embodiment, for the carbon emission signal X, only its time dimension is concerned, and the enterprise is fixed, which can be expressed as signal t=(t0, t1, ..., t M-1 ) T = X[N,:], the signal is passed through the time graph topology G t =(v t , E t , A t ) represents. Since the carbon emissions of enterprises change over time, the carbon emission data generated at similar times are similar. Therefore, the time when the carbon emission data of each enterprise is collected is taken as the vertex, and the interval time of data collection is set to τ. t (A t ∈R M×M ) represents the time graph adjacency matrix, whose elements Represents the time vertex p m and p n The correlation between adjacent time vertices is greater, It is expressed as:
[0069]
[0070] Among them, the time interval τ between two adjacent data collections affects the correlation between time vertices.
[0071] Step S20, performing a joint graph Fourier transform of the spatial dimension and the temporal dimension on the carbon emission signal based on the spatial graph topology structure and the temporal graph topology structure, mapping the carbon emission signal to a graph frequency domain, and constructing a graph low-pass filter based on the carbon emission signal in the graph frequency domain;
[0072] At present, the existing anomaly determination methods based on graph representation learning use nonlinear calculations to extract features from spatial information, which requires a lot of computing resources to complete feature extraction and anomaly determination, and the algorithm has low scalability.
[0073] In this embodiment, a joint graph Fourier transform is used for linear calculation to extract features from two dimensions. Compared with nonlinear calculations in graph representation learning, it consumes less computing resources and has stronger scalability. Specifically, the graph signal processing technology is used to process the carbon emission signal, and the carbon emission signal is mapped to the graph frequency domain through the joint graph Fourier transform, and a graph low-pass filter is constructed. Subsequently, the filtered signal and the original signal are calculated for abnormality determination.
[0074] In one embodiment, a filter is constructed to filter the space-time graph signal. Since the graph Laplacian matrix has symmetric semi-positive definiteness, matrix inversion can be avoided when performing joint graph Fourier transform, reducing the computational complexity. For the spatial graph topology structure, its degree matrix D s The m-th row element of is equal to the sum of the weights of all edges connected to vertex m. According to the degree matrix and the spatial graph adjacency matrix, the graph Laplacian matrix can be obtained as:
[0075] L s =D s -A s
[0076] Definition G t The degree matrix is D t , according to D t And the time graph adjacency matrix can get the graph Laplacian matrix as:
[0077] L t =D t -A t
[0078] When performing JGFT (Joint Graph Fourier Transform), since the graph Laplace matrix has symmetric semi-positive definiteness, the graph Laplace matrix is eigen-decomposed to obtain the basis of the graph Fourier transform so that the graph signal processing can be performed more efficiently. The spatial graph Laplace matrix L s It can be expressed as L s =U s AU s T , where A s =diag(λ s1 ,λ s1 , ..., λ sN-1 ) is the matrix L s Eigenvalue diagonal matrix, U s is a standard orthogonal matrix, and its columns are eigenvectors. Similarly, the time graph Laplacian matrix L t It can be expressed as L t =U t AU t T . Graph Fourier transform is used in both dimensions, using U s and U t As the graph Fourier transform basis of spatial and temporal dimensions, the carbon emission signal X∈R N ×M Mapped to the frequency domain, it is expressed as:
[0079]
[0080] In the blockchain-based carbon emission monitoring method, the cutoff frequency λ in the spatial and temporal dimensions is cs and λ ct Set it as the median bandwidth after Fourier transforming the graph to the frequency domain in two dimensions, and then construct the graph low-pass filter h LP (λ s ,λ t ), in order to filter out abnormal high-frequency components, which can be specifically expressed as:
[0081]
[0082] It should be noted that, in the image frequency domain, filtering an image signal is equivalent to multiplying the spectrum of the signal by the frequency response of the filter.
[0083] Step S30, combining the spatial graph topology structure and the temporal graph topology structure to obtain a temporal-spatial graph topology structure of the carbon emission signal;
[0084] In one embodiment, the spatial graph topology structure G constructed on the spatial and temporal dimensions of the carbon emission signal s and the temporal graph topology G t , these two topologies are combined using the Kronecker product to form a joint space-time graph topology.
[0085] That is to say, first, we define enterprise similarity according to enterprise type and scale, take an enterprise as a vertex, and construct a graph topology structure in the spatial dimension in the vertex domain. At the same time, because the carbon emission data generated by enterprises at similar times are similar and change with time trends, we take the time node as a vertex to construct a graph topology structure in the time dimension. On this basis, we construct a joint time-space graph topology structure through the Kronecker product.
[0086] Step S40, filtering the carbon emission signal through the graph low-pass filter and the space-time graph topological structure, determining the enterprises with abnormal carbon emissions according to the carbon emission signals before and after filtering, and storing the abnormal carbon emission information of the enterprises with abnormal carbon emissions through blockchain.
[0087] In one embodiment, referring to Figure 2 In order to analyze the carbon emission data of each enterprise X i,j Is there an abnormality? i,j , spatial graph Laplacian matrix L s and the time graph Laplacian matrix L t Passed to the information processing layer.
[0088] In one embodiment, the carbon emission data X of each enterprise obtained from the carbon emission data acquisition layer i,j , first through the consensus mechanism to make all nodes agree on whether the data is valid. Then, combined with the trusted computing environment in privacy computing, the off-chain deployment of abnormal monitoring methods, the calculation process is migrated to the off-chain, the pressure of on-chain calculation is alleviated, and data privacy security is guaranteed. In this secure environment, the carbon emission signal X composed of each enterprise is jointly Fourier transformed, mapped to the frequency domain to obtain the cutoff frequency, and the low-pass filter is designed.
[0089] It should be noted that the carbon emission data of each enterprise is obtained i,j After that, the enterprise node will broadcast the encrypted carbon emission data to other nodes for consensus verification. The main problem solved by the consensus mechanism is to make all nodes agree on whether the data is valid, and finally make the ledger of each node consistent. In one embodiment, first, a bookkeeping node is selected from the blockchain node, and the node is responsible for the packaging of carbon emission data; then, the block verification work is performed, and the blockchain nodes need to reach consistency of block verification results based on the consensus algorithm. At present, the commonly used consensus mechanisms mainly include PoW, PoS, DPoS and PBFT algorithms. Among them, the PoW algorithm has high energy consumption and contains many meaningless calculations, which is inconsistent with the dual carbon concept. The PoS algorithm may lead to the concentration of power and the formation of an oligarchy. Malicious nodes in the DPoS algorithm are likely to be elected as consensus nodes, which are not suitable for use in abnormal monitoring of corporate carbon emissions.
[0090] In order to ensure the security of the data consensus process and the consistency of the node consensus in the blockchain network, in one embodiment, the PBFT consensus mechanism is selected. The principle of this algorithm is based on the solution idea of the Byzantine Generals Problem, and a consistent consensus result is reached through mutual communication and collaboration between multiple nodes. It can ensure that a consistent consensus result can still be reached in the presence of a maximum of f malicious nodes.
[0091] In one embodiment, the carbon emission data confirmed by the consensus mechanism uses the constructed time-space graph topology structure (i.e., the joint time-space graph topology structure constructed in the carbon emission data acquisition layer) to characterize its relationship in the spatial and temporal dimensions, and uses graph signal processing technology for analysis and anomaly judgment.
[0092] In one embodiment, referring to Figure 2In order to ease the computing pressure on the chain and ensure data security, an on-chain and off-chain collaborative approach is adopted. Anomaly monitoring methods are deployed in the off-chain trusted computing environment to perform data calculation and analysis to ensure that the decryption and calculation of carbon emission data will be in a secure and trusted execution environment. The hardware security chip is used as the root of trust. The calculation process cannot be peeped or interfered by any party, and privacy security is guaranteed during the data flow, using the respective characteristics of the on-chain and off-chain to provide double protection for the data.
[0093] In one embodiment, a consortium chain is used to store data of enterprises with abnormal carbon emissions. Compared with public and private chains, participants in the consortium chain are certified enterprises or organizations, and data privacy is more secure. Due to the limited number of participants, the network stability of the consortium chain is higher, the transaction speed is faster, and it is more stable and reliable than the public chain. The administrator of the consortium chain can manage participants according to actual conditions, such as joining, exiting, and authority control, etc., with higher flexibility. In addition, participants in the consortium chain jointly maintain the chain without additional fees, which is lower cost than private chains.
[0094] In a feasible implementation manner, the step S40 includes:
[0095] Obtaining the total variation of the carbon emission signal before and after filtering, and calculating the total variation ratio of the carbon emission signal before and after filtering;
[0096] According to the comparison result of the total variation ratio of the graph and the judgment threshold, the enterprises with abnormal carbon emissions are determined.
[0097] If the carbon emission signal X (also called space-time graph signal because it is represented by a time-space graph topological structure) has an abnormality, the total variation of the filtered graph is much different from the original signal because the abnormal components are filtered out, thereby constructing the abnormal node judgment criterion.
[0098] In one embodiment, the space-time graph signal X is processed by a designed graph low-pass filter, and the space-time graph signal after filtering by the graph low-pass filter is obtained as follows:
[0099]
[0100] Where x is the vectorized representation of the spatiotemporal graph signal X, and U J It's U s with U t The Kronecker product of the carbon emission signal is obtained by combining the spatial graph topology and the temporal graph topology. LP (A s , A t ) is a NM×NM diagonal matrix, which is specifically defined as:
[0101]
[0102] According to the definition of total variation in image signal processing, the total variation of the filtered signal can be expressed as:
[0103]
[0104] Among them, X LP For x LP In matrix form, represents the first-order difference operator, vec(·) represents vectorization, and ||·||1 represents the 1-normal form. The size of the total variation of the graph is affected by the weight factors of enterprise type and scale and the time interval for obtaining carbon emission data. When the total variation of the graph is large, it means that the graph signals of adjacent nodes are significantly different; when the total variation of the graph is small, it means that the graph signals are closer.
[0105] After the space-time graph signal passes through the graph low-pass filter, under normal circumstances, the signal values of adjacent nodes in two dimensions are similar, and after transformation to the graph frequency domain, they are mainly distributed in the low-frequency area. Therefore, in the absence of abnormal nodes, the space-time graph signal before and after filtering is basically consistent. When there are abnormal nodes, data mutations will occur in the time and space dimensions, and high-frequency components will appear after the space-time graph is transformed into the graph frequency domain. When there are abnormal nodes, the graph low-pass filter will filter out the high-frequency components caused by these abnormalities, and the total variation value of the signal after filtering will change.
[0106] According to the above discussion, the total variation ratio of the space-time graph signal after filtering and the total variation ratio of the original space-time graph signal is calculated. If there is no abnormal node, the difference between the space-time graph signal before and after filtering is not large, and the ratio tends to 1. On the contrary, if the ratio is lower than the set judgment threshold, it indicates that there are abnormal components and a large change has occurred after filtering, so the abnormal judgment criterion is constructed:
[0107]
[0108] Among them, H0 represents the presence of abnormal nodes, H1 represents the absence of abnormal nodes, γ th is the decision threshold.
[0109] In one embodiment, if there is an abnormal node in carbon emission data, the space-time graph signal x after being filtered by the graph low-pass filter is LP Convert to matrix X LP , using the difference analysis method to the matrix X LP Compare with the original carbon emission signal X to find the specific enterprises with abnormal carbon emission data. The ID of the enterprise with abnormal carbon emission, the specific time when the abnormality occurred, and the abnormal carbon emission amount are recorded as the calculation results. In order to enhance the verifiability of the results, a specific verification mark is also generated, and the encrypted calculation results and verification mark are returned to the smart contract.
[0110] Currently, in the blockchain network, smart contracts need to be executed on each node, but the on-chain resources are limited, which means that the execution logic of smart contracts cannot be too complicated.
[0111] In one embodiment, referring to Figure 2 , the smart contract can decrypt the ciphertext, obtain the calculation results and verification marks returned from the trusted computing environment, and first verify the results. If the verification passes and there are abnormalities, the smart contract will store the abnormalities, that is, the ID of the company with abnormal carbon emissions, the specific time when the abnormality occurred, and the abnormal carbon emissions on the chain to ensure that the data cannot be tampered with.
[0112] In one embodiment, referring to Figure 2 When an enterprise with abnormal carbon emissions is detected, it will be updated in the storage chain node by the smart contract to prevent tampering. This process requires recording the enterprise ID, the time when the abnormality occurred, and the abnormal carbon emissions. The government can check which enterprises in the city have abnormal carbon emissions, so as to carry out effective management, and also provide a reliable basis for carbon emission traceability. At the same time, enterprises can understand in which periods of time they have abnormal carbon emissions, which helps to find out the problem and formulate corresponding emission reduction strategies.
[0113] The above combines blockchain with the trusted computing environment in privacy computing, transfers complex calculations on the chain to the off-chain, and makes up for the problem of insufficient resources on the chain. The subject information is recorded on the chain to ensure traceability, while the trusted computing environment provides privacy protection in data flow and a secure carbon emission data analysis computing environment, which is used to determine companies with abnormal carbon emissions and avoid data privacy leaks.
[0114] As described above, in this embodiment, the temporal trend of the carbon emission signal and the correlation between enterprises are comprehensively considered, and the abnormal situation is analyzed and judged in two dimensions, which has a higher accuracy rate than considering only the spatial dimension.
[0115] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. On this basis, before the step S10, it includes:
[0116] Constructing an optimization problem; wherein the optimization problem is to maximize the accuracy of a decision threshold, and the decision threshold is used to determine enterprises with abnormal carbon emissions based on carbon emission signals before and after filtering;
[0117] By optimizing the optimization problem, the optimal solution of the target parameters in the blockchain-based carbon emission monitoring method is obtained; wherein the target parameters include the weight factors of the enterprise type and enterprise scale that affect the first spatial correlation between the two enterprises, the time interval between two adjacent carbon emission data collections, and the judgment threshold.
[0118] It should be noted that there are unknown parameters in the graph topology structure constructed in the carbon emission data acquisition layer. In order to adapt to unknown data sets and improve the judgment accuracy, in this embodiment, the simulated annealing algorithm is improved to solve the topological structure and decision threshold of the optimized graph signal, and solve the optimal time-space graph topology structure to be suitable for most enterprises.
[0119] In one embodiment, with the improvement of accuracy as the optimization goal, the weight factors, time intervals and decision thresholds of enterprise types and sizes in constructing the time-space graph topology structure are optimized to improve the adaptability of the time-space graph signal topology structure so as to more accurately determine abnormal nodes.
[0120] In one embodiment, in order to improve the accuracy of carbon emission anomaly determination, the determination threshold is optimized. First, sample statistics are performed on the carbon emission signals of enterprises with and without abnormal nodes, and the total variation ratio η of the filtered spatiotemporal graph signal and the original signal is calculated, where the largest ratio is recorded as η max , the minimum ratio is denoted as η min Then, η min and η max Set as the selection interval of the decision threshold. Finally, according to the current decision threshold, abnormal nodes are determined and the sample data is classified to obtain the confusion matrix, whose structure is as follows: Figure 3 shown.
[0121] From the confusion matrix, classification indicators can be obtained, including at least precision and accuracy. Precision is used to indicate the accuracy of the model, that is, the total number of samples identified correctly, expressed as (TP+TN) / (TP+FN+FP+TN). Accuracy indicates the proportion of samples that are truly positive among the samples identified as positive, which is expressed as TP / (TP+FP). Precision is an overall evaluation indicator, while accuracy is an evaluation indicator predicted for a certain category. In this embodiment, the category of observation is judged to be abnormal, so the accuracy is used for evaluation, which is defined as the proportion of truly abnormal samples among the samples judged to be abnormal, expressed as:
[0122]
[0123] Since there are unknown parameters when constructing the time-space graph topology, in order to adapt to unknown data sets and strengthen the accurate judgment of carbon emission anomalies of different types of enterprises, the optimization goal is to improve the accuracy, find the optimal solution of γ, α, β, τ, and improve the adaptability of the constructed time-space graph topology structure and the accurate judgment of anomalies. The optimization problem and constraints are constructed as follows:
[0124]
[0125] st.η min ≤γ≤η max
[0126] α, β, τ>0
[0127] In this way, the optimal solution of the optimization problem is obtained under the constraints.
[0128] In a feasible implementation, the step of optimizing the optimization problem to obtain the optimal solution of the target parameters in the blockchain-based carbon emission monitoring method includes:
[0129] Initializing the target parameters in the blockchain-based carbon emission monitoring method, obtaining an initial solution to the optimization problem, and calculating the accuracy of the decision threshold under the initial solution;
[0130] Generate a temporary solution to the optimization problem through random perturbations, and calculate the accuracy of the decision threshold under the temporary solution and the accuracy increment of the current temporary solution;
[0131] If the accuracy increment is greater than zero, the provisional solution is received, and the number of times the optimal solution has not been updated is set to zero; if the accuracy increment is less than or equal to zero, the provisional solution is received according to a preset criterion, and the number of times the optimal solution has not been updated is incremented by one;
[0132] If the number of times the optimal solution has not been updated is less than the preset maximum number of times the optimal solution has not been updated, returning to the step of generating a temporary solution to the optimization problem by random perturbation until the number of times the optimal solution has not been updated is greater than or equal to the preset maximum number of times the optimal solution has not been updated;
[0133] If the number of times the optimal solution has not been updated is greater than or equal to the preset maximum number of times the non-optimal solution has not been updated, then when the current temperature is less than the termination temperature, the latest temporary solution is output as the optimal solution; when the current temperature is greater than or equal to the termination temperature, the number of times the optimal solution has not been updated is set to zero and the current temperature is lowered, and the process returns to the step of generating a temporary solution to the optimization problem through random perturbations.
[0134] It should be noted that this optimization is a multivariable optimization problem, and there may be a local optimal solution, so the simulated annealing algorithm is used to solve it. However, when solving multivariable optimization problems, the algorithm converges slowly and takes a long time to get the optimal solution. In order to improve the solution efficiency, it has been improved. The improved algorithm dynamically adjusts the number of internal loops. When the optimal solution is no longer updated for a certain number of times, it is determined to be a local optimal solution and jumps out of the loop, thereby speeding up the iteration rate of the algorithm. For details of the process, see Figure 4 The specific description is as follows:
[0135] Step 1: Initialize the judgment threshold γ0, the weight factors α0, β0 of enterprise type and scale, and the carbon emission collection time interval τ0 to form the initial solution c0, and initialize the optimal solution unupdated times num = 0. Calculate the accuracy corresponding to the initial solution Set the starting temperature T0 and the ending temperature T f and the maximum number of times no better solution is generated k max ; The number of inner and outer loop iterations is represented by i and k, both of which are currently 0.
[0136] Step 2: Under the constraints, i Generate a new solution c by random perturbation j , that is, the temporary solution, calculate the corresponding accuracy And calculate the increment of accuracy
[0137] Step 3: If the increment is greater than 0, accept the current new solution and set c i =c j , num=0. Otherwise, execute num=num+1 and generate a random number ξ=rand(0,1). Then accept the current new solution and update it to c i =c j , otherwise the original solution remains unchanged; this way, the current solution can be accepted with a certain probability, and there is a chance to jump out when trapped in a local optimal solution, which helps to obtain the global optimal solution. It should be noted that the preset criterion for accepting the temporary solution in step 3 can be the Metropolis acceptance criterion.
[0138] Step 4: Record the current optimal solution as c*=c i ;
[0139] Step 5: If the current optimal solution has not been updated for times num<k max , turn to step 2 and enter the inner loop for further optimization; otherwise, turn to step 6. This can effectively control the number of iterations of the inner loop and improve the iteration rate.
[0140] Step 6: Determine whether the stop condition T is met k <Tf If satisfied, output the optimal solution c*, if not satisfied, reset the optimal solution unupdated times, and adjust the temperature to gradually reduce T k =εT k-1 (0<ε<11, then go to step 2 to continue optimization.
[0141] Above, the optimal decision threshold γ is obtained according to the improved simulated annealing algorithm. th , and the weight factor α of enterprise type and scale * , β * , and the time interval τ for collecting corporate carbon emissions * After that, a universal joint time-space graph topology can be constructed. In a trusted computing environment, the time-space graph topology is used to represent the carbon emission signal X, and the graph signal processing technology is used to perform anomaly analysis and judgment. If an anomaly exists, the anomaly point is further located.
[0142] Currently, the existing expression of graph signals is a priori known graph topology. For unknown data sets, the graph topology may need to be redesigned, which lacks flexibility and is difficult to adapt to complex practical application scenarios.
[0143] In this embodiment, the graph topology and decision threshold are optimized to be applicable to unknown data sets. Compared with thresholds set based on a priori known graph topology and human experience, this method is more flexible and accurate in practical applications.
[0144] In this embodiment, first, the graph signal topology and decision threshold are optimized to improve the adaptability of the graph topology so that it is applicable to most enterprises and the accurate judgment of abnormal nodes is strengthened. The accuracy in the confusion matrix is used as an evaluation index, and the accuracy is improved as the optimization goal to optimize the weight factors, time intervals and decision thresholds of the enterprise type and scale in the construction of the time-space graph topology. Secondly, when solving multivariable optimization problems, the traditional simulated annealing algorithm converges slowly and takes a long time to obtain the optimal solution. In order to improve the solution efficiency, it is improved to dynamically adjust the number of iterations of the inner loop to find the global optimal solution faster.
[0145] Reference Figure 2, this application proposes a method for monitoring anomalies in carbon emission graph signals based on blockchain and privacy computing. First, the type, scale and carbon emission data of each enterprise in the city are obtained, and the graph topology structure in space and time is constructed, and the Kronecker product is used to design a joint time-space graph topology structure for graph signal processing. To ensure data privacy and security, an anomaly monitoring and positioning method is deployed in a trusted computing environment. Then, the space-time graph signal is transformed into the graph frequency domain by a joint graph Fourier transform, and the cutoff frequency is obtained to design a graph low-pass filter. Secondly, the simulated annealing algorithm is improved to solve the optimized time-space graph topology structure and the decision threshold; finally, the total variation ratio and decision threshold of the filtered signal and the original carbon emission signal are compared to determine whether there is an abnormal node. If there is an anomaly, locate it, determine the abnormal carbon emission enterprise, and store the relevant information on the chain to provide data basis for the government and enterprises, and help formulate emission reduction measures.
[0146] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the blockchain-based carbon emission monitoring method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.
[0147] This application also provides a blockchain-based carbon emission monitoring device, please refer to Figure 5 , the blockchain-based carbon emission monitoring device includes:
[0148] A mapping module 10 is used to map the carbon emission signal of the enterprise to each vertex of the graph topology to obtain a spatial graph topology structure and a temporal graph topology structure of the carbon emission signal;
[0149] A construction module 20 is used to perform a joint graph Fourier transform of the spatial dimension and the temporal dimension on the carbon emission signal based on the spatial graph topology structure and the temporal graph topology structure, map the carbon emission signal to a graph frequency domain, and construct a graph low-pass filter based on the carbon emission signal in the graph frequency domain;
[0150] A combining module 30, configured to combine the spatial graph topology structure and the temporal graph topology structure to obtain the temporal-spatial graph topology structure of the carbon emission signal and the temporal-spatial graph signal of the temporal-spatial graph topology structure;
[0151] The determination module 40 is used to filter the carbon emission signal through the graph low-pass filter and the space-time graph topological structure, determine the enterprises with abnormal carbon emissions according to the carbon emission signals before and after filtering, and store the abnormal carbon emission information of the enterprises with abnormal carbon emissions through blockchain.
[0152] In one embodiment, the spatial graph topology structure includes a spatial graph adjacency matrix, and the matrix elements represent the first correlation between the two enterprises in space; the mapping module is further used for:
[0153] Before the step of mapping the carbon emission signal of the enterprise to each vertex of the graph topology to obtain the spatial graph topology structure and the temporal graph topology structure of the carbon emission signal,
[0154] Acquire the enterprise type and enterprise scale of the enterprise, and the weight factors of the enterprise type and the enterprise scale respectively affecting the first correlation;
[0155] The first correlation is calculated based on the enterprise type, the enterprise scale and the respective weight factors.
[0156] In one embodiment, the time graph topology structure includes a time graph adjacency matrix, and the matrix elements represent the second correlation between the two enterprises in time; the mapping module is further used to:
[0157] Before the step of mapping the carbon emission signal of the enterprise to each vertex of the graph topology to obtain the spatial graph topology structure and the temporal graph topology structure of the carbon emission signal,
[0158] Obtain the number of enterprises and the number of time nodes for collecting carbon emission data, as well as the time interval between two consecutive carbon emission data collections;
[0159] The second correlation is calculated based on the number of enterprises, the number of time nodes, and the time interval.
[0160] In one embodiment, the determining module is further configured to:
[0161] Obtaining the total variation of the carbon emission signal before and after filtering, and calculating the total variation ratio of the carbon emission signal before and after filtering;
[0162] According to the comparison result of the total variation ratio of the graph and the judgment threshold, the enterprises with abnormal carbon emissions are determined.
[0163] In one embodiment, the device includes an optimization module, which is used before the step of mapping the carbon emission signal of the enterprise to each vertex of the graph topology to obtain the spatial graph topology structure and the temporal graph topology structure of the carbon emission signal:
[0164] Constructing an optimization problem; wherein the optimization problem is to maximize the accuracy of a decision threshold, and the decision threshold is used to determine enterprises with abnormal carbon emissions based on carbon emission signals before and after filtering;
[0165] By optimizing the optimization problem, the optimal solution of the target parameters in the blockchain-based carbon emission monitoring method is obtained; wherein the target parameters include the weight factors of the enterprise type and enterprise scale that affect the first spatial correlation between the two enterprises, the time interval between two adjacent carbon emission data collections, and the judgment threshold.
[0166] In one embodiment, the optimization module is further used to:
[0167] Initializing the target parameters in the blockchain-based carbon emission monitoring method, obtaining an initial solution to the optimization problem, and calculating the accuracy of the decision threshold under the initial solution;
[0168] Generate a temporary solution to the optimization problem through random perturbations, and calculate the accuracy of the decision threshold under the temporary solution and the accuracy increment of the current temporary solution;
[0169] If the accuracy increment is greater than zero, the provisional solution is received, and the number of times the optimal solution has not been updated is set to zero; if the accuracy increment is less than or equal to zero, the provisional solution is received according to a preset criterion, and the number of times the optimal solution has not been updated is incremented by one;
[0170] If the number of times the optimal solution has not been updated is less than the preset maximum number of times the optimal solution has not been updated, returning to the step of generating a temporary solution to the optimization problem by random perturbation until the number of times the optimal solution has not been updated is greater than or equal to the preset maximum number of times the optimal solution has not been updated;
[0171] If the number of times the optimal solution has not been updated is greater than or equal to the preset maximum number of times the non-optimal solution has not been updated, then when the current temperature is less than the termination temperature, the latest temporary solution is output as the optimal solution; when the current temperature is greater than or equal to the termination temperature, the number of times the optimal solution has not been updated is set to zero and the current temperature is lowered, and the process returns to the step of generating a temporary solution to the optimization problem through random perturbations.
[0172] The blockchain-based carbon emission monitoring device provided by this application adopts the blockchain-based carbon emission monitoring method in the above embodiment, which can solve the technical problem of inaccurate monitoring of abnormal carbon emissions. Compared with the prior art, the beneficial effects of the blockchain-based carbon emission monitoring device provided by this application are the same as the beneficial effects of the blockchain-based carbon emission monitoring method provided by the above embodiment, and the other technical features of the blockchain-based carbon emission monitoring device are the same as the features disclosed in the above embodiment method, which will not be repeated here.
[0173] The present application provides a blockchain-based carbon emission monitoring device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the blockchain-based carbon emission monitoring method in the above-mentioned embodiment one.
[0174] Reference below Figure 6 , which shows a schematic diagram of the structure of a blockchain-based carbon emission monitoring device suitable for implementing the embodiment of the present application. The blockchain-based carbon emission monitoring device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The blockchain-based carbon emission monitoring device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present application.
[0175] like Figure 6As shown, the carbon emission monitoring device based on blockchain may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM: Read Only Memory) 1002 or the program loaded from the storage device 1003 to the random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the carbon emission monitoring device based on blockchain are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. The input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the blockchain-based carbon emission monitoring device to communicate wirelessly or wired with other devices to exchange data. Although the blockchain-based carbon emission monitoring device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or provided alternatively.
[0176] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.
[0177] The blockchain-based carbon emission monitoring device provided by this application adopts the blockchain-based carbon emission monitoring method in the above embodiment, which can solve the technical problem of inaccurate abnormal carbon emission monitoring. Compared with the prior art, the beneficial effects of the blockchain-based carbon emission monitoring device provided by this application are the same as the beneficial effects of the blockchain-based carbon emission monitoring method provided by the above embodiment, and the other technical features of the blockchain-based carbon emission monitoring device are the same as the features disclosed in the previous embodiment method, which will not be repeated here.
[0178] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.
[0179] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
[0180] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the blockchain-based carbon emission monitoring method in the above-mentioned embodiment.
[0181] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.
[0182] The above-mentioned computer-readable storage medium may be included in the blockchain-based carbon emission monitoring device; or it may exist independently without being assembled into the blockchain-based carbon emission monitoring device.
[0183] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the blockchain-based carbon emission monitoring device, the blockchain-based carbon emission monitoring device: maps the carbon emission signal of the enterprise to each vertex of the graph topology to obtain the spatial graph topological structure and the temporal graph topological structure of the carbon emission signal; performs a joint graph Fourier transform of the spatial dimension and the temporal dimension on the carbon emission signal based on the spatial graph topological structure and the temporal graph topological structure, maps the carbon emission signal to the graph frequency domain, and constructs a graph low-pass filter based on the carbon emission signal in the graph frequency domain; combines the spatial graph topological structure and the temporal graph topological structure to obtain the spatiotemporal graph topological structure of the carbon emission signal; filters the carbon emission signal through the graph low-pass filter and the spatiotemporal graph topological structure, determines the enterprises with carbon emission anomalies according to the carbon emission signals before and after filtering, and stores the carbon emission anomaly information of the enterprises with carbon emission anomalies through blockchain.
[0184] Computer program code for performing the operations of the present application may be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0185] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0186] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.
[0187] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned blockchain-based carbon emission monitoring method, and can solve the technical problem that abnormal carbon emission monitoring is not accurate enough. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the blockchain-based carbon emission monitoring method provided in the above-mentioned embodiment, and will not be repeated here.
[0188] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the blockchain-based carbon emission monitoring method as described above.
[0189] The computer program product provided by this application can solve the technical problem of inaccurate monitoring of abnormal carbon emissions. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the blockchain-based carbon emission monitoring method provided in the above embodiment, which will not be repeated here.
[0190] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.
Claims
1. A carbon emission monitoring method based on blockchain, characterized in that: The method comprises: Mapping the carbon emission signal of the enterprise to each vertex of the graph topology to obtain the spatial graph topology structure and the temporal graph topology structure of the carbon emission signal; By performing a joint graph Fourier transform of the spatial dimension and the temporal dimension on the carbon emission signal based on the spatial graph topology structure and the temporal graph topology structure, the carbon emission signal is mapped to a graph frequency domain, and a graph low-pass filter is constructed based on the carbon emission signal in the graph frequency domain; Combining the spatial graph topology structure and the temporal graph topology structure to obtain a temporal-spatial graph topology structure of the carbon emission signal; The carbon emission signal is filtered by the graph low-pass filter and the space-time graph topological structure, and enterprises with abnormal carbon emissions are determined based on the carbon emission signals before and after filtering, and the carbon emission anomaly information of the enterprises with abnormal carbon emissions is stored through blockchain.
2. The method according to claim 1, characterized in that The spatial graph topological structure includes a spatial graph adjacency matrix, and the matrix elements represent the first correlation between two enterprises in space; Before the step of mapping the carbon emission signal of the enterprise to each vertex of the graph topology to obtain the spatial graph topology structure and the temporal graph topology structure of the carbon emission signal, the method includes: Acquire the enterprise type and enterprise scale of the enterprise, and the weight factors of the enterprise type and the enterprise scale respectively affecting the first correlation; The first correlation is calculated based on the enterprise type, the enterprise scale and the respective weight factors.
3. The method according to claim 1 or 2, characterized in that The time graph topology structure includes a time graph adjacency matrix, and the matrix elements represent the second correlation between the two enterprises in time; before the step of mapping the carbon emission signals of the enterprises to each vertex of the graph topology to obtain the spatial graph topology structure and the time graph topology structure of the carbon emission signals, the step includes: Obtain the number of enterprises and the number of time nodes for collecting carbon emission data, as well as the time interval between two consecutive carbon emission data collections; The second correlation is calculated based on the number of enterprises, the number of time nodes, and the time interval.
4. The method according to claim 1, characterized in that The step of determining the enterprise with abnormal carbon emissions according to the carbon emission signals before and after filtering includes: Obtaining the total variation of the carbon emission signal before and after filtering, and calculating the total variation ratio of the carbon emission signal before and after filtering; According to the comparison result of the total variation ratio of the graph and the judgment threshold, the enterprises with abnormal carbon emissions are determined.
5. The method according to claim 1, characterized in that Before the step of mapping the carbon emission signal of the enterprise to each vertex of the graph topology to obtain the spatial graph topology structure and the temporal graph topology structure of the carbon emission signal, the method includes: Constructing an optimization problem; wherein the optimization problem is to maximize the accuracy of a decision threshold, and the decision threshold is used to determine enterprises with abnormal carbon emissions based on carbon emission signals before and after filtering; By optimizing the optimization problem, the optimal solution of the target parameters in the blockchain-based carbon emission monitoring method is obtained; wherein the target parameters include the weight factors of the enterprise type and enterprise scale that affect the first spatial correlation between the two enterprises, the time interval between two adjacent carbon emission data collections, and the judgment threshold.
6. The method according to claim 5, characterized in that The step of optimizing the optimization problem to obtain the optimal solution of the target parameters in the blockchain-based carbon emission monitoring method includes: Initializing the target parameters in the blockchain-based carbon emission monitoring method, obtaining an initial solution to the optimization problem, and calculating the accuracy of the decision threshold under the initial solution; Generate a temporary solution to the optimization problem through random perturbations, and calculate the accuracy of the decision threshold under the temporary solution and the accuracy increment of the current temporary solution; If the accuracy increment is greater than zero, the provisional solution is received, and the number of times the optimal solution has not been updated is set to zero; if the accuracy increment is less than or equal to zero, the provisional solution is received according to a preset criterion, and the number of times the optimal solution has not been updated is incremented by one; If the number of times the optimal solution has not been updated is less than the preset maximum number of times the optimal solution has not been updated, returning to the step of generating a temporary solution to the optimization problem by random perturbation until the number of times the optimal solution has not been updated is greater than or equal to the preset maximum number of times the optimal solution has not been updated; If the number of times the optimal solution has not been updated is greater than or equal to the preset maximum number of times the non-optimal solution has not been updated, then when the current temperature is less than the termination temperature, the latest temporary solution is output as the optimal solution; when the current temperature is greater than or equal to the termination temperature, the number of times the optimal solution has not been updated is set to zero and the current temperature is lowered, and the process returns to the step of generating a temporary solution to the optimization problem through random perturbations.
7. A carbon emission monitoring device based on blockchain, characterized in that: The device comprises: A mapping module, used to map the carbon emission signal of the enterprise to each vertex of the graph topology to obtain the spatial graph topology structure and the temporal graph topology structure of the carbon emission signal; A construction module, used to perform a joint graph Fourier transform of the spatial dimension and the temporal dimension on the carbon emission signal based on the spatial graph topology structure and the temporal graph topology structure, map the carbon emission signal to a graph frequency domain, and construct a graph low-pass filter based on the carbon emission signal in the graph frequency domain; A combining module, used for combining the spatial graph topology structure and the temporal graph topology structure to obtain the temporal-spatial graph topology structure of the carbon emission signal and the temporal-spatial graph signal of the temporal-spatial graph topology structure; The determination module is used to filter the carbon emission signal through the graph low-pass filter and the space-time graph topological structure, determine the enterprises with abnormal carbon emissions according to the carbon emission signals before and after filtering, and store the abnormal carbon emission information of the enterprises with abnormal carbon emissions through blockchain.
8. A blockchain-based carbon emission monitoring device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the blockchain-based carbon emission monitoring method as described in any one of claims 1 to 6.
9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the blockchain-based carbon emission monitoring method as described in any one of claims 1 to 6 are implemented.
10. A computer program product, characterized in that The computer program product comprises a computer program, which, when executed by a processor, implements the steps of the blockchain-based carbon emission monitoring method as described in any one of claims 1 to 6.
Citation Information
Cited By
Robot sound source localization method, device and equipment based on graph signal processing and storage medium
CN119375832A
Zero-carbon footprint real-time monitoring method and terminal system
CN121120080A
A zero-carbon footprint real-time monitoring method and terminal system
CN121120080B
