Method and system for safely storing data of electric carbon meter

Abstract

The invention belongs to the technical field of electric carbon meter data, and discloses an electric carbon meter data security storage method and system. The method comprises the following steps that a cloud data center constructs an artificial intelligence model and a block chain storage network; the data acquisition device is used for acquiring real-time electric carbon meter data and real-time user basic data, encrypting and uploading the real-time electric carbon meter data and the real-time user basic data to the cloud data center; the cloud data center is used for collecting real-time access flow data and carrying out illegal attack identification; if the real-time illegal attack identification result is that the illegal attack exists, the cloud data center blocks access and deletes data; the cloud data center carries out decryption; the cloud data center is used for processing electric carbon meter data; the cloud data center is used for generating user permission; and the cloud data center is used for carrying out distributed storage on the decrypted real-time electric carbon meter data and the decrypted real-time user basic data. The problems that in the prior art, the storage safety is low, the data integrity is difficult to guarantee, and the real-time processing capacity is insufficient are solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of electro-carbon meter data, and particularly relates to a method and system for secure storage of electro-carbon meter data. Background Art

[0002] An electro-carbon meter is an innovative metering device that combines electricity metering and carbon metering functions. It can monitor and calculate carbon emissions in real time during the electricity usage process, thereby helping users understand the impact of their energy usage on the environment. Electro-carbon meter data generally refers to various data information related to the electro-carbon meter, and this data can be used for multiple purposes, such as energy management, carbon emission monitoring, energy conservation and emission reduction, cost control, etc. By analyzing electro-carbon meter data, users can better understand their energy usage situation, formulate corresponding energy-saving measures, and reduce the impact on the environment. Storing electro-carbon meter data allows users and analysis systems to review past energy consumption and carbon emission patterns. Continuous storage of electro-carbon meter data provides management with a comprehensive view of energy usage and carbon emissions. In short, storing electro-carbon meter data is the basis for achieving effective energy management, reducing carbon emissions, supporting decision-making, and meeting compliance requirements..

[0003] The existing electro-carbon meter data storage technologies have the following defects:

[0004] 1) Low storage security: Electro-carbon meter data may contain sensitive data such as users' electricity usage habits and enterprise operation information, and is easily maliciously tampered with, resulting in serious consequences. In existing storage methods, there is often a lack of effective protection mechanisms and is vulnerable to security threats such as hacker attacks and virus infections, leading to data leakage or being tampered with;

[0005] 2) Difficulty in ensuring data integrity: During data transmission and storage, once the data is tampered with, it is often difficult for existing technologies to detect and locate the tampering point in a timely manner;

[0006] 3) Insufficient real-time processing ability: Existing technologies have obvious delays in data collection, transmission, and processing, cannot meet the high requirements for real-time data, and lack an effective real-time monitoring mechanism, and cannot detect and process data anomalies in a timely manner. Summary of the Invention

[0007] In order to solve the problems of low storage security, difficulty in ensuring data integrity, and insufficient real-time processing ability existing in the prior art, the purpose of the present invention is to provide a method and system for secure storage of electro-carbon meter data.

[0008] The technical solution adopted by the present invention is as follows:

[0009] A method for secure storage of electro-carbon meter data, comprising the following steps:

[0010] The cloud data center uses artificial intelligence algorithms to build an electric carbon meter data processing engine, a user permission generation model, and an illegal attack identification model, and uses blockchain technology to build a blockchain storage network;

[0011] The data acquisition device encrypts the collected real-time electric carbon meter data and real-time user basic data to obtain encrypted real-time electric carbon meter data and encrypted real-time user basic data, and uploads them to the cloud data center;

[0012] The cloud data center collects the real-time access traffic data of the data acquisition device accessing the cloud data center, and uses the illegal attack identification model according to the real-time access traffic data to perform illegal attack identification to obtain the real-time illegal attack identification result;

[0013] If the real-time illegal attack identification result of the cloud data center is that there is an illegal attack, it blocks the access behavior of the data acquisition device and deletes the encrypted real-time electric carbon meter data and encrypted real-time user basic data;

[0014] The cloud data center decrypts the encrypted real-time electric carbon meter data and encrypted real-time user basic data to obtain decrypted real-time electric carbon meter data and decrypted real-time user basic data;

[0015] The cloud data center uses the electric carbon meter data processing engine to process the electric carbon meter data according to the decrypted real-time electric carbon meter data to obtain the processed real-time electric carbon meter data;

[0016] The cloud data center uses the user permission generation model to generate user permissions according to the decrypted real-time user basic data to obtain real-time user permissions;

[0017] The cloud data center uses the blockchain storage network to perform distributed storage on the decrypted real-time electric carbon meter data and decrypted real-time user basic data according to the real-time user permissions.

[0018] Furthermore, the cloud data center uses artificial intelligence algorithms to build an electric carbon meter data processing engine, a user permission generation model, and an illegal attack identification model, and uses blockchain technology to build a blockchain storage network, including the following steps:

[0019] The cloud data center collects a number of historical electric carbon meter data, a number of historical user basic data, and a number of historical access traffic data, and performs preprocessing to obtain a number of preprocessed historical electric carbon meter data, a number of preprocessed historical user basic data, and a number of preprocessed historical access traffic data;

[0020] According to a number of preprocessed historical electric carbon meter data, use a deep learning and reinforcement learning fusion algorithm to build an electric carbon meter data processing engine;

[0021] Based on a number of historical user basic data, a user privilege generation model is constructed using a fusion algorithm of deep learning and swarm intelligence optimization;

[0022] Based on a number of preprocessed historical access traffic data, an illegal attack recognition model is constructed using a fusion algorithm of deep learning and decision tree;

[0023] A number of data servers in the cloud data center are distributedly connected, and an IFPS system and smart contracts are set up to construct a blockchain storage network.

[0024] Furthermore, the electro-carbon meter data processing engine is constructed based on the LSTM-MOPPO-DPA algorithm, and the electro-carbon meter data processing engine includes an electro-carbon meter data feature extraction module constructed based on the LSTM algorithm, a data processing strategy generation module constructed based on the MOPPO algorithm, and a data processing algorithm library connected in sequence. The data processing algorithm library is set with a number of DPA algorithm encapsulations;

[0025] The user privilege generation model is constructed based on the LSTM-Attention-MLP-IFWA algorithm, and the user privilege generation model includes a user data feature extraction module constructed based on the LSTM algorithm, an attention weight module constructed based on the Attention mechanism, a user privilege generation module constructed based on the MLP algorithm, and a user privilege optimization module constructed based on the IFWA algorithm connected in sequence;

[0026] The illegal attack recognition model is constructed based on the DBN-RF algorithm, and the illegal attack recognition model includes a traffic data feature extraction module constructed based on the DBN algorithm and an illegal attack recognition module constructed based on the RF algorithm connected in sequence.

[0027] Furthermore, the data acquisition device encrypts the collected real-time electro-carbon meter data and real-time user basic data to obtain encrypted real-time electro-carbon meter data and encrypted real-time user basic data, and uploads them to the cloud data center, including the following steps:

[0028] The data acquisition device constructs a quantum communication line and an open communication line with the cloud data center, and collects the user's biometric features, real-time electro-carbon meter data, and real-time user basic data;

[0029] According to the biometric features, a random key generation algorithm is used to generate a random key, and the random key is sent to the cloud data center using the QKD technology;

[0030] According to the random key, a dynamic encryption algorithm is used to dynamically encrypt the real-time electro-carbon meter data and real-time user basic data to obtain encrypted real-time electro-carbon meter data and encrypted real-time user basic data;

[0031] Upload the encrypted real-time electricity-carbon meter data and the encrypted real-time basic user data to the cloud data center through a public communication line.

[0032] Furthermore, the cloud data center collects the real-time access traffic data of the data acquisition device accessing the cloud data center, and based on the real-time access traffic data, uses an illegal attack recognition model to perform illegal attack recognition and obtain a real-time illegal attack recognition result, including the following steps:

[0033] The cloud data center collects the real-time access traffic data of the data acquisition device accessing the cloud data center and inputs the real-time access traffic data into the illegal attack recognition model;

[0034] Use the traffic data feature extraction module of the illegal attack recognition model to extract the real-time access traffic data features of the real-time access traffic data;

[0035] Use the illegal attack recognition module of the illegal attack recognition model to perform illegal attack recognition on the real-time access traffic data features and obtain a real-time illegal attack recognition result.

[0036] Furthermore, the cloud data center decrypts the encrypted real-time electricity-carbon meter data and the encrypted real-time basic user data to obtain the decrypted real-time electricity-carbon meter data and the decrypted real-time basic user data, including the following steps:

[0037] The cloud data center receives the random key sent by the data acquisition device and verifies the legitimacy of the random key. If the legitimacy verification passes, proceed to the next step;

[0038] Receive the encrypted real-time electricity-carbon meter data and the encrypted real-time basic user data sent by the data acquisition device and verify the integrity of the encrypted real-time electricity-carbon meter data and the encrypted real-time basic user data. If the legitimacy verification passes, proceed to the next step;

[0039] Decrypt the encrypted real-time electricity-carbon meter data and the encrypted real-time basic user data according to the random key to obtain the decrypted real-time electricity-carbon meter data and the decrypted real-time basic user data.

[0040] Furthermore, the cloud data center processes the decrypted real-time electricity-carbon meter data using an electricity-carbon meter data processing engine to obtain processed real-time electricity-carbon meter data, including the following steps:

[0041] The cloud data center uses the electricity-carbon meter data feature extraction module of the electricity-carbon meter data processing engine to extract the real-time electricity-carbon meter data features of the decrypted real-time electricity-carbon meter data;

[0042] Using the data processing strategy generation module of the electric carbon meter data processing engine, according to the characteristics of real-time electric carbon meter data, generate a data processing strategy to obtain a real-time data processing strategy;

[0043] According to the real-time data processing strategy, extract several corresponding DPA algorithm encapsulations from the data processing algorithm library, and use the several DPA algorithm encapsulations to process the decrypted real-time electric carbon meter data to obtain the processed real-time electric carbon meter data.

[0044] Furthermore, the cloud data center, according to the decrypted real-time user basic data, uses the user permission generation model to generate user permissions to obtain real-time user permissions, including the following steps:

[0045] The cloud data center uses the user data feature extraction module of the user permission generation model to extract the real-time user data features of the decrypted real-time user basic data;

[0046] According to the preset attention weight value, use the attention weight module of the user permission generation model to perform weighted fusion on several feature components of the real-time user data features to obtain real-time weighted fusion features;

[0047] Use the user permission generation module of the user permission generation model to generate user permissions according to the real-time weighted fusion features to obtain the real-time user permission probability distribution;

[0048] Use the user permission optimization module of the user permission generation model to optimize the real-time user permission probability distribution to obtain real-time user permissions.

[0049] Furthermore, the cloud data center, according to the real-time user permissions, uses the blockchain storage network to perform distributed storage on the decrypted real-time electric carbon meter data and the decrypted real-time user basic data, including the following steps:

[0050] The cloud data center stores the decrypted real-time electric carbon meter data and the decrypted real-time user basic data into the IFPS system of the blockchain storage network, and obtains the real-time data hash value returned by the IFPS system;

[0051] Call the smart contract of the blockchain storage network, generate real-time transaction data according to the real-time data hash value, and send the real-time transaction data to several distributed-connected data servers;

[0052] Make the real-time transaction data public in the blockchain storage network, and use the data server to perform consensus on the real-time transaction data. If the consensus is successful, proceed to the next step;

[0053] Use a data server to convert real-time transaction data into real-time data blocks and send the real-time data blocks to other data servers for distributed storage.

[0054] An electric carbon meter data security storage system is used to implement an electric carbon meter data security storage method. The system includes a cloud data center and several data acquisition devices. The several data acquisition devices are all communicatively connected to the cloud data center. The cloud data center includes a model construction unit, an illegal attack identification unit, an access interception unit, a data decryption unit, an electric carbon meter data processing unit, a user permission generation unit, and a distributed storage unit that are connected in sequence.

[0055] The beneficial effects of the present invention are as follows:

[0056] An electric carbon meter data security storage method and system provided by the present invention, through artificial intelligence algorithms and blockchain technology, construct a powerful illegal attack identification model and a blockchain storage network, effectively resist hacker attacks and virus infections, ensure that data is not leaked or tampered with, use a user permission generation model to dynamically generate user permissions, achieve refined user permission management, avoid unauthorized access or data abuse, use high-strength encryption technology to encrypt real-time electric carbon meter data and user basic data, and ensure the security of data during transmission and storage; utilize the immutable feature of the blockchain to ensure the integrity of data during storage and transmission, and any tampering with the data can be detected and located in a timely manner; construct an efficient electric carbon meter data processing engine to achieve real-time data acquisition and processing, meet the high requirements for real-time data, implement a real-time monitoring mechanism, timely detect and process data anomalies, and ensure the stable operation of the system.

[0057] Other beneficial effects of the present invention will be further described in the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 is a flowchart of the electric carbon meter data security storage method in the present invention.

[0059] Figure 2 is a structural block diagram of the electric carbon meter data security storage system in the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0060] The present invention will be further explained below in conjunction with the accompanying drawings and specific embodiments.

[0061] Embodiment 1:

[0062] As Figure 1 shown, this embodiment provides an electric carbon meter data security storage method, including the following steps:

[0063] S1: The cloud data center uses artificial intelligence algorithms to build an electric carbon meter data processing engine, a user privilege generation model, and an illegal attack identification model, and uses blockchain technology to build a blockchain storage network, including the following steps:

[0064] S1-1: The cloud data center collects a number of historical electric carbon meter data, a number of historical user basic data, and a number of historical access traffic data, and performs preprocessing to obtain a number of preprocessed historical electric carbon meter data, a number of preprocessed historical user basic data, and a number of preprocessed historical access traffic data;

[0065] S1-2: According to a number of preprocessed historical electric carbon meter data, use a deep learning and reinforcement learning fusion algorithm to build an electric carbon meter data processing engine;

[0066] The electric carbon meter data processing engine is built based on the Long Short-Term Memory (LSTM)-Multi-Objective Proximal Policy Optimization (MOPPO)-Data Processing Algorithm (DPA) algorithm. The electric carbon meter data processing engine includes an electric carbon meter data feature extraction module built based on the LSTM algorithm, a data processing policy generation module built based on the MOPPO algorithm, and a data processing algorithm library connected in sequence. The data processing algorithm library is set with a number of DPA algorithm encapsulations, and the data processing policy generation module is set with a set of objective functions, an experience replay pool, an Actor network, a Critic network, and an agent;

[0067] The electro-carbon meter data feature extraction module is used to extract the deep features of electro-carbon meter data, providing a basis for the subsequent generation of data processing strategies; the Actor network of the data processing strategy generation module is responsible for outputting the probability distribution of the actions that should be taken in a given state, with the goal of learning an optimal strategy, that is, maximizing the long-term cumulative reward. In a continuous action space, the Actor network usually outputs a mean value and an optional variance parameter to describe the probability distribution of the actions. The Critic network is responsible for evaluating the value of a given state, that is, predicting the expected return that can be obtained starting from this state and following the current strategy, and usually outputs a scalar value representing the value of the state or the state-action value. The experience replay pool is used to store historical experiences for reuse during the training process. The set of objective functions includes functions that define multiple data processing objectives, including minimizing data processing errors, minimizing data processing costs, maximizing data processing efficiency, etc.; the DPA algorithm encapsulation in the data processing algorithm library uses the function call interface of a computer program to encapsulate the DPA algorithm. The input quantity is electro-carbon meter data, and the output quantity is the processed electro-carbon meter data, realizing the intelligent processing of electro-carbon meter data. The types of DPA algorithms include data cleaning algorithms, data conversion algorithms, data dimensionality reduction algorithms, and data clustering algorithms, etc., which can perform various forms and types of data processing on electro-carbon meter data;

[0068] According to a number of preprocessed historical electro-carbon meter data, use a deep learning and reinforcement learning fusion algorithm to construct an electro-carbon meter data processing engine, including the following steps:

[0069] S1-2-1: Use the LSTM-MOPPO-DPA algorithm to construct an initial electro-carbon meter data processing engine; the initial electro-carbon meter data processing engine includes an initial electro-carbon meter data feature extraction module, an initial data processing strategy generation module, and an initial data processing algorithm library;

[0070] S1-2-2: Set a number of DPA algorithm encapsulations for the initial data processing algorithm library to obtain the final data processing algorithm library;

[0071] S1-2-3: Optimize and train the initial electro-carbon meter data feature extraction module according to a number of preprocessed historical electro-carbon meter data to obtain the final electro-carbon meter data feature extraction module and generate a number of historical electro-carbon meter data features;

[0072] S1-2-4: Set the set of objective functions, experience replay pool, Actor network, Critic network, and agent for the initial data processing strategy generation module;

[0073] S1-2-5: Generate problems with data processing strategies. As the simulation environment of the initial data processing strategy generation module, define the state space of the intelligent agent according to the characteristics of historical electro-carbon meter data, and define the action space of the intelligent agent according to the encapsulation of several DPA algorithms in the final data processing algorithm library;

[0074] S1-2-6: Based on any objective function in the set of objective functions, optimize and train the initial data processing strategy generation module according to the characteristics of several historical electro-carbon meter data to obtain the final data processing strategy generation module, and generate several historical data processing strategy generation experiences;

[0075] S1-2-7: Integrate the final electro-carbon meter data feature extraction module, the final data processing strategy generation module, and the final data processing algorithm library to obtain the final electro-carbon meter data processing engine, and store several historical data processing strategy generation experiences in the experience replay pool;

[0076] S1-3: Use the deep learning and swarm intelligence optimization fusion algorithm to construct a user privilege generation model according to several historical user basic data;

[0077] The user privilege generation model is constructed based on the LSTM-Attention-Multilayer Perceptron (MLP)-Improved Fireworks Optimization Algorithm (IFWA) algorithm, and the user privilege generation model includes a user data feature extraction module constructed based on the LSTM algorithm, an attention weight module constructed based on the Attention mechanism, a user privilege generation module constructed based on the MLP algorithm, and a user privilege optimization module constructed based on the IFWA algorithm, which are connected in sequence;

[0078] The user data feature extraction module is used to extract the deep features of user basic data, providing a basis for subsequent user privilege generation. Among them, user basic data includes multi-dimensional data such as the basic information data of users and storage and access behavior data, and the extracted user data features include multi-dimensional feature components; The Attention mechanism assigns weights to multi-dimensional feature components, effectively focusing on key features, improving the accuracy of user privilege generation, and enhancing the model's adaptability to complex data; Use the IFWA algorithm to optimize the probability distribution of user privileges, effectively improving the accuracy and stability of user privilege generation, enhancing the model's optimization ability, and making the recognition results more reliable;

[0079] S1-4: Use the deep learning and decision tree fusion algorithm to construct an illegal attack recognition model according to several preprocessed historical access traffic data;

[0080] The illegal attack recognition model is constructed based on the Deep Belief Network (DBN)-Random Forest (RF) algorithm, and the illegal attack recognition model includes a traffic data feature extraction module constructed based on the DBN algorithm and an illegal attack recognition module constructed based on the RF algorithm, which are connected in sequence;

[0081] The traffic data feature extraction module performs in-depth feature extraction on traffic data. By using the multi-layer structure of the Deep Belief Network (DBN), it learns the complex patterns and internal relationships in the traffic data, and the extracted features are more representative and abstract, which helps the illegal attack recognition module to more accurately understand and process traffic data features; The illegal attack recognition module uses the Random Forest (RF) algorithm to correct the extracted traffic data features. Through the ensemble learning of multiple decision trees, it classifies or regresses and corrects the traffic data, improving the accuracy and reliability of illegal attack recognition. Each tree randomly selects a feature subset during training, enhancing the generalization ability and anti-overfitting ability of the model;

[0082] S1-5: Distributively connect several data servers in the cloud data center, and set up the InterPlanetary File System (IPFS) and smart contracts to build a blockchain storage network;

[0083] S2: The data acquisition device encrypts the collected real-time electricity-carbon meter data and real-time user basic data to obtain the encrypted real-time electricity-carbon meter data and encrypted real-time user basic data, and uploads them to the cloud data center, including the following steps:

[0084] S2-1: The data acquisition device constructs a quantum communication line and an open communication line with the cloud data center, and collects the user's biometric features, real-time electricity-carbon meter data, and real-time user basic data;

[0085] Biometric features (such as fingerprints, iris patterns) are converted into a unique binary representation, and this binary value is used as a seed value to generate a random key. The uniqueness of the biometric features ensures that the generated seed value is unique, thus making the generated random key highly unique and unpredictable; The generation of the random key ensures that each encryption is independent, increasing the intensity and security of encryption;

[0086] S2-2: According to the biometric features, use a random key generation algorithm to generate a random key, and use Quantum Key Distribution (QKD) technology to send the random key to the cloud data center, including the following steps:

[0087] S2-2-1: The cloud data center converts biometric features into binary seed values, and based on the binary seed values, uses a cryptographically secure pseudo-random number generator to generate random keys;

[0088] S2-2-2: Encodes the random key into a key quantum state, transmits the key quantum state through a quantum communication channel to the cloud data center, and measures the key quantum state to obtain a first measurement result;

[0089] S2-2-3: Through a public communication line, obtains a second measurement result obtained by the cloud data center measuring the key quantum state;

[0090] S2-2-4: Based on the second measurement result and the first measurement result, conducts quantum key interaction to generate random keys in the cloud data center;

[0091] The QKD technology utilizes the characteristics of quantum communication to provide a key distribution method that is almost impossible to crack, greatly improving the security of key transmission, ensuring that it is not tampered with during the transmission process, and ensuring the integrity of information;

[0092] S2-3: Based on the random keys, uses a dynamic encryption algorithm to dynamically encrypt the real-time electricity-carbon meter data and real-time user basic data to obtain encrypted real-time electricity-carbon meter data and encrypted real-time user basic data;

[0093] S2-4: Uploads the encrypted real-time electricity-carbon meter data and encrypted real-time user basic data to the cloud data center through a public communication line;

[0094] S3: The cloud data center collects the real-time access traffic data of the data collection device accessing the cloud data center, and based on the real-time access traffic data, uses an illegal attack identification model to conduct illegal attack identification to obtain a real-time illegal attack identification result, including the following steps:

[0095] S3-1: The cloud data center collects the real-time access traffic data of the data collection device accessing the cloud data center, and inputs the real-time access traffic data into the illegal attack identification model;

[0096] S3-2: Uses the traffic data feature extraction module of the illegal attack identification model to extract the real-time access traffic data features of the real-time access traffic data;

[0097] S3-3: Uses the illegal attack identification module of the illegal attack identification model to conduct illegal attack identification on the real-time access traffic data features to obtain a real-time illegal attack identification result;

[0098] S4: In the cloud data center, if the real-time illegal attack recognition result indicates the existence of an illegal attack, block the access behavior of the data acquisition device, and delete the encrypted real-time electricity-carbon meter data and the encrypted real-time user basic data.

[0099] S5: In the cloud data center, decrypt the encrypted real-time electricity-carbon meter data and the encrypted real-time user basic data to obtain the decrypted real-time electricity-carbon meter data and the decrypted real-time user basic data, including the following steps:

[0100] S5-1: In the cloud data center, receive the random key sent by the data acquisition device and verify the legitimacy of the random key. If the legitimacy verification passes, proceed to the next step.

[0101] S5-2: Receive the encrypted real-time electricity-carbon meter data and the encrypted real-time user basic data sent by the data acquisition device, and verify the integrity of the encrypted real-time electricity-carbon meter data and the encrypted real-time user basic data. If the legitimacy verification passes, proceed to the next step.

[0102] S5-3: Decrypt the encrypted real-time electricity-carbon meter data and the encrypted real-time user basic data according to the random key to obtain the decrypted real-time electricity-carbon meter data and the decrypted real-time user basic data.

[0103] S6: In the cloud data center, use the electricity-carbon meter data processing engine to process the decrypted real-time electricity-carbon meter data to obtain the processed real-time electricity-carbon meter data, including the following steps:

[0104] S6-1: In the cloud data center, use the electricity-carbon meter data feature extraction module of the electricity-carbon meter data processing engine to extract the real-time electricity-carbon meter data features of the decrypted real-time electricity-carbon meter data.

[0105] S6-2: Use the data processing strategy generation module of the electricity-carbon meter data processing engine to generate a data processing strategy according to the real-time electricity-carbon meter data features to obtain a real-time data processing strategy.

[0106] S6-3: According to the real-time data processing strategy, extract the corresponding several DPA algorithm packages from the data processing algorithm library, and use the several DPA algorithm packages to process the decrypted real-time electricity-carbon meter data to obtain the processed real-time electricity-carbon meter data.

[0107] S7: In the cloud data center, use the user permission generation model to generate user permissions according to the decrypted real-time user basic data to obtain real-time user permissions, including the following steps:

[0108] S7-1: In the cloud data center, use the user data feature extraction module of the user permission generation model to extract the real-time user data features of the decrypted real-time user basic data.

[0109] S7-2: Using the attention weight module of the user privilege generation model according to the preset attention weight value, perform weighted fusion on several feature components of the real-time user data features to obtain real-time weighted fusion features;

[0110] S7-3: Using the user privilege generation module of the user privilege generation model, perform user privilege generation according to the real-time weighted fusion features to obtain the real-time user privilege probability distribution;

[0111] S7-4: Using the user privilege optimization module of the user privilege generation model, perform user privilege optimization on the real-time user privilege probability distribution to obtain the real-time user privilege, including the following steps:

[0112] S7-4-1: According to the real-time user privilege probability distribution, set the real-time adjustment parameter of the real-time user privilege probability distribution as the solution vector of the user privilege optimization module, and perform initialization according to the solution vector to obtain several initial solutions;

[0113] Specifically, use the Circle chaotic mapping sequence for initialization to generate several initial solutions of the user privilege optimization module, and obtain an initial IFWA population composed of several initial IFWA individuals (initial solutions);

[0114] The formula is:

[0115]

[0116] In the formula, q l' is the initial IFWA individual (initial solution) of the Circle chaotic mapping; q' l' is a randomly generated initial IFWA individual; l' is the IFWA individual indicator;

[0117] S7-4-2: Taking the minimization of the classification error as the optimization goal, use the optimization goal as the fitness function, and set the IFWA population parameters and the maximum number of iterations of the IFWA optimization algorithm;

[0118] The formula is:

[0119] f(q l ) = minMSE

[0120] In the formula, f(q l ) is the fitness function of the IFWA individual q l ; MSE is the classification error value; q l is the IFWA individual variable; l is the IFWA individual indicator;

[0121] S7-4-3: Obtain the explosion radius, the number of sparks, and the fitness value of the initial IFWA individual according to the fitness function;

[0122] The formula is:

[0123]

[0124] In the formula, S l' is the number of sparks of the initial IFWA individual q l' ; M' is a number constant; f max is the maximum fitness value in the initialized IFWA population; f(q l' ) is the fitness value of the initial IFWA individual q l' ; τ is an infinitesimal constant; a is a convergence factor; σ is a non-zero positive real number; q l' is the IFWA individual variable; l' is the IFWA individual indicator;

[0125]

[0126] In the formula, R l' is the explosion radius of the initial IFWA individual q l' ; is the explosion radius adjustment constant; f min is the minimum fitness value in the initialized IFWA population;

[0127]

[0128] In the formula, a is the convergence factor; tanh(.) is the hyperbolic tangent function; t, t max are the current iteration number and the maximum iteration number respectively; a max , a min are the maximum and minimum values of the convergence factor respectively; λ is the decreasing rate parameter, k is the decreasing period parameter, λ = -2π, k = π;

[0129] The number of sparks determines the number of sub-fireworks generated after each firework explosion, and the explosion radius determines the distribution range of the sparks generated after the firework explosion in the solution space. In the early stage of iteration, the value of a is larger, the number of sparks of the IFWA individual is smaller, and the explosion radius is larger, which helps to reduce the computational burden and is more widely distributed, helping to explore more solution spaces. In the later stage of iteration, a smaller explosion radius helps to perform fine search in the local area, and a larger number of sparks helps to increase the diversity of the search;

[0130] S7-4-4: Perform firework explosion according to the explosion radius, the number of sparks, and the fitness value to obtain several updated IFWA individuals of the updated IFWA population;

[0131] The formula is:

[0132] q' l' = q l' + S l' × rand(-1, 1)

[0133] In the formula, q' l' is the updated IFWA individual; rand(-1, 1) is a random number from -1 to 1;

[0134] S7-4-5: Use the Gaussian mutation algorithm to perform Gaussian mutation on the initialized IFWA population to generate several Gaussian-mutated IFWA individuals of the Gaussian-mutated IFWA population;

[0135] The formula is:

[0136] q" l' = q l' + S l' × G(1, 1)

[0137] In the formula, q" l' is the Gaussian-mutated IFWA individual; G(1, 1) is a random number of a Gaussian distribution with both mean and variance equal to 1;

[0138] S7-4-6: Use the dynamic reverse learning algorithm to perform dynamic reverse learning on the initialized IFWA population to obtain several reverse IFWA individuals of the reverse IFWA population;

[0139] The formula is:

[0140] q''' l' = γ(L max + L min ) - q l'

[0141] In the formula, q''' l' is the reverse IFWA individual; γ is a decreasing inertia coefficient; L max , L min are the maximum and minimum values of the vector space respectively;

[0142] S7-4-7: Obtain the fitness values of each updated IFWA individual, Gaussian-mutated IFWA individual, and reverse IFWA individual, and use the IFWA individual with the minimum fitness value as the optimal individual;

[0143] S7-4-8: If the number of iterations of iterative optimization reaches the maximum number of iterations or the fitness value of the optimal individual meets the requirements, then output the optimal individual;

[0144] S7-4-9: Decode the solution vector of the optimal individual to obtain the optimal real-time adjustment parameters, and adjust the real-time user permission probability distribution according to the optimal real-time adjustment parameters to obtain the adjusted real-time user permission probability distribution;

[0145] S7-4-10: Use the real-time user permission prediction label with the highest probability in the adjusted real-time user permission probability distribution as the real-time user permission;

[0146] S8: The cloud data center, according to the real-time user permission, uses the blockchain storage network to perform distributed storage on the decrypted real-time electricity-carbon meter data and the decrypted real-time user basic data, including the following steps:

[0147] S8-1: The cloud data center stores the decrypted real-time electricity-carbon meter data and the decrypted real-time user basic data into the IFPS system of the blockchain storage network, and obtains the real-time data hash value returned by the IFPS system;

[0148] S8-2: Invoke the smart contract of the blockchain storage network, generate real-time transaction data according to the real-time data hash value, and send the real-time transaction data to several distributed-connected data servers;

[0149] S8-3: Make the real-time transaction data public in the blockchain storage network, and use the data server to perform consensus on the real-time transaction data. If the consensus is successful, proceed to the next step;

[0150] S8-4: Use the data server to convert the real-time transaction data into a real-time data block, and send the real-time data block to other data servers for distributed storage.

[0151] Embodiment 2:

[0152] As Figure 2 shown, this embodiment provides an electricity-carbon meter data security storage system for implementing the electricity-carbon meter data security storage method. The system includes a cloud data center and several data collection devices. The several data collection devices are all communicatively connected to the cloud data center. The cloud data center includes a model construction unit, an illegal attack identification unit, an access interception unit, a data decryption unit, an electricity-carbon meter data processing unit, a user permission generation unit, and a distributed storage unit that are connected in sequence.

[0153] The data collection device is used to encrypt the collected real-time electricity-carbon meter data and real-time user basic data to obtain the encrypted real-time electricity-carbon meter data and the encrypted real-time user basic data, and upload them to the cloud data center;

[0154] A model construction unit, which is used to construct an electric carbon meter data processing engine, a user permission generation model, and an illegal attack identification model using artificial intelligence algorithms, and construct a blockchain storage network using blockchain technology;

[0155] An illegal attack identification unit, which is used to collect the real-time access traffic data of the data collection device accessing the cloud data center, and based on the real-time access traffic data, use the illegal attack identification model to perform illegal attack identification to obtain the real-time illegal attack identification result;

[0156] An access interception unit, which is used to block the access behavior of the data collection device and delete the encrypted real-time electric carbon meter data and the encrypted real-time user basic data when the real-time illegal attack identification result indicates the existence of an illegal attack;

[0157] A data decryption unit, which is used to decrypt the encrypted real-time electric carbon meter data and the encrypted real-time user basic data to obtain the decrypted real-time electric carbon meter data and the decrypted real-time user basic data;

[0158] An electric carbon meter data processing unit, which is used to process the electric carbon meter data according to the decrypted real-time electric carbon meter data using the electric carbon meter data processing engine to obtain the processed real-time electric carbon meter data;

[0159] A user permission generation unit, which is used to generate user permissions according to the decrypted real-time user basic data using the user permission generation model to obtain real-time user permissions;

[0160] A distributed storage unit, which is used to perform distributed storage of the decrypted real-time electric carbon meter data and the decrypted real-time user basic data using the blockchain storage network according to the real-time user permissions.

[0161] An electric carbon meter data security storage method and system provided by the present invention, through artificial intelligence algorithms and blockchain technology, constructs a powerful illegal attack identification model and a blockchain storage network, effectively resists hacker attacks and virus infections, ensures that data is not leaked or tampered with, uses a user permission generation model to perform dynamic user permission generation, realizes refined user permission management, avoids unauthorized access or data abuse, uses high-strength encryption technology to encrypt real-time electric carbon meter data and user basic data, and ensures the security of data during transmission and storage; utilizes the immutable characteristic of the blockchain to ensure the integrity of data during storage and transmission, and any tampering with the data can be detected and located in a timely manner; constructs an efficient electric carbon meter data processing engine to realize real-time data collection and processing, meet the high requirements for real-time data, implement a real-time monitoring mechanism, and timely discover and process data anomalies to ensure the stable operation of the system.

[0162] The present invention is not limited to the above optional embodiments, and any person can obtain other various forms of products under the inspiration of the present invention. The above specific embodiments should not be construed as limiting the protection scope of the present invention, and the protection scope of the present invention should be defined by the claims, and the specification can be used to interpret the claims.

Claims

1. A method for securely storing data of an electric carbon meter, characterized in that: The steps include: The cloud data center uses artificial intelligence algorithms to build an electricity and carbon meter data processing engine, a user authority generation model, and an illegal attack identification model, and uses blockchain technology to build a blockchain storage network; The data collection device encrypts the collected real-time electricity carbon meter data and real-time user basic data, obtains the encrypted real-time electricity carbon meter data and the encrypted real-time user basic data, and uploads them to the cloud data center; The cloud data center collects real-time access flow data of the data collection device accessing the cloud data center, and uses an illegal attack identification model to identify illegal attacks based on the real-time access flow data to obtain real-time illegal attack identification results; The cloud data center, if the real-time illegal attack identification result is that there is an illegal attack, blocks the access behavior of the data collection device, and deletes the encrypted real-time electricity carbon meter data and the encrypted real-time user basic data; The cloud data center decrypts the encrypted real-time electricity carbon meter data and the encrypted real-time user basic data to obtain the decrypted real-time electricity carbon meter data and the decrypted real-time user basic data; The cloud data center processes the electric carbon meter data according to the decrypted real-time electric carbon meter data using the electric carbon meter data processing engine to obtain the processed real-time electric carbon meter data; The cloud data center generates user permissions based on the decrypted real-time user basic data using the user permission generation model to obtain real-time user permissions; The cloud data center uses the blockchain storage network to distribute the decrypted real-time electricity carbon meter data and the decrypted real-time user basic data based on the real-time user permissions.

2. A method for securely storing data of an electric carbon meter according to claim 1, characterized in that: The cloud data center uses artificial intelligence algorithms to build an electricity and carbon meter data processing engine, a user authority generation model, and an illegal attack identification model, and uses blockchain technology to build a blockchain storage network, including the following steps: The cloud data center collects a number of historical electricity-carbon meter data, a number of historical user basic data, and a number of historical access flow data, and performs preprocessing to obtain a number of preprocessed historical electricity-carbon meter data, a number of preprocessed historical user basic data, and a number of preprocessed historical access flow data; Based on some pre-processed historical electricity-carbon meter data, a deep learning and reinforcement learning fusion algorithm is used to build an electricity-carbon meter data processing engine; Based on some historical user basic data, a user permission generation model is constructed using deep learning and swarm intelligence optimization fusion algorithm; Based on some pre-processed historical access traffic data, an illegal attack identification model is constructed using deep learning and decision tree fusion algorithms; Distribute and connect several data servers in the cloud data center, set up the IFPS system and smart contracts, and build a blockchain storage network.

3. A method for securely storing data of an electric carbon meter according to claim 2, characterized in that: The electric carbon meter data processing engine is constructed based on the LSTM-MOPPO-DPA algorithm, and the electric carbon meter data processing engine includes an electric carbon meter data feature extraction module constructed based on the LSTM algorithm, a data processing strategy generation module constructed based on the MOPPO algorithm, and a data processing algorithm library connected in sequence, and the data processing algorithm library is provided with several DPA algorithm packages; The user authority generation model is constructed based on the LSTM-Attention-MLP-IFWA algorithm, and the user authority generation model includes a user data feature extraction module constructed based on the LSTM algorithm, an attention weight module constructed based on the Attention mechanism, a user authority generation module constructed based on the MLP algorithm, and a user authority optimization module constructed based on the IFWA algorithm, which are sequentially connected; The illegal attack identification model is constructed based on the DBN-RF algorithm, and the illegal attack identification model includes a flow data feature extraction module constructed based on the DBN algorithm and an illegal attack identification module constructed based on the RF algorithm, which are connected in sequence.

4. A method for securely storing data of an electric carbon meter according to claim 1, characterized in that: The data collection device encrypts the collected real-time electricity carbon meter data and real-time user basic data to obtain the encrypted real-time electricity carbon meter data and the encrypted real-time user basic data, and uploads them to the cloud data center, including the following steps: The data collection device builds quantum communication lines and public communication lines with the cloud data center, and collects the user's biometrics, real-time electricity and carbon meter data, and real-time user basic data; Based on the biometrics, a random key generation algorithm is used to generate a random key, and the random key is sent to the cloud data center using QKD technology; According to the random key, the real-time electricity carbon meter data and the real-time user basic data are dynamically encrypted using a dynamic encryption algorithm to obtain the encrypted real-time electricity carbon meter data and the encrypted real-time user basic data; The encrypted real-time electricity carbon meter data and encrypted real-time user basic data are uploaded to the cloud data center through public communication lines.

5. The method for securely storing data of an electric carbon meter according to claim 3 is characterized in that: The cloud data center collects real-time access flow data of the data collection device accessing the cloud data center, and uses an illegal attack identification model to identify illegal attacks based on the real-time access flow data to obtain real-time illegal attack identification results, including the following steps: The cloud data center collects real-time access flow data of the data collection device accessing the cloud data center, and inputs the real-time access flow data into an illegal attack identification model; Using the traffic data feature extraction module of the illegal attack identification model to extract the real-time access traffic data features of the real-time access traffic data; The illegal attack identification module of the illegal attack identification model is used to identify illegal attacks on the real-time access traffic data features to obtain real-time illegal attack identification results.

6. A method for securely storing data of an electric carbon meter according to claim 4, characterized in that: The cloud data center decrypts the encrypted real-time electricity carbon meter data and the encrypted real-time user basic data to obtain the decrypted real-time electricity carbon meter data and the decrypted real-time user basic data, including the following steps: The cloud data center receives the random key sent by the data acquisition device and verifies the legitimacy of the random key. If the legitimacy verification passes, it proceeds to the next step; Receive the encrypted real-time electricity carbon meter data and the encrypted real-time user basic data sent by the data acquisition device, and perform integrity verification on the encrypted real-time electricity carbon meter data and the encrypted real-time user basic data. If the legitimacy verification passes, proceed to the next step; According to the random key, the encrypted real-time electricity carbon meter data and the encrypted real-time user basic data are decrypted to obtain the decrypted real-time electricity carbon meter data and the decrypted real-time user basic data.

7. A method for securely storing data of an electric carbon meter according to claim 3, characterized in that: The cloud data center processes the electric carbon meter data using the electric carbon meter data processing engine according to the decrypted real-time electric carbon meter data to obtain the processed real-time electric carbon meter data, including the following steps: The cloud data center uses the electric carbon meter data feature extraction module of the electric carbon meter data processing engine to extract the real-time electric carbon meter data features after decryption; Use the data processing strategy generation module of the electric carbon meter data processing engine to generate data processing strategies according to the real-time electric carbon meter data characteristics to obtain real-time data processing strategies; According to the real-time data processing strategy, several corresponding DPA algorithm packages are extracted from the data processing algorithm library, and several DPA algorithm packages are used to perform electricity carbon meter data processing on the decrypted real-time electricity carbon meter data to obtain the processed real-time electricity carbon meter data.

8. The method for securely storing data of an electric carbon meter according to claim 3, characterized in that: The cloud data center generates user permissions based on the decrypted real-time user basic data using the user permission generation model to obtain real-time user permissions, including the following steps: The cloud data center uses the user data feature extraction module of the user permission generation model to extract the real-time user data features of the decrypted real-time user basic data; According to the preset attention weight value, the attention weight module of the user authority generation model is used to perform weighted fusion on several feature components of the real-time user data feature to obtain a real-time weighted fusion feature; The user authority generation module of the user authority generation model is used to generate user authority according to the real-time weighted fusion features to obtain the real-time user authority probability distribution; The user permission optimization module of the user permission generation model is used to optimize the real-time user permission probability distribution to obtain the real-time user permission.

9. A method for securely storing data of an electric carbon meter according to claim 2, characterized in that: The cloud data center uses the blockchain storage network to perform distributed storage of the decrypted real-time electricity carbon meter data and the decrypted real-time user basic data according to the real-time user permissions, including the following steps: The cloud data center stores the decrypted real-time electricity carbon meter data and the decrypted real-time user basic data in the IFPS system of the blockchain storage network, and obtains the real-time data hash value returned by the IFPS system; Call the smart contract of the blockchain storage network, generate real-time transaction data according to the real-time data hash value, and send the real-time transaction data to several distributed connected data servers; The real-time transaction data is made public on the blockchain storage network, and a consensus is reached on the real-time transaction data using a data server. If the consensus is successful, the next step is entered; Using data servers, real-time transaction data is converted into real-time data blocks, and the real-time data blocks are sent to other data servers for distributed storage.

10. A system for securely storing data of an electric carbon meter, used to implement the method for securely storing data of an electric carbon meter as claimed in any one of claims 1 to 9, characterized in that: The system includes a cloud data center and several data acquisition devices, and the several data acquisition devices are all communicatively connected to the cloud data center. The cloud data center includes a model building unit, an illegal attack identification unit, an access interception unit, a data decryption unit, an electricity carbon meter data processing unit, a user authority generation unit and a distributed storage unit connected in sequence.

Images