Secure storage method and system for digital earth data

Abstract

The invention belongs to the technical field of digital earth, and discloses a secure storage method and system for digital earth data. The method comprises the following steps: a ground data station collects real-time digital earth data, preprocesses and encrypts the data, and uploads the data to a cloud data center; the cloud data center carries out decryption, constructs a real-time digital twinborn model and extracts real-time metadata; the cloud data center performs data analysis by using a data analysis model according to the real-time digital twin model to obtain a real-time data analysis result; the cloud data center generates a secure storage scheme by using a secure storage scheme generation model according to the real-time data analysis result to obtain a real-time secure storage scheme; and the cloud data center performs encryption and distributed storage on the real-time metadata according to the real-time secure storage scheme. The problems of insufficient data storage security, low data processing efficiency and poor storage scheme flexibility in the prior art are solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of digital earth, and particularly relates to a method and system for securely storing digital earth data. Background Art

[0002] The digital earth is a digital model of the earth. Through digital technologies and methods, spatio-temporal change data of the earth, its activities, and the environment are sorted according to the earth coordinates and stored in computers distributed globally to form a global digital model. Generally speaking, digital earth data is a comprehensive earth information database that uses modern information technology means to digitally describe and manage the earth in all aspects, aiming to provide high-quality services and support for human society. With the rapid development of digital earth technology, digital earth data plays an increasingly important role in various fields. Therefore, how to manage and store digital earth data has become an important development direction in this field.

[0003] The existing digital earth data management technologies have the following defects:

[0004] 1) Insufficient data storage security: Existing technologies often adopt traditional encryption methods such as AES, RSA, etc. These encryption methods may become vulnerable when facing emerging data attack technologies, resulting in insufficient data storage security. Moreover, data is usually stored on centralized servers, which are easily targeted by hackers. Once breached, a large amount of data may be leaked.

[0005] 2) Low data processing efficiency: The complexity and volume of digital earth data are high, while the existing digital earth data processing methods are simple and unable to discover the deep features of digital earth data, resulting in low efficiency in analyzing and processing digital earth data and being unable to be applied to the application scenarios of digital earth data management.

[0006] 3) Poor flexibility of the storage scheme: Existing technologies usually adopt fixed storage strategies and are unable to dynamically adjust the storage scheme according to the real-time changes and requirements of digital earth data. The resource scheduling strategy is relatively fixed and difficult to adapt to the real-time changing storage requirements, resulting in low resource utilization. Summary of the Invention

[0007] In order to solve the problems of insufficient data storage security, low data processing efficiency, and poor flexibility of the storage scheme existing in the prior art, the purpose of the present invention is to provide a method and system for securely storing digital earth data.

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

[0009] A method for securely storing digital earth data includes the following steps:

[0010] The ground data station collects real-time digital earth data, preprocesses and encrypts the real-time digital earth data to obtain encrypted real-time digital earth data, and uploads it to the cloud data center;

[0011] The cloud data center decrypts the encrypted real-time digital earth data, constructs a real-time digital twin model based on the obtained decrypted real-time digital earth data, and extracts real-time metadata;

[0012] The cloud data center performs data analysis based on the real-time digital twin model using a pre-trained data analysis model to obtain real-time data analysis results;

[0013] The cloud data center generates a real-time secure storage solution based on the real-time data analysis results using a pre-trained secure storage solution generation model;

[0014] The cloud data center encrypts the real-time metadata according to the real-time secure storage solution and uses a pre-deployed blockchain network to perform distributed storage on the obtained encrypted real-time metadata.

[0015] Furthermore, the real-time digital earth data includes real-time remote sensing data, real-time GIS data, real-time GPS data, real-time earth environment monitoring data, and real-time earth social data.

[0016] Furthermore, the ground data station collects real-time digital earth data, preprocesses and encrypts the real-time digital earth data to obtain encrypted real-time digital earth data, and uploads it to the cloud data center, including the following steps:

[0017] The ground data station receives the initial real-time remote sensing data sent by the remote sensing platform, the initial real-time GIS data sent by the geographic information system, the initial real-time GPS data sent by the global positioning system, the initial real-time earth environment monitoring data sent by the earth environment monitoring sensor network, and the initial real-time earth social data sent by the earth social server to obtain real-time digital earth data;

[0018] Preprocess the heterogeneous initial real-time remote sensing data, initial real-time GIS data, initial real-time GPS data, initial real-time earth environment monitoring data, and initial real-time earth social data to obtain homogeneous final real-time remote sensing data, final real-time GIS data, final real-time GPS data, final real-time earth environment monitoring data, and final real-time earth social data, and integrate them to obtain preprocessed real-time digital earth data;

[0019] Construct a quantum transmission channel and a data transmission channel between the ground data station and the cloud data center, generate a homomorphic key, and use QKD technology to send the homomorphic key to the cloud data center through the quantum transmission channel;

[0020] Encrypt the preprocessed real-time digital earth data according to the homomorphic key to obtain the encrypted real-time digital earth data, and upload the encrypted real-time digital earth data to the cloud data center through the data transmission channel.

[0021] Furthermore, the cloud data center decrypts the encrypted real-time digital earth data, constructs a real-time digital twin model according to the obtained decrypted real-time digital earth data, and extracts real-time metadata, including the following steps:

[0022] The cloud data center decrypts the encrypted real-time digital earth data according to the homomorphic key to obtain the decrypted real-time digital earth data, and sets the digital twin modeling rules;

[0023] Based on the physical modeling rules in the digital twin modeling rules, construct a real-time three-dimensional geometric model of the earth according to the real-time GIS data and real-time GPS data in the decrypted real-time digital earth data;

[0024] Adjust the real-time three-dimensional geometric model of the earth according to the real-time remote sensing data to obtain the adjusted real-time three-dimensional geometric model of the earth;

[0025] Based on the data-driven rules in the digital twin modeling rules, perform digital twin configuration on the adjusted real-time three-dimensional geometric model of the earth according to the real-time earth environmental monitoring data and real-time earth social data in the decrypted real-time digital earth data to obtain a real-time digital twin model, and extract the real-time metadata of the real-time digital twin model.

[0026] Furthermore, the data analysis model is constructed based on the 3D-DBN-LSTM-Attention-MLP algorithm, and the data analysis model includes a spatial feature extraction module constructed based on the 3D-DBN algorithm, a sequence feature extraction module constructed based on the LSTM algorithm, a feature weighted fusion module constructed based on the Attention mechanism, and a data analysis module constructed based on the MLP algorithm. The spatial feature extraction module and the sequence feature extraction module are both connected to the feature weighted fusion module, and the feature weighted fusion module is connected to the data analysis module.

[0027] Furthermore, the secure storage scheme generation model is constructed based on the ISGA algorithm, and the secure storage scheme generation model includes a result parsing module, an optimization objective update module, an initial solution generation module, an iterative optimization module, and an optimal solution decoding module connected in sequence.

[0028] Furthermore, the cloud data center uses the pre-trained data analysis model to perform data analysis according to the real-time digital twin model to obtain real-time data analysis results, including the following steps:

[0029] The spatial feature extraction module using a pre-trained data analysis model extracts the real-time spatial features of the real-time digital twin model;

[0030] The sequence feature extraction module using the data analysis model extracts the real-time sequence features of the real-time digital twin model;

[0031] According to the preset attention weight values, the feature weighted fusion module of the data analysis model performs weighted fusion on the real-time spatial features and the real-time sequence features to obtain real-time weighted fusion features;

[0032] According to the real-time weighted fusion features, the data analysis module of the data analysis model performs data analysis to obtain real-time data analysis results.

[0033] Further, the cloud data center, according to the real-time data analysis results, uses a pre-trained secure storage scheme generation model to generate a secure storage scheme and obtains a real-time secure storage scheme, including the following steps:

[0034] The result parsing module of the pre-trained secure storage scheme generation model parses the real-time data analysis results to obtain real-time impact factors;

[0035] According to the real-time impact factors, the optimization target update module of the secure storage scheme generation model updates the optimization target to obtain a real-time optimization target and sets a real-time fitness function;

[0036] The initial solution generation module of the secure storage scheme generation model generates initial solutions to obtain a number of initial solutions; the initial solutions correspond to initial real-time secure storage schemes;

[0037] According to the real-time fitness function, the iterative optimization module of the secure storage scheme generation model performs iterative optimization on a number of initial solutions within the search space to obtain an optimal solution;

[0038] The optimal solution decoding module of the secure storage scheme generation model decodes the optimal solution to obtain an optimal real-time secure storage scheme.

[0039] Further, the cloud data center encrypts the real-time metadata according to the real-time secure storage scheme and uses a pre-deployed blockchain network to perform distributed storage on the encrypted real-time metadata, including the following steps:

[0040] The cloud data center encrypts the real-time metadata according to the real-time secure encryption policy in the real-time secure storage scheme to obtain encrypted real-time metadata;

[0041] According to the real-time resource scheduling policy in the real-time secure storage scheme, it schedules the real-time distributed storage resources of the pre-deployed blockchain network;

[0042] Based on real-time distributed storage resources, according to the real-time distributed storage strategy in the real-time security storage solution, use the pre-deployed blockchain network to perform distributed storage on the encrypted real-time metadata.

[0043] A secure storage system for digital earth data, used to implement the secure storage method. The system includes a cloud data center, a number of ground data stations, and a number of data acquisition terminals. The cloud data center is respectively communicatively connected to the number of ground data stations, and each ground data station is respectively communicatively connected to the corresponding number of data acquisition terminals;

[0044] The cloud data center includes a model construction unit, a data analysis unit, a solution generation unit, and a secure storage unit connected in sequence;

[0045] The data acquisition terminals include a remote sensing platform, a geographic information system, a global positioning system, an earth environment monitoring sensor network, and an earth social server.

[0046] The beneficial effects of the present invention are:

[0047] A secure storage method and system for digital earth data provided by the present invention. In data transmission, the quantum key distribution technology is adopted to improve the security level of the homomorphic key, ensure the confidentiality of data during transmission and storage, effectively resist the threats of emerging technologies for data attacks, and utilize the distributed storage characteristics of blockchain technology to achieve decentralized storage of data, greatly reducing the risk of centralized attack and leakage of data; the ground data stations have strong preprocessing capabilities, can effectively eliminate redundant information, reduce the amount of uploaded data, relieve the processing burden of the cloud data center, adopt advanced data analysis models, deeply excavate data features and values, improve the accuracy and efficiency of data processing and analysis, and are applicable to the application scenarios of digital earth data management; convert real-time digital earth data into real-time digital twin models, and by storing the real-time metadata of the real-time digital twin models, not only can the efficient storage of real-time digital earth data be realized, but also the memory requirements can be reduced and the efficiency of data management can be improved; use the secure storage solution generation model to dynamically generate secure storage solutions according to real-time data changes and requirements, realize flexible adjustment of secure encryption and distributed storage strategies, and flexibly schedule the distributed storage resources of the blockchain network to improve resource utilization.

[0048] Other beneficial effects of the present invention will be further described in the specific implementation manners. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 is a flowchart of the secure storage method for digital earth data in the present invention.

[0050] Figure 2It is the structural block diagram of the secure storage system for digital earth data in the present invention. Detailed implementation manners

[0051] The present invention will be further explained below in conjunction with the accompanying drawings and specific embodiments.

[0052] Embodiment 1:

[0053] As Figure 1 shown, this embodiment provides a secure storage method for digital earth data, including the following steps:

[0054] S1: The ground data station collects real-time digital earth data, preprocesses and encrypts the real-time digital earth data to obtain encrypted real-time digital earth data, and uploads it to the cloud data center;

[0055] The real-time digital earth data includes real-time remote sensing data, real-time GIS data, real-time GPS data, real-time earth environment monitoring data, and real-time earth social data;

[0056] The real-time remote sensing data includes data such as images of the earth's surface obtained in real time by remote sensing platforms such as satellites and drones; the real-time GIS data includes spatial data such as maps, terrain, land use, and infrastructure obtained in real time by a geographic information system; the real-time GPS data includes data such as position, speed, and time obtained in real time by a global positioning system; the real-time earth environment monitoring data includes sensor data such as air quality, water quality, and soil conditions obtained in real time by an earth environment monitoring sensor network; the real-time earth social data includes data such as human activities, event propagation, population flow, traffic conditions, and social and economic activities obtained in real time by an earth social server;

[0057] The ground data station collects real-time digital earth data, preprocesses and encrypts the real-time digital earth data to obtain encrypted real-time digital earth data, and uploads it to the cloud data center, including the following steps:

[0058] S1-1: The ground data station receives the initial real-time remote sensing data sent by the remote sensing platform, the initial real-time GIS data sent by the geographic information system, the initial real-time GPS data sent by the global positioning system, the initial real-time earth environment monitoring data sent by the earth environment monitoring sensor network, and the initial real-time earth social data sent by the earth social server to obtain real-time digital earth data;

[0059] S1-2: Preprocess the heterogeneous initial real-time remote sensing data, initial real-time GIS data, initial real-time GPS data, initial real-time earth environmental monitoring data, and initial real-time earth social data to obtain homogeneous final real-time remote sensing data, final real-time GIS data, final real-time GPS data, final real-time earth environmental monitoring data, and final real-time earth social data, and integrate them to obtain preprocessed real-time digital earth data;

[0060] The preprocessing includes processing tasks such as format conversion, denoising, and calibration on the collected raw data to ensure data quality and consistency, as well as processing tasks such as format conversion, normalization, and standardization on heterogeneous data so that the data can be recognized by the cloud data center;

[0061] S1-3: Construct a quantum transmission channel and a data transmission channel between the ground data station and the cloud data center, generate a homomorphic key, and use the Quantum Key Distribution (QKD) technology to send the homomorphic key to the cloud data center through the quantum transmission channel, including the following steps:

[0062] S1-3-1: Construct a quantum transmission channel and a data transmission channel between the ground data station and the cloud data center, generate a homomorphic key at the ground data station, and convert the homomorphic key into a key quantum state;

[0063] S1-3-2: At the cloud data center, verify the legitimacy of the identity information of the ground data station. After the legitimacy verification passes, the cloud data center sends a key distribution signal to the ground data station;

[0064] S1-3-3: At the ground data station, confirm the key distribution signal, send the key quantum state to the cloud data center through the quantum transmission channel, and measure the key quantum state to obtain a first measurement result;

[0065] 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;

[0066] S1-3-4: At the cloud data center, measure the received key quantum state to obtain a second measurement result, and through an open communication line, perform a public basis comparison and error rate estimation with the first measurement result of the ground data station. After the public basis comparison and error rate estimation pass, obtain the homomorphic key in the cloud data center;

[0067] The basis vectors used for measuring quantum states are publicly disclosed through an open communication channel. The measurement results are only valid when the basis vectors of the first measurement result and the second measurement result are the same. By comparing partial measurement results, the error rate of the quantum communication line is estimated. If the error rate is too high, it may indicate eavesdropping, and in this case, the current quantum key interaction should be abandoned;

[0068] S1-4: Encrypt the preprocessed real-time digital earth data according to the homomorphic key to obtain the encrypted real-time digital earth data, and upload the encrypted real-time digital earth data to the cloud data center through the data transmission channel;

[0069] S2: The cloud data center decrypts the encrypted real-time digital earth data, constructs a real-time digital twin model based on the obtained decrypted real-time digital earth data, and extracts real-time metadata, including the following steps:

[0070] S2-1: The cloud data center decrypts the encrypted real-time digital earth data according to the homomorphic key to obtain the decrypted real-time digital earth data, and sets the digital twin modeling rules;

[0071] S2-2: Based on the physical modeling rules in the digital twin modeling rules, construct a real-time three-dimensional geometric model of the earth according to the real-time GIS data and real-time GPS data in the decrypted real-time digital earth data;

[0072] The real-time three-dimensional geometric model of the earth protects information such as the shape, size, terrain, landforms, and locations on the earth's surface;

[0073] S2-3: Adjust the real-time three-dimensional geometric model of the earth according to the real-time remote sensing data to obtain the adjusted real-time three-dimensional geometric model of the earth, improving the accuracy and authenticity of the three-dimensional geometric model of the earth;

[0074] S2-4: Based on the data-driven rules in the digital twin modeling rules, perform digital twin configuration on the adjusted real-time three-dimensional geometric model of the earth according to the real-time earth environmental monitoring data and real-time earth social data in the decrypted real-time digital earth data to obtain a real-time digital twin model, and extract the real-time metadata of the real-time digital twin model;

[0075] The real-time digital twin model can simulate the dynamic change process on the earth's surface, such as human activities, meteorological changes, traffic flows, etc.; The real-time metadata is used to describe the mapping relationship between the digital twin model and the digital earth data, that is, how to correspond the data in the digital twin model to the real digital earth data, and can trace the source of the data in the digital twin model to ensure the credibility of the data, the format, structure, update time, etc. of the real-time digital earth data, and the specific data sources of the real-time digital earth data;

[0076] S3: The cloud data center performs data analysis based on the real-time digital twin model using a pre-trained data analysis model to obtain real-time data analysis results;

[0077] The data analysis model is constructed based on the 3D - Deep Belief Network (DBN) - Long Short-Term Memory (LSTM) - Attention - Multilayer Perceptron (MLP) algorithm. The data analysis model includes a spatial feature extraction module constructed based on the 3D-DBN algorithm, a sequence feature extraction module constructed based on the LSTM algorithm, a feature weighted fusion module constructed based on the Attention mechanism, and a data analysis module constructed based on the MLP algorithm. The spatial feature extraction module and the sequence feature extraction module are both connected to the feature weighted fusion module, and the feature weighted fusion module is connected to the data analysis module;

[0078] The spatial feature extraction module captures the complex structure and relationships of the data in the three-dimensional space by learning the representation of the data layer by layer, and can effectively extract the deep features of the data, improving the efficiency and quality of feature extraction, that is, the spatial features of the earth's surface represented by the real-time digital twin model; The sequence feature extraction module controls the flow of information by introducing memory units and gating mechanisms (including input gates, forget gates, and output gates), so as to be able to learn and retain long-term dependencies, capture the dynamic changes in the sequence, and can extract the dynamic change data features represented by the real-time digital twin model; The feature weighted fusion module uses the Attention mechanism to perform weighted fusion on the spatial features and sequence features, automatically adjusts the weights according to the importance of the features, and highlights the key information; The data analysis module uses a multilayer perceptron to further analyze and process the fused features, and learns the complex mapping relationship between the features and the output labels through non-linear transformation;

[0079] The cloud data center performs data analysis based on the real-time digital twin model using a pre-trained data analysis model to obtain real-time data analysis results, including the following steps:

[0080] S3-1: Use the spatial feature extraction module of the pre-trained data analysis model to extract the real-time spatial features of the real-time digital twin model;

[0081] S3-2: Use the sequence feature extraction module of the data analysis model to extract the real-time sequence features of the real-time digital twin model;

[0082] S3-3: According to the preset attention weight value, use the feature weighted fusion module of the data analysis model to perform weighted fusion on the real-time spatial features and real-time sequence features to obtain real-time weighted fusion features;

[0083] S3-4: Using the data analysis module of the data analysis model, perform data analysis based on the real-time weighted fusion features to obtain real-time data analysis results;

[0084] The real-time data analysis results include the integrity analysis results of real-time digital earth data, the accuracy analysis results of real-time digital twin models, data distribution analysis results, memory occupancy analysis results, complexity analysis results, sensitivity analysis results, and dynamic data analysis results of the earth's surface, etc.;

[0085] S4: The cloud data center, according to the real-time data analysis results, uses a pre-trained security storage scheme generation model to perform security storage scheme generation to obtain a real-time security storage scheme;

[0086] The security storage scheme generation model is constructed based on the Improved Snow Geese Algorithm (ISGA), and the security storage scheme generation model includes a result parsing module, an optimization objective update module, an initial solution generation module, an iterative optimization module, and an optimal solution decoding module connected in sequence;

[0087] The result parsing module is used to parse the real-time data analysis results to obtain real-time influencing factors;

[0088] The optimization objective update module is used to update the optimization objective according to the real-time influencing factors to obtain a real-time optimization objective and set a real-time fitness function;

[0089] The initial solution generation module is used to generate initial solutions to obtain a number of initial solutions; the initial solutions correspond to initial real-time security storage schemes;

[0090] The iterative optimization module is used to perform iterative optimization on a number of initial solutions within the search space according to the real-time fitness function to obtain an optimal solution;

[0091] The optimal solution decoding module is used to decode the optimal solution to obtain an optimal real-time security storage scheme;

[0092] The cloud data center, according to the real-time data analysis results, uses a pre-trained security storage scheme generation model to perform security storage scheme generation to obtain a real-time security storage scheme, including the following steps:

[0093] S4-1: Use the result parsing module of the pre-trained security storage scheme generation model to parse the real-time data analysis results to obtain real-time influencing factors;

[0094] In this embodiment, taking the memory occupancy analysis result in the real-time data analysis result as large memory occupancy and the complexity analysis result as low complexity as an example, the real-time impact factors are the real-time distributed storage memory occupancy rate and the real-time encryption algorithm complexity; the real-time digital twin model has a large memory occupancy. When performing distributed storage, it is necessary to ensure that its memory occupancy rate is as low as possible. The real-time digital twin model has a low complexity, and the complexity of the encryption algorithm used should be kept as low as possible;

[0095] S4-2: According to the real-time impact factors, use the secure storage scheme to generate an optimization target update module for the model, perform optimization target update to obtain the real-time optimization target, and set the real-time fitness function;

[0096] The formula for the real-time fitness function is:

[0097] Fit(P) = min[W1AX(P) + W2AC(P)]

[0098] In the formula, Fit(P) is the real-time fitness function; AX(P) is the real-time distributed storage memory occupancy rate; AC(P) is the real-time encryption algorithm complexity; P is the ISGA individual; W1 and W2 are the first weight value and the second weight value;

[0099] S4-3: Use the secure storage scheme to generate an initial solution generation module for the model, perform initial solution generation to obtain a number of initial solutions; the initial solutions correspond to the initial real-time secure storage scheme;

[0100] The formula is:

[0101]

[0102] In the formula, P i is the initial ISGA individual generated by the Circle chaotic mapping sequence, that is, the initial solution; P o is the randomly generated ISGA individual; i is the ISGA individual indicator; mod(*) is the remainder function;

[0103] S4-4: According to the real-time fitness function, use the secure storage scheme to generate an iterative optimization module for the model, and perform iterative optimization on a number of initial solutions within the search space to obtain the optimal solution, including the following steps:

[0104] S4-4-1: Take a number of initial solutions as the initial ISGA population, and the initial ISGA population includes a number of initial ISGA individuals;

[0105] S4-4-2: Use the real-time fitness function to obtain the initial real-time fitness value of each initial ISGA individual, and take the initial ISGA individual with the lowest real-time fitness value as the leading goose;

[0106] S4-4-3: Enter the exploration stage, introduce the leading goose rotation mechanism, the call guidance mechanism, and the dynamic reverse mechanism, iterate and update the initial ISGA population, obtain the once-updated ISGA population, and retain the optimal individual;

[0107] In the leading goose rotation mechanism, in each iteration, new leading geese are selected according to the fitness values of the ISGA individuals through competition. This mechanism can prevent the leading geese from falling into local optima prematurely and enhance the global search ability of the algorithm;

[0108] The formula is:

[0109]

[0110] In the formula, P i t+1 is the once-updated leading goose; is the initial ISGA individual with the third-lowest reciprocal fitness value in the initial ISGA populations at the t-th and (t + 1)-th iteration times; is the initial ISGA individual with the fifth-lowest reciprocal fitness value in the initial ISGA population at the t-th iteration time; t is the current iteration time; is the optimal individual; a is the first weight factor; rand is the random number generation function;

[0111] In the call guidance mechanism, according to the distance between the ISGA individuals and the leading geese, the sound wave propagation attenuation model is used to adjust the individual position update. For the ISGA individuals with a relatively short distance, their position updates are more affected by the leading geese and can quickly approach the optimal solution. For the ISGA individuals with a relatively long distance, their position updates are less affected by the leading geese and can maintain a certain exploration ability. This mechanism can prevent the group from over-aggregating or dispersing and improve the local search accuracy of the algorithm;

[0112] The formula is:

[0113]

[0114] In the formula, is the once-updated ISGA individual; is the initial ISGA individual at the t-th iteration time; is the sound intensity received by the initial ISGA individual; is the sound intensity parameter; L WA is the initial sound intensity; L low is the lowest receivable sound intensity; a" is the convergence factor; is the initial ISGA individual with the farthest distance; r' is the random parameter; B(d) is the Brownian motion function; d is the Brownian motion parameter; ⊕ is the exclusive OR processing symbol;

[0115]

[0116] Wherein, a" is the convergence factor; tanh(.) is the hyperbolic tangent function; t is the current iteration number; t max is the maximum iteration number; a max and 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;

[0117] The dynamic reverse mechanism dynamically reverses the initial ISGA individuals to improve the diversity of exploration directions and avoid falling into local optima;

[0118] The formula is:

[0119]

[0120] Wherein, is the reverse ISGA individual updated once; γ is the decreasing inertia coefficient; L max and L min are the maximum and minimum values of the vector space respectively;

[0121] Integrate the leading goose updated once, several ISGA individuals updated once, and several reverse ISGA individuals updated once to obtain the ISGA population updated once, and retain the ISGA individual with the lowest fitness value as the optimal individual;

[0122] S4-4-4: Enter the development stage, introduce the abnormal boundary strategy and the Gaussian mutation mechanism to perform secondary update on the ISGA population updated once to obtain the ISGA population updated twice, and retain the optimal individual;

[0123] The abnormal boundary strategy calculates the difference between the fitness value of each ISGA individual updated once and the average fitness value of the group. For the ISGA individuals whose fitness values are much higher than the average value of the group, the position update method will be adjusted, such as using the Gaussian mutation mechanism, a larger step size or a smaller step size. This mechanism can help individuals avoid falling into local optima and improve the convergence speed and accuracy of the algorithm;

[0124] The formula is:

[0125]

[0126] Wherein, is the ISGA individual updated twice; is the ISGA individual updated once; Fit(*) is the fitness function; Fit avg is the average fitness value of the group; The ISGA individual with the highest fitness value; a' and e are the second weight factor and the third weight factor; G(1,1) is the parameter of the Gaussian mutation mechanism;

[0127] S4-4-5: If the number of iterations is greater than or equal to the iteration threshold or the real-time fitness value of the optimal individual is less than the fitness threshold, then output the optimal individual as the optimal solution;

[0128] S4-5: Use the optimal solution decoding module of the security storage scheme generation model to decode the optimal solution to obtain the optimal real-time security storage scheme;

[0129] S5: The cloud data center encrypts the real-time metadata according to the real-time security storage scheme and uses the pre-deployed blockchain network to perform distributed storage on the encrypted real-time metadata, including the following steps:

[0130] S5-1: The cloud data center encrypts the real-time metadata according to the real-time security encryption policy in the real-time security storage scheme to obtain the encrypted real-time metadata;

[0131] S5-2: According to the real-time resource scheduling policy in the real-time security storage scheme, schedule the real-time distributed storage resources of the pre-deployed blockchain network;

[0132] The blockchain network includes several distributedly connected data nodes. According to the real-time resource scheduling policy, schedule some real-time data nodes among the several data nodes as real-time distributed storage resources for realizing distributed storage;

[0133] S5-3: Based on the real-time distributed storage resources, according to the real-time distributed storage policy in the real-time security storage scheme, use the pre-deployed blockchain network to perform distributed storage on the encrypted real-time metadata, including the following steps:

[0134] S5-3-1: According to the real-time data sharding decision of the real-time distributed storage policy in the real-time security storage scheme, use the corresponding replication policy to shard the encrypted real-time metadata to obtain several real-time data shards including replicated shards;

[0135] S5-3-2: According to the real-time distributed storage decision of the real-time distributed storage policy in the real-time security storage scheme, send several real-time data shards to several real-time data nodes included in the real-time distributed storage resources of the pre-deployed blockchain network;

[0136] S5-3-3: Use several real-time data nodes to locally store the received real-time data shards and store the real-time storage address and the real-time data analysis result in the distributed ledger.

[0137] Embodiment 2:

[0138] As shown Figure 2 in the figure, this embodiment provides a secure storage system for digital earth data to implement a secure storage method. The system includes a cloud data center, a number of ground data stations, and a number of data acquisition terminals. The cloud data center is communicatively connected to the number of ground data stations respectively, and each ground data station is communicatively connected to the corresponding number of data acquisition terminals respectively;

[0139] The data acquisition terminal is used to collect real-time digital earth data and send the real-time digital earth data to the corresponding ground data station;

[0140] The ground data station is used to receive the real-time digital earth data, preprocess and encrypt the real-time digital earth data to obtain the encrypted real-time digital earth data, and upload it to the cloud data center;

[0141] The cloud data center includes a model construction unit, a data analysis unit, a solution generation unit, and a secure storage unit that are connected in sequence;

[0142] The model construction unit is used to use artificial intelligence algorithms to construct a data analysis model and a secure storage solution generation model, deploy a blockchain network; decrypt the encrypted real-time digital earth data, construct a real-time digital twin model based on the obtained decrypted real-time digital earth data, and extract real-time metadata;

[0143] The data analysis unit is used to perform data analysis according to the real-time digital twin model using a pre-trained data analysis model to obtain a real-time data analysis result;

[0144] The solution generation unit is used to generate a secure storage solution according to the real-time data analysis result using a pre-trained secure storage solution generation model to obtain a real-time secure storage solution;

[0145] The secure storage unit is used to encrypt the real-time metadata according to the real-time secure storage solution and perform distributed storage on the obtained encrypted real-time metadata using a pre-deployed blockchain network;

[0146] The data acquisition terminal includes a remote sensing platform, a geographic information system, a global positioning system, an earth environment monitoring sensor network, and an earth social server.

[0147] The present invention provides a secure storage method and system for digital earth data. In data transmission, quantum key distribution technology is used to improve the security level of homomorphic keys, ensure the confidentiality of data during transmission and storage, effectively resist the threat of emerging data attack technologies, and utilize the distributed storage characteristics of blockchain technology to achieve decentralized storage of data, greatly reducing the risk of data being attacked and leaked in a centralized manner. The ground data station has a strong pre-processing capability, can effectively eliminate redundant information, reduce the amount of uploaded data, and reduce the processing burden of the cloud data center. Advanced data analysis models are used to deeply mine data features and values, improve the accuracy and efficiency of data processing and analysis, and are suitable for application scenarios of digital earth data management. Real-time digital earth data is converted into a real-time digital twin model. By storing real-time metadata of the real-time digital twin model, not only can efficient storage of real-time digital earth data be achieved, but also memory requirements can be reduced and data management efficiency can be improved. A secure storage solution generation model is used to dynamically generate a secure storage solution according to real-time data changes and requirements, to achieve flexible adjustment of secure encryption and distributed storage strategies, and to flexibly schedule distributed storage resources of the blockchain network to improve resource utilization.

[0148] The present invention is not limited to the above optional implementations, and anyone can derive other various forms of products under the enlightenment of the present invention. The above specific implementations should not be understood as limiting the scope of protection of the present invention. The scope of protection of the present invention should be based on the definition in the claims, and the description can be used to interpret the claims.

Claims

1. A secure storage method for digital earth data, characterized in that: It includes the following steps: The ground data station collects real-time digital earth data, preprocesses and encrypts the real-time digital earth data to obtain encrypted real-time digital earth data, and uploads it to the cloud data center; The cloud data center decrypts the encrypted real-time digital earth data, constructs a real-time digital twin model based on the obtained decrypted real-time digital earth data, and extracts real-time metadata; The cloud data center uses a pre-trained data analysis model to perform data analysis based on the real-time digital twin model to obtain real-time data analysis results; The cloud data center uses a pre-trained secure storage scheme generation model to generate a secure storage scheme based on the real-time data analysis results to obtain a real-time secure storage scheme; The cloud data center encrypts the real-time metadata according to the real-time secure storage scheme and uses a pre-deployed blockchain network to perform distributed storage on the obtained encrypted real-time metadata.

2. The secure storage method of digital earth data according to claim 1, characterized in that: The real-time digital earth data includes real-time remote sensing data, real-time GIS data, real-time GPS data, real-time earth environment monitoring data, and real-time earth social data.

3. A secure storage method for digital earth data according to claim 2, characterized in that: The ground data station collects real-time digital earth data, preprocesses and encrypts the real-time digital earth data to obtain encrypted real-time digital earth data, and uploads it to the cloud data center, including the following steps: The ground data station receives the initial real-time remote sensing data sent by the remote sensing platform, the initial real-time GIS data sent by the geographic information system, the initial real-time GPS data sent by the global positioning system, the initial real-time earth environment monitoring data sent by the earth environment monitoring sensor network, and the initial real-time earth social data sent by the earth social server to obtain real-time digital earth data; Preprocess the heterogeneous initial real-time remote sensing data, initial real-time GIS data, initial real-time GPS data, initial real-time earth environment monitoring data, and initial real-time earth social data to obtain homogeneous final real-time remote sensing data, final real-time GIS data, final real-time GPS data, final real-time earth environment monitoring data, and final real-time earth social data, and integrate them to obtain preprocessed real-time digital earth data; Build a quantum transmission channel and a data transmission channel between the ground data station and the cloud data center, generate a homomorphic key, and use QKD technology to send the homomorphic key to the cloud data center through the quantum transmission channel; Encrypt the preprocessed real-time digital earth data according to the homomorphic key to obtain encrypted real-time digital earth data, and upload the encrypted real-time digital earth data to the cloud data center through the data transmission channel.

4. A secure storage method for digital earth data according to claim 3, characterized in that: The cloud data center decrypts the encrypted real-time digital earth data, constructs a real-time digital twin model based on the obtained decrypted real-time digital earth data, and extracts real-time metadata, including the following steps: The cloud data center decrypts the encrypted real-time digital earth data according to the homomorphic key to obtain decrypted real-time digital earth data, and sets digital twin modeling rules; Based on the physical modeling rules in the digital twin modeling rules, a real-time three-dimensional geometric model of the earth is constructed according to the real-time GIS data and real-time GPS data in the decrypted real-time digital earth data; According to the real-time remote sensing data, the real-time three-dimensional geometric model of the earth is adjusted to obtain an adjusted real-time three-dimensional geometric model of the earth; Based on the data-driven rules in the digital twin modeling rules, according to the real-time earth environmental monitoring data and real-time earth social data in the decrypted real-time digital earth data, digital twin configuration is performed on the adjusted real-time three-dimensional geometric model of the earth to obtain a real-time digital twin model, and the real-time metadata of the real-time digital twin model is extracted.

5. A secure storage method for digital earth data according to claim 4, characterized in that: The described data analysis model is constructed based on the 3D-DBN-LSTM-Attention-MLP algorithm, and the data analysis model includes a spatial feature extraction module constructed based on the 3D-DBN algorithm, a sequence feature extraction module constructed based on the LSTM algorithm, a feature weighted fusion module constructed based on the Attention mechanism, and a data analysis module constructed based on the MLP algorithm. The spatial feature extraction module and the sequence feature extraction module are both connected to the feature weighted fusion module, and the feature weighted fusion module is connected to the data analysis module.

6. A secure storage method for digital earth data according to claim 5, characterized in that: The described secure storage scheme generation model is constructed based on the ISGA algorithm, and the secure storage scheme generation model includes a result parsing module, an optimization target update module, an initial solution generation module, an iterative optimization module, and an optimal solution decoding module connected in sequence.

7. A method for secure storage of digital earth data according to claim 6, characterized in that: The cloud data center, according to the real-time digital twin model, uses a pre-trained data analysis model to perform data analysis to obtain real-time data analysis results, including the following steps: Use the spatial feature extraction module of the pre-trained data analysis model to extract the real-time spatial features of the real-time digital twin model; Use the sequence feature extraction module of the data analysis model to extract the real-time sequence features of the real-time digital twin model; According to the preset attention weight value, use the feature weighted fusion module of the data analysis model to perform weighted fusion on the real-time spatial features and real-time sequence features to obtain real-time weighted fusion features; According to the real-time weighted fusion features, use the data analysis module of the data analysis model to perform data analysis to obtain real-time data analysis results.

8. A method for secure storage of digital earth data according to claim 7, characterized in that: The cloud data center, according to the real-time data analysis results, uses a pre-trained secure storage scheme generation model to generate a secure storage scheme to obtain a real-time secure storage scheme, including the following steps: Use the result parsing module of the pre-trained secure storage scheme generation model to parse the real-time data analysis results to obtain real-time impact factors; According to the real-time impact factors, use the optimization target update module of the secure storage scheme generation model to perform optimization target update to obtain a real-time optimization target and set a real-time fitness function; Use the initial solution generation module of the secure storage scheme generation model to generate initial solutions to obtain a number of initial solutions; the initial solutions correspond to initial real-time secure storage schemes; According to the real-time fitness function, an iterative optimization module of the model is generated using a secure storage scheme, and several initial solutions are iteratively optimized within the search space to obtain the optimal solution; An optimal solution decoding module of the model is generated using a secure storage scheme to decode the optimal solution and obtain the optimal real-time secure storage scheme.

9. The secure storage method of digital earth data according to claim 8, characterized in that: The cloud data center encrypts the real-time metadata according to the real-time secure storage scheme and uses a pre-deployed blockchain network to perform distributed storage on the encrypted real-time metadata, including the following steps: The cloud data center encrypts the real-time metadata according to the real-time security encryption policy in the real-time secure storage scheme to obtain the encrypted real-time metadata; According to the real-time resource scheduling policy in the real-time secure storage scheme, the real-time distributed storage resources of the pre-deployed blockchain network are scheduled; Based on the real-time distributed storage resources, according to the real-time distributed storage policy in the real-time secure storage scheme, the pre-deployed blockchain network is used to perform distributed storage on the encrypted real-time metadata.

10. A secure storage system for digital earth data, which is used to implement the secure storage method as described in any one of claims 1-9, and is characterized in that: The described system includes a cloud data center, several ground data stations, and several data acquisition terminals. The cloud data center is respectively communicatively connected to several ground data stations, and each of the ground data stations is respectively communicatively connected to the corresponding several data acquisition terminals; The cloud data center includes a model construction unit, a data analysis unit, a solution generation unit, and a secure storage unit connected in sequence; The data acquisition terminal includes a remote sensing platform, a geographic information system, a global positioning system, an earth environmental monitoring sensor network, and an earth social server.

Images