Construction method of unmanned aerial vehicle real-time data analysis model based on blockchain

Abstract

The application discloses a method for constructing a real-time data analysis model of a blockchain-based unmanned aerial vehicle, and relates to the technical field of unmanned aerial vehicle communication, comprising the following steps: an unmanned aerial vehicle establishes an ad-hoc mesh network through a 5G NR-U frequency band, a ground control station performs legality verification, an initial network topology graph is generated, a private blockchain network is built based on a Hyperledger Fabric framework, and a genesis block is generated; video stream data is collected, an inertial measurement unit records attitude data, and compressed data packets are generated; the unmanned aerial vehicle scans a body super surface pattern through a terahertz transmitter to obtain a scattering characteristic matrix, generates a composite hash value, and appends the composite hash value to the compressed data packets to form a data packet to be transmitted; the refractive index structure constant of a current region is measured to obtain a turbulence intensity level.The application obtains physical fingerprint characteristics by scanning a body super surface through a terahertz, generates an anti-interference hash value in combination with space-time parameters, realizes hardware-level identity authentication, and fundamentally eliminates the risk of unmanned aerial vehicle identity cloning.

Description

Technical Field

[0001] This invention relates to the field of unmanned aerial vehicle (UAV) communication technology, and in particular to a method for constructing a blockchain-based real-time data analysis model for UAVs. Background Technology

[0002] In recent years, with the rapid development of drone technology, in order to ensure the efficient collaboration and data security of drone swarms in complex environments, a distributed ledger has been constructed to achieve trusted storage and sharing of drone data. This technology utilizes smart contracts to verify and authorize drone data and employs traditional erasure coding technology to ensure the reliability of data transmission. However, this solution lacks physical layer security at the data acquisition end. Drone identity authentication relies on traditional digital certificate mechanisms, which are difficult to defend against hardware cloning attacks. Furthermore, the fixed error correction coding strategy used at the data transmission layer cannot adapt to changes in dynamic channel conditions such as atmospheric turbulence, leading to difficulties in guaranteeing data integrity in high-error-rate scenarios.

[0003] Existing blockchain-based drone communication technologies lack a collaborative guarantee mechanism for drone physical identity and data transmission reliability, and have insufficient adaptive coding and real-time analysis capabilities in dynamic environments. This invention mainly addresses the issues of trusted networking, anti-interference transmission, and real-time analysis of drone swarms in complex environments. By integrating metasurface terahertz fingerprint authentication, turbulent adaptive coding, and edge intelligent analysis, it achieves full-stack security and efficiency optimization from the physical layer to the application layer. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides a method for constructing a blockchain-based real-time data analysis model for drones, addressing the technical problem that existing technologies cannot coordinate and optimize drone physical identity authentication and dynamic channel adaptive transmission.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, the present invention provides a method for constructing a real-time data analysis model for unmanned aerial vehicles (UAVs) based on blockchain, which includes: the UAV establishing an ad-hoc mesh network through the 5G NR-U band; the ground control station performing legality verification; generating an initial network topology map; building a private blockchain network based on the Hyperledger Fabric framework; and generating a genesis block.

[0008] The system acquires video stream data, records attitude data using the inertial measurement unit, and generates compressed data packets.

[0009] The UAV scans the metasurface pattern on its fuselage with a terahertz transmitter to obtain a scattering feature matrix, generates a composite hash value, and appends it to the compressed data packet to form a data packet to be transmitted.

[0010] The refractive index structure constant of the current region is measured to obtain the turbulence intensity level. The turbulence intensity level is added to the data packet to be transmitted. The data packet to be transmitted is split into data fragments according to the initial network topology. The relay node is selected for routing and forwarding using the Kademeria algorithm.

[0011] Based on the turbulence intensity level, redundant encoding is performed on the data packets to be transmitted to generate transmission units with error correction codes. The endorsement nodes of the private blockchain network verify the transmission units with error correction codes through the Byzantine fault-tolerant consensus mechanism, sort the service nodes in the private blockchain network to generate new blocks, and send the verified transmission units with error correction codes to the new blocks.

[0012] The smart contract triggers the edge computing node to perform Reed-Solomon decoding on the transmission unit with error correction code to restore it into the data packet to be transmitted. The TensorFlow Lite inference engine is used to perform target detection analysis and generate a format analysis report.

[0013] As a preferred embodiment of the blockchain-based drone real-time data analysis model construction method described in this invention, the drone establishes an ad-hoc mesh network via the 5G NR-U band, the ground control station verifies legitimacy, generates an initial network topology map, and a private blockchain network is built based on the Hyperledger Fabric framework to generate a genesis block, including the following steps.

[0014] The baseband chip scans the 5925-7125MHz frequency band, measures the frequency signal-to-noise ratio, and generates a spectrum analysis report. The ground control station receives the spectrum analysis report, executes the frequency point algorithm to obtain the center frequency point, and derives the TDMA time slot allocation scheme based on the center frequency point to obtain the time slot configuration table.

[0015] The UAV sends beacon frames according to the time slot configuration table, establishes connection nodes and generates a neighbor list. The ground control station sends PUF challenge codes to each UAV to obtain the PUF feature vector set. The control station sends maneuver commands and generates behavior authentication results through IMU data verification.

[0016] The behavioral authentication results are combined with the PUF feature vector set to perform threshold judgment and output a list of legal drones;

[0017] Based on the neighbor list and the list of legal drones, an initial topology graph is generated using Dijkstra's algorithm;

[0018] Based on the list of legitimate drones, the cryptogen tool is used to generate a set of node certificates. The node certificate set is then configured to obtain the genesis block.

[0019] As a preferred embodiment of the blockchain-based UAV real-time data analysis model construction method of the present invention, the method includes the following steps: acquiring video stream data, recording attitude data by an inertial measurement unit, and generating a compressed data packet.

[0020] The drone aligns its sensor clock with the GPS PPS signal to obtain a timestamp sequence, and dynamically adjusts the frame rate based on the timestamp sequence and IMU speed data to obtain video stream data;

[0021] The inertial measurement unit uses timestamp sequence IMU velocity data to trigger differential coding to obtain attitude data;

[0022] The video stream data and pose data are concatenated to obtain a compressed data packet.

[0023] As a preferred embodiment of the blockchain-based UAV real-time data analysis model construction method of the present invention, the UAV obtains a scattering feature matrix by scanning the metasurface pattern of its fuselage with a terahertz transmitter, generates a composite hash value, and appends it to a compressed data packet to form a data packet to be transmitted, including the following steps.

[0024] The UAV uses a 0.3THz transmission module to scan the metasurface of the fuselage in a spiral trajectory to obtain the raw scattered signal data. The raw scattered signal data is then subjected to a short-time Fourier transform to obtain the time-frequency matrix.

[0025] The ResNet-18 model is trained based on the sample dataset in the time-frequency matrix. The time-frequency matrix is ​​input into the trained ResNet-18 model to obtain a unique scattering fingerprint feature vector.

[0026] Anti-interference data is obtained by reading the current grid code and fuselage temperature of the UAV and its unique scattering fingerprint feature vector;

[0027] Perform a SHA3-256 hash operation on the data to combat interference, and obtain a composite hash value;

[0028] The composite hash value is concatenated with the compressed data packet to obtain the data packet to be transmitted.

[0029] As a preferred embodiment of the blockchain-based UAV real-time data analysis model construction method described in this invention, the method includes: measuring the refractive index structure constant of the current region to obtain the turbulence intensity level; adding the turbulence intensity level to the data packet to be transmitted; splitting the data packet into data fragments according to the initial network topology; and selecting relay nodes for routing and forwarding using the Kademilla algorithm. This includes the following steps:

[0030] By collecting and measuring temperature, humidity and air pressure in real time, atmospheric data is compiled, and the refractive index structure constant is calculated based on the atmospheric data.

[0031] The turbulence intensity level is obtained based on the drone's current altitude and refractive index structure constant.

[0032] Add the turbulence intensity level to the header flag of the data packet to be transmitted to obtain the turbulence-tagged data packet. Calculate the fragment size based on the initial network topology and the turbulence-tagged data packet, and split the turbulence-tagged data packet into a data fragment sequence.

[0033] The Kademlia algorithm is used to select relay nodes from the initial network topology to obtain a node list, and the data slice sequence is sent to the target node according to the node list.

[0034] As a preferred embodiment of the method for constructing a blockchain-based real-time data analysis model for unmanned aerial vehicles (UAVs) according to the present invention, the method includes: redundantly encoding the data packets to be transmitted according to the turbulence intensity level to generate transmission units with error correction codes; and verifying the transmission units with error correction codes by the endorsement nodes of the private blockchain network through a Byzantine fault-tolerant consensus mechanism. This includes the following steps:

[0035] Based on the turbulence intensity level, the Reed-Solomon coding scheme is selected to perform redundant coding on the data packet to be transmitted, thereby obtaining the configuration instruction. The compressed data packet is then divided into byte blocks to obtain a data fragment group of the data block sequence to be encoded. The data fragment group of the data block sequence to be encoded is then encoded to obtain the original coding unit. A packet header is added to the original coding unit to generate the final transmission unit with error correction code.

[0036] Cyclic redundancy check is performed on the transmission unit with error correction code by the endorsement node of the private blockchain network to obtain the initial verification state. Reed-Solomon decoding is performed on the initial verification state to obtain the decoding state. The difference between the original data fragment timestamp and the current block height is checked to obtain the spatiotemporal verification state. The digital signature of the transmission unit with error correction code is verified in the Intel SGX enclave to obtain the security authentication state.

[0037] Based on the initial verification state, decoding state, spatiotemporal verification state, and security authentication state, generate a local verification result;

[0038] The local verification result is verified using the Byzantine fault-tolerant consensus mechanism to obtain the verified transmission unit with error correction code.

[0039] As a preferred embodiment of the method for constructing a blockchain-based real-time data analysis model for unmanned aerial vehicles (UAVs) according to the present invention, the method includes the following steps: sorting service nodes in a private blockchain network to generate new blocks, and transmitting verified transmission units with error correction codes to the new blocks.

[0040] Based on the CPU load, network latency, and storage IOPS of the service nodes in the private blockchain network, a priority queue is generated. Verified transmission units with error correction codes are selected from the memory pool, sorted by the received timestamp, and a block structure template is generated. The block structure template is then hashed using SHA3-256 to obtain the block hash value. The block hash value is then signed using ECDSA with the private key to obtain the block signature.

[0041] A new block is obtained by combining the block structure template, block hash value, and block signature.

[0042] The verified transmission unit with error correction code is sent to the new block via the gRPC protocol.

[0043] As a preferred embodiment of the blockchain-based real-time data analysis model for drones described in this invention, the method includes: a smart contract triggering an edge computing node to perform Reed-Solomon decoding on a transmission unit with error correction codes to restore it to a data packet to be transmitted; using the TensorFlow Lite inference engine to perform target detection analysis; and generating an analysis report, comprising the following steps.

[0044] Dynamic thresholds are obtained by statistically analyzing video stream data and posture data in a private blockchain network using smart contracts.

[0045] When a transmission unit with error correction code that has passed the smart contract monitoring and verification reaches a dynamic threshold, a trigger command is sent to the edge node to obtain a list of transmission unit IDs.

[0046] Based on the list of transmission unit IDs, the transmission units with Reed-Solomon error correction codes are retrieved from IPFS and decoded to obtain the data packets to be transmitted.

[0047] The data packets to be transmitted are decoded, input into the TensorFlow Lite model, and an analysis report is generated.

[0048] In a second aspect, the present invention provides a computer device including a memory and a processor, wherein the memory stores a computer program, wherein when the computer program is executed by the processor, it implements any step of the method for constructing a blockchain-based real-time data analysis model for unmanned aerial vehicles as described in the first aspect of the present invention.

[0049] Thirdly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the method for constructing a blockchain-based real-time data analysis model for unmanned aerial vehicles as described in the first aspect of the present invention.

[0050] The beneficial effects of this invention are as follows: physical fingerprint features are obtained by scanning the metasurface of the fuselage using terahertz scanning, and anti-interference hash values ​​are generated by combining spatiotemporal parameters to achieve hardware-level identity authentication, fundamentally eliminating the risk of drone identity cloning. The RS coding scheme and routing strategy are dynamically adjusted based on real-time turbulence intensity, and the channel state is accurately quantified by the refractive index structure constant, which improves coding efficiency and ensures transmission success rate even in strong interference environments. Physical fingerprint authentication ensures the credibility of the data source, dynamic coding ensures the reliability of the transmission process, and together with the blockchain consensus mechanism, a full-stack security system from the physical layer to the application layer is constructed. Attached Figure Description

[0051] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0052] Figure 1 This is a flowchart illustrating the construction method of a blockchain-based real-time data analysis model for drones.

[0053] Figure 2 This is a schematic diagram of the initial topology.

[0054] Figure 3 This is a schematic diagram of the analysis report.

[0055] Figure 4 This is a schematic diagram of data acquisition and processing. Detailed Implementation

[0056] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0057] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0058] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0059] Reference Figures 1-4 This is one embodiment of the present invention, which provides a method for constructing a blockchain-based real-time data analysis model for unmanned aerial vehicles, including the following steps:

[0060] S1. The drone establishes an ad-hoc mesh network via the 5G NR-U band. The ground control station verifies the legitimacy, generates an initial network topology map, builds a private blockchain network based on the Hyperledger Fabric framework, and generates the genesis block.

[0061] S1.1 The baseband chip scans the 5925-7125MHz frequency band, measures the frequency signal-to-noise ratio, and generates a spectrum analysis report. The ground control station receives the spectrum analysis report, executes the frequency point algorithm to obtain the center frequency point, and derives the TDMA time slot allocation scheme based on the center frequency point to obtain the time slot configuration table.

[0062] Specifically, the expression is,

[0063]

[0064] Among them, f optimal As the center frequency, P interf (i) represents the interference power of the i-th transmitting node, SNR(i) represents the signal-to-interference-plus-noise ratio of the i-th transmitting node, CQI(f) represents the channel quality score of frequency point f, f is the frequency point index, b is the channel quality weight coefficient, i is the transmitting node index, and N is the total number of transmitting nodes.

[0065] It should be noted that the baseband chip scans the 5925-7125MHz frequency band, measures the signal-to-noise ratio (SNR) of each frequency point, and generates a spectrum analysis report. After receiving the spectrum analysis report, the ground control station executes a frequency point selection algorithm to calculate the optimal center frequency point. For example, when the SNR of the frequency point 6100MHz is the highest and the interference power is the lowest, it is selected as the center frequency point. Based on the center frequency point, the time division multiple access (TDMA) time slot allocation scheme is calculated, and a time slot configuration table containing the mapping relationship between time slot numbers and UAV numbers is output. For example, when the center frequency point is 6100MHz, an 8-time slot cyclic allocation configuration table is generated. The spectrum analysis report includes the SNR, interference power, and channel quality score of each frequency point.

[0066] S1.2 The UAV sends beacon frames according to the time slot configuration table, establishes connection nodes and generates a neighbor list. The ground control station sends PUF challenge codes to each UAV to obtain the PUF feature vector set. The control station sends maneuver commands and generates behavior authentication results through IMU data verification.

[0067] Furthermore, the UAV sends beacon frames containing device ID and location information in the designated time slot according to the time slot configuration table, and nodes that successfully establish communication connections form a neighbor list; the ground control station sends a physically unclonable function challenge code to each UAV, and the UAV returns a hardware fingerprint response to generate a set of physically unclonable function feature vectors; the control station sends instructions containing a preset maneuver trajectory, and the UAV records the actual motion data through the inertial measurement unit, calculates the correlation coefficient between the preset trajectory and the actual trajectory, and generates a behavior authentication pass result when the correlation coefficient exceeds 0.9.

[0068] S1.3 Combine the behavior authentication results with the PUF feature vector set, perform threshold decision and output a list of legal drones.

[0069] Furthermore, the behavioral authentication results are combined with the physical non-cloning function feature vector set for verification. When the correlation coefficient of the motion trajectory in the behavioral authentication results is greater than 0.9 and the detection distance of the physical non-cloning function feature vector set is less than 0.15, it is determined to be a legitimate UAV and output to the list of legitimate UAVs. During the verification process, the correlation coefficient of the motion trajectory in the behavioral authentication results is calculated using the triaxial acceleration and angular velocity data collected by the inertial measurement unit, and the Hamming distance of the physical non-cloning function feature vector set is used to derive the list of legitimate UAVs by comparing the response code with the pre-stored benchmark value.

[0070] S1.4. Based on the neighbor list and the list of legal drones, use Dijkstra's algorithm to generate the initial topology graph.

[0071] Furthermore, based on the communication connection status in the neighbor list and the device verification information in the list of legitimate drones, the Dijkstra algorithm is used to calculate the optimal path and generate an initial topology graph. The neighbor list contains the drone device IDs and signal strength data of those with established connections, and the list of legitimate drones contains the drone device IDs that have passed the physical no-cloning function and behavioral authentication. The Dijkstra algorithm uses communication latency and signal strength as edge weights. When the signal strength between two nodes is greater than -85dBm and the communication latency is less than 20ms, a connection edge is established. The final output is an adjacency matrix representation containing all legitimate drone nodes and their optimal paths. In the initial topology graph, nodes represent verified drones, edges represent connection paths that meet communication quality requirements, and an element value of 1 in the adjacency matrix indicates the existence of a valid connection, while 0 indicates no connection.

[0072] S1.5. Based on the list of legitimate drones, use the cryptogen tool to generate a node certificate set, configure the node certificate set, and obtain the genesis block.

[0073] Furthermore, based on the device IDs and physical unclonable function feature vectors in the list of legitimate drones, the cryptogen tool generates a node certificate set containing ECDSA key pairs and X.509 certificates. The node certificate set is written into the crypto-config.yaml file according to the Hyperledger Fabric framework configuration specifications, specifying the organizational relationship and certificate paths of Orderer nodes and Peer nodes. The configtxgen tool reads the configuration and generates a genesis block containing MSP identity information and channel configuration.

[0074] S2. Acquire video stream data, the inertial measurement unit records attitude data, and generates compressed data packets.

[0075] S2.1 The UAV aligns the sensor clock with the GPS PPS signal to obtain a timestamp sequence. Based on the timestamp sequence and IMU speed data, the frame rate is dynamically adjusted to obtain video stream data.

[0076] Furthermore, the drone receives GPS PPS signals as a global clock reference and synchronizes the sampling clocks of the inertial measurement unit and camera via the PTP protocol to generate a timestamp sequence with microsecond-level precision. Based on the interval distribution of the timestamp sequence and the three-dimensional velocity values ​​measured in real time by the inertial measurement unit, the target frame rate is dynamically calculated. When the velocity value is less than 5 m / s, 30 fps is selected; when it is between 5 and 15 m / s, 60 fps is selected; and when it is greater than 15 m / s, 120 fps is selected. The camera collects video stream data according to the frame rate.

[0077] S2.2 The inertial measurement unit uses the timestamp sequence IMU velocity data to trigger differential coding to obtain attitude data.

[0078] Furthermore, the inertial measurement unit (IMU) triggers differential encoding based on the sampling time recorded by the timestamp sequence and the IMU velocity data. When the velocity change rate is less than 0.1g, it incrementally encodes the Euler angle data of adjacent timestamps and outputs compressed attitude data. The timestamp sequence provides a synchronization reference with an accuracy of 10μs. The IMU velocity data is obtained through the fusion calculation of the three-axis accelerometer and gyroscope. The differential encoding process uses a first-order differential algorithm to quantize the difference between the attitude quaternion at the current time and the previous time into a 16-bit integer for storage. The attitude data includes compressed representations of roll angle, pitch angle, and yaw angle. When the velocity change rate exceeds 0.1g, it switches to full-precision mode to record the original data. The compression algorithm achieves a 4:1 compression ratio by discarding higher-order decimal places. During decompression, continuous attitude is restored through linear interpolation.

[0079] S2.3. The video stream data and attitude data are concatenated to obtain a compressed data packet.

[0080] Furthermore, the H.265 encoded video stream data and the differentially compressed attitude data are concatenated by aligning them with timestamps. The attitude data at the corresponding moment is inserted into the header of each frame of the video stream data to form a composite data block. The composite data block is then compressed a second time using the Zstandard algorithm with a compression level of 9 to generate the final compressed data packet. The frame header of the video stream data reserves a 20-byte metadata area to store the timestamp index of the attitude data. The attitude data uses little-endian to store the 16-bit integer values ​​of roll angle, pitch angle, and yaw angle. Zstandard compression uses a dictionary (containing 100 sets of typical flight data patterns) to improve the compression ratio. The header of the compressed data packet contains a 4-byte synchronization identifier and a 2-byte length field, and a 4-byte CRC-32 checksum is appended to the tail. The timestamp alignment uses a hardware clock synchronized by the PTP protocol with an error of less than 1ms. The concatenation of the composite data block is achieved through DMA transfer to achieve zero-copy operation.

[0081] S3. The UAV scans the metasurface pattern on its fuselage using a terahertz transmitter to obtain a scattering feature matrix, generates a composite hash value, and appends it to the compressed data packet to form a data packet to be transmitted.

[0082] S3.1 The UAV uses a 0.3THz transmission module to scan the metasurface of the fuselage along a spiral trajectory to obtain the original scattered signal data. The original scattered signal data is then subjected to a short-time Fourier transform to obtain the time-frequency matrix.

[0083] Furthermore, the UAV activates the 0.3THz transmission module, scans the metasurface structure of the fuselage according to the preset spiral path, transmits a linear frequency modulated continuous wave and receives the reflected signal, collects the raw scattered signal data containing amplitude and phase information, performs a short-time Fourier transform on the raw scattered signal data with a window of 128ns, and generates a time-frequency matrix.

[0084] S3.2. Train the ResNet-18 model based on the sample dataset in the time-frequency matrix. Input the time-frequency matrix into the trained ResNet-18 model to obtain a unique scattering fingerprint feature vector.

[0085] Furthermore, a dataset containing 10,000 time-frequency matrix samples was used to train the ResNet-18 model through transfer learning. The input layer accepts a 128×128 complex time-frequency matrix, and after extracting features through the residual connection structure, it outputs a 128-dimensional unique scattering fingerprint feature vector. During training, the Adam optimizer is used, and the loss function is triplet loss. Training stops when the distance between the anchor sample and the positive sample is less than 0.2 and the distance between the anchor sample and the negative sample is greater than 0.8. During the inference stage, the real-time collected time-frequency matrix is ​​input into the trained ResNet-18 model, and the fully connected layer outputs a normalized feature vector. The unique scattering fingerprint feature vector takes values ​​in the range [0, 1] for each dimension. The feature matching degree is calculated by cosine similarity, and the threshold is set to 0.95 to determine the validity.

[0086] S3.3 Read the current grid code and fuselage temperature of the UAV and its unique scattering fingerprint feature vector to obtain anti-interference data.

[0087] Furthermore, the 10cm precision grid code of the current GPS coordinates of the drone and the measured value of the fuselage temperature sensor are read and concatenated with the 128-dimensional unique scattering fingerprint feature vector output by the ResNet-18 model; the grid code is converted into a 20-bit binary coordinate identifier, and the fuselage temperature is quantized into an 8-bit unsigned integer (resolution 0.5℃), which, together with the unique scattering fingerprint feature vector, are input into SHA3-256 hash operation to generate anti-interference data.

[0088] S3.4 Perform SHA3-256 hash operation on the anti-interference data to obtain a composite hash value.

[0089] Specifically, the expression is,

[0090] PUF hash =SHA3 256 (v feature ⊕v GPS ⊕T amb );

[0091] Among them, PUF hash For a composite hash value, v feature For unique scattering fingerprint feature vectors, v GPS T represents the current latitude and longitude. amb为 Drone temperature.

[0092] S3.5. Concatenate the composite hash value with the compressed data packet to obtain the data packet to be transmitted.

[0093] Furthermore, the composite hash value of the SHA3-256 algorithm is concatenated with the Zstandard compressed data packet, the composite hash value is written into the authentication field of the packet header, the compressed data packet body is stored continuously starting from address 0x20, a 4-byte synchronization flag and a 2-byte length field are added to the packet header, and a 4-byte CRC-32 checksum is appended to the tail to form a complete data packet to be transmitted.

[0094] S4. Measure the refractive index structure constant of the current region to obtain the turbulence intensity level, add the turbulence intensity level to the data packet to be transmitted, split the data packet to be transmitted into data fragments according to the initial network topology, and select relay nodes for routing and forwarding using the Kademlia algorithm.

[0095] S4.1. By collecting and measuring temperature, humidity and air pressure in real time, atmospheric data is compiled, and the refractive index structure constant is calculated based on the atmospheric data.

[0096] Specifically, the expression is,

[0097]

[0098] in, Let m be the structure constant for refractive index, P be atmospheric pressure, and T be temperature. For the temperature derivative, For an infinitesimal change in altitude, is the specific humidity differential, and m is the refractive index.

[0099] S4.2. Based on the current altitude of the UAV and the refractive index structure constant, obtain the turbulence intensity level.

[0100] Furthermore, based on the current altitude and refractive index structure constant measured by the barometric altimeter, the turbulence intensity level is determined by looking up a table. When the altitude is below 100 meters and the refractive index structure constant is less than 5×10^-16 m^(-2 / 3), it is classified as L1 (weak turbulence); when the altitude is between 100 and 500 meters and the refractive index structure constant is between 5×10^-16 and 2×10^-15 m^(-2 / 3), it is classified as L2 (moderate turbulence); and when the altitude is above 500 meters or the refractive index structure constant is greater than 2×10^-15 m^(-2 / 3), it is classified as L3 (strong turbulence).

[0101] S4.3 Add the turbulence intensity level to the header flag of the data packet to be transmitted to obtain the turbulence-marked data packet. Calculate the fragment size based on the initial network topology and the turbulence-marked data packet, and split the turbulence-marked data packet into a data fragment sequence.

[0102] Specifically, the expression is,

[0103]

[0104] Among them, S frag The segment size is MTU, the maximum length of a single frame is Turbo. level This is the turbulence level.

[0105] Furthermore, based on the intensity level identifier (L1 / L2 / L3) in the turbulence marker packet header, the fragment size is dynamically determined: L1 level uses 1024-byte fragments, L2 level uses 768-byte fragments, and L3 level uses 512-byte fragments. The packet body is divided into continuous data blocks according to the fragment size, and each data block is appended with a 6-byte header (including a 2-byte fragment sequence number, a 2-byte total number of fragments, and a 2-byte turbulence marker), generating an ordered data fragment sequence.

[0106] S4.4. Relay nodes are selected from the initial network topology using the Kademlia algorithm to obtain a node list. Data slice sequences are then sent to the target nodes according to the node list.

[0107] Specifically, the expression is,

[0108]

[0109] Among them, D ij ID is the normalized composite distance between sending node i and target node j. i ID is the unique identifier for node i. j SNR is the unique identifier of the target node j. ij The channel quality is defined by XOR for the signal transmitted from node i to target node j, where XOR is the bitwise XOR operation, α is the logical distance weight, β is the turbulence intensity weight, and γ is the signal-to-noise ratio weight.

[0110] S5. Redundant encoding is performed on the data packets to be transmitted according to the turbulence intensity level to generate transmission units with error correction codes. The endorsement nodes of the private blockchain network verify the transmission units with error correction codes through the Byzantine fault-tolerant consensus mechanism.

[0111] S5.1. Based on the turbulence intensity level, select the Reed-Solomon coding scheme to perform redundant coding on the data packet to be transmitted, obtain the configuration instruction, divide the compressed data packet into byte blocks, obtain the data block sequence data fragment group to be encoded, encode the data block sequence data fragment group to be encoded, obtain the original coding unit, add a packet header to the original coding unit, and generate the final transmission unit with error correction code.

[0112] Furthermore, the corresponding Reed-Solomon coding parameters are selected according to the turbulence intensity level. Reed-Solomon coding is used for L1 level, L2 level, and L3 level. The data packets to be transmitted are divided into 1024-byte blocks to generate a sequence of data blocks to be encoded. Each data block is given a 4-byte header (including a 2-byte fragment ID and a 2-byte length identifier). The Reed-Solomon encoder performs redundant encoding on the sequence of data blocks to be encoded to generate an original encoding unit containing a check byte. The number of check bytes is determined by the encoding scheme. An 8-byte header (including a 4-byte synchronization code and a 4-byte timestamp) is added to the beginning of the original encoding unit, and a 4-byte CRC-32 check code is added to the end to generate the final transmission unit with error correction code.

[0113] S5.2. Based on the endorsement nodes of the private blockchain network, perform cyclic redundancy check on the transmission unit with error correction code to obtain the initial check state. Perform Reed-Solomon decoding on the initial check state to obtain the decoding state. Check the difference between the original data fragment timestamp and the current block height to obtain the spatiotemporal check state. Verify the digital signature of the transmission unit with error correction code in the Intel SGX enclave to obtain the security authentication state.

[0114] Furthermore, the endorsing nodes of the private blockchain network perform CRC-32 verification on the received transmission units with error correction codes. The verification range covers all data from the packet header to the checksum byte. When the checksum matches, an initial verification pass state is generated. The Reed-Solomon encoded block is extracted from the transmission unit that passes the initial verification. Galois domain decoding is performed according to the encoding parameters recorded in the packet header. When the original data block is successfully recovered, a decoding pass state is generated. The timestamp is extracted from the header of the decoded data fragment and compared with the time window corresponding to the current blockchain height. When the timestamp is within the valid range, a spatiotemporal verification pass state is generated. The digital signature at the end of the transmission unit is verified using a pre-built ECDSA public key in the Intel SGX enclave. When the signature is valid and the certificate has not been revoked, a security authentication pass state is generated.

[0115] S5.3 Generate local verification results based on the initial verification state, decoding state, spatiotemporal verification state, and security authentication state.

[0116] Furthermore, a four-state logic is used to generate local verification results: when the Cyclic Redundancy Check (CRC) status is passed, the Reed-Solomon decoding status indicates complete data recovery, the timestamp deviation of the Spatiotemporal Verification status is within ±3 seconds, and the digital signature verification of the Security Authentication status is passed, the local verification result is marked as valid; if any status fails, it is marked as invalid. The CRC status is determined by the CRC-32 checksum matching, the Reed-Solomon decoding status depends on whether the original data block can be successfully recovered, the Spatiotemporal Verification status is generated by comparing the data fragment timestamp with the blockchain height corresponding time window, and the Security Authentication status is determined by the ECDSA signature verification result within the Intel SGX enclave.

[0117] S5.4. The local verification result is verified through the Byzantine fault-tolerant consensus mechanism to obtain the verified transmission unit with error correction code.

[0118] Furthermore, the endorsing nodes of the private blockchain network collect at least 2f+1 valid local verification results (f being the maximum number of fault-tolerant nodes) and conduct multiple rounds of voting verification through the Byzantine fault-tolerant consensus mechanism: In the first round, the master node broadcasts a proposal containing local verification results, and the replica nodes compare the cyclic redundancy check state, Reed-Solomon decoding state, spatiotemporal check state, and security authentication state in the proposal to see if they are consistent with their own verification. When they receive f+1 matching preliminary responses, they enter the submission stage. Finally, a transmission unit with error correction code that receives 2f+1 consistent confirmations is marked as verified.

[0119] S6. Sort the service nodes in the private blockchain network to generate new blocks, and send the verified transmission units with error correction codes to the new blocks.

[0120] S6.1. Based on the CPU load, network latency, and storage IOPS of the service nodes in the private blockchain network, generate a priority queue, select verified transmission units with error correction codes from the memory pool, sort them by the received timestamp, generate a block structure block template, perform SHA3-256 hash processing on the block structure block template to obtain the block hash value, and use the private key to perform ECDSA signature on the block hash value to obtain the block signature.

[0121] Furthermore, the service nodes of the private blockchain network monitor CPU utilization, end-to-end network latency, and storage IOPS metrics in real time. They calculate node priorities and generate sorting queues using a weighted scoring algorithm (CPU weight 0.4, latency weight 0.3, IOPS weight 0.3). They extract transmission units with error correction codes that have been verified by practical Byzantine fault-tolerant consensus from the memory pool, arrange them in ascending order according to the received timestamp synchronized by the IEEE 1588 precise time protocol, and generate a block structure template containing a block header (parent hash, timestamp, Merkle root) and a transaction list. They perform a SHA3-256 hash operation on the block structure template to generate a 256-bit block hash value, and use the secp256k1 private key from the node certificate set to perform ECDSA signing on the block hash value, outputting a 64-byte block signature.

[0122] S6.2 combines the block structure block template, block hash value, and block signature to obtain a new block.

[0123] Furthermore, the block structure, block template, block hash value, and block signature are combined in a predefined format: the block structure, block template, serves as the main content (including the block header and transaction list), the block hash value is written into the hash field of the block header, and the block signature is appended to the end of the block; the combined data structure is broadcast to all network nodes via the gRPC protocol to form a new block.

[0124] S6.3 uses the gRPC protocol to send the verified transmission unit with error correction code to the new block.

[0125] Furthermore, through the streaming transmission channel of the gRPC protocol, transmission units with error correction codes, verified by the practical Byzantine fault-tolerant consensus, are sent to the newly generated block. The transmission process uses HTTP / 2 multiplexing technology, and each transmission unit is encapsulated as an independent gRPC message frame (containing a 4-byte length prefix and payload data). The message header is appended with the block height identifier and the target node ID. Transmission units with error correction codes are transmitted in batches after being sorted by the receiving timestamp, with each batch containing a maximum of 50 transmission units and a maximum frame length of no more than 16KB. The receiver confirms the data integrity by verifying the CRC-32 checksum in the message frame header. After successful reception, the data is written into the transaction list of the new block. The gRPC connection remains in a long-term connection state, and flow control uses the token bucket algorithm (rate limit of 10Mbps). The error retransmission mechanism is based on sequence number confirmation. The binding relationship between the transmission unit and the new block is verified by the Merkle root hash in the block header.

[0126] S7. The smart contract triggers the edge computing node to perform Reed-Solomon decoding on the transmission unit with error correction code to restore it into the data packet to be transmitted. The TensorFlow Lite inference engine is used to perform target detection analysis and generate an analysis report.

[0127] S7.1. Statistical analysis of video stream data and posture data in the private blockchain network is performed using smart contracts to obtain dynamic thresholds.

[0128] Specifically, the expression is,

[0129] Thresh old=max(100MB,0.2×AvgLast10Blocks);

[0130] Where Thresh old is a dynamic threshold, and vgLast10Blocks is the average value of 10 blocks in the private blockchain network.

[0131] S7.2 When a transmission unit with error correction code that has passed the smart contract monitoring and verification reaches the dynamic threshold, a trigger command is sent to the edge node to obtain a list of transmission unit IDs.

[0132] Furthermore, the smart contract continuously monitors the number of on-chain verified transmission units with error correction codes. When the cumulative value reaches a dynamic threshold, it sends a trigger command containing a list of transmission unit IDs to the edge nodes. The list of transmission unit IDs is generated by the smart contract by traversing the memory pool. Each ID is a 32-byte SHA3-256 hash value, and the list is sorted in ascending order by the transmission unit's on-chain timestamp. The dynamic threshold is calculated based on the block data volume recorded in the Hyperledger Fabric state database, with the statistical window being the average of the most recent 10 blocks. The trigger command is sent to the gRPC streaming channel subscribed to by the edge nodes via an event push mechanism. The command payload is encoded using Protocol Buffers. After receiving the command, the edge nodes retrieve the corresponding transmission unit data with error correction codes from the IPFS distributed storage according to the list of transmission unit IDs.

[0133] S7.3. Based on the list of transmission unit IDs, retrieve the transmission unit with Reed-Solomon error correction code from IPFS, perform decoding, and obtain the data packet to be transmitted.

[0134] Furthermore, the edge node retrieves the corresponding transmission unit with Reed-Solomon error correction code via the IPFS distributed storage network based on the 32-byte SHA3-256 hash value in the transmission unit ID list. It extracts the Reed-Solomon coded block parameters from the retrieved transmission unit, performs decoding operations on the Galois domain, restores the original data fragments, reassembles the decoded data fragments according to their fragment sequence numbers, removes the turbulence level marker and check field from the packet header, and generates a data packet to be transmitted. IPFS retrieval uses the Content Identifier CIDv1 (based on the SHA2-256 hash algorithm), and the Reed-Solomon decoder is configured with the same generator polynomial and Galois domain parameters as the sender. The integrity of the data packet to be transmitted is confirmed by verifying the consistency between the reassembled CRC-32 value and the value stored in the packet header; the verification scope covers all bytes of the data fragment payload.

[0135] S7.4 Decode the data packets to be transmitted, input them into the TensorFlow Lite model, and generate an analysis report.

[0136] Furthermore, the process involves H.265 video decoding and attitude data decompression of the data packets to be transmitted. The decoded video frames are then aligned with the attitude data of the inertial measurement unit (IMU) according to their timestamps. The aligned data is input into the TensorFlow Lite model, where target detection analysis is performed to generate structured results. The analysis results are combined with timestamps and location information to generate a JSON-formatted analysis report. H.265 decoding is implemented using the FFmpeg library, and attitude data decompression is performed by inverse operation using differential encoding to recover the original quaternions. The TensorFlow Lite model uses a quantized YOLOv5s architecture (INT8 precision), and the target detection threshold is set to 0.5. The JSON report fields include timestamp (Uni x millisecond timestamp), location (WGS84 coordinates), and objects (object array). The alignment of video frames and attitude data is based on a PTP synchronization clock. TensorFlow Lite inference is accelerated using the NEON instruction set to generate the analysis report.

[0137] This embodiment also provides a computer device applicable to the construction method of a blockchain-based real-time data analysis model for unmanned aerial vehicles (UAVs), comprising: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the construction method of a blockchain-based real-time data analysis model for UAVs as proposed in the above embodiment.

[0138] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0139] This embodiment also provides a storage medium storing a computer program. When executed by a processor, the program implements the method for constructing a blockchain-based real-time data analysis model for unmanned aerial vehicles as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0140] In summary, this invention achieves hardware-level identity authentication by: acquiring physical fingerprint features through terahertz scanning of the fuselage metasurface and generating anti-interference hash values ​​by combining spatiotemporal parameters, thereby fundamentally eliminating the risk of drone identity cloning; dynamically adjusting the RS coding scheme and routing strategy based on real-time turbulence intensity; and accurately quantifying the channel state through the refractive index structure constant, thus improving coding efficiency and ensuring transmission success rate even in strong interference environments. Physical fingerprint authentication ensures the credibility of the data source, dynamic coding guarantees reliable transmission, and together with the blockchain consensus mechanism, it constructs a full-stack security system from the physical layer to the application layer.

[0141] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for constructing a blockchain-based real-time data analysis model for unmanned aerial vehicles (UAVs), characterized by: include, The drone establishes an ad-hoc mesh network via the 5G NR-U band, the ground control station verifies its legitimacy, generates an initial network topology map, builds a private blockchain network based on the Hyperledger Fabric framework, and generates the genesis block. The system acquires video stream data, records attitude data using the inertial measurement unit, and generates compressed data packets. The UAV scans the metasurface pattern on its fuselage with a terahertz transmitter to obtain a scattering feature matrix, generates a composite hash value, and appends it to the compressed data packet to form a data packet to be transmitted. The UAV measures the refractive index structure constant of the current area to obtain the turbulence intensity level, adds the turbulence intensity level to the data packet to be transmitted, splits the data packet to be transmitted into data fragments according to the initial network topology, and selects relay nodes for routing and forwarding through the Kademlia algorithm. The data packets to be transmitted are redundantly encoded according to the turbulence intensity level to generate transmission units with error correction codes. The endorsement nodes of the private blockchain network verify the transmission units with error correction codes through the Byzantine fault-tolerant consensus mechanism. The service nodes in the private blockchain network are sorted to generate new blocks, and the verified transmission units with error correction codes are sent to the new blocks. The smart contract triggers the edge computing node to perform Reed-Solomon decoding on the transmission unit with error correction code to restore it into the data packet to be transmitted. The TensorFlow Lite inference engine is then used to perform object detection analysis and generate an analysis report.

2. The method for constructing a blockchain-based real-time data analysis model for unmanned aerial vehicles as described in claim 1, characterized in that: The drone establishes an ad-hoc mesh network via the 5G NR-U band, the ground control station verifies its legitimacy, generates an initial network topology map, and builds a private blockchain network based on the Hyperledger Fabric framework to generate the genesis block. This process includes the following steps: The baseband chip scans the 5925-7125MHz frequency band, measures the frequency signal-to-noise ratio, and generates a spectrum analysis report. The ground control station receives the spectrum analysis report, executes the frequency point algorithm to obtain the center frequency point, and derives the TDMA time slot allocation scheme based on the center frequency point to obtain the time slot configuration table. The UAV sends beacon frames according to the time slot configuration table, establishes connection nodes and generates a neighbor list. The ground control station sends PUF challenge codes to each UAV to obtain the PUF feature vector set. The control station sends maneuver commands and generates behavior authentication results through IMU data verification. The behavioral authentication results are combined with the PUF feature vector set to perform threshold judgment and output a list of legal drones; Based on the neighbor list and the list of legal drones, an initial topology graph is generated using Dijkstra's algorithm; Based on the list of legitimate drones, the cryptogen tool is used to generate a set of node certificates. The node certificate set is then configured to obtain the genesis block.

3. The method for constructing a blockchain-based real-time data analysis model for unmanned aerial vehicles as described in claim 2, characterized in that: The system acquires video stream data, records attitude data using an inertial measurement unit, and generates compressed data packets. Includes the following steps, The drone aligns its sensor clock with the GPS PPS signal to obtain a timestamp sequence, and dynamically adjusts the frame rate based on the timestamp sequence and IMU speed data to obtain video stream data; The inertial measurement unit uses timestamp sequence IMU velocity data to trigger differential coding to obtain attitude data; The video stream data and pose data are concatenated to obtain a compressed data packet.

4. The method for constructing a blockchain-based real-time data analysis model for unmanned aerial vehicles as described in claim 3, characterized in that: The drone uses a terahertz transmitter to scan the metasurface pattern on its fuselage to obtain a scattering feature matrix, generates a composite hash value, and appends it to a compressed data packet to form the data packet to be transmitted. Includes the following steps, The UAV uses a 0.3 THz transmission module to scan the metasurface of the fuselage in a spiral trajectory to obtain the raw scattered signal data. A short-time Fourier transform is performed on the raw scattered signal data to obtain the time-frequency matrix. The ResNet-18 model is trained based on the sample dataset in the time-frequency matrix. The time-frequency matrix is ​​input into the trained ResNet-18 model to obtain a unique scattering fingerprint feature vector. Anti-interference data is obtained by reading the current grid code and fuselage temperature of the UAV and its unique scattering fingerprint feature vector; Perform a SHA3-256 hash operation on the data to combat interference, and obtain a composite hash value; The composite hash value is concatenated with the compressed data packet to obtain the data packet to be transmitted.

5. The method for constructing a blockchain-based real-time data analysis model for unmanned aerial vehicles as described in claim 4, characterized in that: The UAV measures the refractive index structure constant of the current region to obtain the turbulence intensity level, adds the turbulence intensity level to the data packet to be transmitted, splits the data packet into data segments according to the initial network topology, and selects relay nodes for routing and forwarding using the Kademlia algorithm, including the following steps. By collecting and measuring temperature, humidity and air pressure in real time, atmospheric data is compiled, and the refractive index structure constant is calculated based on the atmospheric data. The turbulence intensity level is obtained based on the drone's current altitude and refractive index structure constant. Add the turbulence intensity level to the header flag of the data packet to be transmitted to obtain the turbulence-tagged data packet. Calculate the fragment size based on the initial network topology and the turbulence-tagged data packet, and split the turbulence-tagged data packet into a data fragment sequence. The Kademlia algorithm is used to select relay nodes from the initial network topology to obtain a node list, and the data slice sequence is sent to the target node according to the node list.

6. The method for constructing a blockchain-based real-time data analysis model for unmanned aerial vehicles as described in claim 5, characterized in that: Based on the turbulence intensity level, redundant encoding is performed on the data packets to be transmitted to generate transmission units with error-correcting codes. These transmission units with error-correcting codes are then verified by the endorsed nodes of the private blockchain network through a Byzantine fault-tolerant consensus mechanism. The process includes the following steps: Based on the turbulence intensity level, the Reed-Solomon coding scheme is selected to perform redundant coding on the data packet to be transmitted, thereby obtaining the configuration instruction. The compressed data packet is then divided into byte blocks to obtain a data fragment group of the data block sequence to be encoded. The data fragment group of the data block sequence to be encoded is then encoded to obtain the original coding unit. A packet header is added to the original coding unit to generate the final transmission unit with error correction code. Cyclic redundancy check is performed on the transmission unit with error correction code by the endorsement node of the private blockchain network to obtain the initial verification state. Reed-Solomon decoding is performed on the initial verification state to obtain the decoding state. The difference between the original data fragment timestamp and the current block height is checked to obtain the spatiotemporal verification state. The digital signature of the transmission unit with error correction code is verified in the Intel SGX enclave to obtain the security authentication state. Based on the initial verification state, decoding state, spatiotemporal verification state, and security authentication state, generate a local verification result; The local verification result is verified using the Byzantine fault-tolerant consensus mechanism to obtain the verified transmission unit with error correction code.

7. The method for constructing a blockchain-based real-time data analysis model for unmanned aerial vehicles as described in claim 6, characterized in that: The process of sorting service nodes in a private blockchain network to generate new blocks and sending verified transmission units with error correction codes to the new blocks includes the following steps: Based on the CPU load, network latency, and storage IOPS of the service nodes in the private blockchain network, a priority queue is generated. Verified transmission units with error correction codes are selected from the memory pool, sorted by the received timestamp, and a block structure template is generated. The block structure template is then hashed using SHA3-256 to obtain the block hash value. The block hash value is then signed using ECDSA with the private key to obtain the block signature. A new block is obtained by combining the block structure template, block hash value, and block signature. The verified transmission unit with error correction code is sent to the new block via the gRPC protocol.

8. The method for constructing a blockchain-based real-time data analysis model for unmanned aerial vehicles as described in claim 7, characterized in that: The smart contract triggers the edge computing node to perform Reed-Solomon decoding on the transmission unit with error correction code to restore it to the data packet to be transmitted. The TensorFlow Lite inference engine is then used to perform object detection analysis and generate an analysis report, including the following steps. Dynamic thresholds are obtained by statistically analyzing video stream data and posture data in a private blockchain network using smart contracts. When a transmission unit with error correction code that has passed the smart contract monitoring and verification reaches a dynamic threshold, a trigger command is sent to the edge node to obtain a list of transmission unit IDs. Based on the list of transmission unit IDs, the transmission units with Reed-Solomon error correction codes are retrieved from IPFS and decoded to obtain the data packets to be transmitted. The data packets to be transmitted are decoded, input into the TensorFlow Lite model, and an analysis report is generated.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the method for constructing a blockchain-based real-time data analysis model for unmanned aerial vehicles as described in any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the method for constructing a blockchain-based real-time data analysis model for unmanned aerial vehicles as described in any one of claims 1 to 8.

Images