Remote identity recognition method and system based on unmanned aerial vehicle management and control requirements

Abstract

The invention provides a remote identity recognition method and system based on unmanned aerial vehicle management and control requirements. Wherein the preparation state of the unmanned aerial vehicle is determined by generating an inquiry code, sending the inquiry code to all online unmanned aerial vehicles in a target airspace, and receiving an identity response signal comprising a unique identifier, a task brief description and a flight path. A multi-dimensional data fusion algorithm is combined with historical flight data, meteorological conditions and geographic information to predict an unmanned aerial vehicle behavior mode, and a behavior prediction report is formed. The block chain technology is used for cross verification, and the real identity and authorization state of the unmanned aerial vehicle are verified through the dual key encryption technology and the consensus algorithm. And according to a verification result, using machine learning to construct a temporary virtual fence and plan an optimized route, and automatically adjusting an air corridor to form a traffic management scheme. And finally, analyzing actual flight parameters by applying a self-adaptive control algorithm, and further optimizing route setting. According to the technical scheme provided by the embodiment of the invention, the safety and efficiency of air traffic management of the unmanned aerial vehicle are improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of drone safety technology, and in particular, to a remote identity recognition method and system based on drone management and control requirements. Background Art

[0002] With the rapid development of drone technology, its application scenarios are becoming increasingly extensive, including logistics distribution, agricultural monitoring, disaster response, and geographic mapping. In these applications, it is particularly important to ensure the safe flight and effective management of drones. Especially in urban airspace or specific control areas, a technical solution is needed that can monitor the status of drones in real time, predict their behavior patterns, and dynamically adjust the flight path to avoid collisions and other safety hazards, while improving airspace utilization.

[0003] The current UAV management system mainly relies on traditional radar monitoring and manual operation to track the location and status of the UAV, and transmits commands and plans the path of the UAV through the ground control station. In addition, some more advanced systems have begun to use data transmission methods based on GPS positioning to track and manage UAVs.

[0004] There are several obvious shortcomings in existing drone management solutions: First, in terms of identity authentication, traditional methods cannot provide sufficient security and are vulnerable to attacks by forged signals; second, due to the lack of effective data fusion and intelligent algorithm support, existing systems find it difficult to accurately predict the behavior patterns of drones, resulting in inaccurate flight path planning and increased flight risks; finally, existing solutions generally lack a unified and scalable platform to integrate multiple data sources (such as historical flight data, meteorological information, etc.), which limits the performance and adaptability of the overall system. Summary of the invention

[0005] The embodiments of the present application provide a remote identity recognition method and system based on drone management and control requirements to solve the problems of insufficient security and low efficiency in drone air traffic management in the prior art.

[0006] In a first aspect, the embodiments of the present application provide a remote identity recognition method based on drone control requirements, including: Generate an inquiry code using the real-time traffic conditions and safety level of the drone, send an identification request signal containing the inquiry code to all online drones in the target airspace of the drone, receive an identity response signal, and obtain the readiness status of the online drone according to the identity response signal, wherein the identity response signal encapsulates the unique identifier of the drone, a brief description of the current mission, and a summary of the flight path; Processing the readiness state and the identity response signal using a multi-dimensional data fusion algorithm, and combining the historical flight data, meteorological conditions and geographic information of the UAV, predicting and analyzing the behavior pattern of the online UAV, and generating a behavior prediction report; Based on the cross-validation mechanism of blockchain technology, the behavior prediction report is compared with the registration information database pre-stored in the control center to obtain a comparison result, and based on the comparison result, the real identity and authorization status of the online drone are verified by using dual key encryption technology and consensus algorithm to generate an identity verification result; Using the flight data of the online drone provided by the identity authentication result, combined with a machine learning algorithm, a temporary virtual fence is constructed, based on the temporary virtual fence and using a path planning algorithm, the route of the online drone is calculated, and the air corridor is automatically adjusted and optimized to obtain an adjustment result, and the adjustment result is updated to the relevant drones to form an air traffic management plan; An adaptive control algorithm is used to analyze the actual flight parameters of the UAV collected in the air traffic management plan, optimize the route of the UAV and the setting of the air corridor, and obtain feedback adjustment suggestions, wherein the actual flight parameters of the UAV include speed and altitude change rate.

[0007] Optionally, based on a cross-validation mechanism of blockchain technology, the behavior prediction report is compared with a registration information database pre-stored in a control center to obtain a comparison result, and based on the comparison result, the real identity and authorization status of the online drone are verified using dual key encryption technology and a consensus algorithm to generate an identity verification result, including: Using advanced hashing algorithms and sharding technology to optimize the registration information database pre-stored in the control center, building a distributed ledger system, recording the authentication information of all registered drones based on the distributed ledger system, and automatically performing regular audits through smart contracts to generate a blockchain database, where the authentication information includes a unique identifier and authorization status; Based on the blockchain database, the identity response signal and the readiness status of the online drone are processed, and the behavior pattern of the online drone is predicted and analyzed in combination with a multi-dimensional data fusion algorithm to generate a behavior prediction report; Encrypting the summary of the behavior prediction report using the Advanced Encryption Standard combined with the Elliptic Curve Digital Signature Algorithm to generate an encrypted summary; Sending a verification request to each node in the blockchain network according to the encrypted summary and the unique identifier of the drone, and applying a privacy protection algorithm in combination with a timestamp service to verify the request of the drone to obtain a verification request; Processing the verification request using a fast Byzantine fault-tolerant algorithm, reaching a preliminary consensus among the nodes in the blockchain network, and evaluating the historical transaction records and current authorization status of the drone to generate a risk score, and assisting in reaching a consensus result based on the risk score; Based on the consensus result, the encrypted summary is deeply compared with the registration information pre-stored in the blockchain database. If there is any inconsistency, the security check process is triggered until the verification is correct, and the real identity and authorization status of the online drone are dynamically verified using double-key encryption technology to generate an identity authentication result.

[0008] Optionally, the verification request is processed using a fast Byzantine fault-tolerant algorithm, a preliminary consensus is reached among the nodes in the blockchain network, and the historical transaction records and current authorization status of the drone are evaluated to generate a risk score, and a consensus result is reached based on the risk score, including: Desensitizing the verification request data to generate a verification request data packet; A fast Byzantine fault-tolerant algorithm is started at each node in the blockchain network, and each node broadcasts the verification request data packet to all other nodes. A distributed hash table is used to optimize the data transmission path of the drone, and a group of leader nodes are selected to obtain a leader node set. Based on the leader node set, receiving copies of verification request data packets from other nodes, and using a fast Byzantine fault-tolerant algorithm to make preliminary consensus decisions, monitor abnormal behaviors of each node in the blockchain network in real time, and obtain preliminary consensus results; Based on the preliminary consensus result, using a preset integrated learning model, deeply evaluate the historical transaction records and current authorization status of the drone, and identify potential risk patterns of the drone to generate a risk score for the drone; The risk score is input as an additional parameter into the fast Byzantine fault tolerance algorithm, and combined with the behavior analysis results of the drone, the trust scores and voting rights distribution between nodes are adjusted to affect the consensus results, wherein the behavior analysis results include the flight trajectory deviation and task completion rate of the drone.

[0009] Optionally, based on the consensus result, the encrypted summary is deeply compared with the registration information pre-stored in the blockchain database. If there is any inconsistency, a security check process is triggered until the verification is correct, including: Extracting the deeply compared data according to the consensus result, applying differential privacy technology to desensitize the deeply compared data, and generating high-level comparison data; Based on the advanced comparison data, multi-dimensional feature fusion and graph comparison learning processing are performed on the blockchain database to generate a deep comparison framework; According to the deep comparison framework, a direct matching algorithm is used to compare the encrypted summary with the registration information pre-stored in the blockchain database, and if they are consistent, a preliminary identity verification result is generated; If no match is found, a similarity score between the encrypted summary and the registration information is calculated. When the similarity score exceeds a preset threshold and passes a semantic consistency check, it is considered that the encrypted summary and the registration information are successfully matched, and a similarity analysis result is obtained; For cases that fail the matching and similarity analysis, the preset intelligent anomaly detection system is started for analysis, and the time series analysis algorithm is used to monitor the trend of the encrypted summary and the registration information over time to obtain the detection results; If inconsistencies are detected, a safety inspection process of the drone is triggered based on the inspection result, and a manual review mechanism is applied to review the safety of the inspection steps to obtain a safety inspection result.

[0010] Optionally, according to the encrypted summary and the unique identifier of the drone, a verification request is sent to each node in the blockchain network, and a privacy protection algorithm is applied in combination with a timestamp service to verify the request of the drone, to obtain a verification request, including: Encrypting the summary of the behavior prediction report using the Advanced Encryption Standard combined with the Elliptic Curve Digital Signature Algorithm to generate an encrypted summary, and combining the encrypted summary with the unique identifier of the drone to form a data packet; According to the data packet, applying a privacy protection algorithm to perform protection processing on the encrypted summary and the unique identifier to obtain a privacy protection data packet; Based on the privacy protection data packet, adding a timestamp to the data packet through a timestamp service to obtain a timestamp data packet; A verification request is constructed using the timestamp data packet, wherein the verification request includes not only an encrypted digest, a unique identifier, a timestamp, and metadata, but also the metadata includes a request source and a target node list.

[0011] Optionally, a temporary virtual fence is constructed by using the flight data of the online drone provided by the identity authentication result in combination with a machine learning algorithm, the route of the online drone is calculated based on the temporary virtual fence and a path planning algorithm, and the air corridor is automatically adjusted and optimized to obtain an adjustment result, and the adjustment result is updated to the relevant drones to form an air traffic management plan, including: Based on the identity verification result, a deep learning model is applied to extract the flight characteristics of the online drone and generate flight data; According to the flight data, combined with an integrated learning algorithm and a reinforcement learning strategy, the activity range of the drone in a specific area is analyzed to construct a temporary virtual fence; Based on the temporary virtual fence, a preliminary flight route of the online UAV is calculated using a path planning and optimization algorithm, and the restriction conditions of the temporary virtual fence are considered, and the mutual influence between the online UAVs is analyzed in combination with a graph neural network to obtain a flight route; Using the flight route, combined with real-time traffic conditions, safety levels, and adaptive control algorithms, the air corridor is adjusted and optimized, and the flight paths and interval distances of the online drones are coordinated using distributed optimization technology to obtain air corridor settings; Analyzing actual flight parameters using an adaptive control algorithm, and continuously adjusting flight instructions and the air corridor settings through a feedback mechanism to obtain updated flight instructions; An air traffic management plan is formed based on the updated flight instructions.

[0012] Optionally, based on the temporary virtual fence, a preliminary flight route of the online UAV is calculated using a path planning and optimization algorithm, and the restriction conditions of the temporary virtual fence are considered, and the mutual influence between the online UAVs is analyzed in combination with a graph neural network to obtain a flight route, including: Based on the restriction conditions of the temporary virtual fence, a preliminary flight route of the online UAV is calculated using mixed integer linear programming; Based on the preliminary flight route, the mutual influence between the online drones is modeled and analyzed using a graph neural network, and the complex relationship between the online drones is captured, collision points and high-risk areas are predicted, and a preliminary flight path is obtained; Based on the preliminary flight path, taking into account weather conditions, geographical obstacles and flight plans of other online drones, the preliminary flight route is adjusted to obtain an optimized flight route; The simulation technology is used to evaluate the optimized flight route, simulate the flight conditions under different scenarios, detect risks and bottlenecks, obtain simulation results, and adjust the optimized flight route based on the simulation results to obtain the flight route.

[0013] In a second aspect, the embodiment of the present application provides a remote identity recognition system based on drone control requirements, including: A receiving module, used to generate an inquiry code using the real-time traffic conditions and safety level of the drone, send an identification request signal containing the inquiry code to all online drones in the target airspace of the drone, and receive an identity response signal, and obtain the readiness status of the online drone according to the identity response signal, wherein the identity response signal encapsulates the unique identifier of the drone, a brief description of the current mission, and a summary of the flight path; An analysis module, used to process the readiness state and the identity response signal by using a multi-dimensional data fusion algorithm, and to predict and analyze the behavior pattern of the online drone in combination with the historical flight data, meteorological conditions and geographic information of the drone, and to generate a behavior prediction report; A comparison module is used for comparing the behavior prediction report with the registration information database pre-stored in the control center based on the cross-validation mechanism of blockchain technology to obtain a comparison result, and based on the comparison result, using dual-key encryption technology and consensus algorithm to verify the real identity and authorization status of the online drone to generate an identity verification result; An adjustment module is used to use the flight data of the online drone provided by the identity authentication result and a machine learning algorithm to build a temporary virtual fence, calculate the route of the online drone based on the temporary virtual fence and a path planning algorithm, and automatically adjust and optimize the air corridor to obtain an adjustment result, and update the adjustment result to the relevant drones to form an air traffic management plan; The optimization module is used to analyze the actual flight parameters of the UAV collected in the air traffic management plan using an adaptive control algorithm, optimize the route of the UAV and the setting of the air corridor, and obtain feedback adjustment suggestions, wherein the actual flight parameters of the UAV include speed and altitude change rate.

[0014] In a third aspect, an embodiment of the present application provides a computing device, comprising a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement the remote identity recognition method based on the drone control requirements as described in the first aspect above.

[0015] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program. When the computer program is executed by a computer, the remote identity recognition method based on the drone control requirements as described in the first aspect is implemented.

[0016] In an embodiment of the present application, an inquiry code is generated using the real-time traffic conditions and safety level of the drone, an identification request signal containing the inquiry code is sent to all online drones in the target airspace of the drone, and an identity response signal is received, and the readiness state of the online drone is obtained according to the identity response signal, wherein the identity response signal encapsulates the unique identifier of the drone, a brief description of the current mission, and a summary of the flight path; the readiness state and the identity response signal are processed using a multidimensional data fusion algorithm, and the behavior pattern of the online drone is predicted and analyzed in combination with the historical flight data, meteorological conditions, and geographic information of the drone, to generate a behavior prediction report; based on the cross-validation mechanism of blockchain technology, the behavior prediction report is compared with the registration information database pre-stored in the control center to obtain a comparison. The result is obtained, and based on the comparison result, the real identity and authorization status of the online UAV are verified by using dual-key encryption technology and consensus algorithm to generate an identity authentication result; a temporary virtual fence is constructed by using the flight data of the online UAV provided by the identity authentication result in combination with a machine learning algorithm, and the route of the online UAV is calculated based on the temporary virtual fence and using a path planning algorithm, and the air corridor is automatically adjusted and optimized to obtain an adjustment result, and the adjustment result is updated to relevant UAVs to form an air traffic management plan; the actual flight parameters of the UAV collected in the air traffic management plan are analyzed by using an adaptive control algorithm, the route of the UAV and the setting of the air corridor are optimized, and feedback adjustment suggestions are obtained, wherein the actual flight parameters of the UAV include speed and altitude change rate.

[0017] The technical solution of this application has the following beneficial effects: This application not only ensures the safe flight of drones in complex environments, but also greatly reduces the risk of flight conflicts through real-time monitoring and intelligent adjustments, and improves the overall airspace utilization and management efficiency. At the same time, blockchain technology enhances the transparency and traceability of drone operations, providing strong technical support for the development of the drone industry.

[0018] Furthermore, the application uses the cross-validation mechanism of blockchain technology, advanced hashing algorithms and sharding technology to optimize the registration information database, and builds a distributed ledger system to record drone authentication information. Based on this system, the identity response signal and readiness status of online drones are processed, and the multi-dimensional data fusion algorithm is combined to predict its behavior pattern and generate a report. The behavior prediction report summary is encrypted using the Advanced Encryption Standard and the Elliptic Curve Digital Signature Algorithm, and a verification request is sent to the blockchain network. At the same time, the privacy protection algorithm and timestamp service are applied to ensure the authenticity of the request. A consensus is reached among network nodes through a fast Byzantine fault-tolerant algorithm, and the historical transaction records and authorization status of the drone are evaluated to generate a risk score. Finally, the encrypted summary is deeply compared with the registration information based on the consensus result. If inconsistencies are found, the security check process is initiated, and the identity and authorization status of the drone are dynamically verified using dual-key encryption technology.

[0019] Through the above method, the security and accuracy of drone identification are significantly improved, and the immutability and transparency of drone authentication information are ensured through blockchain technology and encryption algorithms. It can not only effectively prevent forged identity attacks, but also realize automatic auditing through smart contracts, enhancing the self-maintenance ability of the system. In addition, the use of a fast Byzantine fault-tolerant algorithm to reach a consensus among network nodes further ensures the reliability and efficiency of the identity authentication process, so that drones can be accurately identified and managed even in complex environments, greatly improving the safety and intelligence level of air traffic management.

[0020] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0022] Figure 1 A flowchart of a remote identity recognition method based on drone control requirements provided by the present application is shown; Figure 2 The schematic diagram of the structure of the remote identification system based on the drone control requirements provided by the present application is shown; Figure 3 A schematic diagram of the structure of a computing device provided by the present application is shown. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0024] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0025] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0026] Figure 1 A flowchart of a remote identity recognition method based on drone control requirements is provided for an embodiment of the present application, such as Figure 1 As shown, the method includes: 101. Generate an inquiry code using the real-time traffic status and safety level of the drone, send an identification request signal containing the inquiry code to all online drones in the target airspace of the drone, receive an identity response signal, and obtain the readiness status of the online drone according to the identity response signal, wherein the identity response signal encapsulates the unique identifier of the drone, a brief description of the current mission, and a summary of the flight path; Among them, real-time traffic conditions include all air activity information in the airspace where the drone is located, such as the location, speed and flight direction of other drones. It is used to assess the busyness of the current airspace and potential conflict points.

[0027] Safety Level: The level of safety risk determined based on weather conditions, geographical obstacles and other factors in a specific area. It helps determine whether drones need to be more strictly monitored or restricted from entering certain high-risk areas.

[0028] Interrogation code: An encrypted code generated based on real-time traffic conditions and security levels, used to verify the identity of the drone and ensure the validity and pertinence of the identification request.

[0029] Target airspace: refers to the specific flight area specified in the drone operation plan, which may be subject to special control requirements or have special mission requirements.

[0030] Identification request signal: A communication signal sent to all online drones in the airspace, containing an interrogation code, designed to obtain the drone's identity response.

[0031] Identity response signal: An information packet sent by a drone after receiving an identification request signal, which encapsulates data such as the drone's unique identifier, a brief description of the current mission, and a summary of the flight path, and is used to confirm the drone's identity and status.

[0032] Readiness status: reflects the operational readiness of the drone when receiving an identification request, including but not limited to battery status, payload status, and flight permission status.

[0033] Unique identifier: A number or code that is unique to each drone and is used to distinguish between different drones. It is an important part of the drone’s identity.

[0034] Brief description of current mission: Describe the type and purpose of the mission the drone is currently performing, such as cargo transportation, terrain mapping, etc.

[0035] Flight Path Summary: This summarizes the route the drone plans to fly, usually including the starting point, end point, and key points along the way.

[0036] In actual operation, the system first generates a unique interrogation code for each drone based on real-time traffic conditions and safety levels, and embeds this interrogation code into the identification request signal and sends it to all online drones in the target airspace. Then, it receives the identity response signal from the drone and extracts the information about the drone's readiness status.

[0037] For example, in a logistics distribution scenario, a company uses multiple drones to perform package delivery tasks. One day, because the weather forecast showed an impending storm, the control center increased the safety level of the relevant airspace. Subsequently, the system automatically generates the corresponding interrogation code and sends it to all drones in operation. After receiving the interrogation signal, a drone named Drone-Alpha immediately sends an identity response signal containing its unique identifier, a brief description of the mission it is currently flying to area A to deliver goods, and the expected flight route. This enables the control center to quickly understand the status of Drone-Alpha and make further decisions based on it.

[0038] 102. Processing the readiness state and the identity response signal using a multi-dimensional data fusion algorithm, and combining the historical flight data, meteorological conditions and geographic information of the UAV, predicting and analyzing the behavior pattern of the online UAV, and generating a behavior prediction report; Among them, the multidimensional data fusion algorithm is a technology that integrates different types of data (such as historical flight data, meteorological conditions, and geographic information) to predict and analyze the behavior patterns of drones. It improves the accuracy of predictions by comprehensively processing data from various sources.

[0039] In actual operation, the readiness state and identity response signals obtained in step 101 are processed using a multi-dimensional data fusion algorithm, and combined with factors such as the UAV's historical flight records, weather forecasts, and geographical environment to generate a behavior prediction report.

[0040] Continuing with the above embodiment, continuing with the previous example, after learning the basic information of Drone-Alpha, the system begins to use a multi-dimensional data fusion algorithm, combining Drone-Alpha's flight logs in the past month, the upcoming storm weather forecast, and the terrain characteristics of destination area A, to predict Drone-Alpha's next behavior pattern, such as the most likely challenges or risks of delays, and form a detailed behavior prediction report for subsequent analysis.

[0041] 103. A cross-validation mechanism based on blockchain technology is used to compare the behavior prediction report with the registration information database pre-stored in the control center to obtain a comparison result, and based on the comparison result, a dual-key encryption technology and a consensus algorithm are used to verify the real identity and authorization status of the online drone to generate an identity verification result; Among them, the cross-verification mechanism of blockchain technology refers to a way of using distributed ledger technology to ensure data consistency and security, verifying the true identity and authorization status of the drone by comparing behavior prediction reports with the registration information database.

[0042] In actual operation, with the help of blockchain technology, the behavior prediction report is compared with the pre-stored registration information database, and double-key encryption technology and consensus algorithm are used to complete identity authentication and generate the final identity authentication result.

[0043] Continuing with the above example, based on the information collected previously, the system uses blockchain technology to check the authenticity of Drone-Alpha's identity. By comparing its historical flight data with the registration information and applying double-key encryption technology to ensure that it is correct, it is confirmed that Drone-Alpha has a legal identity and authorization status for the current task, allowing it to continue to perform the delivery task.

[0044] 104. Using the flight data of the online drone provided by the identity authentication result and combining it with a machine learning algorithm, a temporary virtual fence is constructed, based on the temporary virtual fence and using a path planning algorithm, the route of the online drone is calculated, and the air corridor is automatically adjusted and optimized to obtain an adjustment result, and the adjustment result is updated to the relevant drones to form an air traffic management plan; Among them, temporary virtual fence: a dynamic boundary created based on a machine learning algorithm, used to limit the flight range of drones and prevent them from entering dangerous or restricted areas.

[0045] Path planning algorithm: A technique for calculating the optimal flight path, taking into account various constraints (such as weather and geographical obstacles) to ensure safe and efficient flight.

[0046] Automatically adjust and optimize the air corridor: The process of adjusting the drone's flight path in real time based on the actual flight situation and the requirements of the temporary virtual fence.

[0047] In actual operation, based on the identity authentication results, machine learning is used to build a temporary virtual fence, plan the drone route, and automatically adjust and optimize the air corridor to adapt to the new flight plan.

[0048] According to the above embodiment, as the storm approaches, the system sets up a temporary virtual fence for Drone-Alpha to prevent it from crossing the bad weather area. At the same time, the optimal flight path is recalculated to avoid the storm-affected area to ensure that the goods are delivered safely on time.

[0049] 105. Analyze the actual flight parameters of the UAV collected in the air traffic management plan using an adaptive control algorithm, optimize the route of the UAV and the setting of the air corridor, and obtain feedback adjustment suggestions, wherein the actual flight parameters of the UAV include speed and altitude change rate.

[0050] Among them, the adaptive control algorithm is an intelligent algorithm that can automatically adjust parameters based on actual feedback, which is used to optimize the UAV's route and air corridor settings.

[0051] Actual flight parameters of the UAV: ​​including key indicators such as speed and altitude change rate, which reflect the performance of the UAV during actual flight.

[0052] In actual operation, adaptive control algorithms are used to analyze actual flight parameters in air traffic management plans, provide optimization suggestions, and continuously improve the routes and air corridor layouts of drones.

[0053] According to the above embodiment, during the flight of Drone-Alpha, the system continuously monitors parameters such as its speed and altitude change rate, and immediately adjusts the route upon detecting a trend of deviation from the original path to ensure the safe and efficient completion of the delivery task.

[0054] Through the implementation of steps 101 to 105, the safety and efficiency of drones in complex environments have been significantly improved by integrating advanced data processing technology, blockchain verification mechanisms, and intelligent path planning methods. Not only does it achieve fast and accurate identity recognition and authorization verification, it can also respond to external changes in real time, dynamically optimize flight paths, effectively reduce the risk of flight conflicts, and enhance the reliability and flexibility of the overall air traffic management system. These measures work together to ensure that drone operations are safer and more efficient, while also improving the utilization of airspace resources.

[0055] In order to solve the security and accuracy problems in the drone identity authentication process and further improve the reliability and efficiency of the drone management system, in some embodiments, in step 103, based on the cross-validation mechanism of blockchain technology, the behavior prediction report and the registration information database pre-stored in the control center are compared to obtain a comparison result, and based on the comparison result, the real identity and authorization status of the online drone are verified using dual key encryption technology and consensus algorithm to generate an identity authentication result, including: The registration information database pre-stored in the control center is optimized by using advanced hashing algorithms and sharding technology, a distributed ledger system is constructed, the authentication information of all registered drones is recorded based on the distributed ledger system, and regular audits are automatically performed through smart contracts to generate a blockchain database, wherein the authentication information includes a unique identifier and an authorization status; based on the blockchain database, the identity response signal and the readiness status of the online drone are processed, and the behavior pattern of the online drone is predicted and analyzed in combination with a multi-dimensional data fusion algorithm to generate a behavior prediction report; the summary of the behavior prediction report is encrypted using the advanced encryption standard combined with the elliptic curve digital signature algorithm to generate an encrypted summary; based on the encrypted summary and the unique identifier of the drone, a Each node in the blockchain network sends a verification request, and applies a privacy protection algorithm combined with a timestamp service to verify the request of the drone to obtain a verification request; the verification request is processed using a fast Byzantine fault-tolerant algorithm, a preliminary consensus is reached among the nodes in the blockchain network, and the historical transaction records and current authorization status of the drone are evaluated to generate a risk score, and a consensus result is reached based on the risk score; based on the consensus result, the encrypted summary is deeply compared with the registration information pre-stored in the blockchain database. If there is any inconsistency, a security check process is triggered until the verification is correct, and the real identity and authorization status of the online drone are dynamically verified using dual-key encryption technology to generate an identity authentication result.

[0056] In this embodiment, an advanced hash algorithm: a technology for generating data summaries, ensuring the integrity and non-tamperability of data, suitable for quickly comparing large amounts of data.

[0057] Sharding technology: Divide large databases into smaller, more manageable parts (called "shards") to improve query efficiency and system performance.

[0058] Distributed ledger system: A decentralized database system based on blockchain technology, in which all participants can access the same copy of records, ensuring data transparency and security.

[0059] Smart contract: A computer program or transaction protocol that automatically executes predefined conditions, often used in blockchain to achieve automated auditing and rule enforcement.

[0060] Risk scoring: Assess the risk level of a drone based on multiple factors, such as historical behavior, current status, etc., to assist in deciding whether to trust the drone.

[0061] In the embodiment of the present application, firstly, the registration information database is optimized using advanced hashing algorithms and sharding technology to build a distributed ledger system.

[0062] Then, the information of all registered drones is regularly audited through smart contracts to ensure that the data is up-to-date and accurate. After receiving the identity response signal of the online drone, the multi-dimensional data fusion algorithm is combined to predict its behavior pattern and generate a behavior prediction report.

[0063] Next, the summary of the behavior prediction report is encrypted using the Advanced Encryption Standard and the Elliptic Curve Digital Signature Algorithm to form an encrypted summary.

[0064] Finally, a verification request is sent to the blockchain network, and the privacy protection algorithm and timestamp service are applied to ensure the authenticity of the request. A fast Byzantine fault-tolerant algorithm is used to reach a consensus among network nodes, evaluate the drone's historical transaction records and current authorization status, generate a risk score, and perform in-depth comparison and final verification based on it.

[0065] Here is a specific example: In a city logistics distribution scenario, a logistics company uses multiple drones to deliver packages every day. In order to ensure the authenticity of each drone's identity and the legality of its operation, the control center adopts the above solution.

[0066] For example, one day a drone named Drone-Beta plans to fly from a warehouse to the city center to deliver goods. Before taking off, the system automatically generates an interrogation code and sends an identification request signal to all online drones. After receiving the request, Drone-Beta sends an identity response signal containing a unique identifier, a brief description of the mission, and a summary of the flight path.

[0067] Subsequently, the system uses advanced hashing algorithms and sharding technology to optimize the stored registration information database, build a distributed ledger system, and perform regular audits through smart contracts. Based on this system, the identity response signal of Drone-Beta and its readiness status are processed, and its behavior pattern is predicted by combining multi-dimensional data fusion algorithms to generate a behavior prediction report.

[0068] Next, the report summary is encrypted using the Advanced Encryption Standard and Elliptic Curve Digital Signature Algorithm, and a verification request is sent to the blockchain network. After verification by the privacy protection algorithm and timestamp service, a consensus is reached among network nodes through the Fast Byzantine Fault Tolerance algorithm, and Drone-Beta's historical transaction records and current authorization status are evaluated to generate a risk score.

[0069] If everything is normal, Drone-Beta is allowed to continue the mission; if there are any inconsistencies, the safety check process is triggered until it is verified to be correct. This process greatly improves the safety and reliability of drone operations and ensures the smooth progress of logistics delivery tasks.

[0070] In order to solve the node consensus and risk assessment problems in the drone identity authentication process and further improve the security and decision-making accuracy of the drone management system, in the above embodiment, a fast Byzantine fault-tolerant algorithm is used to process the verification request, a preliminary consensus is reached among the nodes in the blockchain network, and the historical transaction records and current authorization status of the drone are evaluated to generate a risk score, and a consensus result is assisted according to the risk score, including: Desensitizing the data of the verification request to generate a verification request data packet; starting a fast Byzantine fault-tolerant algorithm at each node in the blockchain network, each node broadcasts the verification request data packet to all other nodes, and at the same time uses a distributed hash table to optimize the data transmission path of the drone, selects a group of leader nodes, and obtains a leader node set; based on the leader node set, receiving copies of the verification request data packet from other nodes, and using a fast Byzantine fault-tolerant algorithm to make a preliminary consensus decision, and monitoring the abnormal behavior of each node in the blockchain network in real time to obtain a preliminary consensus result; based on the preliminary consensus result, using a preset integrated learning model, deeply evaluating the historical transaction records and current authorization status of the drone, and identifying the potential risk pattern of the drone to generate a risk score for the drone; inputting the risk score as an additional parameter into the fast Byzantine fault-tolerant algorithm, and combining the behavior analysis results of the drone, adjusting the trust score and voting rights distribution between nodes, thereby affecting the consensus result, wherein the behavior analysis results include the flight trajectory deviation and task completion rate of the drone.

[0071] In this embodiment, desensitization refers to the process of removing sensitive information before data transmission or storage, thereby protecting privacy while ensuring the validity of the data.

[0072] Verification request data packet: a data set containing an anonymized verification request, used for transmission between network nodes for verification.

[0073] Distributed Hash Table (DHT): A distributed system structure that allows efficient location and access to resources in the network, often used to optimize data transmission paths.

[0074] Leader node set: A group of nodes in the network that are selected to coordinate and process specific tasks, and their selection is usually based on certain preset rules or algorithms.

[0075] Preliminary consensus decision: In the first phase of the fast Byzantine fault tolerance algorithm, each node forms a temporary consensus based on the information received.

[0076] Ensemble learning models: A method that combines the advantages of multiple machine learning models to improve prediction accuracy and robustness.

[0077] Trust score and voting rights allocation: The trust value and the weight of the voice in the consensus process are dynamically adjusted according to the node's behavior, which affects the final decision result.

[0078] In the embodiment of the present application, the data of the verification request is first desensitized to generate a verification request data packet.

[0079] Then, the fast Byzantine fault tolerance algorithm is started at each node in the blockchain network, and the verification request data packet is broadcast to all other nodes. At the same time, a distributed hash table is used to optimize the data transmission path and select a group of leader nodes. Based on these leader nodes, copies of data packets from other nodes are received, and the fast Byzantine fault tolerance algorithm is used to make preliminary consensus decisions, and abnormal behavior in the network is monitored in real time.

[0080] Next, the preset integrated learning model is used to deeply evaluate the drone’s historical transaction records and current authorization status, identify potential risk patterns, and generate a risk score.

[0081] Finally, the risk score is input as an additional parameter into the fast Byzantine fault-tolerant algorithm, and the trust scores and voting rights distribution between nodes are adjusted in combination with the behavior analysis results of the drone, thereby affecting the consensus results.

[0082] Here is a specific example: Continuing with the above example, after the control center sent an identification request signal to Drone-Gamma, it responded with an identity response signal containing a unique identifier, a mission summary, and a flight path summary. In order to verify the true identity and authorization status of Drone-Gamma, the system desensitized its verification request, generated a verification request data packet, and started the fast Byzantine fault tolerance algorithm at each node in the network. Each node broadcasts the verification request data packet to other nodes, and uses a distributed hash table to optimize the data transmission path, and selects several leader nodes.

[0083] Based on these leader nodes, the system received copies of data packets from other nodes and made preliminary consensus decisions using the fast Byzantine fault tolerance algorithm. During this process, the system also used an integrated learning model to evaluate Drone-Gamma's historical transaction records and current authorization status, identified potential risk patterns, such as deviations from the scheduled flight trajectory or low mission completion rates, and generated corresponding risk scores. This score was input into the fast Byzantine fault tolerance algorithm as an additional parameter, and the trust scores and voting rights distribution between nodes were adjusted in combination with the results of the drone's behavioral analysis, and finally a consensus on Drone-Gamma's identity and authorization status was reached. This process ensures the safety and legality of drone operations and ensures the smooth execution of logistics and distribution tasks.

[0084] In order to solve the problem of inconsistency between the encrypted summary and the registration information during the drone identity authentication process and further improve the security and accuracy of identity authentication, in one of the above embodiments, based on the consensus result, the encrypted summary is deeply compared with the registration information pre-stored in the blockchain database. If there is any inconsistency, the security check process is triggered until the verification is correct, including: According to the consensus result, the data after deep comparison is extracted, and the data after deep comparison is desensitized by using differential privacy technology to generate high-level comparison data; based on the high-level comparison data, multi-dimensional feature fusion and graph comparison learning processing are performed on the basis of the blockchain database to generate a deep comparison framework; according to the deep comparison framework, the encrypted summary is compared with the registration information pre-stored in the blockchain database using a direct matching algorithm, and if they are consistent, a preliminary identity authentication result is generated; if they fail to match, the similarity score between the encrypted summary and the registration information is calculated, and when the similarity score exceeds a preset threshold and passes a semantic consistency check, it is considered that the encrypted summary and the registration information are successfully matched, and a similarity analysis result is obtained; for cases that fail to pass the matching and similarity analysis, a preset intelligent anomaly detection system is started for analysis, and a time series analysis algorithm is used to monitor the trend of the encrypted summary and the registration information over time to obtain a detection result; if inconsistencies are detected, the safety inspection process of the drone is triggered based on the detection result, and a manual review mechanism is used to review the safety of the detection steps to obtain a safety inspection result.

[0085] In this embodiment, differential privacy technology: a technology for protecting data privacy that prevents sensitive information leakage by adding noise to the data while maintaining the overall statistical properties of the data.

[0086] Advanced comparison data: Desensitized deep comparison data, used for subsequent more detailed matching and analysis processes.

[0087] Multi-dimensional feature fusion: Combine data features from different sources (such as behavioral patterns, geographic information, etc.) to obtain a more comprehensive information perspective and enhance data analysis capabilities.

[0088] Graph contrastive learning: A machine learning method that constructs graph structures to represent complex relationships and performs contrastive learning between these graphs, often used to discover hidden patterns or anomalies.

[0089] Direct matching algorithm: An algorithm used to directly compare two data sets (such as encrypted digest and registration information) to see if they are completely consistent.

[0090] Similarity score: A numerical measure of the similarity between two datasets, often used to assess whether they are close enough to be considered a match.

[0091] Semantic consistency check: A method to check whether the contents of two data sets are consistent at the semantic level, ensuring that they are consistent not only in form but also in meaning.

[0092] Time series analysis algorithm: A method for analyzing patterns in data that change over time, often used to predict future trends or identify unusual fluctuations.

[0093] In an embodiment of the present application, first, the data after deep comparison is extracted according to the consensus result, and the data is desensitized using differential privacy technology to generate high-level comparison data.

[0094] Then, based on the blockchain database, a deep comparison framework is generated by utilizing multi-dimensional feature fusion and graph contrast learning processing.

[0095] Next, a direct matching algorithm is used to compare the encrypted summary with the pre-stored registration information. If they match, a preliminary identity verification result is generated. If there is no match, a similarity score is calculated between the two, and the match is considered successful when the score exceeds a preset threshold and passes the semantic consistency check.

[0096] For cases that fail to pass the matching and similarity analysis, the intelligent anomaly detection system is activated, and the time series analysis algorithm is used to monitor the trend of the encrypted summary and the registration information over time to obtain the detection results. If inconsistencies are detected, the security check process is triggered, and the manual review mechanism is applied to review the security of the steps to ensure that the final security check results are accurate.

[0097] Here is a specific example: According to the above embodiment, after receiving the identity response signal of Drone-Delta, the control center starts to perform a deep comparison between its encrypted summary and the registration information in the blockchain database.

[0098] First, the data extracted based on the consensus results were desensitized using differential privacy technology to generate high-level comparative data.

[0099] Then, based on the blockchain database, a deep comparison framework is generated by using multi-dimensional feature fusion and graph comparative learning processing.

[0100] Then, a direct matching algorithm is used to try to compare the encrypted summary with the registration information. If they are consistent, a preliminary identity verification result is generated. If the direct match is not successful, the system calculates the similarity score and considers the match successful if the score exceeds the preset threshold and passes the semantic consistency check.

[0101] However, if a match is still not found, the system activates the intelligent anomaly detection system, which uses a time series analysis algorithm to monitor the changing trends of the encrypted summary and the registration information, and detects abnormal fluctuations.

[0102] Based on this, the security check process is triggered, and the manual review mechanism is used to review the security of the inspection steps to ensure the true identity and authorization status of Drone-Delta, so that it can complete the logistics distribution tasks safely and efficiently. This process significantly improves the security and reliability of the drone management system and effectively prevents potential security threats.

[0103] In order to solve the privacy protection and timestamp verification problems in drone identity authentication requests and further improve the security and timeliness of identity authentication, in the above multiple embodiments, according to the encrypted summary and the unique identifier of the drone, a verification request is sent to each node in the blockchain network, and a privacy protection algorithm is applied in combination with a timestamp service to verify the request of the drone, and a verification request is obtained, including: The summary of the behavior prediction report is encrypted using the Advanced Encryption Standard in combination with the Elliptic Curve Digital Signature Algorithm to generate an encrypted summary, which is combined with the unique identifier of the UAV to form a data packet; based on the data packet, a privacy protection algorithm is applied to protect the encrypted summary and the unique identifier to obtain a privacy protection data packet; based on the privacy protection data packet, a timestamp is added to the data packet through a timestamp service to obtain a timestamp data packet; using the timestamp data packet, a verification request is constructed, wherein the verification request includes not only the encrypted summary, the unique identifier, the timestamp and metadata, but also the metadata includes a list of request source and target nodes.

[0104] In this embodiment, Advanced Encryption Standard (AES): a symmetric key encryption technology used to protect the confidentiality of data and widely used in scenarios requiring high security.

[0105] Elliptic Curve Digital Signature Algorithm (ECDSA): A digital signature algorithm based on elliptic curve cryptography that provides efficient data integrity verification and non-repudiation.

[0106] Privacy-preserving algorithms: A collection of technologies designed to protect personal or sensitive information from being accessed by unauthorized third parties, including but not limited to differential privacy, homomorphic encryption, and other methods.

[0107] Timestamp service: A service that provides an accurate time stamp for electronic documents or data, ensuring the existence and status of the data at a specific point in time and enhancing the credibility of the data.

[0108] Metadata: Information that describes data attributes, such as the source of the data, creation time, modification history, etc., to help understand and manage the data itself.

[0109] In an embodiment of the present application, first, the summary of the behavior prediction report is encrypted using the Advanced Encryption Standard combined with the Elliptic Curve Digital Signature Algorithm to generate an encrypted summary.

[0110] The encrypted summary is then combined with the drone’s unique identifier to form a data packet. Next, a privacy-preserving algorithm is applied to this data packet to protect the encrypted summary and unique identifier, generating a privacy-preserving data packet.

[0111] Subsequently, a timestamp is added to the privacy-preserving data packet through the timestamp service to ensure its validity and authenticity at a specific point in time and generate a timestamp data packet.

[0112] Finally, the timestamp packet is used to construct a verification request, which not only contains a cryptographic digest, a unique identifier, and a timestamp, but also metadata (such as a list of request source and target nodes) to support the subsequent authentication process.

[0113] Here is a specific example: Continuing with the above embodiment, the control center needs to verify the true identity and authorization status of Drone-Epsilon. First, the system encrypts the summary of its behavior prediction report using the Advanced Encryption Standard and the Elliptic Curve Digital Signature Algorithm, generates an encrypted summary, and combines it with the unique identifier of Drone-Epsilon to form a data packet.

[0114] Next, the privacy protection algorithm is applied to process the data packet to generate a privacy protection data packet. In order to ensure the authenticity of the data packet, the system adds a timestamp to it through the timestamp service to generate a timestamp data packet.

[0115] Finally, a verification request is constructed based on the timestamp data packet, which contains not only the encrypted summary, unique identifier and timestamp, but also detailed metadata, such as the request source (control center) and the target node list (various nodes in the blockchain network). These steps work together to ensure that Drone-Epsilon's authentication request is both secure and reliable, preventing potential forgery attacks and time tampering risks, and ensuring the safe execution of logistics distribution tasks. This process significantly improves the security and reliability of drone management systems in complex environments.

[0116] In some embodiments, in step 104, the flight data of the online drone provided by the identity authentication result is used in combination with a machine learning algorithm to build a temporary virtual fence, the route of the online drone is calculated based on the temporary virtual fence and a path planning algorithm, and the air corridor is automatically adjusted and optimized to obtain an adjustment result, and the adjustment result is updated to the relevant drones to form an air traffic management plan, including: Based on the identity authentication result, a deep learning model is applied to extract the flight characteristics of the online UAV and generate flight data; based on the flight data, the activity range of the UAV in a specific area is analyzed in combination with an integrated learning algorithm and a reinforcement learning strategy, and a temporary virtual fence is constructed; based on the temporary virtual fence, a path planning and optimization algorithm is used to calculate the preliminary flight route of the online UAV, and the restriction conditions of the temporary virtual fence are considered, and the mutual influence between the online UAVs is analyzed in combination with a graph neural network to obtain a flight route; using the flight route, combined with real-time traffic conditions, safety levels and adaptive control algorithms, the air corridor is adjusted and optimized, and distributed optimization technology is used to coordinate the flight path and interval distance of the online UAV to obtain an air corridor setting; an adaptive control algorithm is used to analyze actual flight parameters, and flight instructions and the air corridor setting are continuously adjusted through a feedback mechanism to obtain updated flight instructions; based on the updated flight instructions, an air traffic management plan is formed.

[0117] In this embodiment, deep learning model: a machine learning method based on artificial neural network, used to automatically extract complex feature patterns from large amounts of data, commonly used in image recognition, natural language processing and other fields.

[0118] Flight characteristics: Key indicators that describe the flight behavior of a drone, such as speed, altitude change rate, trajectory, etc., which are used to analyze and predict its future flight behavior.

[0119] Ensemble learning algorithm: A method that combines multiple different machine learning models to improve prediction performance. Common ones include random forests, gradient boosting trees, etc.

[0120] Reinforcement learning strategy: A machine learning method that learns the optimal action strategy through trial and error mechanism, usually used in scenarios that require making a series of decisions.

[0121] Temporary virtual fence: A restricted area dynamically generated based on specific conditions (such as weather and mission requirements) to guide drones to fly within a safe range.

[0122] Path planning and optimization algorithm: A technology that calculates the optimal flight path, taking into account various constraints (such as weather and geographical obstacles) to ensure safe and efficient flight.

[0123] Graph neural network: A neural network model that can process graph-structured data and is suitable for analyzing the relationships and mutual influences between nodes, such as the interactions between drones.

[0124] Distributed optimization technology: A technology that decomposes the optimization problem and solves it in parallel on multiple computing nodes. It is suitable for resource allocation and coordination in large-scale systems.

[0125] In an embodiment of the present application, firstly, a deep learning model is applied based on the identity authentication result to extract the flight characteristics of the online drone and generate flight data.

[0126] Then, an integrated learning algorithm and reinforcement learning strategy are used to analyze the range of drone activities in a specific area and construct a temporary virtual fence.

[0127] Next, the path planning and optimization algorithm is used to calculate the preliminary flight route, and the graph neural network is combined to analyze the mutual influence between drones to obtain the final flight route.

[0128] Subsequently, the air corridor is adjusted and optimized based on real-time traffic conditions, safety levels and adaptive control algorithms, and distributed optimization technology is used to coordinate the flight paths and interval distances of drones to form an air corridor setting.

[0129] Finally, an adaptive control algorithm is used to analyze actual flight parameters and continuously adjust flight instructions and air corridor settings through a feedback mechanism to ultimately form an air traffic management plan.

[0130] Here is a specific example: Continuing with the above embodiment, the control center first applies a deep learning model based on the identity authentication result to extract the flight characteristics of Drone-Zeta, including key data such as its historical flight speed and altitude change rate.

[0131] Then, the system used ensemble learning algorithms and reinforcement learning strategies to analyze the activity range of other drones in the area and built a temporary virtual fence to ensure that Drone-Zeta operated within its safe flight range. Based on this information, the system used path planning and optimization algorithms to calculate Drone-Zeta's preliminary flight route, and combined with graph neural networks to analyze the interaction with other drones and optimize the flight route.

[0132] During this process, the system also combined the real-time traffic conditions and safety levels, used adaptive control algorithms to adjust and optimize the air corridors, and used distributed optimization technology to coordinate the flight paths and interval distances of all online drones. Throughout the flight, the system continuously monitored the actual flight parameters of Drone-Zeta, and continuously adjusted the flight instructions and air corridor settings through a feedback mechanism to ensure that it was always in the best flight state. This series of measures significantly improved the flexibility and safety of the drone management system and ensured the safe and efficient execution of logistics distribution tasks.

[0133] In order to solve the complex constraints and mutual influence problems in the flight path planning of drones and further improve the safety and efficiency of the flight path, in the above embodiment, based on the temporary virtual fence, the path planning and optimization algorithm is used to calculate the preliminary flight route of the online drone, and the constraints of the temporary virtual fence are considered. The mutual influence between the online drones is analyzed in combination with the graph neural network to obtain the flight route, including: Based on the restriction conditions of the temporary virtual fence, the preliminary flight route of the online UAV is calculated using mixed integer linear programming; based on the preliminary flight route, the mutual influence between the online UAVs is modeled and analyzed using a graph neural network, and the complex relationship between the online UAVs is captured, collision points and high-risk areas are predicted, and a preliminary flight path is obtained; based on the preliminary flight path, the preliminary flight route is adjusted by comprehensively considering meteorological conditions, geographical obstacles and flight plans of other online UAVs to obtain an optimized flight route; the optimized flight route is evaluated using simulation technology, flight conditions under different scenarios are simulated, risks and bottlenecks are detected, and simulation results are obtained; based on the simulation results, the optimized flight route is adjusted to obtain a flight route.

[0134] In this embodiment, Mixed Integer Linear Programming (MILP): a mathematical optimization technique used to find the optimal solution under a series of linear and integer constraints, suitable for problems such as resource allocation and path planning.

[0135] Preliminary flight path: The UAV flight path generated based on initial conditions and constraints, which usually needs to be further optimized to suit actual operational needs.

[0136] Graph Neural Network (GNN): A deep learning model that processes graph-structured data and can capture the relationships and interactions between nodes. It is suitable for modeling and predicting complex systems.

[0137] High-risk areas: areas where the risk of drone flight may increase due to meteorological conditions, geographical obstacles or other factors.

[0138] Simulation technology: A method of simulating real-world situations through computers to test the effects of different strategies or designs and assess potential risks and bottlenecks.

[0139] In the embodiment of the present application, firstly, based on the restriction conditions of the temporary virtual fence, a mixed integer linear programming (MILP) is used to calculate the preliminary flight route of the online UAV.

[0140] Next, graph neural networks are used to model and analyze the interactions between drones, capture the complex relationships between them, predict collision points and high-risk areas, and obtain preliminary flight paths.

[0141] Then, the preliminary flight route is adjusted to generate an optimized flight route by taking into account weather conditions, geographical obstacles and flight plans of other online drones.

[0142] Finally, simulation technology is used to evaluate the optimized flight route, detect flight conditions in different scenarios in a simulated environment, identify risks and bottlenecks, and further adjust and optimize the flight route based on the simulation results to ultimately determine a safe and efficient flight route.

[0143] Here is a specific example: Continuing with the above embodiment, the control center first calculates the preliminary flight path of Drone-Omega using mixed integer linear programming (MILP) based on the constraints of the temporary virtual fence.

[0144] Subsequently, graph neural networks were used to analyze the mutual impact between Drone-Omega and other online drones, predict possible collision points and high-risk areas, and obtain a preliminary flight path.

[0145] Next, the system adjusted the initial flight route and generated an optimized flight route, taking into account the day's weather forecast (such as an upcoming storm), geographical obstacles (such as tall buildings), and the flight plans of other drones. In order to verify the actual effect of this optimized flight route, the system used simulation technology to simulate flight conditions under different weather conditions and traffic conditions, and detected some potential risks and bottlenecks. Based on these simulation results, the system further adjusted and optimized the flight route to ensure that Drone-Omega can complete the delivery task efficiently under the premise of safety. This series of measures not only improves the safety and efficiency of the flight path, but also enhances the reliability and flexibility of the entire drone management system.

[0146] Figure 2 A schematic diagram of the structure of a remote identity recognition device (or system) based on drone control requirements is provided for the embodiment of the present application, such as Figure 2 As shown, the device comprises: The receiving module 21 is used to generate an inquiry code using the real-time traffic conditions and safety level of the drone, send an identification request signal containing the inquiry code to all online drones in the target airspace of the drone, and receive an identity response signal, and obtain the readiness state of the online drone according to the identity response signal, wherein the identity response signal encapsulates the unique identifier of the drone, a brief description of the current mission, and a summary of the flight path; The analysis module 22 is used to process the preparation state and the identity response signal by using a multi-dimensional data fusion algorithm, and to predict and analyze the behavior pattern of the online drone in combination with the historical flight data, meteorological conditions and geographic information of the drone, and to generate a behavior prediction report; A comparison module 23 is used to compare the behavior prediction report with the registration information database pre-stored in the control center based on the cross-validation mechanism of blockchain technology to obtain a comparison result, and based on the comparison result, use dual key encryption technology and consensus algorithm to verify the real identity and authorization status of the online drone to generate an identity verification result; The adjustment module 24 is used to use the flight data of the online drone provided by the identity authentication result and combine it with a machine learning algorithm to build a temporary virtual fence, calculate the route of the online drone based on the temporary virtual fence and a path planning algorithm, and automatically adjust and optimize the air corridor to obtain an adjustment result, and update the adjustment result to the relevant drones to form an air traffic management plan; The optimization module 25 is used to analyze the actual flight parameters of the UAV collected in the air traffic management plan using an adaptive control algorithm, optimize the route of the UAV and the setting of the air corridor, and obtain feedback adjustment suggestions, wherein the actual flight parameters of the UAV include speed and altitude change rate.

[0147] Figure 2 The remote identification device based on the drone control requirements can perform Figure 1 The implementation principle and technical effect of the remote identity recognition method based on drone control requirements described in the illustrated embodiment will not be described in detail. The specific manner in which each module and unit performs operations in the remote identity recognition device based on drone control requirements in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0148] In one possible design, Figure 2 An XX device of the embodiment shown may be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32; The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0149] The processing component 32 is used for the above Figure 1 The embodiment of the invention provides a remote identity recognition method based on drone control requirements.

[0150] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0151] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component 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 read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0152] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0153] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0154] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0155] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0156] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The illustrated embodiment is a remote identity recognition method based on drone control requirements.

[0157] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0158] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0159] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0160] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A remote identity recognition method based on drone control requirements, characterized in that: include: Generate an inquiry code using the real-time traffic conditions and safety level of the drone, send an identification request signal containing the inquiry code to all online drones in the target airspace of the drone, receive an identity response signal, and obtain the readiness status of the online drone according to the identity response signal, wherein the identity response signal encapsulates the unique identifier of the drone, a brief description of the current mission, and a summary of the flight path; Processing the readiness state and the identity response signal using a multi-dimensional data fusion algorithm, and combining the historical flight data, meteorological conditions and geographic information of the UAV, predicting and analyzing the behavior pattern of the online UAV, and generating a behavior prediction report; Based on the cross-validation mechanism of blockchain technology, the behavior prediction report is compared with the registration information database pre-stored in the control center to obtain a comparison result, and based on the comparison result, the real identity and authorization status of the online drone are verified by using dual key encryption technology and consensus algorithm to generate an identity verification result; Using the flight data of the online drone provided by the identity authentication result, combined with a machine learning algorithm, a temporary virtual fence is constructed, based on the temporary virtual fence and using a path planning algorithm, the route of the online drone is calculated, and the air corridor is automatically adjusted and optimized to obtain an adjustment result, and the adjustment result is updated to the relevant drones to form an air traffic management plan; An adaptive control algorithm is used to analyze the actual flight parameters of the UAV collected in the air traffic management plan, optimize the route of the UAV and the setting of the air corridor, and obtain feedback adjustment suggestions, wherein the actual flight parameters of the UAV include speed and altitude change rate.

2. The method according to claim 1, characterized in that The cross-validation mechanism based on blockchain technology compares the behavior prediction report with the registration information database pre-stored in the control center to obtain a comparison result, and based on the comparison result, uses dual key encryption technology and consensus algorithm to verify the real identity and authorization status of the online drone to generate an identity verification result, including: Using advanced hashing algorithms and sharding technology to optimize the registration information database pre-stored in the control center, building a distributed ledger system, recording the authentication information of all registered drones based on the distributed ledger system, and automatically performing regular audits through smart contracts to generate a blockchain database, where the authentication information includes a unique identifier and authorization status; Based on the blockchain database, the identity response signal and the readiness status of the online drone are processed, and the behavior pattern of the online drone is predicted and analyzed in combination with a multi-dimensional data fusion algorithm to generate a behavior prediction report; Encrypting the summary of the behavior prediction report using the Advanced Encryption Standard combined with the Elliptic Curve Digital Signature Algorithm to generate an encrypted summary; Sending a verification request to each node in the blockchain network according to the encrypted summary and the unique identifier of the drone, and applying a privacy protection algorithm in combination with a timestamp service to verify the request of the drone to obtain a verification request; Processing the verification request using a fast Byzantine fault-tolerant algorithm, reaching a preliminary consensus among the nodes in the blockchain network, and evaluating the historical transaction records and current authorization status of the drone to generate a risk score, and assisting in reaching a consensus result based on the risk score; Based on the consensus result, the encrypted summary is deeply compared with the registration information pre-stored in the blockchain database. If there is any inconsistency, the security check process is triggered until the verification is correct, and the real identity and authorization status of the online drone are dynamically verified using double-key encryption technology to generate an identity authentication result.

3. The method according to claim 2, characterized in that The verification request is processed using a fast Byzantine fault-tolerant algorithm, a preliminary consensus is reached among the nodes in the blockchain network, and the historical transaction records and current authorization status of the drone are evaluated to generate a risk score, and a consensus result is reached based on the risk score, including: Desensitizing the verification request data to generate a verification request data packet; A fast Byzantine fault-tolerant algorithm is started at each node in the blockchain network, and each node broadcasts the verification request data packet to all other nodes. A distributed hash table is used to optimize the data transmission path of the drone, and a group of leader nodes are selected to obtain a leader node set. Based on the leader node set, receiving copies of verification request data packets from other nodes, and using a fast Byzantine fault-tolerant algorithm to make preliminary consensus decisions, monitor abnormal behaviors of each node in the blockchain network in real time, and obtain preliminary consensus results; Based on the preliminary consensus result, using a preset integrated learning model, deeply evaluate the historical transaction records and current authorization status of the drone, and identify potential risk patterns of the drone to generate a risk score for the drone; The risk score is input as an additional parameter into the fast Byzantine fault tolerance algorithm, and combined with the behavior analysis results of the drone, the trust scores and voting rights distribution between nodes are adjusted to affect the consensus results, wherein the behavior analysis results include the flight trajectory deviation and task completion rate of the drone.

4. The method according to claim 2, characterized in that Based on the consensus result, the encrypted summary is deeply compared with the registration information pre-stored in the blockchain database. If there is any inconsistency, the security check process is triggered until the verification is correct, including: Extracting the deeply compared data according to the consensus result, applying differential privacy technology to desensitize the deeply compared data, and generating high-level comparison data; Based on the advanced comparison data, multi-dimensional feature fusion and graph comparison learning processing are performed on the blockchain database to generate a deep comparison framework; According to the deep comparison framework, a direct matching algorithm is used to compare the encrypted summary with the registration information pre-stored in the blockchain database, and if they are consistent, a preliminary identity verification result is generated; If no match is found, a similarity score between the encrypted summary and the registration information is calculated. When the similarity score exceeds a preset threshold and passes a semantic consistency check, it is considered that the encrypted summary and the registration information are successfully matched, and a similarity analysis result is obtained; For cases that fail the matching and similarity analysis, the preset intelligent anomaly detection system is started for analysis, and the time series analysis algorithm is used to monitor the trend of the encrypted summary and the registration information over time to obtain the detection results; If inconsistencies are detected, a safety inspection process of the drone is triggered based on the inspection result, and a manual review mechanism is applied to review the safety of the inspection steps to obtain a safety inspection result.

5. The method according to claim 2, characterized in that According to the encrypted summary and the unique identifier of the drone, a verification request is sent to each node in the blockchain network, and a privacy protection algorithm is applied in combination with a timestamp service to verify the request of the drone, thereby obtaining a verification request, including: Encrypting the summary of the behavior prediction report using the Advanced Encryption Standard combined with the Elliptic Curve Digital Signature Algorithm to generate an encrypted summary, and combining the encrypted summary with the unique identifier of the drone to form a data packet; According to the data packet, applying a privacy protection algorithm to perform protection processing on the encrypted summary and the unique identifier to obtain a privacy protection data packet; Based on the privacy protection data packet, adding a timestamp to the data packet through a timestamp service to obtain a timestamp data packet; A verification request is constructed using the timestamp data packet, wherein the verification request includes not only an encrypted digest, a unique identifier, a timestamp, and metadata, but also the metadata includes a request source and a target node list.

6. The method according to claim 1, characterized in that Using the flight data of the online drone provided by the identity authentication result, combined with a machine learning algorithm, a temporary virtual fence is constructed, based on the temporary virtual fence and using a path planning algorithm, the route of the online drone is calculated, and the air corridor is automatically adjusted and optimized to obtain an adjustment result, and the adjustment result is updated to the relevant drones to form an air traffic management plan, including: Based on the identity verification result, a deep learning model is applied to extract the flight characteristics of the online drone to generate flight data; According to the flight data, combined with an integrated learning algorithm and a reinforcement learning strategy, the activity range of the drone in a specific area is analyzed to construct a temporary virtual fence; Based on the temporary virtual fence, a preliminary flight route of the online UAV is calculated using a path planning and optimization algorithm, and the restriction conditions of the temporary virtual fence are considered, and the mutual influence between the online UAVs is analyzed in combination with a graph neural network to obtain a flight route; Using the flight route, combined with real-time traffic conditions, safety levels, and adaptive control algorithms, the air corridor is adjusted and optimized, and the flight paths and interval distances of the online drones are coordinated using distributed optimization technology to obtain air corridor settings; Analyzing actual flight parameters using an adaptive control algorithm, and continuously adjusting flight instructions and the air corridor settings through a feedback mechanism to obtain updated flight instructions; An air traffic management plan is formed based on the updated flight instructions.

7. The method according to claim 6, characterized in that Based on the temporary virtual fence, the preliminary flight route of the online UAV is calculated using a path planning and optimization algorithm, and the restriction conditions of the temporary virtual fence are considered. The mutual influence between the online UAVs is analyzed in combination with a graph neural network to obtain a flight route, including: Based on the restriction conditions of the temporary virtual fence, a preliminary flight route of the online UAV is calculated using mixed integer linear programming; Based on the preliminary flight route, the mutual influence between the online drones is modeled and analyzed using a graph neural network, and the complex relationship between the online drones is captured, collision points and high-risk areas are predicted, and a preliminary flight path is obtained; Based on the preliminary flight path, taking into account weather conditions, geographical obstacles and flight plans of other online drones, the preliminary flight route is adjusted to obtain an optimized flight route; The simulation technology is used to evaluate the optimized flight route, simulate the flight conditions under different scenarios, detect risks and bottlenecks, obtain simulation results, and adjust the optimized flight route based on the simulation results to obtain the flight route.

8. A remote identification system based on drone control requirements, characterized in that: include: A receiving module, used to generate an inquiry code using the real-time traffic conditions and safety level of the drone, send an identification request signal containing the inquiry code to all online drones in the target airspace of the drone, and receive an identity response signal, and obtain the readiness status of the online drone according to the identity response signal, wherein the identity response signal encapsulates the unique identifier of the drone, a brief description of the current mission, and a summary of the flight path; An analysis module, used to process the readiness state and the identity response signal by using a multi-dimensional data fusion algorithm, and to predict and analyze the behavior pattern of the online drone in combination with the historical flight data, meteorological conditions and geographic information of the drone, and to generate a behavior prediction report; A comparison module is used for comparing the behavior prediction report with the registration information database pre-stored in the control center based on the cross-validation mechanism of blockchain technology to obtain a comparison result, and based on the comparison result, using dual-key encryption technology and consensus algorithm to verify the real identity and authorization status of the online drone to generate an identity verification result; An adjustment module is used to use the flight data of the online drone provided by the identity authentication result and a machine learning algorithm to build a temporary virtual fence, calculate the route of the online drone based on the temporary virtual fence and a path planning algorithm, and automatically adjust and optimize the air corridor to obtain an adjustment result, and update the adjustment result to the relevant drones to form an air traffic management plan; The optimization module is used to analyze the actual flight parameters of the UAV collected in the air traffic management plan using an adaptive control algorithm, optimize the route of the UAV and the setting of the air corridor, and obtain feedback adjustment suggestions, wherein the actual flight parameters of the UAV include speed and altitude change rate.

9. A computing device, characterized in that It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement the remote identity recognition method based on drone control requirements as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, the remote identity recognition method based on the drone control requirements as described in any one of claims 1 to 7 is implemented.

Images