Blockchain-based shared unmanned aerial vehicle distributed traceability management system

Abstract

The application provides a blockchain-based shared unmanned aerial vehicle distributed traceability management system, which comprises a task data acquisition module, a collaborative trust graph construction module, a trust-task coupling enhancement module, a trust-driven dynamic consensus module and a joint traceability module.The application solves the problems of lack of credibility in the existing centralized system, insufficient dynamic adaptability and weak privacy protection in the blockchain system, and improves the collaboration credibility, traceability capability and privacy protection capability of the shared unmanned aerial vehicle in the multi-user, multi-organization and multi-task scenarios.

Description

Technical Field

[0001] This invention belongs to the field of blockchain, and in particular relates to a blockchain-based distributed traceability management system for shared drones. Background Technology

[0002] With the rapid development of the sharing economy, drones have gradually penetrated from traditional military, surveying, and logistics fields into new business models of multi-party sharing, forming the application trend of "shared drones." In this model, drones are dynamically rented and collaboratively used by different users, organizations, or platforms in various business scenarios, serving complex and ever-changing task requirements such as urban logistics, security patrols, and agricultural monitoring. The widespread application of shared drones has not only effectively improved resource utilization and reduced operating costs, but has also brought unprecedented management challenges. Especially in the context of multi-party use and cross-organizational cooperation, the reliability and traceability of the task execution process, data collection process, and collaborative process of shared drones have become key pain points.

[0003] Existing shared drone management systems typically employ centralized or semi-distributed architectures, using a single platform for drone task allocation, flight data collection, and log management. However, this centralized management model has significant limitations. First, in centralized systems, all drone flight data and mission logs are centrally stored on the management platform, creating a single point of failure and risks of data tampering or loss, making it difficult to guarantee data integrity and reliability during mission execution. Second, existing systems often use simple log storage and basic encryption mechanisms, lacking the ability to dynamically model and reliably record complex collaborative relationships between drones, failing to accurately reflect the collaborative behavior and task dependencies of multiple drones in a shared environment. Especially in scenarios where multiple parties share drone resources or multiple organizations or users jointly schedule drone swarms to execute missions, the lack of transparent and verifiable mechanisms for collaborative and trust relationships makes subsequent accountability, behavior auditing, and collaboration optimization difficult to achieve.

[0004] To overcome the security and trustworthiness deficiencies inherent in centralized systems, some research and systems have begun to incorporate blockchain technology, leveraging its distributed ledger, immutability, and end-to-end recording capabilities to ensure traceability of drone flights and mission execution. However, these blockchain-based shared drone traceability management systems still have shortcomings. First, existing blockchain-based solutions typically focus on simple data on-chaining and smart contract execution, lacking dynamic and intelligent descriptions and trusted management of drone swarm collaboration relationships. This is particularly problematic in environments with frequent changes in drone swarm missions and complex node entry and exit dynamics, making it difficult to meet the demands for efficient and real-time traceability. Second, most current blockchain solutions employ fixed consensus mechanisms, failing to make intelligent and adaptive adjustments to changes in the number of nodes, trust relationships, and collaboration modes in shared drone scenarios. This can easily lead to inefficient consensus processes or inconsistencies in dynamic environments, reducing the real-time performance and stability of the traceability system. Furthermore, in shared environments, multi-party drone collaboration missions often involve risks such as data privacy and leakage of sensitive mission information. Existing systems lack privacy-friendly trust management mechanisms, making it difficult to protect mission collaboration privacy while ensuring transparency and trusted verification of the mission process. To address the above issues, existing technologies have not yet proposed a distributed solution for shared drones. Summary of the Invention

[0005] The purpose of this invention is to propose a blockchain-based distributed traceability management system for shared drones. It establishes a unified technical framework and solves the problems of lack of trust in existing centralized systems, insufficient dynamic adaptability and weak privacy protection in blockchain-based systems. It improves the collaborative trust, traceability and privacy protection capabilities of shared drones in multi-user, multi-organization and multi-task scenarios.

[0006] To achieve the above objectives, this invention provides a blockchain-based distributed traceability management system for shared drones, the system comprising the following modules:

[0007] The task data acquisition module is used to collect UAV collaborative data and generate a standardized dataset; the UAV collaborative data includes position coordinates, the original code of the current collaborative action, flight speed and battery level, timestamp and task number;

[0008] The collaborative trust graph construction module is used to map each data point in the standardized dataset to a node in the graph to construct a collaborative trust graph that reflects the collaborative relationship between drones. Based on the collaborative trust graph, the module performs correlation calculation and analysis to generate trust edge weights. It also performs weighted fusion of the actions of adjacent nodes with the trust edge weights to generate node trust embeddings, which are used to reflect the trust in the collaborative environment and behavior patterns of drones.

[0009] The trust-task coupling enhancement module is used to dynamically enhance the trust embedding of nodes in the trust graph by combining the corresponding task features, so as to obtain enhanced trust embedding, which is then input into the trust-driven dynamic consensus module.

[0010] A trust-driven dynamic consensus module is used to dynamically determine the consensus node set of the collaborative trust graph based on the enhanced trust embedding, and to allocate corresponding task-aware consensus weights.

[0011] The joint tracing module is used to generate a multi-dimensional tracing data structure based on consensus nodes, the type of tasks executed by corresponding nodes and standardized collaborative actions, the trust embedding of corresponding nodes, the weighting degree of corresponding nodes in the trust graph, the set of adjacent nodes of corresponding nodes, and the set of edge weights between corresponding nodes and their neighbors.

[0012] Preferably, the task data acquisition module further includes:

[0013] Map the original code and task number of the current collaborative action to the type of task to be executed by the corresponding node and the standardized collaborative action;

[0014] Within a preset time range, only the latest valid data for each drone is retained to remove redundancy and reduce noise introduced by time resampling during graph modeling.

[0015] Preferably, the step of performing correlation calculation and analysis based on the collaborative trust graph to generate trust edge weights specifically includes:

[0016] For any pair of nodes (v) i ,v j The trust edge weight e is calculated using correlation analysis. i,j as follows:

[0017]

[0018] in, and For v i and v j The standardized collaborative action vectors; Sim(·) is the cosine similarity of the action vectors; ||pos i -pos j || represents the Euclidean distance to the node location, and Exp(-||·||) is the spatial trust decay factor; θ task It is a task type awareness factor, determined by the type of task executed by the corresponding node;

[0019] According to the trust edge weight e i,j The standardized collaborative actions of the drone and its neighboring nodes are weighted and aggregated to generate a trust embedding that reflects the drone's collaborative environment and behavioral patterns.

[0020] Preferably, the trust-task coupling enhancement module specifically performs the following:

[0021] Based on the types of tasks executed in the standardized dataset and the system's built-in task feature table, a corresponding task feature vector is generated for each node, including: task risk level and task collaboration density prediction.

[0022] Based on the task risk level R i Task collaboration density prediction D i Trust embedding w i • Enhancement is performed to obtain enhanced trust embedding. Represented as:

[0023]

[0024] Where γ1 and γ2 are coupling adjustment factors, which are dynamically configured by the system depending on the task type;

[0025] In high-risk, sparsely collaborative task scenarios, R i and 1-D i At the same time, it is relatively large, making Achieve more significant enhancements and improve the system's trust response to specific task environments;

[0026] In collaborative, low-risk task scenarios The enhancement effect is weaker, and the original distribution of the trust graph is maintained to ensure optimal rationality. The conditions for the consensus node set are as follows:

[0027] Condition 1: in, To enhance trust embedding, τ task For task-aware dynamic trust thresholds, the system determines them based on task_type. i Automatic adjustment: Logistics task: τ task =0.5; Security patrol task: τ task =0.7;

[0028] Condition 2: The collaborative influence of a node is not lower than the minimum collaboration threshold κ. min κ i ≥κ min κ i Let κ be the weighted degree of a node in the trust graph, where κ is the weighted degree of the node. i =∑ j∈N(i) e i,j Let j be an adjacent node, N(i) be the set of adjacent nodes, and e be the number of adjacent nodes. i,j Let be the weight of the trust edge from node i to node j.

[0029] Preferably, the task-aware consensus weight of each consensus node is obtained by performing normalized weight analysis on the enhanced trust embedding.

[0030] Preferably, the task risk level includes low risk and high risk; the task collaboration density is estimated to be 0-1, where a lower value indicates that the drone collaboration is sparser under the task, and the reliability of a single node is more important.

[0031] Preferably, in the joint tracing module, a trustworthy behavior factor θ is designed. i Used to comprehensively characterize v i The degree of trustworthiness in collaboration; the trustworthiness behavior factor θ i Represented as:

[0032]

[0033] Among them, |E i |for v i The sum of trust edge weights; |N(i)| is the number of adjacent nodes; η is the cooperation density sensitivity factor; θ i A composite credibility index used to reflect the strength of trust and collaborative relationships.

[0034] The beneficial technical effects of the present invention are at least as follows:

[0035] This invention proposes a distributed traceability management system for shared drone environments, focusing on addressing the shortcomings of existing technologies in areas such as trusted collaboration, dynamic traceability, and privacy protection. This invention innovatively establishes a "dynamic trust collaboration management mechanism" for shared drone swarms, capable of real-time perception and modeling of collaboration and trust relationships between drones, and dynamically driving the consensus process of the distributed ledger system as core parameters. By introducing a closed-loop mechanism of "collaboration-trust-traceability" within the system, it ensures both the transparency of drone collaboration and trusted traceability capabilities in multi-party shared environments, while effectively mitigating problems such as low consensus efficiency and discontinuous traceability chains caused by dynamic environmental changes. Furthermore, this invention designs a "privacy-friendly collaboration and trust management mechanism" to protect the privacy of task data and collaboration data involved in drone sharing tasks, preventing the leakage of sensitive collaboration relationships, while ensuring that external users and multiple management parties can complete complete and verifiable traceability analysis based on the system.

[0036] This invention addresses the core issue of "distributed traceability management in a shared drone environment," establishing a unified technical framework that solves problems such as the lack of trust in existing centralized systems, insufficient dynamic adaptability in blockchain-based systems, and weak privacy protection. It enhances the collaborative trust, traceability capabilities, and privacy protection capabilities of shared drones in multi-user, multi-organization, and multi-task scenarios. Attached Figure Description

[0037] The present invention will be further described with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present invention. For those skilled in the art, other drawings can be obtained based on the following drawings without creative effort.

[0038] Figure 1 This is a framework diagram of the blockchain-based distributed traceability management system for shared drones according to the present invention. Detailed Implementation

[0039] Embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0040] like Figure 1 As shown in the embodiment of the present invention, a blockchain-based distributed traceability management system for shared drones includes:

[0041] The task data acquisition module 1 is used to collect UAV collaborative data and generate a standardized dataset; the UAV collaborative data includes position coordinates, the original code of the current collaborative action, flight speed and battery level, timestamp and task number.

[0042] Specifically, the execution is as follows:

[0043] In a shared drone environment, this module aims to complete the distributed collection and standardization of collaborative behavior data, ensuring highly consistent and low-redundancy input data D for trust graph modeling, serving the trust modeling and distributed traceability goals of the overall patent system.

[0044] Each drone node i in the shared drone swarm collects collaborative data in real time based on local sensors and communication modules during the execution of collaborative tasks, generating standardized data packets d. i It contains the following fields:

[0045] pos i =[x i ,y i ,z i ]: Location coordinates;

[0046] act i The original code of the current collaborative action (such as "handing over supplies" or "coordinated patrol").

[0047] state i =[v i ,b i Flight speed and battery power;

[0048] t i : timestamp;

[0049] task i Task number.

[0050] Due to the heterogeneous characteristics of the shared drone environment, including multi-tenancy, multi-task, and multi-platform nature, the system, after data collection, targets specific tasks... i Activate the "task type standardization mechanism" to classify tasks i Mapped to task_type i (Such as logistics, inspection, security, etc.), and call the corresponding "cooperative action standard dictionary". ", will act i Mapped to a unified action code within the task

[0051] The system then applies a time window redundancy removal mechanism, retaining only the latest valid data for each UAV within a time range of t±Δt, thereby removing redundancy and reducing noise introduced by time resampling during graph modeling.

[0052] The final output standardized collaborative dataset D has the following structure:

[0053]

[0054] Combination formation:

[0055] D = {d1, d2, ..., d} n}

[0056] The dataset D serves as the input for constructing the trust graph G(V,E), and is directly used in the subsequent "trust relationship determination and edge generation" process, completing the first step of trust graph modeling.

[0057] The collaborative trust graph construction module 2 is used to map each data point of the standardized dataset to a node in the graph to construct a collaborative trust graph that reflects the collaborative relationship of UAVs. Based on the collaborative trust graph, the module performs correlation calculation and analysis to generate trust edge weights, and weights and fuses the actions of adjacent nodes with the trust edge weights to generate node trust embeddings, which are used to reflect the trust in the collaborative environment and behavior patterns of UAVs.

[0058] Specifically, the execution is as follows:

[0059] This module receives the standardized collaborative behavior dataset D = {d1, d2, ..., d...} output by module 1. n Construct a trust graph G(V,E) reflecting the collaborative relationships of a shared drone swarm, and generate the trust embedding {w} for each node. iThis serves as input for the subsequent dynamic consensus mechanism. Data D already contains structured records of the cooperative behavior of each drone. This module directly maps it to node v in the graph. i This forms a node set V = {v1, v2, ..., v} n Subsequently, the system establishes the edge set E of the graph using the "task-collaboration-spatial coupling rule".

[0060] To address the diverse, cross-organizational, and spatially complex nature of shared drone collaborative tasks, the system proposes a "Dynamic Collaboration-Spatial Coupling Edge Weight Mechanism (DCSE)" to assign trust edge weights e. i,j The system generates any node pair (v). i ,v j The trust edge weights are calculated using correlation analysis as follows:

[0061]

[0062] Variable definition:

[0063] and For v i and v j Standardized collaborative action vectors;

[0064] Sim(·) represents the cosine similarity of the action vectors;

[0065] ||pos i -pos j || represents the Euclidean distance to the node location, and Exp(-||·||) is the spatial trust decay factor;

[0066] θ task This is the "task type-aware factor," determined by task_type, for example:

[0067] Logistics task: θ task =0.7, indicating a higher weight for action similarity;

[0068] Inspection task: θ task =0.4, the position adjacency weight is higher.

[0069] Through this mechanism, the system ensures that the collaborative trust graph not only captures the similarity of collaborative behaviors, but also adapts the spatial relationship influence according to the characteristics of the task, which is in line with the actual scenario of shared drone mission collaboration.

[0070] After constructing the graph G(V,E), the system designs a "Neighbor Collaborative Aggregation Embedding Mechanism (NCAA)" based on trust edge relationships, embedding the mechanism into each node v. i Generate trust embedding wi This serves as a representation of the credibility of their subsequent participation in the consensus and tracing process.

[0071] The formula for generating trust embedding is as follows:

[0072]

[0073] Variable definition:

[0074] N(i) is v i The set of adjacent nodes;

[0075] e i,j The weight of the trusted edge;

[0076] This is the standard action for neighboring nodes;

[0077] σ(·) is an activation function (such as ReLU) that ensures that the trust embedding is non-negative.

[0078] This embedding mechanism innovatively aggregates the "actions and behaviors of adjacent nodes" and the "strength of trust edges" in a weighted manner to generate a trust embedding w that reflects the collaborative environment and behavioral patterns of UAVs. i It directly serves the "consensus node selection" and "consensus weight assignment" in the subsequent dynamic consensus mechanism.

[0079] Trust-task coupling enhancement module 3 is used to dynamically enhance the trust embedding of nodes in the trust graph by combining corresponding task features, resulting in enhanced trust embeddings, which are then input into the trust-driven dynamic consensus module. Specifically,

[0080] Execute as follows:

[0081] This module uses the trust graph G(V,E) generated in module 2 and the basic trust embedding {w i Using [a specific input] as input, and considering the dynamic collaboration characteristics of multi-task scenarios in a shared drone environment, a "trust-task coupling mechanism" is proposed. Based on the trust graph, task awareness enhancement through trust embedding is achieved, generating [a specific function / mechanism]. As input for subsequent dynamic consensus mechanisms.

[0082] Shared drones offer diverse missions, including logistics, inspection, and security, with significant differences in the density of collaboration and risk sensitivity. This leads to the limitations of a single drone... i It is difficult to accurately reflect the real trust needs in different task scenarios. To solve this problem, this module proposes the "Task Dynamic Feature Aware Trust Enhancement Mechanism (TDC-TEM)" to improve the sensitivity of trust embedding to task dynamic features.

[0083] First, the system is based on the task_type in D. i(Obtained from Module 1) and the system's built-in task characteristic table, for each node v i Generate task feature vector T i =[R i D i ],in:

[0084] R i The task risk level is defined by the system (predefined, e.g., 0.1 for low risk, 0.9 for high risk).

[0085] D i For task collaboration density estimation (0-1, the lower the value, the sparser the drone collaboration under the task, and the more important the reliability of a single node).

[0086] Subsequently, an innovative trust-task coupling model was designed for w. i Perform dynamic enhancements:

[0087]

[0088] Where γ1 and γ2 are coupling adjustment factors, dynamically configured by the system depending on the task type. For example:

[0089] For logistics tasks, γ1 = 0.2, γ2 = 0.3; for security tasks, γ1 = 0.5, γ2 = 0.2.

[0090] R i and D i The introduction of this technology gives trust embedding the ability to perceive tasks with "high risk / low collaboration density".

[0091] The core innovation of this mechanism lies in its sensitivity to task characteristics:

[0092] In high-risk, sparsely collaborative task scenarios (such as inspection tasks), R i and 1-D i At the same time, it is relatively large, making Achieve more significant enhancements and improve the system's trust response to specific task environments;

[0093] In collaborative, low-risk tasks (such as routine logistics collaboration), The enhancement effect is weaker, maintaining the original reasonable distribution of the trust graph.

[0094] Ultimately, the system outputs enhanced trust embedding. This serves as a direct input for subsequent module 4 in the selection of consensus nodes and the allocation of consensus weights.

[0095] For example:

[0096] U1 and U2 simultaneously participate in a high-risk, sparsely coordinated security task. The original values ​​are w1 = 0.6, R1 = 0.9, and D1 = 0.3. The security task configuration is γ1 = 0.5 and γ2 = 0.2. The calculated values ​​are... The trust value has been significantly enhanced compared to the original value, reflecting the dynamic adjustment effect of the task scenario.

[0097] The trust-driven dynamic consensus module 4 is used to dynamically determine the consensus node set of the collaborative trust graph based on the enhanced trust embedding, and to allocate the corresponding task-aware consensus weights.

[0098] Specifically, the execution is as follows:

[0099] This module is based on the trust graph G(V,E) generated in Module 3 and the task-aware trust embedding. Design a Trust-Driven Dynamic Consensus Control (TDC-CM) mechanism to dynamically select the set C of nodes participating in distributed consensus and assign task-aware consensus weights {ω} to these nodes. i}, which serves as input for the subsequent consensus process.

[0100] Shared drone systems typically feature dynamic topologies, uneven collaborative distribution, and diverse task types. Traditional static mechanisms with fixed consensus nodes and fixed weights are ill-suited to the real-time changing trust dynamics within shared task environments. To address this issue, this module designs a task-dynamically aware "trust-graph structure fusion mechanism" to dynamically select consensus nodes and assign them weights.

[0101] Dynamic filtering of consensus nodes

[0102] The system is based on G(V,E). The consensus node set C is dynamically determined. Node v i A candidate set C is added to the consensus set when the following conditions are met:

[0103] Condition 1: Where τ task For task-aware dynamic trust thresholds, the system determines them based on task_type. i Automatic adjustment:

[0104] Logistics task: τ task =0.5

[0105] Security patrol tasks: τ task =0.7

[0106] Condition 2: The collaborative influence of a node is not lower than the minimum collaboration threshold κ. min κ i ≥κ min , where κ i =∑j∈N(i) e i,j .

[0107] Consensus weight allocation mechanism

[0108] Within system C, a "trust-topology coupling" weight allocation mechanism is designed, combining trust distribution with collaborative topology influence to output {ω}. i}

[0109]

[0110] Variable definition:

[0111] Trust value for task awareness;

[0112] κ i : The collaborative weighting degree of the nodes;

[0113] α∈[1,2]: controls the sensitivity of topological influence to weight distribution;

[0114] ∑ i∈C ω i =1, which satisfies weight normalization.

[0115] Output content

[0116] {C}: The dynamically selected set of consensus candidate nodes;

[0117] {ω i}: The task-aware consensus weight of each consensus node.

[0118] For example, in a logistics task, the trust values ​​of U1, U2, and U3 are respectively... System configuration τ task =0.5:

[0119] U1 and U2 meet the screening criteria, while U3 is because... Lower values ​​were excluded;

[0120] The system then based on κ i Calculate ω i Output ω U1 =0.4, ω U2 =0.6, directly passed to module 5 for the actual consensus process.

[0121] The joint tracing module 5 is used to generate a multi-dimensional tracing data structure based on consensus nodes, the type of tasks executed by corresponding nodes and standardized collaborative actions, the trust embedding of corresponding nodes, the weighting degree of corresponding nodes in the trust graph, the set of adjacent nodes of corresponding nodes, and the set of edge weights between corresponding nodes and their neighbors.

[0122] Specifically, the execution is as follows:

[0123] In a shared drone system, this module is based on the existing trust graph G(V,E), collaborative behavior data D, and task-aware trust embedding. and the dynamic consensus control result {C,ω i This paper proposes a "Trusted Collaboration-Trust-Task Joint Trace Model (TTT-Trace)" to model the multi-dimensional traceability data structure R, providing foundational data for subsequent on-chain consensus and traceability verification. In multi-task, multi-tenant environments, shared drones exhibit dispersed collaboration processes, dynamic trust scoring, and often separate behavioral and trust data, making it difficult to trace the three-dimensional causal relationship of "task-collaboration-trust" in drone behavior.

[0124] To address this, the system proposes to integrate 3D data and generate R models within each task cycle to ensure that the collaborative behavior, trust status, and task background of each node are fully traceable.

[0125] Joint traceability structure design

[0126] The proposed R structure is as follows:

[0127]

[0128] Variable definition:

[0129] v i Consensus node, selected from C by Module 4;

[0130] task_type i , Node v i The types of tasks performed and the standardized collaborative actions are derived from D;

[0131] Node trust embedding, from module 3;

[0132] κ i κ: The weighted degree of a node in G i =∑ j∈N(i) e i,j ;

[0133] N(i): v i The set of adjacent nodes;

[0134] E i :v i The set of edge weights between the neighboring countries, E i ={e i,j |j∈N(i)}.

[0135] Special Innovation Item – Trustworthy Behavior Factor

[0136] To enhance the interpretability of traceability data regarding the intrinsic causal relationship between "collaborative behavior - trust score - task context", the system innovatively proposes a "trustworthy behavior factor" θ. i Used to comprehensively characterize v i The credibility of collaboration.

[0137]

[0138] Variable description:

[0139] |E i |for v i The sum of the weights of the trusted edges;

[0140] |N(i)| represents the number of adjacent nodes;

[0141] η is a sensitivity factor for cooperation density;

[0142] θ i A composite credibility index reflecting "trust value + strength of collaborative relationship";

[0143] This factor is directly used as one of the fields of R to assist in subsequent on-chain verification or tracing and accountability.

[0144] Source tracing link output

[0145] Ultimately, the system outputs a joint traceability record R, whose core function is to provide direct evidence for future anomaly detection, traceability auditing, and liability determination.

[0146] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0147] In the embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of apparatuses or units may be electrical, mechanical, or other forms.

[0148] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the modules of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0149] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

Claims

1. A blockchain-based distributed traceability management system for shared drones, characterized in that: The system includes the following modules: The task data acquisition module is used to collect UAV collaborative data and generate a standardized dataset; the UAV collaborative data includes position coordinates, the original code of the current collaborative action, flight speed and battery level, timestamp and task number; The collaborative trust graph construction module is used to map each data point in the standardized dataset to a node in the graph to construct a collaborative trust graph that reflects the collaborative relationship between drones. Based on the collaborative trust graph, the module performs correlation calculation and analysis to generate trust edge weights. It also performs weighted fusion of the actions of adjacent nodes with the trust edge weights to generate node trust embeddings, which are used to reflect the trust in the collaborative environment and behavior patterns of drones. The trust-task coupling enhancement module is used to dynamically enhance the trust embedding of nodes in the trust graph by combining the corresponding task features, so as to obtain enhanced trust embedding, which is then input into the trust-driven dynamic consensus module. A trust-driven dynamic consensus module is used to dynamically determine the consensus node set of the collaborative trust graph based on the enhanced trust embedding, and to allocate corresponding task-aware consensus weights. The joint tracing module is used to generate a multi-dimensional tracing data structure based on consensus nodes, the type of tasks executed by corresponding nodes and standardized collaborative actions, the trust embedding of corresponding nodes, the weighting degree of corresponding nodes in the trust graph, the set of adjacent nodes of corresponding nodes, and the set of edge weights between corresponding nodes and their neighbors. The step of performing correlation calculation and analysis based on the collaborative trust graph to generate trust edge weights specifically includes: For any node pair The trust edge weights are calculated using correlation analysis. as follows: ; in, and for and Standardized collaborative action vectors; Cosine similarity of action vectors; Let be the Euclidean distance between the node locations. As a spatial trust decay factor; It is a task type awareness factor, determined by the type of task executed by the corresponding node; Based on the trust edge weight The standardized collaborative actions of the drone and its neighboring nodes are weighted and aggregated to generate a trust embedding that reflects the drone's collaborative environment and behavior patterns. The trust-task coupling enhancement module specifically performs the following: Based on the types of tasks executed in the standardized dataset and the system's built-in task feature table, a corresponding task feature vector is generated for each node, including: task risk level and task collaboration density prediction. Based on the task risk level Task collaboration density prediction Trust embedding Enhancement is performed to obtain enhanced trust embedding. , represented as: ; in The coupling adjustment factor is dynamically configured by the system depending on the task type. In high-risk, sparsely collaborative task scenarios, and At the same time, it is relatively large, making Achieve more significant enhancements and improve the system's trust response to specific task environments; In collaborative, low-risk task scenarios The enhancement effect is weaker, maintaining the original reasonable distribution of the trust graph; The task risk level includes low risk and high risk; the task collaboration density is estimated to be... The lower the value, the sparser the drone collaboration under the task, and the more important the reliability of a single node.

2. The blockchain-based distributed traceability management system for shared drones according to claim 1, characterized in that, The task data acquisition module also includes: Map the original code and task number of the current collaborative action to the type of task to be executed by the corresponding node and the standardized collaborative action; Within a preset time range, only the latest valid data for each drone is retained to remove redundancy and reduce noise introduced by time resampling during graph modeling.

3. The blockchain-based distributed traceability management system for shared drones according to claim 1, characterized in that, The conditions for the consensus node set are as follows: Condition 1: ,in, To enhance trust embedding, For task-aware dynamic trust thresholds, the system based on Automatic adjustment: Logistics tasks: Security patrol tasks: ; Condition 2: The node's collaborative influence is not lower than the minimum collaboration threshold. , , Let be the weighted degree of a node in the trust graph, where j is the adjacent node. For the set of adjacent nodes, Let be the weight of the trust edge from node i to node j.

4. The blockchain-based distributed traceability management system for shared drones according to claim 1, characterized in that, Based on the normalized weight analysis of the enhanced trust embedding, the task-aware consensus weight of each consensus node is obtained.

5. The blockchain-based distributed traceability management system for shared drones according to claim 1, characterized in that, In the joint tracing module, a trustworthy behavior factor is designed. Used for comprehensive characterization The degree of trustworthiness in collaboration; the trustworthy behavior factor Represented as: ; in, for The sum of the weights of the trusted edges; This represents the number of adjacent nodes; It is a sensitivity factor to cooperation density; A composite credibility index used to reflect the strength of trust and collaborative relationships.

Images