A method and storage medium for low-altitude economic reliable data processing

Abstract

This invention discloses a method and storage medium for reliable low-altitude economic data processing, belonging to the field of low-altitude economics and data element circulation technology. The method includes: responding to a Shapley value calculation instruction, for each of multiple drones operating collaboratively in low-altitude airspace, reading low-altitude data corresponding to the drone from a blockchain, and determining the drone's contribution value based on the low-altitude data; using a target Shapley formula, determining the alliance contribution value based on the drone's contribution value and a first airspace openness correction factor, and determining a weighting coefficient based on the first airspace openness correction factor and the alliance size; and determining the drone's target Shapley value based on the alliance contribution value and the weighting coefficient, so as to allocate value to each drone for all low-altitude data based on the target Shapley value corresponding to each drone. The technical solution of this invention can ensure fairness in the value allocation of low-altitude data.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of low-altitude economy and data element circulation technology, and in particular to a reliable data processing method and storage medium for low-altitude economy. Background Technology

[0002] With the opening of low-altitude airspace and the large-scale application of drones, the low-altitude economy is becoming a new growth engine. Drone inspections, logistics delivery, and urban air traffic tasks continuously generate massive amounts of high-value low-altitude data (such as flight trajectories, high-definition imagery, real-time weather, airspace status, and equipment monitoring). Allocating value for this low-altitude data is crucial.

[0003] Taking a drone inspection mission as an example, multiple drones work together to perform the mission. In this case, the value of each drone can be allocated based on the low-altitude data generated during the execution of the mission.

[0004] However, the current value distribution scheme for low-altitude data cannot guarantee fairness and urgently needs to be addressed. Summary of the Invention

[0005] This invention provides a method and storage medium for processing reliable low-altitude economic data, which solves the problem of not being able to guarantee fairness when allocating value for low-altitude data.

[0006] According to one aspect of the present invention, a method for processing reliable low-altitude economic data is provided, which may include:

[0007] In response to the Shapley value calculation instruction, for each of the multiple drones operating collaboratively in low-altitude airspace, the corresponding low-altitude data is read from the blockchain, and the drone contribution value is determined based on the low-altitude data. Low-altitude airspace refers to airspace within a preset distance from the ground plane, and low-altitude data is generated during the first time period of the drone's operation. Using the target Shapley formula, the alliance contribution value is determined based on the drone contribution value and the first airspace openness correction factor. A weighting coefficient is also determined based on the first airspace openness correction factor and the alliance size. Finally, the target Shapley value for each drone is determined based on the alliance contribution value and the weighting coefficient. Based on the target Shapley value for each drone, value is allocated to each drone for all low-altitude data. The first airspace openness correction factor is determined based on the effective duration of the airspace openness policy for the first time period and the time decay rate corresponding to the first time period. The airspace openness policy is an openness policy related to low-altitude airspace.

[0008] According to another aspect of the present invention, a low-altitude economic reliable data processing apparatus is provided, which may include:

[0009] The drone contribution value determination module can be used to respond to the Shapley value calculation command, for each of the multiple drones working collaboratively in low-altitude airspace, read the low-altitude data corresponding to the drone from the blockchain, and determine the drone contribution value of the drone based on the low-altitude data. The low-altitude airspace is the airspace that is within a preset distance range from the ground plane, and the low-altitude data is the data generated in the first time period during the drone's operation.

[0010] The value allocation module can be used to determine the alliance contribution value based on the UAV contribution value and the first airspace openness correction factor using the target Shapley formula, and to determine the weight coefficient based on the first airspace openness correction factor and the alliance size. It can also determine the target Shapley value of the UAV based on the alliance contribution value and the weight coefficient. Based on the target Shapley value corresponding to each UAV, the module allocates value to each UAV for all low-altitude data. The first airspace openness correction factor is determined based on the effective duration of the airspace openness policy for the first time period and the time decay rate corresponding to the first time period. The airspace openness policy is an openness policy related to low-altitude airspace.

[0011] According to another aspect of the present invention, an electronic device is provided, which may include:

[0012] At least one processor; and

[0013] A memory that is communicatively connected to at least one processor; wherein,

[0014] The memory stores a computer program that can be executed by at least one processor, such that when the at least one processor executes the program, it implements the low-altitude economical and reliable data processing method provided in any embodiment of the present invention.

[0015] According to another aspect of the present invention, a computer-readable storage medium is provided having computer instructions stored thereon, which are used to cause a processor to execute and implement the low-altitude economical and reliable data processing method provided in any embodiment of the present invention.

[0016] According to another aspect of the present invention, a computer program product is provided, on which a computer program is stored, which, when executed by a processor, implements the low-altitude economic reliable data processing method provided in any embodiment of the present invention.

[0017] The technical solution of this invention, in response to the Shapley value calculation instruction, reads the low-altitude data corresponding to each UAV in a multi-UAV collaborative operation in low-altitude airspace from the blockchain for each UAV, and then determines the UAV contribution value based on the low-altitude data to reflect the dynamic contribution value of an individual UAV. Further, using an improved target Shapley formula, the alliance contribution value is determined based on the UAV contribution value and a first airspace openness correction factor to respond to environmental changes. A weighting coefficient is determined based on the first airspace openness correction factor and the alliance size to obtain a weighting coefficient related to the timeliness (i.e., dynamic) of the airspace openness policy. Then, the target Shapley value of the UAV can be determined based on the alliance contribution value and the weighting coefficient. Thus, value allocation can be performed for each UAV based on the target Shapley value corresponding to each UAV for all low-altitude data. The first airspace openness correction factor can be determined based on the effective duration of the airspace openness policy for the first time period and the time decay rate corresponding to the first time period. Compared to using static value allocation weights for value allocation, the above technical solution introduces a first airspace openness correction factor to characterize the timeliness of airspace openness policies. Based on this, when calculating the target Shapley value (i.e., value allocation weights), the alliance contribution value is determined by introducing the UAV contribution value and the first airspace openness correction factor to respond to environmental changes. Furthermore, the first airspace openness correction factor is introduced to determine dynamic weight coefficients to correlate with the timeliness of airspace openness policies. These technical features work together to effectively ensure fairness in value allocation for low-altitude data.

[0018] It should be understood that the description in this section is not intended to identify key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart of a low-altitude economic reliable data processing method provided by an embodiment of the present invention;

[0021] Figure 2 This is a flowchart of another low-altitude economic reliable data processing method provided by an embodiment of the present invention;

[0022] Figure 3This is a schematic diagram of a game tree in another low-altitude economic reliable data processing method provided by an embodiment of the present invention;

[0023] Figure 4 This is a flowchart of another low-altitude economic reliable data processing method provided by an embodiment of the present invention;

[0024] Figure 5 This is a structural block diagram of a low-altitude economic reliable data processing device provided according to an embodiment of the present invention;

[0025] Figure 6 This is a schematic diagram of the structure of an electronic device that implements the low-altitude economic reliable data processing method according to an embodiment of the present invention. Detailed Implementation

[0026] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. The same applies to "target," "original," etc., and will not be repeated here. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] Before introducing the embodiments of the present invention, the application scenarios and modules that may be involved in the embodiments of the present invention will be described by way of example. For example, the current technical solutions related to low-altitude economic reliable data space have the following problems:

[0029] 1. Data silos: Data is scattered among multiple entities such as air traffic control departments, drone operators, meteorological service providers and logistics platforms, lacking secure and reliable sharing channels, forming "data chimneys";

[0030] 2. Lack of trust mechanisms: Cross-entity data sharing faces risks such as unclear ownership, difficulty in verifying authenticity, and privacy leaks, making it difficult for centralized platforms to establish mutual trust among multiple parties;

[0031] 3. Inaccurate value measurement: Data value is affected by multiple dimensions such as quality (accuracy and timeliness), scarcity (regional coverage) and application scenarios. Existing static pricing or simple revenue sharing models cannot fairly quantify dynamic contributions.

[0032] 4. Low collaboration efficiency: Lack of dynamic and fine-grained data access control and collaboration strategies, making it difficult to respond to emergencies (such as severe weather emergencies).

[0033] 5. Insufficient incentive compatibility: Contributors struggle to receive reasonable rewards, and users find it difficult to access reliable data, thus inhibiting the vitality of data element circulation.

[0034] To address this, the embodiments of the present invention include five modules, as detailed below:

[0035] Module 1: Dynamic Game Model Construction, which involves three aspects: 1. Airspace Openness Correction Factor, 2. Bayesian Policy Update Mechanism, and 3. Extended Game Tree Design. This module addresses the static limitations of existing dynamic game models, which are often based on static equilibrium assumptions and cannot effectively characterize the dynamic policy interactions among multiple stakeholders (e.g., drones from different departments and missions) in low-altitude data scenarios. Specifically:

[0036] 1) The airspace opening policy has a significant time sensitivity, and the relevant dynamic game model does not introduce the relevant spatiotemporal decay function. The lack of representation of the spatiotemporal decay effect leads to policy rigidity.

[0037] 2) In low-altitude scenarios, there is information asymmetry among multiple stakeholders such as drone operators and air traffic control departments (e.g., delayed sharing of meteorological risk data), and the relevant dynamic game models lack an update mechanism, making it difficult to optimize strategies in real time.

[0038] Module Two: Improvement of the Shapley Participation and Contribution Proof (PPC) Algorithm. This module involves two aspects: 1. PPC consensus mechanism design - quality scoring; and 2. Improved Shapley formula. PPC can be understood as a consensus mechanism specifically designed for low-altitude data collaboration scenarios. Its core is to dynamically quantify the true contributions of participants through mathematical proof, solving the reliable verification problem of "who created how much value, when, and where". This module is designed to address the issue of insufficient fairness and adaptability of related revenue distribution models (such as the classic Shapley value) in low-altitude data scenarios. Specifically, it is manifested in the following ways:

[0039] 1) The value contribution of low-altitude data has significant spatiotemporal differences (such as regional coverage density and data update frequency), and the relevant Shapley values ​​cannot quantify dynamic contributions, leading to allocation results that deviate from reality;

[0040] 2) Sensor data may accumulate errors over time (such as a decrease in the accuracy of meteorological monitoring equipment), and the related revenue distribution model cannot dynamically correct the data reliability, leading to distribution disputes.

[0041] Module 3: Dual-chain blockchain design, which involves three aspects: 1. Consortium blockchain: storing static data; 2. Directed Acyclic Graph (DAG) chain: storing dynamic data; and 3. Smart contract execution. Module 3 is designed to address the problem that related blockchain technologies cannot separate structured data from time-series data, which leads to on-chain execution latency and throughput bottlenecks.

[0042] Module Four: Technical Collaboration and Closed-Loop Feedback. This module outlines the closed-loop feedback logic for 1. updating airspace openness priorities, 2. calculating Shapley values, and 3. comprehensively evaluating and tuning the Gini coefficient. Module Four is designed to address the problem of related systems or models lacking feedback loops, thus failing to adjust strategies and allocations promptly based on sudden changes in results.

[0043] Module 5: Trusted Data Space Module, which connects the above four modules from the perspective of trusted data space.

[0044] In other words, this invention, based on blockchain and dynamic collaborative governance, innovatively integrates dynamic strategy generation, data contribution quantification, and blockchain-based trusted execution and closed-loop feedback optimization, solving the challenges of secure sharing, value confirmation, and fair distribution of low-altitude multi-source data. To put it another way, this invention, with a dynamic game theory model and improved Shapley value at its core, constructs a closed-loop system of "dynamic strategy evolution - contribution quantification - revenue distribution," achieving collaborative optimization of the low-altitude data value chain. Specifically, it includes the following:

[0045] Dynamic game model: embedding a spatial openness correction factor (i.e., time decay function) and Bayesian update mechanism to solve the problem of allocating spatiotemporal limitation effects;

[0046] Shapley-PPC Allocation Algorithm: Improves the static defects of related Shapley values ​​by combining the PPC consensus mechanism;

[0047] Blockchain-supported architecture: The game strategy and allocation rules are executed on-chain with trust through smart contracts, forming a closed-loop feedback.

[0048] Among them, the airspace access priority output by Module 1 serves as the core execution basis of the smart contract. By controlling the airspace access status, it affects the drone data (such as data volume, data accuracy, and regional coverage weight), thereby driving the resource allocation calculation of Module 2. The allocation results and verification results affect the parameters and are fed back to Module 1, forming a closed-loop optimization.

[0049] The above content will be explained in detail below.

[0050] Figure 1 This is a flowchart of a low-altitude economic trusted data processing method provided in an embodiment of the present invention. This embodiment is applicable to situations involving value allocation of low-altitude data, particularly low-altitude economic trusted data. This low-altitude economic trusted data can be understood as economically valuable low-altitude data generated in low-altitude airspace and trusted due to its storage on a blockchain. This method can be executed by the low-altitude economic trusted data processing device provided in this embodiment of the present invention. This device can be implemented in software and / or hardware and can be integrated into an electronic device, which can be various user terminals or servers.

[0051] See Figure 1 The method of this invention specifically includes the following steps:

[0052] S110. In response to the Shapley value calculation instruction, for each of the multiple drones operating collaboratively in the low-altitude airspace, read the low-altitude data corresponding to the drone from the blockchain, and determine the drone contribution value of the drone based on the low-altitude data.

[0053] Low-altitude airspace refers to the airspace within a preset distance from the ground plane, and low-altitude data is the data generated during the first period of the drone's operation.

[0054] The low-altitude airspace can be understood as the airspace located at a distance from the ground plane, especially the airspace with a vertical distance within a preset range. This preset range can be [0, 1000], [0, 2000], or [0, 3000], etc., and can be set according to actual conditions, without specific limitations here. In this embodiment of the invention, optionally, the low-altitude airspace can be divided into two or more regions, and each region can be further divided into two or more grids to achieve fine-grained calculation.

[0055] Multiple drones can be understood as drones working collaboratively (i.e., cooperating) in low-altitude airspace. During the operation, these multiple drones generate multiple low-altitude data points, all of which are stored on the blockchain to ensure their credibility.

[0056] Based on this, the Shapley value calculation instruction can be understood as an instruction to calculate the Shapley value (i.e., Shapley value) of low-altitude data generated during the first time period of the operation, where the first time period corresponds to the instruction. In response to this instruction, for each drone, the low-altitude data generated by the drone during the first time period is read from the blockchain, and the drone contribution value of the drone is determined based on the low-altitude data.

[0057] In this embodiment of the invention, optionally, the first of a plurality of drones is referred to here. Taiwanese drones (i.e., unmanned aerial vehicles) For example, low-altitude data can include data volume. Data accuracy and regional coverage weight At least one of them. Among them, It can represent the number of flight trajectory points of the drone per unit time. This number is limited by the size of the area it is allowed to enter and the flight time. The unit time can be minutes or hours, etc., which can be set according to actual needs and is not specifically limited here. Characterizing the measurement accuracy of the sensors within the drone reflects data reliability. High-precision data reduces decision-making risk and serves as a threshold for accessing high-priority and / or high-risk areas. For example, =1 / sensor error. If the Global Positioning System (GPS) error is 0.5 meters, then... = 2; if the radar error is 0.2 meters, then = 5. The spatial coverage value of UAVs in low-altitude airspace can be represented by kernel density estimation of the actual flight grid. This involves dividing the low-altitude airspace into a 1km × 1km × 100m grid, calculating the number of all UAVs within that grid, and generating density values ​​[0, 1] based on the UAV distribution. For example, this can be estimated using the following formula: :

[0058] .

[0059] For example, drones Located in a high-density grid, = 0.3, while located in a low-density grid (i.e., an edge grid). = 0.9, thus ensuring fairness in resource allocation and preventing peripheral drones from being overlooked. This is understandable. A low value indicates that the corresponding grid has been densely covered. A high coverage indicates weak grid coverage. Drones operating in low-coverage grids contribute more than those operating in high-coverage grids. For example, operations in mountainous areas have more marginal value than operations in urban areas.

[0060] Based on this, according to , and It is possible to calculate the drone The contribution value of drones ( Here, we take weighted calculation as an example to obtain... The corresponding first weight , The corresponding second weight as well as The corresponding third weight and according to and , and ,as well as and ,Sure For example, they can be directly weighted and calculated to obtain... ,Right now ; You can also first , and The data is converted to dimensionless data, and then weighted calculations are performed on this basis; etc. This can be configured according to actual needs and is not specifically limited here. This is the main content of the PPC consensus mechanism design - quality scoring described above.

[0061] S120. Using the target Shapley formula, determine the alliance contribution value based on the UAV contribution value and the first airspace openness correction factor, and determine the weight coefficient based on the first airspace openness correction factor and the alliance size. Then, determine the target Shapley value of the UAV based on the alliance contribution value and the weight coefficient. Based on the target Shapley value corresponding to each UAV, allocate value for all low-altitude data for each UAV.

[0062] The first airspace openness correction factor is determined based on the effective duration of the airspace openness policy for the first time period and the time decay rate corresponding to the first time period. The airspace openness policy is an openness policy related to low-altitude airspace.

[0063] Among them, the airspace opening policy can characterize the opening status of low-altitude airspace (such as the opening time period, i.e., the flight time period), and can further characterize the opening status of each area within the low-altitude airspace.

[0064] It should be noted that airspace openness policies have a significant time-sensitive nature; that is, their effectiveness decreases over time and is not static. Therefore, to characterize this time-sensitive nature, this embodiment of the invention proposes an airspace openness correction factor. The concept. Of course, in order to be consistent with the concept used in subsequent embodiments for updating airspace openness priority. To distinguish between them, the method used here for calculating the Shapley value will be... This is called the first airspace openness correction factor, and it will be applied subsequently to update the airspace openness priority. This is called the second airspace openness correction factor. It should be noted that, for simplicity, both the first and second airspace openness correction factors mentioned below can be referred to as... This can be represented. Of course, if there is a need for differentiation, it can also be done through... Indicates the first spatial openness correction factor and passes This represents the second airspace openness correction factor. Etc., this can be selected according to actual needs, and no specific limitations are made here.

[0065] Furthermore, the duration of operation This can be understood as the duration for which the airspace openness policy has been in effect relative to the first phase, i.e., the time from its initial effective date to a certain point within the first phase. This duration can be synchronized via a blockchain timestamp. This specific point can be the start, middle, or end date of the first phase, etc., and can be set according to actual needs; no specific limitation is made here. Time decay rate This can be understood as the decay rate corresponding to the first time period, which can be set according to the timeliness requirements of airspace opening policies. Based on this, it can be determined according to... and Determine the first airspace openness correction factor ,For example , or This can be set according to actual needs, and is not specifically limited here. In the embodiments of the present invention, It can be used to dynamically adjust the airspace opening priority, indicating that the airspace opening priority decreases over time.

[0066] In addition, the target Shapley formula (i.e., the target Shapley formula) in this embodiment of the invention is an improvement on the relevant Shapley formula. Therefore, to better understand the improvement points of the target Shapley formula in this embodiment of the invention, the relevant Shapley formula is first described by way of example. For example, the relevant Shapley formula can be expressed as:

[0067] ;

[0068] in, For drones; A subset of the alliance, representing a cooperative alliance formed by a subset of drones; alliance characteristic function. for Total contribution value that can be generated when operating independently (i.e., alliance contribution value); Alliance marginal contribution For drones Join the alliance The added value brought by time; weighting coefficient To measure the weighted probability of each alliance ranking.

[0069] Analysis reveals that the Shapley formula described above has at least the following drawbacks:

[0070] 1. It is a fixed value, meaning it never changes and cannot respond to environmental changes. Therefore, embodiments of the present invention address this issue. Based on this, a personal dynamic contribution value (i.e., the drone contribution value described above) and The impact.

[0071] 2. Only with the size of the alliance There is a relationship. In this regard, embodiments of the present invention introduce... This allows us to obtain dynamic weighting coefficients. ,and It is related to the timeliness of policies.

[0072] This invention improves upon the aforementioned Shapley formula by proposing a target Shapley formula. This target Shapley formula can then be used to determine the contribution value of the unmanned aerial vehicle (UAV). In particular, the contribution value of each drone and the correction factor for the first airspace openness. Determine the alliance contribution value and the correction factor based on the first airspace openness. The weighting coefficients are determined based on the alliance size, and then the target Shapley value of the drone is determined based on the alliance contribution value and the weighting coefficients. ,in, Can represent drones Value allocation weight.

[0073] For example, the target Shapley formula can be expressed as:

[0074] ;

[0075] in, Represents the weighting coefficients, where This is the first spatial openness correction factor. To uniformly control the global timeliness decay, and Describing a subset of the alliance The number of drones in the country When |S| is less than 1, it suppresses the weight of large leagues; the larger |S| is, the more... The smaller the value, the less computation is required; ) is the coalition characteristic function, calculated using the following formula: )= ,pass (t) Unify the correction of the timeliness contribution of all drones; normalize the denominator to ensure that the sum of the value allocation weights corresponding to all participants (i.e. drones) is 1, and prevent the value allocation result from overflowing.

[0076] Based on this, optionally, the relevant Shapley formulas need to be traversed. This involves various combinations, calculating all union subsets, while the embodiments of the present invention can use Monte Carlo sparse sampling, requiring only random selection. indivual Calculations are performed, and using the law of large numbers, the sampling error and... Inversely proportional, for example When the value is 1000, the error is controlled within 5%, thus accelerating the calculation. yes The number of drones in China, i.e. .

[0077] Alternatively, alliance marginal contribution The computation can be distributed to GPU cores for parallel processing. That is, the GPU performs parallel computation, thereby accelerating the computation.

[0078] Furthermore, after obtaining the target Shapley value corresponding to each drone, i.e., obtaining the value allocation weight corresponding to each drone, value can be allocated to each drone for all low-altitude data based on these values. In this embodiment of the invention, optionally, this value allocation process can be triggered periodically or manually, which can be set according to actual needs and is not specifically limited here. For example, value allocation can be automatically performed at 0:00 every day, followed by revenue settlement. In case of disputes, a multi-signature arbitration mechanism can be used through the original data stored on the blockchain.

[0079] The technical solution of this invention, in response to the Shapley value calculation instruction, reads the low-altitude data corresponding to each UAV in a multi-UAV collaborative operation in low-altitude airspace from the blockchain for each UAV, and then determines the UAV contribution value based on the low-altitude data to reflect the dynamic contribution value of an individual UAV. Further, using an improved target Shapley formula, the alliance contribution value is determined based on the UAV contribution value and a first airspace openness correction factor to respond to environmental changes. A weighting coefficient is determined based on the first airspace openness correction factor and the alliance size to obtain a weighting coefficient related to the timeliness (i.e., dynamic) of the airspace openness policy. Then, the target Shapley value of the UAV can be determined based on the alliance contribution value and the weighting coefficient. Thus, value allocation can be performed for each UAV based on the target Shapley value corresponding to each UAV for all low-altitude data. The first airspace openness correction factor can be determined based on the effective duration of the airspace openness policy for the first time period and the time decay rate corresponding to the first time period. Compared to using static value allocation weights for value allocation, the above technical solution introduces a first airspace openness correction factor to characterize the timeliness of airspace openness policies. Based on this, when calculating the target Shapley value (i.e., value allocation weights), the alliance contribution value is determined by introducing the UAV contribution value and the first airspace openness correction factor to respond to environmental changes. Furthermore, the first airspace openness correction factor is introduced to determine dynamic weight coefficients to correlate with the timeliness of airspace openness policies. These technical features work together to effectively ensure fairness in value allocation for low-altitude data.

[0080] One optional technical solution is that the first time period includes multiple sub-time periods, and a corresponding Shapley value is determined for each sub-time period. The Shapley value is determined based on the low-altitude data, the duration of operation, and the time decay rate corresponding to the corresponding sub-time period.

[0081] The target sapley value is determined based on the duration and sapley value of each sub-period.

[0082] As explained above, calculating the target Shapley value involves factors such as low-altitude data, duration of effectiveness, and time decay rate, and the values ​​of these factors may change within the first time period. Therefore, to ensure the accuracy of the target Shapley value calculation, the first time period can be divided into multiple sub-time periods. For example, sub-time periods can be divided based on the update time of airspace openness priority and / or parameter adjustment time. Furthermore, for each sub-time period, the corresponding Shapley value is determined based on the low-altitude data, duration of effectiveness, and time decay rate corresponding to that sub-time period. Thus, the target Shapley value can be determined based on the duration and Shapley value corresponding to each sub-time period. For example, the target Shapley value can be obtained by weighting the Shapley values ​​based on each duration.

[0083] The above technical solution enables accurate determination of the target Shapley value.

[0084] Figure 2 This is a flowchart of another low-altitude economic reliable data processing method provided in this embodiment of the invention. This embodiment is based on the above-mentioned technical solutions and optimized. In this embodiment, optionally, the above-mentioned low-altitude economic reliable data processing method may further include: responding to an airspace openness priority update command, acquiring multiple candidate strategies related to the openness of low-altitude airspace and / or flight restrictions within low-altitude airspace; for each of the multiple candidate strategies, determining the posterior probability of the candidate strategy based on a second airspace openness correction factor and the prior probability and likelihood function of the candidate strategy, wherein the prior probability represents the historical success rate of the candidate strategy, the likelihood function represents the probability of observing the current environmental data when executing the candidate strategy, and the posterior probability represents the feasibility probability of the candidate strategy under the environmental data; updating the currently applied airspace openness priority according to each feasibility probability; and determining the permitted flight modes for each UAV in low-altitude airspace according to the airspace openness priority, so that each UAV can perform flight operations according to the corresponding flight mode. The explanations of terms that are the same as or corresponding to those in the above embodiments will not be repeated here.

[0085] See Figure 2 The method in this embodiment may specifically include the following steps:

[0086] S210. In response to an airspace openness priority update instruction for low-altitude airspace, acquire multiple candidate strategies related to the openness of low-altitude airspace and / or flight restrictions within low-altitude airspace.

[0087] Low-altitude airspace refers to the airspace that is within a preset distance range from the ground plane.

[0088] As explained above, low-altitude airspace can be divided into two or more regions, each with its own airspace opening priority. This priority indicates the tendency to open a particular region for drones to fly; a higher priority indicates a greater likelihood of opening the region for drones. Based on this, the airspace opening priorities corresponding to each region can form an airspace opening priority matrix.

[0089] The airspace openness priority update instruction can be understood as an instruction used to instruct the updating of the openness priority of each airspace, that is, an instruction used to instruct the updating of the airspace openness priority matrix. In this embodiment of the invention, optionally, the instruction can be triggered by a timed event (e.g., triggered when a sudden change in environment is detected, specifically, when the wind speed change is >30% / minute), or manually triggered, etc., which can be set according to actual needs and is not specifically limited here.

[0090] Openness status indicates the openness of various areas within low-altitude airspace, such as whether it is open, the time period for opening, and the priority of airspace opening. This is related to the actual situation and is not specifically limited here. Flight restrictions indicate the restrictions on drone flight in various areas of low-altitude airspace, such as at least one of flight speed restrictions, flight altitude restrictions, and flight path restrictions. This is related to the actual situation and is not specifically limited here.

[0091] Multiple candidate strategies are obtained. These candidate strategies may be related to the aforementioned openness and / or flight restrictions. For example, they may be maintaining the openness of a certain area, closing a certain area and setting its airspace openness priority to 0.1, or limiting the speed of a certain area to 10 m / h, etc. This depends on the actual situation and is not specifically limited here. In this embodiment of the invention, the candidate strategies may also be referred to as Bayesian strategies.

[0092] S220. For each candidate policy among multiple candidate policies, determine the posterior probability of the candidate policy based on the second spatial openness correction factor and the prior probability and likelihood function of the candidate policy.

[0093] Wherein, the prior probability represents the historical success rate of the candidate strategy, the likelihood function represents the probability of observing the current environmental data when executing the candidate strategy, and the posterior probability represents the feasibility assessment of the candidate strategy under the environmental data.

[0094] The second airspace openness correction factor is determined based on the effective duration of the airspace openness policy for the second time period and the corresponding time decay rate for the second time period. The airspace openness policy is an openness policy related to low-altitude airspace.

[0095] Among them, the second airspace openness correction factor The determination process and the first spatial openness correction factor The determination process is similar, with the main difference being that it involves the second time period corresponding to the airspace open priority update instruction.

[0096] Building upon this, and to better understand this step, a specific example is provided below. For instance, regarding the first... candidate strategies (i.e., candidate strategies) Its posterior probability can be determined by the following formula. :

[0097] ;

[0098] in, Represents the posterior probability, indicating the probability under the current environmental data. Next candidate strategy The probability of feasibility; To collect real-time (i.e., current) environmental data, such as weather risk levels, drone density, and airspace control signals; For the set of all candidate strategies; Let be the prior probability, and let represent the candidate policy. Historical success rate; Let be the likelihood function, representing the likelihood if the candidate policy is executed. Observed environmental data The likelihood of it happening; Candidate strategies Unnormalized valuation; This represents the second airspace openness correction factor.

[0099] Based on this, it should be noted that when When it is large, the exponent term While the overall probability increases, the score differences between candidate strategies are relatively compressed, resulting in a more dispersed posterior probability distribution. This, combined with subsequent airspace openness priority, outputs a dynamic priority that balances efficiency and safety. When it is small, the exponent term The overall decrease is significant, but the score differences between candidate strategies are amplified dramatically, and the posterior probability distribution is highly concentrated in [a specific area]. The highest candidate strategy is the one that subsequently outputs a strongly conservative priority for airspace openness.

[0100] In this embodiment of the invention, alternatively to the Bayesian probability update scheme described above, other update schemes may be used. For example, it may be a Markov decision process, i.e., updating candidate strategies based on state transition probabilities; it may be a neural network prediction model, such as predicting future conflict probabilities through a Long Short-Term Memory (LSTM) network and dynamically adjusting the airspace openness priority; or it may be fuzzy logic control, i.e., generating candidate strategies based on fuzzy rules (such as "high density + high risk → close"); and so on, without specific limitations.

[0101] S230. Update the airspace access priority for the current application based on all feasibility probabilities.

[0102] After obtaining the feasibility probabilities for each candidate strategy, the airspace access priority for the current application can be updated based on these probabilities to ensure that the airspace access priority of the current application is consistent with... and This ensures the accuracy of the current application's airspace access priority.

[0103] S240. For multiple drones operating collaboratively in low-altitude airspace, determine the permitted flight modes for each drone in low-altitude airspace based on airspace opening priority, so that each drone can carry out flight operations according to the corresponding flight mode.

[0104] Based on the priority of airspace opening, the permitted flight modes for each UAV in low-altitude airspace are determined. For example, for a certain UAV, the corresponding flight mode can represent the areas in which the UAV is allowed to fly in various regions of low-altitude airspace. Furthermore, it can also represent at least one of the altitude, speed, and path that the UAV is allowed to fly in that area. This can be set according to actual needs and is not specifically limited here.

[0105] In this way, each drone can carry out flight operations in low-altitude airspace according to its corresponding flight mode.

[0106] Based on this, optionally, using the airspace openness priority matrix as an example, each update of the airspace openness priority matrix can have a unique time marker, generating a new matrix version (V0, V1, ...). During the effective period of each matrix, a "container" corresponding to the matrix version is created, which can record the data volume, data precision, area coverage weight, airspace openness correction factor, and corresponding access policies of all drones within that matrix version. Moreover, because the data volume, data precision, area coverage weight, and airspace openness correction factor of drones will change with time or the flight trajectory of drones, even if the duration of a container version may be only a few minutes, due to the dynamic nature of these variables, the following table is used as an example to illustrate their calculated values:

[0107]

[0108] S250. In response to the Shapley value calculation instruction, for each of the multiple drones, read the low-altitude data corresponding to that drone from the blockchain, and determine the drone contribution value of that drone based on the low-altitude data.

[0109] The low-altitude data refers to the data generated during the first period of the drone's operation.

[0110] S260. Using the target Shapley formula, the alliance contribution value is determined based on the UAV contribution value and the first airspace openness correction factor, and the weighting coefficient is determined based on the first airspace openness correction factor and the alliance size. The target Shapley value of the UAV is determined based on the alliance contribution value and the weighting coefficient. Based on the target Shapley value corresponding to each UAV, the value is allocated to each UAV for all low-altitude data.

[0111] The first airspace openness correction factor is determined based on the effective duration of the airspace openness policy for the first time period and the corresponding time decay rate for the first time period.

[0112] The technical solution of this invention combines a second airspace openness correction factor to obtain the feasibility probability of each candidate strategy, which is related to the timeliness of the airspace openness policy. Then, the airspace openness priority of the current application is updated based on each feasibility probability, thereby ensuring that the airspace openness priority is closely related to the timeliness, and thus ensuring the accurate flight of the UAV.

[0113] An optional technical solution involves updating the airspace access priority for the current application based on all feasibility probabilities, including:

[0114] Obtain a pre-constructed game tree, wherein the game tree includes at least a root node, at least two first intermediate nodes connected to the root node to represent the corresponding candidate strategies, second intermediate nodes connected to each of the first intermediate nodes respectively, at least two third intermediate nodes connected to the second intermediate nodes to represent the corresponding candidate strategies, and leaf nodes for outputting the spatial openness priority.

[0115] All feasibility probabilities, environmental data, and the current application's airspace openness priority are input into the root node. The root node then uses a deep reinforcement learning model to evaluate the value of candidate strategies corresponding to each first intermediate node based on the input data, and selects and executes one of the candidate strategies.

[0116] The environmental data and the spatial openness priority obtained after executing the corresponding candidate strategy are input into the second intermediate node. The second intermediate node uses a deep reinforcement learning model to evaluate the value of the candidate strategies corresponding to each third intermediate node based on the input data, so as to select a candidate strategy and execute it to continue the transition in the game tree until the leaf node.

[0117] The airspace access priority is updated based on the output of the leaf nodes.

[0118] The game tree is a tree-like data structure with three core elements: nodes, edges / branches, and hierarchical structure. These will be explained in detail below:

[0119] A node represents a decision point or state point. Each node corresponds to a specific moment in the decision-making process or a specific system state. In this technical solution, the system state may include a probabilistic assessment (i.e., posterior probability) of the feasibility of the Bayesian strategy based on spatiotemporal constraint parameters. The spatiotemporal constraint parameters may include the current airspace state, real-time weather data, UAV density, safe distance warning value, and wind direction, etc. The posterior probability in this technical solution can be used only to initialize the root node state of the game tree. Optionally, when the posterior probability distribution is flat, a probability of 0.05 (e.g., < 0.05) can be calculated for all actions or pruning abnormally small probabilities. The values ​​(i.e., the value assessment results) are compared, and when the posterior probability distribution is very sharp, the action with the highest probability can be selected for subsequent branching. Value calculation. The above actions can be understood as candidate strategies.

[0120] Edges / branches represent possible decision actions. A branch originating from a node represents the specific operation that can be selected in the state of that node. In this technical solution, branches include regional operations (such as opening region A or closing region B), global policies (such as limiting speed across the entire region), and airspace opening priority adjustments (such as increasing the airspace opening priority of region A and decreasing the airspace opening priority of region B), etc. These can be set according to actual needs and are not specifically limited here.

[0121] The hierarchical structure of the game tree includes a root node, internal nodes, and leaf nodes. The root node is the starting point of the game tree, representing the initial decision state. In this technical solution, for example, the starting point can be an initial state of fully open airspace, a received real-time weather risk upgrade to level 5, and the obtained posterior probability. Internal nodes represent intermediate states in the decision-making process, and each internal node has branches linking to other internal nodes. Leaf nodes represent the terminal nodes of the game tree, indicating that a complete decision path has been executed and no further action selection is needed. In this technical solution, the output of the leaf nodes is the final airspace openness priority matrix, which is the final configuration obtained by executing a series of actions from the root node to the leaf nodes, that is, modifying the airspace openness priority matrix step by step.

[0122] In this technical solution, a Deep Reinforcement Learning (DRL) model can be used to select actions within a game tree. Specifically, the DRL model is generally a neural network structure. It learns the growth value of historical airspace data and offline learning policy paths, enabling it to efficiently search the game tree during the inference phase, calculate the value of each action, and dynamically generate an optimal airspace openness priority matrix adapted to current spatiotemporal changes. The DRL model supports periodic offline iterative updates to improve policy accuracy. The input data for the DRL model may include, but is not limited to: the currently applied airspace openness priority matrix, airspace openness correction factors, posterior probabilities (root node only), real-time meteorological data, drone density, airspace control status, and environmental safety thresholds. The input data can be uniformly encoded into a fixed-dimensional tensor through a preprocessing module, and a dynamic masking mechanism is supported to adapt to different data scenarios. Furthermore, the DRL model can be extended to other dynamic parameters, such as emergency alarms and temporary no-fly orders. If some input data is unavailable, alternative inputs can be generated through probabilistic interpolation. In addition, when the DRL model selects an action to transfer to the next internal node, the internal node inherits the updated airspace development priority matrix, real-time environmental data, and airspace openness correction factor, but no longer inherits the posterior probability.

[0123] Next, we will explain the collaborative working relationship between the DRL model and the game tree. Specifically, the DRL model perceives state information at the current node of the game tree. The DRL model uses its trained value function to evaluate the potential value of each action in that state. This represents the expected action to be performed. The total reward that can be obtained afterward. Assuming the action... To close high-risk area A, the DRL model selects an action. Then, perform the action. If the system state is modified (for example, setting the priority of high-risk zone A to 0.1), then the corresponding actions in the game tree can be followed. The branch moves to the next internal node. Upon reaching that internal node, the value function can continue to evaluate the next action under the new state information. The value is used to select the next action, increasing or decreasing its airspace openness priority by a fixed step size. Then, the above steps are repeated on the new internal node until the leaf node is reached, and the optimal airspace openness priority matrix is ​​output.

[0124] Based on this, to better understand the above technical solution, the following is an exemplary illustration with specific examples. For example, see [link to example]. Figure 3 Taking urban drones as an example, suppose there is a high-risk area A (such as a high-rise area in the city center), a high-risk area B (such as a cross-river bridge area), an adjacent area C (such as a ring road network), and a safe area D (such as a suburban logistics hub). Their initial airspace opening priorities are assumed to be 0.8, 0.8, 0.7, and 0.9, respectively. These initial airspace opening priorities can be dynamically generated based on their historical risk levels and adjacency relationships.

[0125] Assume there are three processing methods for priority, with a threshold range of [0, 1]: The first processing method is to directly set the absolute value. For example, for a close-type instruction, the priority can be directly set to 0.1; The second and third processing methods are to increase or decrease the priority by a step size. Here, the step size for high-risk adjacent areas is preset to 0.3, and the step size for ordinary areas is 0.2.

[0126] Furthermore, suppose that the set of feasibility probabilities (i.e., posterior probabilities) output by Bayes' theorem is:

[0127] ;

[0128] Suppose the current scenario is a sudden downpour. This set of feasibility probabilities will be used as the initial probabilities of the game tree. It should be noted that the initial probabilities will not participate in the value function calculation, but only serve as a directional guide. This can reduce the search dimensionality of the DRL model. Specifically, by using feasibility probabilities, the DRL model does not need to evaluate every action, but can focus on high-probability policy branches first, thereby improving the accuracy of action prediction.

[0129] exist Figure 3 In the diagram, the first row of boxes represents the root node; the four boxes in the second row represent the first intermediate nodes described above, and the actions within them are the candidate policies. Based on this, the root node uses the value function in the DRL model to evaluate the value of each of these four actions, obtaining... (Action 1) = 1.8 (Action 2) = 1.6 (Action 3) = 0.4 and (Action 4) = -0.9, because of Action 1 The value is the largest, so action 1 is selected and executed, which leads to the third row. The boxes in the third row represent the second intermediate node described above. Furthermore, the three boxes in the fourth row represent the third intermediate node described above. The second intermediate node uses the value function in the DRL model to evaluate the value of these three actions, obtaining... (Action 1) = 1.5 (Action 2) = 1.7 and (Action 3) = 1.3.

[0130] (Action 1) = 1.8 (Action 2) = 1.6 (Action 3) = 0.4 and (Action 4) = -0.9, because of Action 2 The value is the largest, so action 2 is selected and executed, which leads to the leaf node (the box in the fifth row of the diagram), and outputs the final spatial open priority matrix A=0.1, B=0.8, C=0.4 and D=0.9.

[0131] The above technical solution, by combining game trees and DRL models, achieves accurate updates of airspace openness priority.

[0132] Based on this, optionally, all feasibility probabilities, deep reinforcement learning models, and environmental data are stored on the blockchain. Airspace opening priorities are determined by retrieving all feasibility probabilities, deep reinforcement learning models, and environmental data from the blockchain. Then, based on the airspace opening priorities, the permitted flight modes for each drone in low-altitude airspace are determined, including:

[0133] Store airspace access priority on the blockchain;

[0134] By using smart contracts stored on the blockchain, the permitted flight modes for each drone in low-altitude airspace are determined based on the airspace openness priority stored on the blockchain.

[0135] The aforementioned technical solution stores all relevant data used to determine airspace opening priorities on a blockchain. This allows for the determination of airspace opening priorities by retrieving this data from the blockchain, ensuring the reliability of the determined airspace opening priorities. Furthermore, storing the determined airspace opening priorities on the blockchain allows for the use of smart contracts stored on the blockchain to determine flight modes based on these priorities. This application of blockchain ensures the reliability of the determined flight modes.

[0136] Alternatively, the blockchain can include consortium blockchains and Directed Acyclic Graph (DAG) chains. Low-altitude data, all feasibility probabilities, environmental data, and airspace openness priorities are all stored on the DAG chain, while the deep reinforcement learning model is stored on the consortium blockchain. In other words, dynamic data can be stored on the DAG chain and static data can be stored on the consortium blockchain, thereby achieving the separation of structured data and time-series data, thus solving the problem of execution latency and throughput bottlenecks on the blockchain.

[0137] Building upon this, to better understand the aforementioned blockchain-related technical solutions, the following is an exemplary illustration with specific examples. For instance, a dual-chain blockchain design may include the following:

[0138] 1. Consortium blockchain: Stores static data

[0139] Stored content: airspace openness policies and smart contract logic (such as conflict handling rules and revenue distribution algorithms).

[0140] Technical features: It utilizes the Practical Byzantine Fault Tolerance (PBFT) mechanism, which works by having nodes reach consensus through multiple rounds of voting and tolerating less than 1 / 3 of malicious nodes. It is suitable for scenarios with low-frequency updates (such as airspace open policies being updated once a day) and strong consistency.

[0141] Data structure: Traditional blockchain table, fixed block size, 10-minute block interval, to ensure data immutability.

[0142] 2. DAG chain: Stores dynamic data

[0143] Stored content: drone real-time location, weather sensor data, and real-time PPC Score and Shapley values.

[0144] Technical characteristics: Tangle (a distributed ledger structure based on DAG) is based on the principle that a new transaction needs to verify the previous two transactions. There are no miners or blocks, which naturally supports high concurrency and is suitable for scenarios that require high-frequency writes and allow eventual consistency.

[0145] Data structure: Transaction units are directly linked into a graph, transaction confirmation latency is less than 1 second, and throughput is only limited by network bandwidth.

[0146] 3. Smart Contract Execution

[0147] Consortium blockchain contracts: manage voting on rule changes and Shapley parameter adjustments. For example, when the weights in the PPC Score need to be changed, a multi-signature vote can be initiated.

[0148] DAG chain contracts: handle real-time events (such as conflict avoidance and profit distribution).

[0149] Figure 4 This is a flowchart of another low-altitude economic reliable data processing method provided in this embodiment of the invention. This embodiment is based on the above-mentioned technical solutions and optimized. In this embodiment, optionally, the contribution value of the UAV is also determined according to a first weight, a second weight, and a third weight. The above method may also include: responding to a closed-loop feedback command, determining the current airspace utilization rate of the low-altitude airspace, and determining the Gini coefficient according to the target Shapley value corresponding to each UAV; determining a comprehensive Gini coefficient according to the airspace utilization rate and the Gini coefficient; if it is determined that parameter adjustment is required according to the comprehensive Gini coefficient, determining the target parameter to be adjusted according to the comprehensive Gini coefficient, adjusting and updating the target parameter, wherein the target parameter includes at least one of the time decay rate, the first weight, the second weight, and the third weight. The explanations of terms that are the same as or corresponding to those in the above embodiments will not be repeated here.

[0150] See Figure 4 The method in this embodiment may specifically include the following steps:

[0151] S310. In response to the Shapley value calculation instruction, for each of the multiple drones operating collaboratively in low-altitude airspace, read the low-altitude data corresponding to the drone from the blockchain;

[0152] Low-altitude airspace refers to the airspace within a preset distance from the ground plane. Low-altitude data is the data generated during the first period of the UAV's operation. Low-altitude data includes data volume, data accuracy, and regional coverage weight. Data volume represents the number of flight trajectory points of the UAV per unit time. Data accuracy represents the measurement accuracy of the sensors inside the UAV. Regional coverage weight represents the spatial coverage value of the UAV in the low-altitude airspace.

[0153] S320. Obtain the first weight corresponding to the data volume, the second weight corresponding to the data precision, and the third weight corresponding to the area coverage weight, and determine the drone contribution value of the drone based on the data volume and the first weight, the data precision and the second weight, and the area coverage weight and the third weight.

[0154] S330. Using the target Shapley formula, the alliance contribution value is determined based on the UAV contribution value and the first airspace openness correction factor, and the weighting coefficient is determined based on the first airspace openness correction factor and the alliance size. The target Shapley value of the UAV is determined based on the alliance contribution value and the weighting coefficient. Based on the target Shapley value corresponding to each UAV, the value is allocated to each UAV for all low-altitude data.

[0155] The first airspace openness correction factor is determined based on the effective duration of the airspace openness policy for the first time period and the time decay rate corresponding to the first time period. The airspace openness policy is an openness policy related to low-altitude airspace.

[0156] S340. In response to closed-loop feedback commands, determine the current airspace utilization rate of the low-altitude airspace, and determine the Gini coefficient based on the target Shapley value corresponding to each UAV.

[0157] Here, the closed-loop feedback command can be understood as a command used to instruct closed-loop feedback; more specifically, it can be understood as a command used to calculate the comprehensive Gini coefficient. An assessment is conducted to determine if parameter tuning is needed, and if so, tuning is performed to achieve closed-loop feedback. In this embodiment of the invention, optionally, this instruction can be triggered periodically or manually, which can be set according to actual needs and is not specifically limited here. In response to this instruction, the airspace utilization rate is determined. and Gini coefficient The specific determination process is as follows:

[0158] As explained above, low-altitude airspace can be divided into two or more regions, and each region can be further divided into two or more grids. This means that low-altitude airspace can be divided into multiple grids. Based on this, the number of grids currently open in the low-altitude airspace... and the number of currently occupied grid cells. This can determine the current airspace utilization rate of low-altitude airspace. This reflects the efficiency of airspace resource utilization. For example, it can be determined by the following formula. :

[0159] .

[0160] Furthermore, the Gini coefficient is determined based on the target Shapley value corresponding to each drone at present. Its allocation fairness can be quantified. For example, it can be determined by the following formula. :

[0161] ;

[0162] in, The total number of all participating drones. Indicates drone The current target Shapley value, Indicates the first Taiwanese drones (i.e., unmanned aerial vehicles) The current target Shapley value.

[0163] S350. Determine the comprehensive Gini coefficient based on airspace utilization and the Gini coefficient.

[0164] Among them, according to and The comprehensive Gini coefficient can be determined. This allows for the simultaneous quantification of allocation fairness and airspace resource utilization efficiency. For example, a weighted calculation can be performed on both to obtain... Furthermore, additional parameters can be introduced based on the weighted calculation to obtain... Here is an example of... Calculation example:

[0165] ;

[0166] in, Efficiency penalty weights are used to adjust for efficiency losses. The intensity of contribution; The lower limit threshold for the Gini coefficient ensures absolute fairness in allocation (i.e., Even when it is approximately equal to 0, the loss of efficiency can still be perceived.

[0167] Regarding the examples given above It has the following characteristics:

[0168] 1. Fairness-driven: When airspace utilization U approaches 1, Degenerates to a normal Gini coefficient ;

[0169] 2. Amplified efficiency loss: When airspace utilization rate When it decreases, the penalty item Increase, and when The amplification effect is stronger at higher values;

[0170] 3. Inefficient scene protection: Through Avoid ignoring system anomalies when allocation is fair but inefficient (e.g., G = 0.05, U = 0.6).

[0171] S360. If it is determined that parameter adjustment is required based on the comprehensive Gini coefficient, the target parameter to be adjusted is determined based on the comprehensive Gini coefficient, and the target parameter is adjusted and updated.

[0172] The target parameters include at least one of the following: time decay rate, first weight, second weight, and third weight.

[0173] Among them, in obtaining the comprehensive Gini coefficient Afterwards, it can be determined whether parameter tuning is needed, such as whether the time decay rate described above needs to be adjusted. First weight Second weight and the third weight Adjustments may be made as needed. In this embodiment of the invention, optionally, adjustments may be made according to… The parameter adjustment is determined based on whether the value is greater than the first preset threshold.

[0174] Furthermore, if it is determined that parameter adjustment is necessary, then it can be done according to... Determine the target parameter to be adjusted; this target parameter can be... , , and At least one of them. It should be noted that the first weight... The significance of adjustments is limited, and changes in data volume may introduce more noise. The adjustment can be expressed as suppressing sensor errors caused by environmental interference; The adjustment can be described as guiding drones towards lower airspace utilization. And / or fly over high-value areas.

[0175] Then, the target parameters can be adjusted and updated so that the latest target parameters can be applied to subsequent target Shapley value calculations and airspace openness priority updates. Based on this, here is an example of a hierarchical response for parameter tuning:

[0176] exist >When the first preset threshold is reached, and parameter tuning is determined to be required,

[0177] If the first preset threshold < If the value is less than or equal to the second preset threshold, a slight adjustment can be made. As a target parameter, for example, ,in, Before the adjustment , It is the adjusted version , It can be a positive number.

[0178] if >The second preset threshold, at which point a heavy adjustment can be made, can be as well as and / or As a target parameter. For example, , It can be a positive number. And, if and The last adjustment target was The target of this adjustment is : ;like and The last adjustment target was The target of this adjustment is : .in, Positive and negative values ​​can be determined based on the most recently adjusted airspace utilization rate. The change is determined, for example, if ,but If positive, otherwise It is a negative number.

[0179] Based on this, optionally, to ensure that the parameter adjustments are within a reasonable range, the following constraints can also be set:

[0180] ;

[0181] , ,and = 1.

[0182] Alternatively, in conjunction with the above regarding In addition to adjusting the above examples, , and In addition, the efficiency penalty weight can be adjusted. and / or the lower limit threshold of the Gini coefficient For example, it can be adjusted in the following way. :

[0183] ;

[0184] in, Indicates the utilization rate of the target airspace. This represents the average airspace utilization rate over the past X hours, assuming... , , and = 0.85, which is used when there is persistent inefficiency ( When < 0.8), It is 0.45.

[0185] As another example, it can be adjusted in the following way :

[0186] ;

[0187] in, This is a record of the Gini coefficient over the past Y days. Based on this, optionally... 0.7, 0.8, or 0.9 are acceptable values.

[0188] The technical solution of this invention determines a comprehensive Gini coefficient that can simultaneously quantify the fairness of allocation and the efficiency of airspace resource use by using airspace utilization rate and Gini coefficient. Then, parameters can be adjusted based on the comprehensive Gini coefficient, thereby realizing closed-loop feedback and timely adjustment of airspace opening priority and value allocation.

[0189] Based on this, to better understand the closed-loop feedback process described in the embodiments of the present invention, the following is an exemplary explanation with specific examples. For example, assume that the airspace openness priority matrix (hereinafter referred to as the matrix) is updated every 5 minutes or when a sudden environmental change is detected, and the Shapley value is calculated every 10 minutes. Let's assume the first preset threshold is 0.25 and the second preset threshold is 0.3.

[0190] Based on this, here is a 30-minute timeline example, as follows:

[0191] 10:00:00 - System Startup

[0192] Environmental conditions: Sunny, wind speed 5 m / s

[0193] Parameter settings: = 0.1, =0.3, =0.5, =0.2

[0194] Matrix version: V0

[0195] Airspace openness correction factor: = 1.0

[0196] Assuming the drone begins its mission, data is recorded in container V0.

[0197] 10:05:00 - Regularly update the matrix

[0198] Generate a new matrix V1

[0199] Operation: Close container V0 and create container V1

[0200] = 0.393

[0201] Drone Response: Trajectory Adjusted According to New Strategy

[0202] 10:07:00 - Sudden weather change (torrential rain)

[0203] Environmental monitoring: Wind speed increased by 15 m / s, rainfall increased by 30 mm / h.

[0204] System response: Immediately generate matrix V2, close container V1 and create container V2.

[0205] = 0.528

[0206] Drone response: High-risk areas closed and low-risk areas speed limited.

[0207] 10:09:59 - Shapley1 calculation cycle ends

[0208] Lock data

[0209] V0 container: 10:00-10:05 (5 minutes)

[0210] V1 container: 10:05-10:07:30 (2.5 minutes)

[0211] V2 container: 10:07:30-10:10:00 (2.5 minutes)

[0212] 10:00:00 - Shapley1 calculation

[0213] 1. Calculate the Shapley value for each container independently.

[0214] V0: φ_V0 (θ=1.0), V1: φ_V1 (θ=0.393), V2: φ_V2 (θ=0.528)

[0215] 2. Time-weighted aggregation: Perform weighted aggregation on φ_V0, φ_V1, and φ_V2.

[0216] 3. IGI Calculation: = 0.18, = 0.85, = 0.18 + 0.3×(1-0.85)×max(0.18,0.1)= 0.188

[0217] decision making: <0.25 → No parameter adjustment

[0218] 10:00:01 - Regularly update the matrix

[0219] Generating matrix V3

[0220] Operation: Close container V2 and create container V3.

[0221] = 0.632

[0222] 10:05:00 - Regularly update the matrix

[0223] Generating matrix V4

[0224] Operation: Close the V3 container and create the V4 container.

[0225] = 0.777

[0226] 10:17:00 - Weather worsens (wind speed 10m / s)

[0227] Environmental monitoring: Wind speed increased to 20 m / s, rainfall 50 mm / h

[0228] System response: Immediately generate matrix V5, close container V4 and create container V5.

[0229] = 0.818

[0230] Drone response: 80% airspace closed, only critical missions continue

[0231] 10:19:59 - Shapley2 calculation cycle ends

[0232] V3 container: 10:10-10:15 (5 minutes)

[0233] V4 container: 10:15-10:17:00 (2 minutes)

[0234] V5 container: 10:17:00-10:20:00 (3 minutes)

[0235] 10:20:00 - Shapley2 calculation

[0236] 1. Calculate the Shapley value for each container independently.

[0237] 2. Time-weighted aggregation

[0238] 3. IGI calculation, = 0.35, = 0.55, = 0.35 + 0.3×(1-0.55)×max(0.35,0.1)= 0.398

[0239] decision making: >0.25 → Parameter tuning (intensive tuning)

[0240] = 0.1 × 1.15 = 0.115, =0.3, =0.4, =0.3, where, Increase by 0.1

[0241] 10:20:01 - Update the matrix periodically (using new parameters)

[0242] Generating matrix V6

[0243] Operation: Close the V5 container and create the V6 container.

[0244] = 0.896

[0245] 10:25:00 - Weather improves (rain stops)

[0246] Environmental monitoring: Wind speed dropped to 8 m / s, rainfall stopped.

[0247] System response: Generate matrix V7, close container V6 and create container V7.

[0248] = 0.942

[0249] Drone Response: Gradually Reopening Airspace and Resuming Regular Missions

[0250] 10:29:59 - Shapley3 calculation cycle ends

[0251] 10:30:00 - Shapley3 calculation

[0252] 1. Calculate the Shapley value for each container independently.

[0253] 2. Time-weighted aggregation

[0254] 3. IGI Calculation: = 0.22, = 0.78, = 0.35 + 0.3×(1-0.55)×max(0.35,0.1)= 0.255

[0255] decision making: >0.25 → Adjust parameters (minor adjustment)

[0256] = 0.115 × 1.1 = 0.1265

[0257] Based on this, here's why the parameter tuning results from the current cycle can be applied to the next cycle:

[0258] 1. Optimized parameters can improve the system's basic capabilities: Optimize and enhance the sensitivity of the strategy to timeliness. , and Optimize and improve the system's ability to identify high-quality data;

[0259] 2. These capabilities have universal applicability across environments: optimized for heavy rain. Prioritization strategies are equally effective on sunny days. The optimization is applicable to various policy environments;

[0260] 3. Dual-track response mechanism: Parameter optimization (10-minute level) enables gradual improvement of the system, while matrix updates can respond to sudden environmental changes in real time.

[0261] In addition, to better understand the various technical solutions described above, an optional example is provided below for illustration. The specific implementation process is as follows:

[0262] 1. Store airspace opening policies (such as a 150-meter height limit during heavy rain), smart contract rules (access principles / logic, rules for determining whether a drone can enter a certain area), DRL models, and parameters of all models on the consortium blockchain; store dynamic data such as weather station and real-time wind speed data on the DAG chain, which is only stored and not executed.

[0263] 2. Calculate the airspace openness correction factor. (Module 1: Construction of Dynamic Game Models)

[0264] 3. Update using Bayesian strategy and Collaboration involves calculating the corresponding posterior probability distribution based on real-time environmental data, which serves as the basis for initializing the root node state of the game tree (Module 1: Dynamic Game Model Construction).

[0265] 4. Based on the posterior probability distribution, the optimal policy path is searched through the DRL model to generate the final airspace openness priority matrix (e.g., high-risk area priority 0.1, adjacent area priority 0.7) and store it on the DAG chain (Module 1: Dynamic Game Model Construction).

[0266] 5. The smart contract determines whether a drone meets the conditions for entering the airspace based on the rules stored in the consortium blockchain, and then controls airspace access in real time with reference to the airspace opening priority matrix stored in the DAG chain: for example, accepting or rejecting the drone's airspace use application, and imposing flight restrictions on drones that are allowed to enter (Module 3: Dual Blockchain Design).

[0267] 6. Calculate the drone contribution value corresponding to each drone using the PPC Score formula and store it on the DAG chain (Module 2: Shapley - PPC Allocation Algorithm).

[0268] 7. Automatically simulate combinations of different participants (i.e., drones) for collaborative operation. Calculate the alliance contribution value for each alliance; for each participant, calculate the difference in contribution before and after joining the alliance, i.e., the marginal contribution value; consider all possible alliance combinations, and use the improved objective Shapley formula to weighted average the marginal contribution value, and finally output the value allocation weight corresponding to each participant and store it on the DAG chain (Module 2: Shapley - PPC Allocation Algorithm).

[0269] 8. Input Indicator: Based on the Gini coefficient and airspace utilization Determine the comprehensive Gini coefficient And adjust the parameters accordingly;

[0270] 9. The adjusted parameters and the game strategy model optimized based on closed-loop feedback (such as DRL weights and Bayesian prior probabilities) will be used to generate the spatial openness priority matrix for the next cycle. The new spatial openness priority matrix again influences the effective participants and PPC parameters through admission control, thereby affecting the value allocation weights, and is expected to improve... and This can form a complete closed loop of "strategy formulation (game) -> access execution -> contribution quantification -> benefit distribution -> effect evaluation -> strategy optimization" (Module 4: technology collaboration and closed loop feedback).

[0271] Furthermore, as described above, embodiments of the present invention may also involve module five: a trusted data space module, which connects the above four modules in series from the perspective of trusted data space. An example of module five is given below in conjunction with the table below:

[0272]

[0273] Based on this, the workflow and multi-module collaboration are as follows:

[0274] (1) Data space access and initialization

[0275] 1. Participant registration identity (Digital credential writing module three - consortium blockchain);

[0276] 2. The data provider publishes the resource domain attribute ("Yangtze River Delta Meteorological Zone", metadata hash is stored in Module 3 - DAG chain).

[0277] (2) Dynamic policy generation and access control

[0278] The data requester initiates an access request (e.g., "Get real-time weather in area A");

[0279] Map the application to a "grid access request", combined with the environment status input module one;

[0280] Module 1 outputs "data access policy" (e.g., "High-resolution UAVs can access de-identified data");

[0281] Module 3 is invoked to determine the smart contract execution strategy, and the authorization results and access logs are written to the DAG chain.

[0282] (3) Data contribution evidence storage and value quantification

[0283] The data provider generates data streams during the service process (such as drone trajectory transmission).

[0284] Real-time extraction of contribution dimensions: Contribution triples (Q, A, W) are stored in real-time to the module 3-DAG chain.

[0285] (4) Value distribution and profit settlement

[0286] When the cycle is triggered, the contribution records of the evidence stored on the chain are summarized and input into Module 2;

[0287] Module 2 executes the Shapley-PPC algorithm and outputs the value reward weight for each participant;

[0288] Data points or settlement instructions are generated based on value and return weights, and the results are written to Module 3 - Consortium Chain.

[0289] (5) Governance closed loop and parameter optimization

[0290] Calculate the spatial performance metrics G and U of the data space:

[0291] Indicator Input Module 4 calculates IGI;

[0292] If the IGI exceeds the threshold (e.g., >0.25), the trigger parameters of module four are optimized (e.g., increased). );

[0293] The new parameters are synchronized to Module 1 (strategy generation) and Module 2 (contribution calculation).

[0294] Figure 5 This is a structural block diagram of a low-altitude economic trusted data processing apparatus provided in an embodiment of the present invention. This apparatus is used to execute the low-altitude economic trusted data processing method provided in any of the above embodiments. This apparatus and the low-altitude economic trusted data processing methods of the above embodiments belong to the same inventive concept. Details not described in detail in the embodiments of the low-altitude economic trusted data processing apparatus can be found in the embodiments of the low-altitude economic trusted data processing method described above. See also... Figure 5 Specifically, the device may include: a drone contribution value determination module 410 and a value allocation module 420. Among them,

[0295] The drone contribution value determination module 410 is used to respond to the Shapley value calculation instruction, for each of the multiple drones working collaboratively in low-altitude airspace, read the low-altitude data corresponding to the drone from the blockchain, and determine the drone contribution value of the drone based on the low-altitude data. The low-altitude airspace is the airspace that is within a preset distance range from the ground plane, and the low-altitude data is the data generated in the first time period during the operation of the drone.

[0296] The value allocation module 420 can be used to determine the alliance contribution value based on the UAV contribution value and the first airspace openness correction factor using the target Shapley formula, and to determine the weight coefficient based on the first airspace openness correction factor and the alliance size. It can also determine the target Shapley value of the UAV based on the alliance contribution value and the weight coefficient, so as to allocate value to each UAV for all low-altitude data according to the target Shapley value corresponding to each UAV. The first airspace openness correction factor is determined based on the effective duration of the airspace openness policy for the first time period and the time decay rate corresponding to the first time period. The airspace openness policy is an openness policy related to low-altitude airspace.

[0297] Optionally, the low-altitude data includes data volume, data accuracy, and regional coverage weight. Data volume represents the number of flight trajectory points of the UAV per unit time, data accuracy represents the measurement accuracy of the sensors inside the UAV, and regional coverage weight represents the spatial coverage value of the UAV to the low-altitude airspace. The UAV contribution value determination module 410 may include:

[0298] The drone contribution value determination unit is used to obtain the first weight corresponding to the data volume, the second weight corresponding to the data accuracy, and the third weight corresponding to the area coverage weight, and determine the drone contribution value of the drone based on the data volume and the first weight, the data accuracy and the second weight, and the area coverage weight and the third weight.

[0299] Optionally, the first time period includes multiple sub-time periods, and a corresponding Shapley value is determined for each sub-time period. The Shapley value is determined based on the low-altitude data, the duration of effectiveness, and the time decay rate corresponding to the sub-time period.

[0300] The target sapley value is determined based on the duration and sapley value of each sub-period.

[0301] Optionally, the aforementioned low-altitude economic reliable data processing device may further include:

[0302] The candidate strategy acquisition module is used to acquire multiple candidate strategies related to the opening status of low-altitude airspace and / or flight restrictions within low-altitude airspace in response to the airspace opening priority update command.

[0303] The posterior probability determination module can be used to determine the posterior probability of each candidate strategy among multiple candidate strategies based on the second spatial openness correction factor and the prior probability and likelihood function of the candidate strategy. Here, the prior probability represents the historical success rate of the candidate strategy, the likelihood function represents the probability of observing the current environmental data when executing the candidate strategy, and the posterior probability represents the feasibility probability of the candidate strategy under the environmental data.

[0304] The airspace access priority update module can be used to update the airspace access priority of the current application based on all feasibility probabilities.

[0305] The flight operation module can be used to determine the permitted flight modes for each UAV in low-altitude airspace based on airspace opening priority, so that each UAV can carry out flight operations according to the corresponding flight mode.

[0306] Based on this, the optional airspace openness priority update module is specifically used for:

[0307] Obtain a pre-constructed game tree, wherein the game tree includes at least a root node, at least two first intermediate nodes connected to the root node to represent the corresponding candidate strategies, second intermediate nodes connected to each of the first intermediate nodes respectively, at least two third intermediate nodes connected to the second intermediate nodes to represent the corresponding candidate strategies, and leaf nodes for outputting the spatial openness priority.

[0308] All feasibility probabilities, environmental data, and the current application's airspace openness priority are input into the root node. The root node then uses a deep reinforcement learning model to evaluate the value of candidate strategies corresponding to each first intermediate node based on the input data, and selects and executes one of the candidate strategies.

[0309] The environmental data and the spatial openness priority obtained after executing the corresponding candidate strategy are input into the second intermediate node. The second intermediate node uses a deep reinforcement learning model to evaluate the value of the candidate strategies corresponding to each third intermediate node based on the input data, so as to select a candidate strategy and execute it to continue the transition in the game tree until the leaf node.

[0310] The airspace access priority is updated based on the output of the leaf nodes.

[0311] Based on this, optionally, all feasibility probabilities, deep reinforcement learning models, and environmental data can be stored on the blockchain. Airspace opening priorities can be determined by reading all feasibility probabilities, deep reinforcement learning models, and environmental data from the blockchain. Therefore, the flight operation module may include:

[0312] Airspace open priority storage unit, used to store airspace open priority on the blockchain;

[0313] The flight mode determination unit is used to determine the permitted flight mode for each drone in low-altitude airspace based on the airspace openness priority stored on the blockchain using smart contracts.

[0314] Based on this, optionally, the blockchain includes consortium blockchains and directed acyclic graph blockchains. Low-altitude data, all feasibility probabilities, environmental data, and airspace openness priorities are all stored on the directed acyclic graph blockchain, while deep reinforcement learning models are stored on the consortium blockchain.

[0315] Optionally, based on any of the above devices, the UAV contribution value is further determined according to a first weight, a second weight, and a third weight. The aforementioned airspace opening priority update module also includes:

[0316] The Gini coefficient determination module is used to determine the current airspace utilization rate of the low-altitude airspace in response to closed-loop feedback commands, and to determine the Gini coefficient based on the target Shapley value corresponding to each UAV at the current time.

[0317] The comprehensive Gini coefficient determination module is used to determine the comprehensive Gini coefficient based on airspace utilization and the Gini coefficient.

[0318] The target parameter update module is used to determine the target parameters to be adjusted based on the comprehensive Gini coefficient when it is determined that parameter adjustment is required based on the comprehensive Gini coefficient, and to adjust and update the target parameters. The target parameters include at least one of time decay rate, first weight, second weight and third weight.

[0319] Based on this, optionally, when the comprehensive Gini coefficient is greater than a first preset threshold, it is determined that parameter tuning is required. The target parameter update module may include:

[0320] The first target parameter determination unit can be used to determine the time decay rate as the target parameter to be adjusted when the comprehensive Gini coefficient is greater than the first preset threshold and less than or equal to the second preset threshold.

[0321] The second target parameter determination unit can be used to determine the time decay rate and the second and / or third weights as target parameters when the comprehensive Gini coefficient is greater than the second preset threshold.

[0322] The low-altitude economic trusted data processing device provided in this embodiment of the invention, through a UAV contribution value determination module, responds to the Shapley value calculation instruction and reads the low-altitude data corresponding to each UAV among multiple UAVs cooperating in low-altitude airspace from the blockchain for each UAV. Then, it determines the UAV contribution value of the UAV based on the low-altitude data to reflect the dynamic contribution value of an individual UAV. Further, through a value allocation module, using an improved target Shapley formula, it determines the alliance contribution value based on the UAV contribution value and a first airspace openness correction factor to respond to environmental changes. It also determines the weight coefficient based on the first airspace openness correction factor and the alliance size to obtain a weight coefficient related to the timeliness (i.e., dynamic) of the airspace openness policy. Then, it can determine the target Shapley value of the UAV based on the alliance contribution value and the weight coefficient. Thus, it can allocate value for each UAV for all low-altitude data based on the target Shapley value corresponding to each UAV. The first airspace openness correction factor can be determined based on the effective duration of the airspace openness policy for the first time period and the time decay rate corresponding to the first time period. Compared to using static value allocation weights for value allocation, the above-mentioned device and technical solution introduce a first airspace openness correction factor to characterize the timeliness of airspace openness policies. Based on this, when calculating the target Shapley value (i.e., value allocation weight), the alliance contribution value is determined by introducing the UAV contribution value and the first airspace openness correction factor to respond to environmental changes. Furthermore, the first airspace openness correction factor is introduced to determine dynamic weight coefficients to correlate with the timeliness of airspace openness policies. These technical features work together to effectively ensure fairness in value allocation for low-altitude data.

[0323] The low-altitude economic reliable data processing device provided in the embodiments of the present invention can execute the low-altitude economic reliable data processing method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0324] It is worth noting that in the embodiments of the low-altitude economic reliable data processing device described above, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the scope of protection of the present invention.

[0325] Figure 6 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0326] like Figure 6 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer programs stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0327] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0328] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, and microcontroller. Processor 11 performs the various methods and processes described above, such as the low-altitude economic trusted data processing method.

[0329] In some embodiments, the low-altitude economic trusted data processing method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the low-altitude economic trusted data processing method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the low-altitude economic trusted data processing method by any other suitable means (e.g., by means of firmware).

[0330] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0331] Computer programs used to implement the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0332] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0333] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0334] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0335] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0336] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication unit 19, or installed from storage unit 18, or installed from ROM 12. When the computer program is executed by processor 11, it performs the functions defined in the methods of the embodiments of the present invention.

[0337] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0338] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A low-altitude economic credible data processing method, characterized in that, The method comprises: in response to a Shapley value calculation instruction, reading low-altitude data corresponding to each unmanned aerial vehicle (UAV) in a plurality of UAVs operating cooperatively in a low-altitude airspace from a blockchain, and determining a UAV contribution value of the UAV according to the low-altitude data, wherein the low-altitude airspace is an airspace within a preset distance range from the ground, and the low-altitude data is data generated in a first time period during operation of the UAV; determining a coalition contribution value according to the UAV contribution value and a first airspace openness correction factor by using a target Shapley formula, determining a weight coefficient according to the first airspace openness correction factor and a coalition size, and determining a target Shapley value of the UAV according to the coalition contribution value and the weight coefficient, so as to perform value distribution for all the low-altitude data for each of the UAVs according to the target Shapley values corresponding to the UAVs respectively, wherein the first airspace openness correction factor is determined according to an effective duration of an airspace opening policy for the first time period and a time decay rate corresponding to the first time period, and the airspace opening policy is an opening policy related to the low-altitude airspace; wherein the first airspace openness correction factor represents the timeliness of the airspace opening policy, the timeliness represents that the effectiveness of the airspace opening policy decreases over time, and the time decay rate is set according to the timeliness requirement; the target Shapley formula is represented by the following manner: ； in, Indicates the first The target Shapley value of the drone. This indicates that the first [item] is not present. A subset of the Taiwanese drone alliance This refers to the set of drones represented by the multiple drones. This represents the weighting coefficient. This represents the first spatial openness correction factor. This represents the size of the alliance subset. Indicates that in the first The contribution value of the alliance obtained after the drone joins the subset of the alliance. Indicates the first in the set of drones Taiwanese drone.

2. The low-altitude economic trustable data processing method according to claim 1, characterized in that, the low-altitude data comprises a data amount, a data accuracy, and a regional coverage weight, the data amount represents the number of flight track points of the UAV per unit time, the data accuracy represents the measurement accuracy of a sensor in the UAV, and the regional coverage weight represents the spatial coverage value of the UAV for the low-altitude airspace, and the UAV contribution value of the UAV is determined according to the low-altitude data, comprising: obtaining a first weight corresponding to the data amount, a second weight corresponding to the data accuracy, and a third weight corresponding to the regional coverage weight, and determining the UAV contribution value of the UAV according to the data amount and the first weight, the data accuracy and the second weight, and the regional coverage weight and the third weight.

3. The low altitude economic trustable data processing method of claim 1, wherein, the first time period comprises a plurality of sub-periods, and a corresponding Shapley value is determined for each of the sub-periods, the Shapley value being determined according to the low-altitude data corresponding to the corresponding sub-period, the effective duration, and the time decay rate; the target Shapley value is determined according to the duration of each of the sub-periods and the Shapley value.

4. The low altitude economic trustable data processing method of claim 1, wherein, The method further comprises: in response to an airspace opening priority update instruction, obtaining a plurality of candidate strategies related to the opening of the low-altitude airspace and / or flight restrictions in the low-altitude airspace. For each of the candidate strategies, a posterior probability of the candidate strategy is determined according to a second airspace openness correction factor and a prior probability and a likelihood function of the candidate strategy, wherein the prior probability represents a historical success rate of the candidate strategy, the likelihood function represents a possibility of observing the current environmental data when the candidate strategy is executed, and the posterior probability represents a probability of feasibility of the candidate strategy under the environmental data; The airspace openness priority currently applied is updated according to all the probabilities of feasibility; Flight modes respectively allowed for each of the unmanned aerial vehicles in the low-altitude airspace are determined according to the airspace openness priority, so that each of the unmanned aerial vehicles performs flight operations according to a corresponding flight mode.

5. The low-altitude economic trustable data processing method according to claim 4, characterized in that, The updating of the airspace openness priority currently applied according to all the probabilities of feasibility includes: A game tree constructed in advance is obtained, wherein the game tree at least includes a root node, at least two first intermediate nodes connected with the root node and used to represent corresponding candidate strategies, second intermediate nodes respectively connected with the first intermediate nodes, at least two third intermediate nodes connected with the second intermediate nodes and used to represent corresponding candidate strategies, and a leaf node used to output an airspace openness priority; All the probabilities of feasibility, the environmental data and the airspace openness priority currently applied are input into the root node, so that the root node performs value evaluation on the candidate strategies respectively corresponding to the first intermediate nodes according to the input data by using a deep reinforcement learning model, so as to select one of the candidate strategies and execute it; The environmental data and the airspace openness priority obtained after the execution of the corresponding candidate strategy are input into the second intermediate node, so that the second intermediate node performs value evaluation on the candidate strategies respectively corresponding to the third intermediate nodes according to the input data by using the deep reinforcement learning model, so as to select one of the candidate strategies and execute it, so as to continue to transfer in the game tree until the leaf node; The airspace openness priority is updated according to an output result of the leaf node.

6. The low-altitude economic trustable data processing method according to claim 5, characterized in that, All the probabilities of feasibility, the deep reinforcement learning model and the environmental data are stored on the blockchain, so that the airspace openness priority is determined by all the probabilities of feasibility, the deep reinforcement learning model and the environmental data read from the blockchain, and the flight modes respectively allowed for each of the unmanned aerial vehicles in the low-altitude airspace are determined according to the airspace openness priority, which includes: The airspace openness priority is stored on the blockchain; An intelligent contract stored on the blockchain is used to determine the flight modes respectively allowed for each of the unmanned aerial vehicles in the low-altitude airspace according to the airspace openness priority stored on the blockchain.

7. The low-altitude economic trustable data processing method according to claim 6, characterized in that, The blockchain comprises a consortium chain and a directed acyclic graph chain, the low-altitude data, the feasibility probabilities, the environment data, and the airspace opening priority are stored on the directed acyclic graph chain, and the deep reinforcement learning model is stored on the consortium chain.

8. The low altitude economic trustable data processing method according to any one of claims 1-7, characterized in that, The UAV contribution value is further determined according to a first weight, a second weight, and a third weight, and the method further comprises: In response to the closed-loop feedback instruction, determining a current airspace utilization rate of the low-altitude airspace, and determining a Gini coefficient according to the target Shapley values currently respectively corresponding to each of the UAVs; Determining a comprehensive Gini coefficient according to the airspace utilization rate and the Gini coefficient; In a case where it is determined to adjust parameters according to the comprehensive Gini coefficient, determining a target parameter to be adjusted according to the comprehensive Gini coefficient, adjusting the target parameter, and updating, wherein the target parameter comprises at least one of the time decay rate, the first weight, the second weight, and the third weight.

9. The low-altitude economic trustable data processing method according to claim 8, characterized in that, It is determined to adjust parameters when the comprehensive Gini coefficient is greater than a first preset threshold, and the determining a target parameter to be adjusted according to the comprehensive Gini coefficient comprises: In a case where the comprehensive Gini coefficient is greater than the first preset threshold and less than or equal to a second preset threshold, taking the time decay rate as the target parameter to be adjusted; In a case where the comprehensive Gini coefficient is greater than the second preset threshold, taking the time decay rate and the second weight and / or the third weight as the target parameter.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for causing the processor to execute the low-altitude economic credible data processing method of any one of claims 1-9 when executed.

Images