Sports equipment time-sharing leasing system based on intelligent contract

Abstract

The invention relates to the technical field of sports equipment leasing, and discloses a sports equipment time-sharing leasing system based on a smart contract. The system comprises a lease master control platform which can obtain a sports equipment distribution thermodynamic diagram and generate an initial time-sharing lease scheme according to the sports equipment distribution thermodynamic diagram; the data acquisition module is used for acquiring user identity features and equipment state features based on the thermodynamic diagram to form a multi-dimensional user feature data set; the contract execution engine performs lease rule analysis on the multi-dimensional data set according to the initial scheme to generate a static lease priority sequence; the dispatching optimization module controls the distribution track of the distribution unmanned aerial vehicle in combination with the static lease priority and the corresponding equipment position; the dynamic calibration module collects environmental fluctuation parameters in real time to generate a dynamic lease priority, and corrects the distribution direction. According to the system, by means of an intelligent means, sports equipment renting is more reasonable and standard, efficiency and strain capacity are improved, and user experience is optimized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of sports equipment rental, in particular to a sports equipment time-sharing rental system based on a smart contract. BACKGROUND

[0002] With the popularization of the concept of national fitness, the demand for sports equipment in society is increasing, and sports equipment rental, as a flexible and efficient way of resource utilization, is gradually favored by the public. However, there are many problems to be solved in the current sports equipment rental mode. Traditional rental relies on manual registration and management, and the rental process is cumbersome. Users need to go to a fixed place to handle procedures, which not only wastes time, but also is limited by the location and business hours, making it difficult to meet the instant and diversified rental needs of users. In terms of equipment allocation, due to the lack of accurate grasp of user distribution and equipment usage status, there are often cases of excess equipment in some areas and shortage of equipment in other areas, resulting in low resource allocation efficiency. At the same time, the information in the rental process is not transparent, which can easily cause disputes between users and rental parties, such as unclear definition of equipment damage liability and rental fee calculation disputes. Traditional rental scheduling mainly relies on manual planning, and the optimization capability of the distribution route is limited. Especially in the case of scattered user demand and complex traffic conditions, it is difficult to achieve efficient distribution, which not only increases the operating cost, but also reduces the user experience. With the development of technologies such as the Internet of Things and blockchain, how to use intelligent means to solve the above problems in sports equipment rental has become an important direction for the development of the industry. SUMMARY

[0003] The purpose of the present application is to provide a sports equipment time-sharing rental system based on a smart contract to solve the problems raised in the background.

[0004] To achieve the above purpose, the present application provides a sports equipment time-sharing rental system based on a smart contract, which comprises: a rental master control platform for obtaining a sports equipment distribution heat map and generating an initial time-sharing rental plan; a data acquisition module for acquiring user identity features and equipment state features based on the sports equipment distribution heat map, and generating a multi-dimensional user feature data set; a contract execution engine for analyzing rental rules for the multi-dimensional user feature data set according to the initial time-sharing rental plan, and generating a static rental priority sequence; a scheduling optimization module for obtaining a feasible path of a distribution drone, combining each static rental priority in the static rental priority sequence and the corresponding equipment location, and controlling the distribution trajectory of the distribution drone on the feasible path; The dynamic calibration module is used to collect environmental fluctuation parameters in real time during equipment use to generate dynamic rental priorities, and to correct the delivery direction of the delivery drone based on the dynamic rental priority and static rental priority of the current equipment location.

[0005] Preferably, when the contract execution engine performs rental rule analysis on the multi-dimensional user feature dataset based on the initial time-sharing rental scheme: Extract the time-sharing rules of the initial time-sharing rental scheme; Obtain the rental demand features and credit rating features corresponding to the first user feature subset, select and compare user feature subsets based on the spatiotemporal attributes of the first user feature subset and the time period segmentation rules, perform priority learning, and generate the first static rental priority. The rental demand features and credit rating features corresponding to other user feature subsets are obtained in sequence, and all static rental priorities are generated in the same way and mapped to the sports equipment distribution heat map to form the static rental priority sequence.

[0006] Preferably, when the scheduling optimization module controls the delivery drone's delivery trajectory on the feasible path: Analyze each static rental priority in the static rental priority sequence and the location coordinates of the equipment it is bound to; Obtain all path segments of the feasible path and the locations of its associated adjacent equipment; The static rental priorities of all adjacent equipment locations associated with each path segment are weighted and aggregated to generate the path segment priority density. The delivery trajectory of the delivery drone is planned from the delivery start point using a time-series optimization algorithm.

[0007] Preferably, when the dynamic calibration module performs correction based on dynamic lease priority and static lease priority: Calculate the deviation between the dynamic rental priority and the static rental priority of the current equipment location; When the deviation exceeds a preset tolerance threshold, the calibration range is determined based on environmental fluctuation parameters. Obtain the dynamic and static rental priorities of nearby equipment locations within the calibration range; Direction correction instructions are generated based on the dynamic and static rental priorities of nearby equipment locations.

[0008] Preferably, when the data acquisition module generates a multi-dimensional user feature dataset: High-density usage areas are segmented from the heat map of sports equipment distribution; Obtain the real-time usage request stream, and select the starting user group based on the real-time usage request stream to collect historical rental frequency characteristics; Based on the real-time usage request flow, the next user group is selected for collecting payment credit features until the features of all user groups are collected; The historical rental frequency features and the payment credit features are integrated to form the multi-dimensional user feature dataset.

[0009] Preferably, when the rental master platform generates an initial time-sharing rental scheme: Obtain the average historical rental frequency feature in the multi-dimensional user feature dataset; Extract the regional use peak period of the sports equipment distribution heat map; Generate a time segment division node according to the regional use peak period and the average historical rental frequency feature; Generate the initial time-sharing rental scheme in combination with the time segment division node.

[0010] Preferably, before the contract execution engine performs rental rule analysis: Obtain the weather influence coefficient in the current geographic fence through the rental master platform; Obtain the credit rating distribution vector of the user group through the data acquisition module.

[0011] Preferably, when the dynamic calibration module generates a dynamic rental priority: Real-time monitor the weather mutation index in the current geographic fence; Collect the temporary use demand fluctuation rate of the user group; Fuse the weather mutation index and the temporary use demand fluctuation rate to generate the dynamic rental priority.

[0012] Preferably, when the scheduling optimization module uses a time sequence optimization algorithm to plan a distribution trajectory: Convert the path segment priority density into a time window constraint condition; Generate a equipment loading sequence according to the maximum load of the distribution unmanned aerial vehicle; Generate a trajectory optimization objective function based on the time window constraint condition and the equipment loading sequence; Solve the trajectory optimization objective function to obtain an optimal distribution trajectory.

[0013] Preferably, when the dynamic calibration module generates a direction correction instruction: Calculate the average dynamic rental priority of the adjacent equipment position; Obtain the historical priority baseline of the corresponding position in the static rental priority sequence; Generate a heading correction amount according to the gradient difference between the average dynamic rental priority and the historical priority baseline; Convert the heading correction amount into the direction correction instruction.

[0014] Compared with the prior art, the present application has the following advantages: By obtaining the sports equipment distribution heat map through the lease master platform and generating an initial time-sharing lease scheme, the lease scheme can be more in line with the actual equipment distribution and user demand distribution characteristics, avoiding the problem of unreasonable scheme caused by information lag in traditional leasing. The data acquisition module acquires user identity features and equipment state features based on the heat map and generates a multi-dimensional user feature data set, providing comprehensive and detailed basic information for subsequent lease rule analysis, making the grasp of user demand and equipment state more accurate, and helping to improve the pertinence of lease service.

[0015] The contract execution engine performs lease rule analysis on the multi-dimensional data set according to the initial scheme and generates a static lease priority sequence, taking advantage of the characteristics of smart contract to make the execution of lease rules more standardized and transparent, reducing the interference of human factors on lease priority determination and ensuring the fairness of the lease process.

[0016] The dispatch optimization module combines the static lease priority and equipment location to control the flight trajectory of the distribution drone, which can fully utilize the flexibility of the drone, realize reasonable planning of the distribution route, reduce invalid transportation, improve the distribution efficiency, and enable users to obtain the required sports equipment more timely. The dynamic calibration module collects environmental fluctuation parameters in real time during equipment use and generates a dynamic lease priority, which in turn corrects the distribution direction, so that the lease service can adapt to the real-time changes in the environment and demand, enhancing the system's response ability, ensuring that the distribution process always matches the actual situation, and improving the reliability of the overall lease service and user satisfaction. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 The timing diagram of the smart contract-based sports equipment time-sharing lease system described in the present application; Figure 2 The flowchart for generating static lease priority; Figure 3 The flowchart for distribution direction correction; Figure 4 The flowchart for generating a multi-dimensional user feature data set; Figure 5 The flowchart for planning the distribution trajectory by the timing optimization algorithm. DETAILED DESCRIPTION

[0018] With reference to the drawings of the embodiments of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of the present application.

[0019] Please refer to Figure 1 The present application provides a smart contract-based sports equipment time-sharing rental system, which comprises a system core composed of a rental master control platform, a data acquisition module, a contract execution engine, a scheduling optimization module and a dynamic calibration module.

[0020] The rental master control platform first acquires a distribution heat map reflecting the spatial use density of sports equipment, and generates an initial time-sharing rental scheme accordingly. Based on the distribution heat map, the data acquisition module acquires user identity features (such as user ID, location) and equipment state features (such as equipment ID, available state, location coordinates), and integrates and processes these features to form a user feature data set containing multi-dimensional information. The contract execution engine receives the initial time-sharing rental scheme and the user feature data set, analyzes and processes them according to the preset smart contract rules, and outputs a static rental priority sequence, which identifies the relative rental priority order of different users or equipment in a specific time period. The scheduling optimization module acquires the feasible path network information of the delivery drone in the service area, combines each priority item in the static rental priority sequence and its bound specific equipment location coordinates, calculates and controls the optimal delivery trajectory of the delivery drone on the feasible path. The dynamic calibration module continuously runs during the actual use of the equipment, real-time acquires environmental fluctuation parameters (such as sudden weather changes, temporary demand surges), generates dynamic rental priorities, compares and analyzes the dynamic priorities with the static rental priorities generated by the contract execution engine, and real-time corrects the current delivery direction of the delivery drone according to the comparison result to adapt to environmental changes.

[0021] Embodiment 1: Please refer to Figure 2When the contract execution engine processes the multi-dimensional user feature dataset, it first parses the time period segmentation rule in the initial time-sharing lease plan. This rule divides the whole day into peak, flat, and valley periods based on historical data. For the first user feature subset in the user feature dataset, the engine extracts its lease demand features (including lease duration, equipment type preference, and emergency level identification) and credit level features (such as historical performance rating and third-party credit score). Based on the spatio-temporal attributes of this subset (user geographic location and request timestamp), the engine filters the comparative user feature subsets with the same time period and adjacent area in the dataset. Through a priority learning algorithm (using rule matching and weighted scoring mechanism), the engine calculates the static lease priority of the first user feature subset: the algorithm linearly superimposes the emergency level in the lease demand features and the credit level features according to the preset weight (e.g., 60% for emergency level and 40% for credit level), and then standardizes them with the mean of the comparative subsets. Then the engine processes the remaining user feature subsets, each time matching the comparative subsets according to the spatio-temporal attributes and generating priorities using the same algorithm. Finally, all static lease priorities are sorted in descending order of numerical value and bound with the latitude and longitude coordinates of the corresponding equipment in the sports equipment distribution heat map to form a static lease priority sequence.

[0022] After the scheduling optimization module parses the static lease priority sequence, it obtains the location coordinates and priority values of each equipment. The module loads the feasible path network data in the geographic information system and identifies the adjacent equipment locations associated with each path segment (within 500 meters of the equipment points). For path segment P1, the weighted aggregation value of the priorities of the three equipment locations (A, B, C) associated with it is calculated: path segment priority density . Wherein is the weight factor (determined by the Euclidean distance from the path segment to the equipment point, ), is the static priority of the equipment. Repeat this process to generate a path segment priority density distribution map for the entire network. When the delivery drone departs from the warehouse coordinates (116.4, 39.9), the module starts the timing optimization algorithm: using the path segment priority density as the time window urgency indicator, high-density areas require arrival within 10 minutes, and low-density areas are relaxed to 20 minutes; the algorithm combines the constraints such as the drone's range of 30 kilometers and maximum load of 5 kilograms, uses Dijkstra's algorithm to initially select the path, and then optimizes the visit order through tabu search. The final output trajectory is: warehouse → equipment point with priority 9 (116.41, 39.91) → equipment point with priority 7 (116.39, 39.88) →..., forming a delivery sequence with a total length of 22.3 kilometers.

[0023] The dynamic calibration module collects environmental fluctuation parameters of the target equipment point in real time during the UAV's execution of the trajectory. When the UAV is heading for the coordinates (116.41, 39.91), the module monitors that sudden rainfall at this point causes the weather influence coefficient to drop to 0.4, while the temporary event causes the rental request volume to grow by 300%. The module calculates the dynamic rental priority: the original static value of 9 is raised to 13 after environmental correction (correction formula: dynamic value = static value x (1 + demand fluctuation rate) x weather coefficient). The deviation from the static value is 44.4% (exceeding the preset threshold of 30%), triggering the calibration program. The module defines a 1-kilometer calibration range centered on the target point, obtains the dynamic values (11 and 14) and static values (8 and 10) of the adjacent points (116.42, 39.90), (116.40, 39.92) within the range. Calculate the gradient difference Δ = 3.2 between the dynamic average value 12.5 and the static average value 9.3, and generate the heading correction amount: adjust the flight direction angle by 15° to the new coordinates (116.40, 39.92). After receiving the command, the flight control system, the UAV turns to the new target point in real time during flight.

[0024] Example 2: refer to Figure 3 The dynamic calibration module continuously monitors the environmental parameters of the target equipment location. For the equipment point at coordinates (116.41, 39.91), the module collects the weather mutation index (every 30 seconds, by obtaining the instantaneous rainfall intensity and wind speed change rate through the weather API) and the temporary use demand fluctuation rate (calculated by the year-on-year increase in request volume). The dynamic rental priority generation formula is:

[0025] Where: is the dynamic rental priority, is the static rental priority (initial value 9), is the demand sensitivity coefficient (preset value 0.8), is the current request volume increase over the historical baseline (monitoring value 200%), is the real-time weather influence coefficient (reduced to 0.5 during rainfall). Substituting . The deviation is calculated using the relative change rate: , which exceeds the tolerance threshold of 50% to trigger correction. The module defines a calibration range of 0.8 kilometers in radius (covering 3 adjacent equipment points), and obtains their dynamic values: the dynamic value of point A (116.42, 39.90) ( ), the dynamic value of point B (116.40, 39.92) ( ), and the dynamic value of point C (116.39, 39.89) ( ). Calculate dynamic priority mean , static priority mean . Gradient difference . Calculate directional gradient according to spatial distribution: take target point as center, point B's maximum and azimuth 215°, generate course correction amount fly 600 meters along 215° direction to point B. Convert instruction to: {“action”:“course_correction”,“azimuth”:215,“distance”:600}.

[0026] After UAV flight control system parses instruction, interrupt original trajectory to go to new target point. After flying 200 meters, module monitors point B's drop to 0.3 (rainstorm upgrade), increase to 300%, recalculate to 21.6. At this time, deviation , trigger calibration again. Point C's dynamic value in new calibration range increases to 14.7, and point D (116.38, 39.93) adds dynamic value 19.2. Dynamic mean updates to 18.5, static mean 9.0, and gradient difference . Spatial analysis shows that high value area shifts southeast, generates new course correction amount fly 450 meters along 140° direction to point D. This process continues until environmental parameters are stable, and finally UAV prioritizes service to equipment point with highest dynamic value under rainstorm conditions.

[0027] Example 3: refer to Figure 4 , when data acquisition module processes sports equipment distribution heat map, use DBSCAN clustering algorithm to identify high use density area (point density > 50 times / square kilometer). Set neighborhood radius meters, minimum point number , output 3 clustering areas: area A (coordinate range 116.38-116.42, 39.88-39.92), area B (116.35-116.38, 39.85-39.88), and area C (116.45-116.48, 39.93-39.96). Real-time use request stream is processed in batches according to time window: first group selects requests within 10 minutes before T0 time (including 12 users), acquires historical rental frequency characteristics (computational formula: ) from user database. For example, user U01's (36 times / 30 days). Second group selects requests from T0+10 to T0+20 minutes (8 users), calls payment system interface to acquire payment credit characteristics (computational formula: ), such as user U15 (overdue 2 times / 40 singles). Cycle to T0+60 minutes to collect 50 user features, integrated dataset format: {user ID, coordinates, , }.

[0028] The rental master platform calculates the arithmetic mean of (the sum of all users / 50). Analyze the regional peak period of the heat map: the daily use density peak of region A occurs at 17:00-19:00 (average 85 times / hour), and the peak of region B occurs at 12:00-14:00 (average 60 times / hour). Combined with (higher than the system benchmark value 0.8), generate period segmentation nodes: the peak period is extended by 30 minutes, region A is adjusted to 16:30-19:30, and region B is adjusted to 11:30-14:30. The trough period division rule is: the density of region A is <20 times / hour at 00:00-06:00, and the density of region B is <15 times / hour at 22:00-05:00. The final scheme defines three periods: peak (region A: 16:30-19:30; region B: 11:30-14:30), flat (the rest of the non-trough period), and trough (region A: 00:00-06:00; region B: 22:00-05:00), each period is configured with differentiated priority calculation weights (peak period credit weight increased to 60%).

[0029] In Example 4, before the contract execution engine starts, the rental master platform obtains the weather influence coefficient within the geographic fence (polygon vertex set: [(116.3, 39.8), (116.5, 39.8), (116.5, 40.0), (116.3, 40.0)]) through the National Meteorological Bureau API. Real-time weather data is quantitatively processed: no precipitation and wind speed <3 m / s , light rain (0-2 mm / h) and wind speed 3-5 m / s , moderate rain (2-10 mm / h) and wind speed 5-8 m / s . The data acquisition module synchronously analyzes the credit rating distribution of the current active user group (102 people), and generates a distribution vector based on the payment behavior history: Table 1: User credit rating distribution vector.

[0030]

[0031] The dynamic calibration module monitors a sudden strong convective weather in region A, and the weather mutation index is calculated as: ​The baseline value is the average of the past hour (rainfall 1 mm / h, wind speed 4 m / s), and the instantaneous value rises to 8 mm / h (rainfall). ), wind speed 9 m / s ( ),have to Meanwhile, due to corporate team-building activities, Region B temporarily utilized demand volatility. (Request volume compared to predicted value). Dynamic lease priority generation uses a two-factor coupling: For example, a certain equipment point in area A. , , ,but This value reflects how severe weather causes a decrease in priority, despite increased demand.

[0032] Example 5: See Figure 5 The scheduling optimization module will adjust the priority density of path segments. Convert to time window constraint: The associated equipment along the route segment must be serviced within 20 minutes. Extended to 40 minutes Allow 60 minutes. The module generates an equipment loading sequence based on the drone's maximum payload (5 kg): prioritizing high-priority equipment (>7), with a maximum of 3 items loaded at a time (average equipment weight 1.8 kg). For example, if the top three priorities in the static sequence are 9 (basketball), 8.5 (badminton racket), and 7.2 (soccer ball), then the initial loading sequence would be {basketball, badminton racket} (total weight 3.2 kg).

[0033] Construct a trajectory optimization objective function: minimize total delivery time. Three types of constraints must be satisfied: 1) Time window constraint (arrival time) ); 2) Loading constraints (equipment weight) ); 3) Range constraints (flight distance) The objective function is expressed as: ,in The departure time is from the warehouse. The branch and bound method is used to solve this: First, an initial path is generated: [Warehouse → P9 → P8.5 → P7.2] (minutes), check the arrival time on P7.2. minutes exceeded its Corresponding time window ( ,Require (Minutes), deemed infeasible. The path was adjusted to [Warehouse → P9 → P7.2 → P8.5], and the calculation was recalculated. minutes (satisfied) minute( ,Require minutes, still over the limit). The final optimized path is [Warehouse -> P8.5 -> P9 -> P7.2]: drone 8:00 departure, 8:18 arrival at P8.5 (flight distance 5.2 km), 8:32 arrival at P9 (cumulative 10.1 km), 8:47 arrival at P7.2 (cumulative 16.3 km), total time 47 minutes to meet all constraints. The output trajectory contains the path point sequence, service schedule and loading list.

[0034] In the process of generating the initial time-sharing rental scheme, in addition to the conventional analysis of the sports equipment distribution heat map and historical rental frequency characteristics, the lease hosting platform pays special attention to the special needs for intelligent shooting analysis equipment in the basketball training scenario, and separately marks such equipment as a high-frequency demand category and includes it in the analysis of high-use-density areas of the heat map. When collecting user identity characteristics and equipment status characteristics, the data collection module additionally collects training scenario characteristics for user groups applying to rent basketball intelligent backboard systems and matching shooting recognition equipment, such as whether the user is a professional training institution, daily training time preference, single training duration, and other information, while recording the device status of camera A (used to detect basketball movement near the basket) and camera B (used to capture the court and three-point line area) in the intelligent backboard system, including lens cleanliness, resolution parameters, real-time transmission rate, etc. These information is integrated with the user's historical rental frequency, payment credit characteristics to form a more multi-dimensional user feature data set that is more in line with the needs of basketball training.

[0035] When analyzing the rental rules, the contract execution engine first extracts the time period segmentation rule for basketball training equipment in the initial time-sharing rental scheme, which is divided according to the common peak period of basketball training (from 3 pm to 9 pm). For the first user feature subset that applies for a basketball intelligent backboard system in the multi-dimensional user feature data set, the engine extracts its rental demand characteristics, such as whether it needs to rent camera A and camera B at the same time, whether it requires the device to support real-time hit rate calculation and three-point shot recognition function, and the user's credit level characteristics. Combined with the user's spatio-temporal attributes, i.e. training site location and application usage period, the engine filters out a comparative user feature subset in the data set that has the same training period, adjacent site, and also rents basketball intelligent equipment, and generates the first static rental priority of the user through a priority learning algorithm. When calculating the priority, the degree of matching of device function requirements is particularly taken into account, and if the user explicitly needs three-point shot recognition function and has a high credit level, the priority weight will be correspondingly increased. Subsequently, the engine processes other user feature subsets that apply for basketball training equipment or regular sports equipment in the same process, generates all static rental priorities and maps them to the sports equipment distribution heat map, forming a static rental priority sequence that includes the demand for basketball special equipment.

[0036] The scheduling optimization module parses the priority information and corresponding equipment location coordinates of the basketball intelligent backboard system and the matching camera in the static lease priority sequence when planning the distribution trajectory. After obtaining the feasible path of the distribution UAV, the part of the path segment passing through the basketball training venue concentrated area is focused on, the static lease priority weighted aggregation value of the adjacent equipment location associated with the path segment is calculated, and the path segment priority density is generated. For the distribution task of the basketball intelligent camera, considering the precision of the equipment, when planning the trajectory by using the timing optimization algorithm, the path segment with more stable road conditions and smaller vibration is preferentially selected, and the area that may block the signal transmission is avoided to ensure that the camera is not damaged during the distribution process and can normally transmit video data afterwards. For example, when one of the equipment locations associated with a path segment has a basketball training venue that applies for a high-priority intelligent backboard system and cameras A and B, the scheduling optimization module will appropriately increase the priority density of the path segment to ensure that the UAV preferentially distributes these equipment to meet the immediate training needs of the venue.

[0037] The dynamic calibration module collects environmental fluctuation parameters in real time during the use of the equipment, including light intensity in the training venue, personnel flow density in the venue, and other parameters that may affect the shooting effect of the camera. According to these parameters, a dynamic lease priority is generated. For example, when the light intensity in a basketball training venue suddenly decreases, which may affect the detection accuracy of camera A for the movement of the basketball near the basket, if other venues apply for a backup camera or adjust the location of the existing equipment, the dynamic calibration module will increase the dynamic lease priority of the application. Calculate the deviation of the dynamic lease priority and the static lease priority of the current equipment location, and when the deviation exceeds the preset tolerance threshold, determine the calibration range based on the light, personnel flow, and other environmental fluctuation parameters, and obtain the dynamic and static lease priorities of the adjacent equipment locations in the calibration range. For example, if multiple basketball venues in a certain area propose the demand for adjusting the camera angle or replacing the high-sensitivity lens due to insufficient evening light, the dynamic calibration module will generate direction correction instructions for the distribution UAV based on the priority of these adjacent venues, guiding the UAV to preferentially distribute related accessories or technical support equipment to these venues that need equipment adjustment or replenishment, ensuring that the shooting detection and three-point recognition functions of the basketball intelligent backboard system can function normally, and meeting the real-time training needs of users. During the entire dynamic calibration process, the module will continuously monitor the use feedback data of the basketball intelligent equipment, such as whether the video frame rate of the camera is stable at 30 frames per second or above, and whether the projection transformation technology can accurately map the three-point line to the plane coordinate system. According to these real-time feedback, further adjust the dynamic lease priority and the distribution direction to ensure the continuity and stability of the use of equipment in the basketball training scenario.

[0038] It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting; it is not intended to exclude myriad other embodiments of the present application that other inventors can develop based on the same general inventive concepts embodied by the described embodiments. That is, although the present application is described in terms of particular embodiments and illustrative figures, it should be apparent that the scope of the present application is not limited to these specific embodiments.

[0039] While the embodiments of the application have been shown and described herein, it will be understood by those of ordinary skill in the art that various changes, modifications, alternatives, and variations can be made to the embodiments without departing from the spirit and scope of the application, which is defined by the appended claims and their equivalents.

Claims

1. A sports equipment time-sharing rental system based on smart contracts, characterized in that, include: The rental control platform is used to obtain a heat map of the distribution of sports equipment and generate an initial time-sharing rental plan; The data acquisition module is used to collect user identity features and equipment status features based on the heat map of sports equipment distribution, and generate a multi-dimensional user feature dataset. The contract execution engine is used to perform rental rule analysis on the multi-dimensional user feature dataset according to the initial time-sharing rental scheme, and generate a static rental priority sequence. The scheduling optimization module is used to obtain the feasible path of the delivery drone, and control the delivery trajectory of the delivery drone on the feasible path by combining each static rental priority in the static rental priority sequence and the corresponding equipment location. The dynamic calibration module is used to collect environmental fluctuation parameters in real time during equipment use to generate dynamic rental priorities, and to correct the delivery direction of the delivery drone based on the dynamic rental priority and static rental priority of the current equipment location.

2. The system according to claim 1, characterized in that, When the contract execution engine performs rental rule analysis on the multi-dimensional user feature dataset based on the initial time-sharing rental scheme: Extract the time-sharing rules of the initial time-sharing rental scheme; Obtain the rental demand features and credit rating features corresponding to the first user feature subset, select and compare user feature subsets based on the spatiotemporal attributes of the first user feature subset and the time period segmentation rules, perform priority learning, and generate the first static rental priority. The rental demand features and credit rating features corresponding to other user feature subsets are obtained in sequence, and all static rental priorities are generated in the same way and mapped to the sports equipment distribution heat map to form the static rental priority sequence.

3. The system according to claim 2, characterized in that, When the scheduling optimization module controls the delivery drone's delivery trajectory on the feasible path: Analyze each static rental priority in the static rental priority sequence and the location coordinates of the equipment it is bound to; Obtain all path segments of the feasible path and the locations of its associated adjacent equipment; The static rental priorities of all adjacent equipment locations associated with each path segment are weighted and aggregated to generate the path segment priority density. The delivery trajectory of the delivery drone is planned from the delivery start point using a time-series optimization algorithm.

4. The system according to claim 3, characterized in that, When the dynamic calibration module performs corrections based on dynamic lease priority and static lease priority: Calculate the deviation between the dynamic rental priority and the static rental priority of the current equipment location; When the deviation exceeds a preset tolerance threshold, the calibration range is determined based on environmental fluctuation parameters. Obtain the dynamic and static rental priorities of nearby equipment locations within the calibration range; Direction correction instructions are generated based on the dynamic and static rental priorities of nearby equipment locations.

5. The system according to claim 1, characterized in that, When the data acquisition module generates a multi-dimensional user feature dataset: High-density usage areas are segmented from the heat map of sports equipment distribution; Obtain the real-time usage request stream, and select the starting user group based on the real-time usage request stream to collect historical rental frequency characteristics; Based on the real-time usage request flow, select the next user group to collect payment credit features, until the feature collection of all user groups is completed. The multi-dimensional user feature dataset is formed by integrating historical rental frequency features and payment credit features.

6. The system according to claim 5, characterized in that, When the rental control platform generates the initial time-sharing rental plan: Obtain the mean of historical rental frequency features from the multi-dimensional user feature dataset; Extract the peak usage times for different areas from the heat map showing the distribution of sports equipment; Time segmentation nodes are generated based on the average of the peak usage periods and historical rental frequency characteristics of the region. The initial time-sharing rental plan is generated by combining the time-segmentation nodes.

7. The system according to claim 1, characterized in that, Before the contract execution engine performs lease rule analysis: Obtain the weather impact coefficient within the current geofence by leasing the main control platform; The credit rating distribution vector of the user group is obtained through the data acquisition module.

8. The system according to claim 7, characterized in that, When the dynamic calibration module generates dynamic lease priorities: Real-time monitoring of the weather change index within the current geofence; Collect the volatility of temporary usage demand from user groups; The dynamic leasing priority is generated by combining the weather change index with the volatility of temporary use demand.

9. The system according to claim 1, characterized in that, When the scheduling optimization module uses a time-series optimization algorithm to plan the delivery trajectory: Convert the path segment priority density into time window constraints; Generate a material loading sequence based on the maximum payload of the delivery drone; Based on the aforementioned time window constraints and equipment loading sequence, a trajectory optimization objective function is generated. The optimal delivery trajectory is obtained by solving the trajectory optimization objective function.

10. The system according to claim 4, characterized in that, When the dynamic calibration module generates a direction correction command: Calculate the average dynamic rental priority of nearby equipment locations; Obtain the historical priority baseline at the corresponding position in the static lease priority sequence; The heading correction is generated based on the gradient difference between the average dynamic lease priority and the historical priority baseline; The heading correction amount is converted into the direction correction command.

Images