Logistics transportation optimization system based on big data

Abstract

The invention discloses a logistics transportation optimization system based on big data. An operation method of the system comprises the following steps: step 1, target location identification and real-time data collection; 2, carrying out path planning and collision avoidance on cargo transportation; step 3, a user realizes cargo tracking through an interactive interface; 4, the cargo transportation efficiency of the unmanned aerial vehicle is evaluated and improved, and the target location identification and data collection module is used for identifying a cargo delivery point and collecting real-time data; the path planning and collision avoidance module is used for determining an optimal flight path of the unmanned aerial vehicle and monitoring positions and obstacles of other aircrafts in real time; and the user interaction and performance monitoring module is used for inputting delivery information by a user, tracking the cargo delivery progress in real time and regularly evaluating the accuracy of path planning and the system efficiency, and the system has the characteristics of improving the cargo delivery efficiency and accuracy and reducing the flight safety risk.

Description

Technical Field

[0001] The present invention relates to the technical field of air transportation, and specifically to a logistics transportation optimization system based on big data. Background Art

[0002] In modern air transportation, with emerging means of transportation such as unmanned aerial vehicles and electric vertical takeoff and landing aircraft, the demand for delivering goods and performing tasks is increasing continuously. However, traditional air transportation systems often face challenges in aspects such as route planning, flight safety, and real-time monitoring, which may lead to inefficiencies, safety risks, and uncertainties.

[0003] Traditional air transportation systems have some deficiencies in route planning and flight safety. Route planning is usually based on simple considerations of distance and speed, lacking the ability to comprehensively consider multiple factors, such as cargo weight, battery life, weather conditions, and traffic situations. This may result in unnecessary delays, energy waste, and flight safety risks. In addition, traditional air transportation systems often lack real-time data collection and monitoring functions, and are unable to effectively respond to emergencies, such as sudden weather changes, traffic jams, or aircraft failures. This makes air transportation tasks more unpredictable and high-risk. Therefore, it is necessary to design a logistics transportation optimization system based on big data to improve the efficiency and accuracy of cargo delivery and reduce flight safety risks. Summary of the Invention

[0004] The purpose of the present invention is to provide a logistics transportation optimization system based on big data to solve the problems raised in the above background art.

[0005] To solve the above technical problems, the present invention provides the following technical solution: A logistics transportation optimization system based on big data, and the operation method of the system includes the following steps:

[0006] Step 1: Target location identification and real-time data collection;

[0007] Step 2: Route planning and collision avoidance for cargo transportation;

[0008] Step 3: Users can track the cargo through an interactive interface;

[0009] Step 4: Evaluate and improve the efficiency of unmanned aerial vehicle cargo transportation.

[0010] According to the above technical solution, the step of target location identification and real-time data collection includes:

[0011] Using high-resolution maps and satellite image technologies for target identification;

[0012] Using computer vision algorithms and image processing technologies to achieve high-precision target identification;

[0013] Integrate terrain features and geographical coordinate information to ensure accurate target recognition;

[0014] Real-time data collection includes wind speed, weather, traffic, and drone performance data.

[0015] According to the above technical solution, the steps of implementing high-precision target recognition using computer vision algorithms and image processing techniques include:

[0016] First, the system obtains high-resolution maps and satellite images, which contain detailed information of the ground surface and provide basic data for target recognition. Then, image processing is carried out, including image segmentation and feature extraction. Through image segmentation, the image is divided into different regions to better identify potential target points. Subsequently, feature extraction algorithms are used to extract key features from the image, such as buildings, roads, and water bodies, to help further identify possible target points. Finally, computer vision algorithms, such as object detection and recognition techniques, are introduced for final target recognition. These algorithms rely on the results of feature extraction to identify potential target delivery points in the image. During this process, it may include detecting buildings, house numbers, landmarks, or other recognition features to determine the target points suitable for drone flight. In addition, the system also comprehensively considers terrain features and geographical coordinate information, including ground height, terrain undulation, traffic roads, and geographical coordinates. By integrating image information with geographical data, the location of the target delivery point can be determined more accurately to ensure that the drone can reach the destination safely and precisely.

[0017] According to the above technical solution, the steps of the real-time data collection including wind speed, weather, traffic, and drone performance data include:

[0018] The system conducts real-time data collection. These data include but are not limited to wind speed, weather conditions, traffic situations, and drone performance data. To collect these data, various sensors and communication devices are required, including meteorological sensors, flight control units, and traffic monitoring units. These sensors communicate with the drone and transmit real-time data to the central data processing unit of the system. In addition, wireless communication technology can be used to obtain real-time meteorological and traffic information from ground stations or meteorological data providers. These data will be used for subsequent path planning to ensure flight safety and efficiency. Through high-resolution maps, satellite images, and real-time sensor data, an accurate information basis is provided for the subsequent steps of drone cargo transportation, which also ensures that the drone can more precisely identify the target delivery point during the delivery mission and consider key weather and traffic factors during flight.

[0019] According to the above technical solution, the steps of path planning and collision avoidance for cargo transportation include:

[0020] Use the A* search algorithm and the TSP optimization algorithm for path planning;

[0021] Implement real-time collision avoidance, monitor the positions and headings of other aircraft, and detect potential collision risks.

[0022] According to the above technical solution, the steps of using the A* search algorithm and the TSP optimization algorithm for path planning include:

[0023] In terms of path planning, the system uses the A* search algorithm to solve the path planning problem of a single target point. This algorithm can fully consider the distance to the cargo delivery point, the flight speed of the drone, and the battery life to determine the best move at each step. The system uses a heuristic function to estimate the cost from the current position to the target point to guide the path selection. At the same time, for the case of multiple target points, the system introduces the TSP optimization algorithm, models the problem as a graph theory problem to minimize the total flight distance and time. The algorithm not only considers the weight of the cargo but also the order and urgency of the delivery points. To consider weather conditions, the system will continuously obtain real-time weather data, including wind speed, rainfall, and temperature, and use this data to predict adverse weather conditions. The path planning algorithm will automatically adjust the flight plan of the drone according to the real-time weather data to ensure safety and efficiency, which includes adjusting the flight altitude and speed to minimize flight time and fuel consumption. When the drone needs to deliver emergency medical supplies from the hospital to three different target points, these target points are respectively:

[0024] Target point A: 10 kilometers away from the hospital, the flight speed of the drone is 60 kilometers per hour, and the battery life is sufficient to support continuous flight for 30 minutes.

[0025] Target point B: 20 kilometers away from the hospital, the flight speed of the drone is 50 kilometers per hour, and the battery life is sufficient to support continuous flight for 40 minutes.

[0026] Target point C: 15 kilometers away from the hospital, the flight speed of the drone is 70 kilometers per hour, and the battery life is sufficient to support continuous flight for 25 minutes.

[0027] The system will plan the flight path of the drone according to the path planning and weather conditions:

[0028] Path planning:

[0029] For target point A, using the A* search algorithm and considering the distance, flight speed, and battery life, the best path is found, so it is necessary to fly directly to target point A.

[0030] For target points B and C, the system uses optimization algorithms such as TSP to find the best sequence to minimize the total flight distance and time. Therefore, possible path plans include Hospital -> Target Point B -> Target Point C -> Hospital, or Hospital -> Target Point C -> Target Point B -> Hospital.

[0031] Weather condition consideration:

[0032] Real-time weather data shows that along the path of the drone flight, the weather conditions at Target Point B are poor, with strong winds and rainfall, while there are no adverse weather conditions on the paths of Target Point A and Target Point C.

[0033] The path planning algorithm selects a safer path based on the weather data, avoiding the adverse weather area at Target Point B and adjusting the flight altitude and speed accordingly.

[0034] Taking into account both path planning and weather considerations, the drone will perform the task according to the following path:

[0035] Take off from the hospital, fly directly to Target Point A to complete the delivery. Subsequently, fly to Target Point B to complete the delivery. Then, fly to Target Point C to complete the delivery. Finally, return to the hospital.

[0036] According to the above technical solution, the steps of implementing real-time collision avoidance, monitoring the positions and headings of other aircraft, and detecting potential collision risks include:

[0037] In terms of collision avoidance, first, real-time monitoring is carried out. Radar, GPS, and other sensor systems are used to track the positions and headings of other aircraft. At the same time, a collision detection algorithm is implemented, and 3D modeling and collision detection technologies are used to accurately predict potential collisions. These algorithms use real-time sensor data, including radar data and GPS data, to continuously update the positions of obstacles and the drone to calculate the collision risk in real time. Once the system detects a potential collision risk, appropriate path adjustment measures will be immediately taken to ensure the flight safety of the drone. This includes changing the flight altitude, raising or lowering it to avoid the paths of other aircraft or obstacles. At the same time, the flight route of the drone will be adjusted to ensure a safe distance from other aircraft. If necessary, the drone will be guided to bypass obstacles to avoid potential collision risks.

[0038] According to the above technical solution, the steps for the user to achieve cargo tracking through an interactive interface include:

[0039] Provide a user interface that allows the shipper or operator to input delivery information;

[0040] Integrate a communication system that allows the user to communicate with the drone bidirectionally to solve problems or confirm the delivery point.

[0041] According to the above technical solution, the step of providing a user interface that allows a shipper or operator to input delivery information includes:

[0042] The system provides a user interface that enables a shipper or operator to easily input delivery information, which includes detailed address of the target delivery point, type of goods, quantity, and critical information on urgency. The user can provide this information through the input fields on the interface to ensure that the system fully understands the specific needs and requirements of each delivery task. In the system, the progress of the goods transportation can be monitored by using the real-time tracking function, which includes displaying the real-time position of the drone on a map and the estimated arrival time. The user can view the current position of the drone at any time to ensure whether the goods transportation is proceeding as planned. This visual delivery monitoring meets the needs of users and provides them with instant information and feedback.

[0043] According to the above technical solution, the steps of evaluating and improving the efficiency of drone cargo transportation include:

[0044] Regularly evaluate the accuracy and efficiency of path planning, and collect flight data and user feedback;

[0045] Analyze flight data, including flight path, time, and fuel consumption;

[0046] Collect user feedback and operation data, including goods delivery time, accuracy, and customer satisfaction;

[0047] Continuously improve the path planning algorithm to improve delivery efficiency and the stability of the drone.

[0048] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: The present invention first accurately identifies the target delivery point through high-resolution maps, satellite images, and computer vision algorithms, and integrates real-time data, including weather, wind speed, and traffic conditions, for path planning. The path planning takes into account multiple factors, such as distance, speed, battery life, and cargo weight, and automatically adjusts the flight plan according to weather conditions. The system also implements collision avoidance technology to monitor other aircraft and obstacles to ensure flight safety. The user inputs delivery information through the interaction interface and real-time tracks the progress of the goods transportation, and can communicate with the system to solve problems. Performance monitoring is used to evaluate the planning accuracy and system efficiency, and the algorithm is continuously improved to improve delivery efficiency. This system has the characteristics of improving the efficiency and accuracy of goods delivery and reducing the flight safety risk. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The drawings are used to provide a further understanding of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention and do not constitute a limitation to the present invention. In the drawings:

[0050] Figure 1 This is a flowchart of a logistics transportation optimization method provided in the first embodiment of the present invention based on big data;

[0051] Figure 2 This is a schematic diagram of the module composition of a logistics transportation optimization system provided in the second embodiment of the present invention based on big data. Detailed implementation manners

[0052] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0053] Embodiment 1: Figure 1 This is a flowchart of a logistics transportation optimization method provided in the first embodiment of the present invention based on big data. This embodiment can be applied to the scenario of unmanned aerial vehicle (UAV) cargo transportation. This method can be executed by a logistics transportation optimization system provided in this embodiment based on big data, as Figure 1 shown. The method specifically includes the following steps:

[0054] Step 1: Target location identification and real-time data collection;

[0055] In the embodiment of the present invention, by identifying the target points and collecting various types of real-time data, the efficiency and accuracy of cargo delivery are improved;

[0056] Exemplarily, high-resolution maps and satellite image technologies are utilized for target recognition, including using satellite remote sensing data or other geographical information data sources to identify target delivery points, which are delivery addresses, warehouses, dropping areas, or other designated locations. In addition, to achieve high-precision target recognition, computer vision algorithms and image processing technologies are required. First, the system acquires high-resolution maps and satellite images, which contain detailed information of the ground surface and provide basic data for target recognition. Then, image processing is performed, including image segmentation and feature extraction. Through image segmentation, the image is divided into different regions to better identify potential target points. Subsequently, feature extraction algorithms are used to extract key features from the image, such as buildings, roads, water bodies, etc., to assist in further identifying possible target points. Finally, computer vision algorithms, such as object detection and recognition technologies, are introduced for final target recognition. These algorithms rely on the results of feature extraction to identify potential target delivery points in the image. During this process, it may include detecting buildings, house numbers, landmarks, or other recognition features to determine target points suitable for drone flight. In addition, the system also comprehensively considers terrain features and geographical coordinate information, including ground height, terrain undulation, traffic roads, and geographical coordinates. By integrating image information with geographical data, the location of the target delivery point can be determined more accurately to ensure that the drone can reach the destination safely and precisely;

[0057] Exemplarily, the system collects real-time data, which includes but is not limited to wind speed, weather conditions, traffic conditions, and drone performance data. To collect these data, various sensors and communication devices are required, including meteorological sensors, flight control units, traffic monitoring units, etc. These sensors communicate with the drone and transmit real-time data to the central data processing unit of the system. In addition, wireless communication technologies can also be used to obtain real-time meteorological and traffic information from ground stations or meteorological data providers. These data will be used for subsequent path planning to ensure flight safety and efficiency. High-resolution maps, satellite images, and real-time sensor data provide an accurate information basis for the subsequent steps of drone cargo transportation, which also ensures that the drone can more accurately identify target delivery points during the delivery task and consider key weather and traffic factors during flight.

[0058] Step 2: Perform path planning and collision avoidance for cargo transportation;

[0059] In the embodiment of the present invention, through path planning and collision avoidance during drone cargo transportation, it is ensured that the cargo can be delivered to the target delivery point efficiently and safely;

[0060] Exemplarily, in terms of path planning, the system adopts the A* search algorithm to solve the path planning problem for a single target point. This algorithm can fully consider the distance to the goods delivery point, the flight speed of the drone, and the battery life to determine the best move at each step. The system uses a heuristic function to estimate the cost from the current position to the target point to guide the path selection. Meanwhile, for the case of multiple target points, the system introduces the TSP optimization algorithm, models the problem as a graph theory problem to minimize the total flight distance and time. The algorithm not only considers the weight of the goods but also the order and urgency of the delivery points. To consider weather conditions, the system will continuously obtain real-time weather data, including wind speed, rainfall, temperature, etc., and use this data to predict adverse weather conditions. The path planning algorithm will automatically adjust the flight plan of the drone according to the real-time weather data to ensure safety and efficiency, which includes adjusting the flight altitude and speed to minimize flight time and fuel consumption;

[0061] Exemplarily, for example, it is required that the drone delivers emergency medical supplies from the hospital to three different target points, which are respectively:

[0062] Target point A: 10 kilometers away from the hospital, the flight speed of the drone is 60 kilometers per hour, and the battery life is sufficient to support continuous flight for 30 minutes.

[0063] Target point B: 20 kilometers away from the hospital, the flight speed of the drone is 50 kilometers per hour, and the battery life is sufficient to support continuous flight for 40 minutes.

[0064] Target point C: 15 kilometers away from the hospital, the flight speed of the drone is 70 kilometers per hour, and the battery life is sufficient to support continuous flight for 25 minutes.

[0065] The system will plan the flight path of the drone according to the path planning and weather conditions:

[0066] Path planning:

[0067] For target point A, using the A* search algorithm considering the distance, flight speed, and battery life, the best path is found, so it is necessary to fly directly to target point A.

[0068] For target point B and target point C, the system adopts optimization algorithms such as TSP to find the best order to minimize the total flight distance and time. Therefore, possible path plans include hospital -> target point B -> target point C -> hospital, or hospital -> target point C -> target point B -> hospital, etc.

[0069] Weather condition consideration:

[0070] Real-time weather data shows that along the flight path of the drone, the weather conditions at target point B are poor, with strong winds and rainfall, while there are no adverse weather conditions along the paths of target point A and target point C.

[0071] The path planning algorithm selects a safer path based on the weather data, avoiding the adverse weather area at target point B and adjusting the flight altitude and speed accordingly.

[0072] Taking into account both path planning and weather considerations, the drone will execute the mission along the following path:

[0073] Taking off from the hospital, flying directly to target point A to complete the delivery. Subsequently, flying to target point B to complete the delivery. Then, flying to target point C to complete the delivery. Finally, returning to the hospital;

[0074] Exemplarily, in terms of collision avoidance, real-time monitoring is first carried out, using radar, GPS, and other sensor systems to track the positions and headings of other aircraft. This real-time monitoring ensures that the system can obtain the position information of other aircraft in a timely manner to detect potential collision risks. At the same time, collision detection algorithms are also implemented, and three-dimensional modeling and collision detection technologies are used to accurately predict potential collisions. These algorithms consider not only other aircraft but also obstacles on the ground, such as buildings, mountains, and communication towers, etc. These algorithms use real-time sensor data, including radar data and GPS data, to continuously update the positions of the obstacles and the drone to calculate the collision risk in real time. Once the system detects a potential collision risk, appropriate path adjustment measures will be immediately taken to ensure the flight safety of the drone. This includes changing the flight altitude, raising or lowering it to avoid the paths of other aircraft or obstacles. At the same time, the flight route of the drone will be adjusted to ensure a safe distance from other aircraft. If necessary, the drone will be guided to bypass the obstacles to avoid potential collision risks. The comprehensive application of these algorithms and technologies ensures that the drone can monitor potential collision risks in real time during flight and take necessary measures to ensure the safety and stability of the flight.

[0075] Step 3: The user realizes the cargo tracking through the interactive interface;

[0076] In an embodiment of the present invention, the system provides a user interface that enables a shipper or operator to easily input delivery information, which includes key information such as the detailed address of the target delivery point, the type of goods, the quantity, and the urgency. The user can provide this information through the input fields on the interface to ensure that the system fully understands the specific needs and requirements of each delivery task. In the system, the progress of the goods transportation can be monitored by using the real-time tracking function, which includes displaying the real-time drone position and the estimated arrival time on a map. The user can view the current position of the drone at any time to ensure whether the goods transportation is proceeding as planned. This visual delivery monitoring meets the needs of users and provides them with instant information and feedback;

[0077] Exemplarily, the user interface is built-in with a communication system that enables two-way communication between the shipper, the operator, and the drone. This communication system supports multiple communication methods, including text messages, audio calls, and video calls. The user can use the interface to send messages to the drone, such as confirming the delivery point, providing additional instructions, or resolving potential problems. At the same time, the drone operator can also use the interface to contact the user to achieve better collaboration and information exchange. In this step, by allowing the user to input delivery information, real-time tracking of the goods transportation progress, and integrating the communication system, real-time interaction and monitoring between the user and the drone goods transportation system are achieved, enabling the user to better manage and control the process of goods transportation.

[0078] Step Four: Evaluate and improve the efficiency of drone goods transportation.

[0079] In an embodiment of the present invention, the system regularly evaluates the accuracy and efficiency of path planning, such as collecting and analyzing the flight data of the drone, including the actual flight path, flight time, and fuel consumption, as well as the problems or challenges encountered during the drone flight, such as weather changes, air traffic interference, or communication problems. By comparing with the predetermined flight path, the system can identify potential performance problems and take measures for improvement. At the same time, in order to obtain more insights for improvement, user feedback and operation data will also be collected, which includes the feedback opinions of the shipper and the operator, as well as the data on the goods delivery time, accuracy, and customer satisfaction. The operation data also includes any problems or challenges in the operation. These data will be used to identify potential improvement points and determine the direction of performance optimization;

[0080] Exemplarily, based on performance monitoring and user feedback, the system continuously improves the path planning algorithm to improve delivery efficiency and ensure the stability and reliability of the drone, including optimizing the algorithm for the flight path to reduce the total flight distance, save fuel, and increase the delivery speed. The improvement is also adjusted for the accuracy of the delivery time and customer satisfaction. In this step, by regularly evaluating the accuracy of the path planning, collecting user feedback and operation data, and continuously improving the path planning algorithm, the continuous performance optimization of the system will be ensured, thus providing a higher quality cargo transportation service.

[0081] Embodiment 2: Embodiment 2 of the present invention provides a logistics transportation optimization system based on big data. Figure 2 As shown in the schematic diagram of the module composition of a logistics transportation optimization system based on big data provided in Embodiment 2 of the present invention, Figure 2 as shown, the system includes:

[0082] A target location identification and data collection module, which is used to identify the cargo delivery point, such as the delivery address, warehouse, or designated location, and collect real-time data;

[0083] A path planning and collision avoidance module, which is used to determine the optimal flight path of the drone and monitor the positions of other aircraft and obstacles in real time to avoid collisions;

[0084] A user interaction and performance monitoring module, which is used for users to input delivery information, and to track the progress of cargo delivery in real time and regularly evaluate the accuracy of path planning and the system efficiency;

[0085] In some embodiments of the present invention, the target location identification and data collection module includes:

[0086] A target identification module, which is used to accurately identify the target delivery point, such as the delivery address, warehouse, or dropping area, by using high-resolution maps, satellite images, and computer vision algorithms;

[0087] A geographic information integration module, which is used to integrate map information with geographic coordinate data to ensure the accurate location of the target delivery point to support the safe arrival of the drone;

[0088] A real-time data collection module, which is used to collect real-time data, including weather, wind speed, traffic, and aircraft performance data, for subsequent path planning;

[0089] In some embodiments of the present invention, the path planning and collision avoidance module includes:

[0090] A path planning algorithm module, which is used to determine the optimal flight path of the drone, considering the distance to the cargo delivery point, flight speed, battery life, and weather conditions, to minimize the flight time and fuel consumption;

[0091] Collision monitoring and avoidance module, which is used to monitor the position and heading of other aircraft in real time, detect possible collision risks, and take measures to avoid collisions;

[0092] Path adjustment and optimization module, which is used to adjust the flight path of the UAV according to real-time data and collision avoidance requirements to ensure safety and efficiency;

[0093] In some embodiments of the present invention, the user interaction and performance monitoring module includes:

[0094] User interface module, which is used to provide a user interface, allowing users to input delivery information, monitor the progress of cargo delivery in real time, and communicate with the UAV;

[0095] Performance monitoring and data collection module, which is used to regularly evaluate the accuracy and efficiency of path planning, and collect UAV flight data and user feedback;

[0096] Path planning algorithm improvement module, which is used to continuously improve the path planning algorithm to improve delivery efficiency and ensure the stability and reliability of the UAV.

[0097] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0098] Finally, it should be noted that the above are only preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A logistics transportation optimization method based on big data, the method comprising the following steps: Step 1: Target location identification and real-time data collection; Step 2: Route planning and collision avoidance for cargo transportation; Step 3: Users achieve cargo tracking through an interactive interface; Step 4: Evaluate and improve the efficiency of drone cargo transportation.

2. The logistics transportation optimization method based on big data according to claim 1, wherein: The step of target location identification and real-time data collection includes: Using high-resolution maps and satellite image technology for target identification; Using computer vision algorithms and image processing technology to achieve high-precision target identification; Integrating terrain features and geographical coordinate information to ensure accurate target identification; Real-time data collection includes wind speed, weather, traffic, and drone performance data.

3. A logistics transportation optimization method based on big data according to claim 2, characterized in that: The step of using computer vision algorithms and image processing technology to achieve high-precision target identification includes: First, the system obtains high-resolution maps and satellite images, which contain detailed information of the ground surface and provide basic data for target identification. Then, image processing is performed, including image segmentation and feature extraction. Through image segmentation, the image is divided into different regions to better identify potential target points. Subsequently, feature extraction algorithms are used to extract key features from the image, such as buildings, roads, and water bodies, to help further identify possible target points. Finally, computer vision algorithms, such as object detection and recognition technologies, are introduced for final target identification. These algorithms rely on the results of feature extraction to identify potential target delivery points in the image. During this process, it may include detecting buildings, house numbers, landmarks, or other identification features to determine the target points suitable for drone flight. In addition, the system also comprehensively considers terrain features and geographical coordinate information, including ground height, terrain undulation, traffic roads, and geographical coordinates. By integrating image information with geographical data, the location of the target delivery point can be determined more accurately to ensure that the drone can reach the destination safely and precisely.

4. A logistics transportation optimization method based on big data according to claim 2, characterized in that: The step of real-time data collection including wind speed, weather, traffic, and drone performance data includes: The system conducts real-time data collection. These data include but are not limited to wind speed, weather conditions, traffic situations, and drone performance data. To collect these data, various sensors and communication devices are required, including meteorological sensors, flight control units, and traffic monitoring units. These sensors communicate with the drone and transmit real-time data to the central data processing unit of the system. In addition, wireless communication technology can be used to obtain real-time meteorological and traffic information from ground stations or meteorological data providers. These data will be used for subsequent route planning to ensure flight safety and efficiency. Through high-resolution maps, satellite images, and real-time sensor data, an accurate information basis is provided for the subsequent steps of drone cargo transportation, which also ensures that the drone can more accurately identify the target delivery point during the delivery task and consider key weather and traffic factors during flight.

5. The logistics transportation optimization method based on big data according to claim 1, characterized in that: The step of route planning and collision avoidance for cargo transportation includes: Using the A* search algorithm and TSP optimization algorithm for route planning; Implement real-time collision avoidance, monitor the positions and headings of other aircraft, and detect potential collision risks.

6. The logistics transportation optimization method based on big data according to claim 5, characterized in that: The steps of using the A* search algorithm and the TSP optimization algorithm for path planning include: In terms of path planning, the system adopts the A* search algorithm to solve the path planning problem for a single target point. This algorithm can fully consider the distance to the cargo delivery point, the flight speed of the drone, and the battery life to determine the best move at each step. The system uses a heuristic function to estimate the cost from the current position to the target point to guide the path selection. At the same time, for the case of multiple target points, the system introduces the TSP optimization algorithm, models the problem as a graph theory problem to minimize the total flight distance and time. The algorithm not only considers the weight of the cargo but also the order and urgency of the delivery points. To consider weather conditions, the system continuously obtains real-time weather data, including wind speed, rainfall, and temperature, and uses this data to predict adverse weather conditions. The path planning algorithm will automatically adjust the flight plan of the drone according to the real-time weather data to ensure safety and efficiency, which includes adjusting the flight altitude and speed to minimize flight time and fuel consumption. When the drone needs to deliver emergency medical supplies from the hospital to three different target points, these target points are: Target point A: 10 kilometers away from the hospital, the flight speed of the drone is 60 kilometers per hour, and the battery life is sufficient to support continuous flight for 30 minutes. Target point B: 20 kilometers away from the hospital, the flight speed of the drone is 50 kilometers per hour, and the battery life is sufficient to support continuous flight for 40 minutes. Target point C: 15 kilometers away from the hospital, the flight speed of the drone is 70 kilometers per hour, and the battery life is sufficient to support continuous flight for 25 minutes. The system will plan the flight path of the drone according to the path planning and weather conditions: Path planning: For target point A, using the A* search algorithm considering the distance, flight speed, and battery life, the best path is found, so it is necessary to fly directly to target point A. For target point B and target point C, the system adopts the TSP optimization algorithm to find the best order to minimize the total flight distance and time. Therefore, possible path plans include hospital -> target point B -> target point C -> hospital, or hospital -> target point C -> target point B -> hospital. Weather condition consideration: Real-time weather data shows that along the flight path of the drone, the weather conditions at target point B are poor, with strong winds and rainfall, while there are no adverse weather conditions on the paths of target point A and target point C. The path planning algorithm selects a safer path according to the weather data, avoids the adverse weather area of target point B, and adjusts the flight altitude and speed accordingly. Taking into account path planning and weather consideration, the drone will perform the task according to the following path: Take off from the hospital, fly directly to target point A to complete the delivery, then fly to target point B to complete the delivery, then fly to target point C to complete the delivery, and finally return to the hospital.

7. The logistics transportation optimization method based on big data according to claim 5, characterized in that: The steps of implementing real-time collision avoidance, monitoring the positions and headings of other aircraft, and detecting potential collision risks include: In terms of collision avoidance, real-time monitoring is first carried out. Radar, GPS, and other sensor systems are used to track the positions and headings of other aircraft. At the same time, collision detection algorithms are implemented, and 3D modeling and collision detection technologies are used to accurately predict potential collisions. These algorithms use real-time sensor data, including radar data and GPS data, to continuously update the positions of obstacles and the drone to calculate the collision risk in real time. Once the system detects a potential collision risk, appropriate path adjustment measures will be immediately taken to ensure the flight safety of the drone. This includes changing the flight altitude, either raising or lowering it, to avoid the paths of other aircraft or obstacles. At the same time, the flight route of the drone will be adjusted to ensure a safe distance from other aircraft. If necessary, the drone will be guided to bypass obstacles to avoid potential collision risks.

8. The logistics transportation optimization method based on big data according to claim 1, characterized in that: The steps for the user to achieve cargo tracking through the interactive interface include: Providing a user interface that allows the shipper or operator to input delivery information; Integrating a communication system that allows the user to communicate with the drone bidirectionally to solve problems or confirm the delivery point.

9. A logistics transportation optimization method based on big data according to claim 8, characterized in that: The step of providing a user interface that allows the shipper or operator to input delivery information includes: The system provides a user interface that enables the shipper or operator to easily input delivery information, which includes key information such as the detailed address of the target delivery point, the type of goods, quantity, and urgency. The user can provide this information through the input fields on the interface to ensure that the system fully understands the specific needs and requirements of each delivery task. In the system, the progress of the cargo transportation can be monitored by using the real-time tracking function, which includes displaying the real-time position of the drone on the map and the estimated arrival time. The user can check the current position of the drone at any time to ensure whether the cargo transportation is proceeding as planned. This visual delivery monitoring meets the needs of users and provides them with instant information and feedback.

10. A logistics transportation optimization method based on big data according to claim 1, characterized in that: The steps for evaluating and improving the efficiency of drone cargo transportation include: Regularly evaluating the accuracy and efficiency of path planning, and collecting flight data and user feedback; Analyzing flight data, including flight paths, time, and fuel consumption; Collecting user feedback and operation data, including cargo delivery time, accuracy, and customer satisfaction; Continuously improving the path planning algorithm to improve the delivery efficiency and the stability of the drone.

Images