A logistics transportation method and system based on drone

Abstract

The present invention provides a logistics transportation method and system based on drones, which relates to the field of drone transportation technology, and specifically includes: real-time collection of drone flight data, meteorological data of target areas and other relevant data; generating condition indexes of each distribution area according to the distribution distance between each area, combined with traffic flow, expected delivery time and cargo load; generating a meteorological evaluation index according to meteorological data, and generating a flight evaluation index according to flight data; combining the above indexes to generate a regional comprehensive evaluation model to obtain a comprehensive score for each target area. The present invention constructs a systematic regional comprehensive evaluation model by real-time collection of flight data and meteorological data. The combination of condition index, meteorological evaluation index and flight evaluation index improves the optimization capability of the distribution path and reduces the distribution risk caused by meteorological and traffic factors.

Description

Technical Field

[0001] The present invention relates to the field of drone transportation technology, and in particular to a drone-based logistics transportation method and system. Background Art

[0002] In recent years, with the surge in e-commerce and the continued increase in consumer demand for fast delivery services, drone delivery has gradually entered the market as an efficient emerging logistics model. However, the current drone delivery system still faces many technical challenges in practical applications. Among them, the most significant is the complexity of delivery path planning. Since drones need to operate under a variety of environmental conditions, including different geographical locations, weather changes and traffic conditions, traditional delivery algorithms often find it difficult to respond to these dynamic changes in real time. In addition, the existing system does not fully consider factors such as the demand, time window and traffic flow of the delivery area, resulting in the inability to achieve optimal delivery under changing market demands, resulting in waste of resources and reduced customer satisfaction.

[0003] On the other hand, changes in meteorological conditions also have a significant impact on the flight safety and delivery efficiency of drones. Factors such as wind speed, rainfall, and temperature not only affect the flight capabilities of drones, but may also cause delivery delays. However, many drone delivery systems currently lack effective meteorological data monitoring and real-time analysis mechanisms, resulting in the inability to adjust the decision-making process based on the latest meteorological information. In addition, comprehensive evaluation and priority sorting for each delivery area are also particularly important. Existing evaluation models often fail to comprehensively consider multiple influencing factors and lack scientificity and rationality. Therefore, an innovative technical solution is urgently needed to solve technical problems in the drone delivery process by combining real-time data collection with a dynamic evaluation model.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0005] The purpose of the present invention is to provide a logistics transportation method and system based on drones to solve the problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A logistics transportation method based on drones, the specific steps include:

[0008] Step 1: Collect the flight data of the drone in real time, determine the target area to be delivered, and number the target areas. , collect meteorological data of the target delivery area, collect geographic information data of the target delivery area;

[0009] Step 2: Construct a distance matrix , calculate the delivery distance between each area, and generate the condition index of each delivery target area by combining the traffic flow, expected delivery time and cargo load of the area;

[0010] Step 3: Based on the collected real-time meteorological data, after dimensionless processing, a meteorological assessment model is established to generate a meteorological assessment index. Based on the collected flight data, after dimensionless processing, a flight assessment model is established to generate a flight assessment index;

[0011] Step 4: Combine the condition index, meteorological assessment index and flight assessment index to generate a regional comprehensive assessment model. Generate the weights in the regional comprehensive assessment model through the hierarchical analysis method. Use the regional comprehensive assessment model to generate the comprehensive scores of the current target areas. Generate a priority list from high to low based on the comprehensive score of each area. The drones perform logistics transportation in sequence according to the current priority list.

[0012] Furthermore, the meteorological data includes the temperature of the target area. , precipitation and wind speed ;

[0013] The specific process of collecting meteorological data of the target area is: using the meteorological API to obtain the temperature of the target area every hour , rainfall and wind speed ; Among them, temperature The unit is degrees Celsius, rainfall The unit is millimeter, wind speed The unit is meters per second;

[0014] The flight data includes the drone’s real-time battery level , Flight altitude , Flight speed , Maximum load ;

[0015] The specific process of collecting flight data is as follows: using the GPS module on the drone to collect battery power in real time , Flight altitude and flight speed , and collect the maximum load of the drone based on the parameters of the drone ;

[0016] The target area related data includes the traffic flow of each target delivery area , longitude and latitude coordinates , the regional cargo demand , expected delivery time for the region ;

[0017] The specific process of collecting relevant data in the target area is as follows: deploy sensors in the target distribution area, and collect traffic flow in the target area in combination with data provided by the traffic control department. ; Collect cargo demand according to customer needs and expected delivery time .

[0018] Furthermore, the distance matrix is ​​constructed The process includes:

[0019] Create a distance matrix , the size is , Represents the total number of target areas that need to be delivered, where Indicates area To area distance;

[0020] The distance between each pair of regions is calculated using the Haversine formula, based on the following formula:

[0021]

[0022] in, Indicates area To area The distance represents the radius of the Earth, and Respectively, the regions and Region The latitude and longitude of and is the difference in latitude and longitude between two points.

[0023] Store the calculated distances in the distance matrix In, and , to ensure that the distance from the region to itself is zero.

[0024] Furthermore, the condition index is generated The process is based on the following formula:

[0025]

[0026] in, It is a region The condition index, From the starting point to the area The distance For Region Expected delivery time, It is a region The demand for goods, for The preset scaling factor, For Region traffic flow, for The preset scaling factor of , is the first constant correction exponent.

[0027] Furthermore, the real-time meteorological data collected is dimensionlessly processed and correlation analyzed to generate regional Meteorological Assessment Index , specifically including:

[0028] The real-time temperature collected Compare with the preset temperature threshold, if it exceeds the threshold, calculate the real-time temperature The difference between the temperature threshold ;

[0029]

[0030] in, For Region The meteorological assessment index, Real-time temperature The difference between the temperature threshold, is the rainfall, is the wind speed, is the second constant correction exponent.

[0031] Furthermore, the collected flight data is dimensionally processed and correlation analyzed to generate the region Flight Evaluation Index , specifically including:

[0032] The real-time flight altitude collected Compare with the preset height threshold, if it exceeds the threshold, calculate the real-time height The difference between the height threshold ;

[0033]

[0034] in, For Region Flight evaluation index, is the real-time altitude The difference between the height threshold , is the wind speed, is the current battery power of the drone, is the maximum payload of the drone, for The preset scale index of greater than zero, is the third constant correction exponent.

[0035] Furthermore, the condition index, meteorological assessment index and flight assessment index are combined to generate a regional comprehensive assessment model, and the regional comprehensive assessment model is used to generate a comprehensive score for each current target area. , the formula is as follows:

[0036]

[0037] in, It is a region The overall rating of It is a region The condition index, For Region The meteorological assessment index, For Region Flight evaluation index, , and are the weights of condition index, meteorological assessment index and flight assessment index, respectively. is the fourth constant correction exponent;

[0038] The above regional comprehensive evaluation model is used to generate the comprehensive score of each current target area. , , …, , and based on the comprehensive score of each area, a priority list is generated from high to low, and drones carry out logistics transportation in turn according to the current priority list.

[0039] Furthermore, the specific logic of generating the weights in the regional comprehensive evaluation model by the analytic hierarchy process is as follows:

[0040] The three indicators of condition index, meteorological assessment index and flight assessment index are marked, and the relative importance between them is determined by the nine-scale method to construct a judgment matrix, in which the condition index is marked as 1, the meteorological assessment index is marked as 2, and the flight assessment index is marked as 3. The constructed judgment matrix is:

[0041]

[0042] in, , The mark indicating the indicator, Indicator For indicators The importance of , ;

[0043] Each element in the judgment matrix is ​​normalized, and the specific formula of the normalization process is:

[0044]

[0045] in, for The normalized value;

[0046] The weight value of each indicator is calculated based on the value of each element in the judgment matrix after normalization. The specific formula is as follows:

[0047]

[0048] in, For indicators The weight value of .

[0049] The weights of the condition index, meteorological assessment index and flight assessment index are calculated based on the following formula:

[0050]

[0051]

[0052]

[0053] in, It represents the importance of the normalized condition index relative to the index j. Represents the normalized meteorological assessment index relative to the index The importance of Represents the normalized flight evaluation index relative to the index The importance of.

[0054] The present invention further provides a drone-based logistics transportation system, wherein the drone-based logistics transportation system is used to execute the above-mentioned drone-based logistics transportation method, comprising:

[0055] The data collection module is used to collect the flight data of the drone in real time, determine the target area to be delivered, and number them respectively. , collect meteorological data of the target delivery area, collect geographic information data of the target delivery area;

[0056] Conditional index generation module for constructing distance matrix , calculate the delivery distance between each area, and generate the condition index of each delivery target area by combining the traffic flow, expected delivery time and cargo load of the area;

[0057] The evaluation index generation module is used to establish a meteorological evaluation model and generate a meteorological evaluation index after dimensionless processing based on the collected real-time meteorological data, and to establish a flight evaluation model and generate a flight evaluation index after dimensionless processing based on the collected flight data;

[0058] The intelligent decision-making module is used to combine the condition index, meteorological assessment index and flight assessment index to generate a regional comprehensive assessment model, generate the weights in the regional comprehensive assessment model through the hierarchical analysis method, and use the regional comprehensive assessment model to generate the comprehensive scores of the current target areas. According to the comprehensive score of each area, a priority list is generated from high to low, and the drones carry out logistics transportation in sequence according to the current priority list.

[0059] Compared with the prior art, the present invention has the following beneficial effects:

[0060] The present invention constructs a systematic regional comprehensive evaluation model by collecting UAV flight data and meteorological data in real time, so that distribution decisions can dynamically adapt to environmental changes. By introducing the combination of condition index, meteorological evaluation index and flight evaluation index, not only the optimization ability of distribution path is improved, but also the distribution risk caused by meteorological and traffic factors is effectively reduced. Finally, the distribution strategy based on the priority list enables UAVs to perform logistics and transportation tasks more efficiently and flexibly, significantly improving distribution efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 It is a schematic diagram of the overall method flow of the present invention;

[0062] Figure 2 It is a schematic diagram of the overall system structure of the present invention. DETAILED DESCRIPTION

[0063] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0064] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0065] Example:

[0066] See also Figure 1 , the present invention provides a technical solution:

[0067] A logistics transportation method based on drones, the specific steps include:

[0068] Step 1: Collect the flight data of the drone in real time, determine the target area to be delivered, and number the target areas. , collect meteorological data of the target delivery area, collect geographic information data of the target delivery area;

[0069] In this embodiment, the meteorological data includes the temperature of the target area. , precipitation and wind speed ;

[0070] The specific process of collecting meteorological data of the target area is: using the meteorological API to obtain the temperature of the target area every hour , rainfall and wind speed ; Among them, temperature The unit is degrees Celsius, rainfall The unit is millimeter, wind speed The unit is meters per second;

[0071] The flight data includes the drone’s real-time remaining battery power , Flight altitude , Flight speed , Maximum load ;

[0072] The specific process of collecting flight data is as follows: using the GPS module on the drone to collect battery power in real time , Flight altitude and flight speed , and collect the maximum load of the drone based on the parameters of the drone ;

[0073] The target area related data includes the traffic flow of each target delivery area , longitude and latitude coordinates , the regional cargo demand , expected delivery time for the region ;

[0074] The specific process of collecting relevant data in the target area is as follows: deploy sensors in the target distribution area, and collect traffic flow in the target area in combination with data provided by the traffic control department. ; Collect cargo demand according to customer needs and expected delivery time The expected delivery time is the time the customer wants the order to be delivered to the designated location after placing the order;

[0075] This step can obtain multi-dimensional, real-time operating environment data, including traffic flow, weather conditions, and the status information of the drone itself, breaking through the limitations of the previous single data source and forming a more comprehensive and accurate monitoring network, thus providing a solid data foundation for subsequent transportation evaluation. By using sensors to collect traffic flow data, traffic congestion can be identified in real time, thus providing a key reference for the route planning of drones; meteorological data obtained by the meteorological API can promptly reflect the impact of weather changes on flight safety and energy consumption; both the flight speed and load information of the drone can help better evaluate the adaptability and transportation capacity of the drone in a specific environment. This comprehensive data collection not only improves the adaptability to the transportation environment, but also provides an important basis for subsequent model construction and evaluation, thereby significantly improving transportation efficiency and safety.

[0076] Step 2: Construct a distance matrix , calculate the delivery distance between each area, and generate the condition index of each delivery target area by combining the traffic flow, expected delivery time and cargo load of the area;

[0077] In this embodiment, the distance matrix is ​​constructed The process includes:

[0078] Create a distance matrix , the size is , Represents the total number of target areas that need to be delivered, where Indicates area To area distance;

[0079] The distance between each pair of regions is calculated using the Haversine formula, based on the following formula:

[0080]

[0081] in, Indicates area To area The distance represents the radius of the Earth, and Respectively, the regions and Region The latitude and longitude of and is the difference in latitude and longitude between two points;

[0082] The Haversing formula is designed to calculate the distance between two points on a sphere, so it can accurately take into account the curvature of the earth. In the case of longer distances or large terrain changes, using the distance formula between two points may lead to significant errors, while the Haversing formula provides more accurate measurements. In aviation navigation, the shortest route is along the great circle route. The Haversing formula can accurately calculate the great circle distance, reflecting the shortest path of the actual route, and is suitable for the flight planning of drones.

[0083] Generate Condition Index The process is based on the following formula:

[0084]

[0085] in, It is a region The condition index, From the starting point to the area The distance For Region Expected delivery time, It is a region The demand for goods, for The preset scaling factor, For Region traffic flow, for The preset scaling factor of , because for customers, on-time delivery is extremely important and directly affects customer experience and the company's brand image; is the first constant correction index. The constant correction index can be used to adjust the output to better match historical data or actual conditions, thereby improving calculation accuracy. Demand for goods When it increases, it means that the demand for transportation in this area is more urgent and needs to be arranged for delivery as soon as possible, so the condition index Increase; when When it increases, it means that the distance between the drone and the area is increasing, and the nearest delivery can be arranged first. Therefore, the condition index Reduce; when area Expected delivery time When it increases, it means that the delivery time in this area is more abundant, and more urgent logistics can be given priority for transportation, so the condition index Reduce, when the area Traffic flow When it increases, it will affect the efficiency of logistics and transportation, so the condition index Decrease; that is, and condition index There is a positive correlation, , , and condition index There is a negative correlation.

[0086] Step 3: Based on the collected real-time meteorological data, after dimensionless processing, a meteorological assessment model is established to generate a meteorological assessment index. Based on the collected flight data, after dimensionless processing, a flight assessment model is established to generate a flight assessment index;

[0087] In this embodiment, the real-time meteorological data collected is dimensionlessly processed and correlation analysis is performed to generate the region Meteorological Assessment Index , specifically including:

[0088] The real-time temperature collected Compare with the preset temperature threshold, if it exceeds the threshold, calculate the real-time temperature The difference between the temperature threshold ;

[0089]

[0090] in, For Region The meteorological assessment index, Real-time temperature The difference between the temperature threshold, is the rainfall, is the wind speed, is the second constant correction index, which can be used to adjust the output to better match historical data or actual conditions, thereby improving calculation accuracy; When it increases, it indicates the area If the temperature exceeds the threshold, high or low temperature conditions may cause the flight efficiency of the drone to decrease under certain temperature conditions, so the meteorological assessment index Increase; when rainfall When it increases, visibility will be reduced, affecting the visual navigation and sensor performance of the drone, increasing the risk during flight, and rainfall may cause the product to become damp and deteriorate. Therefore, the meteorological assessment index Increase; when wind speed When it increases, it will cause airflow instability, thus affecting the flight stability of the drone. Therefore, the meteorological assessment index Increase; that is, , , Meteorological Assessment Index There is a positive correlation.

[0091] The collected flight data is processed dimensionlessly and correlation analysis is performed to generate the region Flight Evaluation Index , specifically including:

[0092] The real-time flight altitude collected Compare with the preset height threshold, if it exceeds the threshold, calculate the real-time height The difference between the height threshold ;

[0093]

[0094] in, For Region Flight evaluation index, is the real-time altitude The difference between the height threshold , is the wind speed, is the current battery power of the drone, is the maximum payload of the drone, for The preset scaling factor of greater than zero, is the third constant correction index, which can be used to adjust the output to better match historical data or actual conditions, thereby improving calculation accuracy; When the altitude increases, on the one hand, if the flight altitude is too low, there may be a risk of collision with ground obstacles. On the other hand, if the flight altitude is too high, it may affect the stability of the drone, especially in areas with large airflow changes. Flight Evaluation Index Increase; when wind speed When it increases, it will cause airflow instability, thus affecting the flight stability of the drone. Flight Evaluation Index Increase; when the drone's battery power When it increases, it means that the endurance of the current drone is enhanced. decrease; when When it increases, it means the drone's load capacity increases. It decreases accordingly; that is, , Flight Evaluation Index There is a positive correlation, , Flight Evaluation Index There is a negative correlation.

[0095] Step 4: Combine the condition index, meteorological assessment index and flight assessment index to generate a regional comprehensive assessment model. Use the analytic hierarchy process to generate the weights in the regional comprehensive assessment model. Use the regional comprehensive assessment model to generate a comprehensive score for each target area. Based on the comprehensive score of each area, a priority list is generated from high to low. The drones carry out logistics transportation in order according to the current priority list.

[0096] In this embodiment, the condition index, meteorological assessment index and flight assessment index are combined to generate a regional comprehensive assessment model, and the regional comprehensive assessment model is used to generate a comprehensive score for each current target area. , the formula is as follows:

[0097]

[0098] in, It is a region The overall rating of It is a region The condition index, For Region The meteorological assessment index, For Region Flight evaluation index, , and are the weights of condition index, meteorological assessment index and flight assessment index, respectively. The fourth constant correction index can be used to adjust the output to better match historical data or actual conditions, thereby improving calculation accuracy; when the area Condition Index When it increases, it means that priority needs to be given to the current situation. Regional logistics and transportation, so the region Overall rating Increase; when area Meteorological Assessment Index When increasing, Reduce; when area Flight Evaluation Index When increasing, Decrease; that is, And comprehensive score There is a positive correlation, , And comprehensive score There is a negative correlation.

[0099] The above regional comprehensive evaluation model is used to generate the comprehensive score of each current target area. , , …, , and based on the comprehensive score of each area, a priority list is generated from high to low, and drones carry out logistics transportation in turn according to the current priority list;

[0100] The specific logic of generating the weights in the regional comprehensive evaluation model by the analytic hierarchy process is as follows:

[0101] The three indicators of condition index, meteorological assessment index and flight assessment index are marked, and the relative importance between them is determined by the nine-scale method to construct a judgment matrix, in which the condition index is marked as 1, the meteorological assessment index is marked as 2, and the flight assessment index is marked as 3. The constructed judgment matrix is:

[0102]

[0103] in, , The sign indicating the index, Indicators For indicators The importance of , ;

[0104] Each element in the judgment matrix is ​​normalized, and the specific formula of the normalization process is:

[0105]

[0106] in, for The normalized value;

[0107] The weight value of each indicator is calculated based on the value of each element in the judgment matrix after normalization. The specific formula is as follows:

[0108]

[0109] in, For indicators The weight value of .

[0110] The weights of the condition index, meteorological assessment index and flight assessment index are calculated based on the following formula:

[0111]

[0112]

[0113]

[0114] in, It represents the importance of the normalized condition index relative to the index j. Represents the normalized meteorological assessment index relative to the index The importance of Represents the normalized flight evaluation index relative to the index The importance of.

[0115] This step combines the condition index, meteorological assessment index and flight assessment index to comprehensively assess the conditions of each target area from multiple dimensions, ensuring the scientificity and accuracy of the decision. The use of the analytic hierarchy process can dynamically assign weights according to the importance of the evaluation indicators, making the comprehensive score more reasonable and reflecting the actual situation; the priority list generated by the comprehensive score enables drones to quickly identify priority delivery areas in logistics transportation and improve transportation efficiency.

[0116] See also Figure 2 The present invention further provides a drone-based logistics transportation system, which is used to execute the above-mentioned drone-based logistics transportation method, including:

[0117] The data collection module is used to collect the flight data of the drone in real time, determine the target area to be delivered, and number them respectively. , collect meteorological data of the target delivery area, collect geographic information data of the target delivery area;

[0118] Conditional index generation module for constructing distance matrix , calculate the delivery distance between each area, and generate the condition index of each delivery target area by combining the traffic flow, expected delivery time and cargo load of the area;

[0119] The evaluation index generation module is used to establish a meteorological evaluation model and generate a meteorological evaluation index after dimensionless processing based on the collected real-time meteorological data, and to establish a flight evaluation model and generate a flight evaluation index after dimensionless processing based on the collected flight data;

[0120] The intelligent decision-making module is used to combine the condition index, meteorological assessment index and flight assessment index to generate a regional comprehensive assessment model, generate the weights in the regional comprehensive assessment model through the hierarchical analysis method, and use the regional comprehensive assessment model to generate the comprehensive scores of the current target areas. According to the comprehensive score of each area, a priority list is generated from high to low, and the drones carry out logistics transportation in sequence according to the current priority list.

[0121] In the formula , and The specific value of is generally determined by those skilled in the art according to actual conditions. The technicians in this field collect multiple groups of sample data, set corresponding preset proportional coefficients for each group of sample data, substitute the preset proportional coefficients and the collected sample data into the formula, observe the accuracy of the model output and the rationality of the results through repeated experiments and parameter adjustments, gradually adjust these factor coefficients, and compare the performance and effect of the model under different parameter settings to find the optimal coefficient combination, screen the calculated factor coefficients and take the average, and obtain , and The value of .

[0122] In addition, the size of the preset factor coefficient is to quantify each parameter to obtain a specific value. In order to facilitate subsequent comparison, the size of the coefficient depends on the amount of sample data and the preset proportional coefficient initially set by technical personnel in this field for each set of sample data. It is not unique as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0123] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0124] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0125] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0126] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0127] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A logistics transportation method based on drones, characterized in that: The specific steps include: Step 1: Collect the flight data of the drone in real time, determine the target area to be delivered, and number the target areas. , collect meteorological data of the target delivery area, collect geographic information data of the target delivery area; Step 2: Construct a distance matrix , calculate the delivery distance between each area, and generate the condition index of each delivery target area by combining the traffic flow, expected delivery time and cargo load of the area; Step 3: Based on the collected real-time meteorological data, after dimensionless processing, a meteorological assessment model is established to generate a meteorological assessment index. Based on the collected flight data, after dimensionless processing, a flight assessment model is established to generate a flight assessment index; Step 4: Combine the condition index, meteorological assessment index and flight assessment index to generate a regional comprehensive assessment model. Use the analytic hierarchy process to generate the weights in the regional comprehensive assessment model. Use the regional comprehensive assessment model to generate a comprehensive score for each target area. Based on the comprehensive score of each area, a priority list is generated from high to low. The drones carry out logistics transportation in order according to the current priority list. The real-time meteorological data collected is processed dimensionlessly and correlation analysis is performed to generate the regional Meteorological Assessment Index , specifically including: The real-time temperature collected Compare with the preset temperature threshold, if it exceeds the threshold, calculate the real-time temperature The difference between the temperature threshold ; in, For Region The meteorological assessment index, Real-time temperature The difference between the temperature threshold, is the rainfall, is the wind speed, is the second constant correction exponent; The collected flight data is processed dimensionlessly and correlation analysis is performed to generate the region Flight Evaluation Index , specifically: The real-time flight altitude collected Compare with the preset height threshold, if it exceeds the threshold, calculate the real-time height The difference between the height threshold ; in, For Region Flight evaluation index, is the real-time altitude The difference between the height threshold , is the wind speed, is the current battery power of the drone, is the maximum payload of the drone, for The preset scaling factor of greater than zero, is the third constant correction exponent; When numbering the target areas, the target areas are numbered as follows: , Indicates the total number of target areas that need to be delivered. The meteorological data includes the temperature of the target area. , precipitation and wind speed ; The specific process of collecting meteorological data of the target area is: using the meteorological API to obtain the temperature of the target area every hour , rainfall and wind speed ; Among them, temperature The unit is degrees Celsius, rainfall The unit is millimeter, wind speed The unit is meters per second; The flight data includes the drone’s real-time battery level , Flight altitude , Flight speed , Maximum load ; The specific process of collecting flight data is as follows: using the GPS module on the drone to collect battery power in real time , Flight altitude and flight speed , and collect the maximum load of the drone based on the parameters of the drone ; Other relevant data of the target area include traffic flow in each target delivery area , longitude and latitude coordinates , the regional cargo demand , expected delivery time for the region ; The specific process of collecting relevant data in the target area is as follows: deploy sensors in the target distribution area, and collect traffic flow in the target area in combination with data provided by the traffic control department. ; Collect cargo demand according to customer needs and expected delivery time ; The distance matrix is ​​constructed The process includes: Create a distance matrix , the size is , Represents the total number of target areas that need to be delivered, where Indicates area To area distance; The distance between each pair of regions is calculated using the Haversine formula, based on the following formula: in, Indicates area To area The distance represents the radius of the Earth, and Respectively, the regions and Region The latitude and longitude of and is the difference in latitude and longitude between two points; Store the calculated distances in the distance matrix In, and , to ensure that the distance from the region to itself is zero; Generate Condition Index The process is based on the following formula: in, It is a region The condition index, From the starting point to the area The distance For Region Expected delivery time, It is a region The demand for goods, for The preset scaling factor, For Region traffic flow, for The preset scaling factor of , is the first constant correction exponent; The condition index, meteorological assessment index and flight assessment index are combined to generate a regional comprehensive assessment model, and the regional comprehensive assessment model is used to generate a comprehensive score for each current target area. , the formula is as follows: in, It is a region The overall rating of It is a region The condition index, For Region The meteorological assessment index, For Region Flight evaluation index, , and are the weights of condition index, meteorological assessment index and flight assessment index, respectively. is the fourth constant correction exponent; The above regional comprehensive evaluation model is used to generate the comprehensive score of each current target area. , , …, , and based on the comprehensive score of each area, a priority list is generated from high to low, and drones carry out logistics transportation in turn according to the current priority list; The specific logic of generating weights in the regional comprehensive assessment model through the analytic hierarchy process is as follows: The three indicators of condition index, meteorological assessment index and flight assessment index are marked, and the relative importance between them is determined by the nine-scale method to construct a judgment matrix, in which the condition index is marked as 1, the meteorological assessment index is marked as 2, and the flight assessment index is marked as 3. The constructed judgment matrix is: in, , The sign indicating the index, Indicator For indicators The importance of , ; Each element in the judgment matrix is ​​normalized, and the specific formula of the normalization process is: in, for Normalized value; The weight value of each indicator is calculated based on the value of each element in the judgment matrix after normalization. The specific formula is as follows: in, For indicators The weight value of The weights of the condition index, meteorological assessment index and flight assessment index are calculated based on the following formula: in, represents the importance of the normalized condition index relative to index j, Represents the normalized meteorological assessment index relative to the index The importance of Represents the normalized flight evaluation index relative to the index The importance of.

2. A logistics transportation system based on drones, characterized by: The drone-based logistics transportation system is used to execute the drone-based logistics transportation method according to claim 1, comprising: The data collection module is used to collect the flight data of the drone in real time, determine the target area to be delivered, and number them respectively. , collect meteorological data of the target delivery area, collect geographic information data of the target delivery area; Conditional index generation module for constructing distance matrix , calculate the delivery distance between each area, and generate the condition index of each delivery target area by combining the traffic flow, expected delivery time and cargo load of the area; The evaluation index generation module is used to establish a meteorological evaluation model and generate a meteorological evaluation index after dimensionless processing based on the collected real-time meteorological data, and to establish a flight evaluation model and generate a flight evaluation index after dimensionless processing based on the collected flight data; The intelligent decision-making module is used to combine the condition index, meteorological assessment index and flight assessment index to generate a regional comprehensive assessment model, generate the weights in the regional comprehensive assessment model through the hierarchical analysis method, and use the regional comprehensive assessment model to generate the comprehensive scores of the current target areas. According to the comprehensive score of each area, a priority list is generated from high to low, and the drones carry out logistics transportation in sequence according to the current priority list.

Images