Driving path optimization system for heavy truck road

By collecting and analyzing heavy truck data, road data and weather data in the driving path optimization system of heavy truck roads, screening road status and optimizing driving time, the driving safety problems caused by weather factors in the existing technology are solved, and transportation is improved Safety and logistics efficiency.

CN119005470APending Publication Date: 2024-11-22ZHONGWEI WUCHUANG INTELLIGENT TECH (SHANGHAI) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411109201.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-13
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

The prior art fails to consider the impact of weather on the driving path of heavy truck vehicles, resulting in possible driving safety issues.

Method used

A driving path optimization system for heavy truck vehicles is designed, including data collection module, path selection module and path optimization module. By collecting heavy truck data, road data and weather data, screening road status, predicting driving time, and optimizing according to weather conditions Driving time.

Benefits of technology

It effectively avoids the risk of traffic accidents caused by bad weather, improves transportation safety and logistics efficiency, reduces operating costs, and ensures drivers' driving safety.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119005470A_ABST
    Figure CN119005470A_ABST
Patent Text Reader

Abstract

The invention discloses a driving path optimization system for a heavy truck road, relates to the technical field of road planning optimization, and solves the technical problem that the driving safety problem may occur due to the fact that the influence of weather on driving is not considered in the prior art. According to the method, the vehicle heavy truck data, the road data and the weather data are collected, the roads are screened according to the heavy truck data and the road data, the road state is obtained by comparing the corresponding sub-data, and the roads are preliminarily screened according to the road state to obtain the pre-selected roads; the predicted driving time of the roads is obtained by combining the passing duration of the speed-limiting road section and the passing duration of the congested road section, and the roads are screened according to the predicted driving time to obtain a driving path; and obtaining the predicted transportation arrival time according to the predicted driving time, comparing the weather data in the transportation period with a preset threshold range, and optimizing and changing the departure time according to a comparison result.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the field of route optimization and relates to big data technology, and specifically is a driving route optimization system for heavy trucks. Background Art

[0002] With the rapid development of the logistics industry, heavy-duty trucks, as one of the main means of road transportation, play a vital role in cargo distribution and long-distance transportation. However, due to the characteristics of heavy-duty trucks, such as their larger body, higher load capacity and special requirements for road conditions, they face a series of challenges in actual operation, including but not limited to road weight and height restrictions, complex and changeable road conditions, weather conditions, and the contradiction between growing transportation demand and cost control.

[0003] The invention patent with application number CN2020101726779 discloses a road inspection vehicle driving path planning system and method. The invention detects the vehicle position and the target area road network data, adds a road planning plan according to the target area road network data, and sets road nodes for connection to obtain the optimal driving path for the vehicle; when obtaining the driving path, the invention does not take into account the impact of weather on driving, and optimizes the driving path, which may cause driving safety problems due to the vehicle continuing to drive in bad weather.

[0004] The present invention provides a heavy truck driving path optimization system to solve the above technical problems. Summary of the Invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes a driving path optimization system for heavy trucks on roads, which is used to solve the technical problem that the prior art does not take into account the impact of weather on driving, which may lead to driving safety problems.

[0006] To achieve the above-mentioned object, a first aspect of the present invention provides a heavy truck driving route optimization system, comprising: a database, a data collection module, a route selection module and a route optimization module;

[0007] Data collection module: used to collect heavy truck data, road data and weather data;

[0008] Path selection module: used to filter and obtain the driving path based on heavy truck data and road data;

[0009] Route optimization module: used to optimize the driving route and select the driving time based on weather data.

[0010] Preferably, the step of obtaining the driving route by screening the heavy truck data and the road data includes:

[0011] Extract heavy truck data and road data; the heavy truck data includes vehicle weight, vehicle height, driving speed, and transported cargo type; the road data includes road length, road height limit, road weight limit, road transport type, speed limit section, and traffic volume;

[0012] Determine whether the vehicle weight exceeds the road weight limit; if yes, mark the weight status of the corresponding road as abnormal; if no, mark the weight status of the corresponding road as normal;

[0013] Determine whether the vehicle height is greater than the road height limit; if yes, mark the corresponding road height status as abnormal; if no, mark the corresponding road height status as normal;

[0014] Determine whether the road transport type includes the transport cargo type; if yes, mark the cargo status of the corresponding road as normal; if not, mark the cargo status of the corresponding road as abnormal;

[0015] The weight status, height status and cargo status are combined to obtain the road status, and the roads without abnormal status are marked as pre-selected roads;

[0016] The predicted travel time of the pre-selected roads is calculated based on the traffic volume, driving speed, road length, speed limit of the restricted section, and length of the restricted section; the pre-selected roads are sorted from small to large according to the predicted travel time, and the pre-selected road with the highest ranking is marked as the travel route.

[0017] Preferably, the predicted travel time of the preselected road is calculated based on the traffic volume, travel speed, road length, speed limit of the restricted road section, and length of the restricted road section, including:

[0018] Extract traffic volume, driving speed, speed limit, road length and restricted road section length;

[0019] The speed limit is marked as ZVp, the restricted road section length is marked as ZLp, and the vehicle's driving speed is marked as DV; determine whether the driving speed is greater than the speed limit of the speed-limited section; if so, the vehicle must travel at the speed limit in the speed-limited section, and the speed-limited section travel time XZTp of the speed-limited section numbered as speed-limited section p is calculated using the formula XZTp=ZLp / ZVp; if not, the vehicle does not need to slow down to pass the speed-limited section, and the speed-limited section travel time XZTp of the speed-limited section numbered as speed-limited section p is calculated using the formula XZTp=ZLp / DV; where p represents the number of the speed-limited section in the pre-selected road, and p=1, 2, 3…n, where n is a positive integer;

[0020] The estimated arrival time is calculated based on the vehicle speed and the distance traveled to the congested section; the estimated time to pass the congested section is calculated based on the traffic volume and the estimated arrival time;

[0021] The road length is marked as DLi, the estimated travel time is marked as YTq, and the length of the congested section is marked as YLq; where q represents the number of the congested section on the road, q = 1, 2, 3...m, where m is a positive integer; i represents the number of the road, i = 1, 2, 3...b, where b is a positive integer;

[0022] By formula The predicted travel time YCTi of road numbered i is calculated.

[0023] Preferably, the estimated arrival time is calculated based on the vehicle's travel speed and the travel distance to the congested road section, including:

[0024] Extract vehicle speed, travel distance to congested road section and current time;

[0025] The driving length to reach the congested road section is marked as YDLq, the number of congested road sections between the congested road sections is marked as x, and the number of speed limit sections is marked as y;

[0026] By formula Calculate the arrival time YJTq at the congested road section; where 0≤x≤q, 0≤y≤p;

[0027] Add the current time to the arrival time to get the estimated arrival time.

[0028] Preferably, obtaining the estimated passing time of the congested road section according to the traffic volume and the estimated arrival time includes:

[0029] Extract the traffic volume and estimated arrival time of the congested road section; extract the historical traffic volume and historical arrival time of the congested road section from the database;

[0030] The historical traffic volume, historical arrival time and corresponding historical passing time of the congested road section are used as training data and test data. The neural network model is trained using the training data, and the trained neural network model is tested using the test data. The parameters of the neural network model are adjusted according to the test results to obtain a passing time prediction model with the input data of arrival time, congested road section and traffic volume and the output data of corresponding passing time.

[0031] The traffic volume and corresponding time of the congested section of the road are input into the through time prediction model to obtain the estimated through time.

[0032] Preferably, the optimizing the driving route and selecting the driving time based on weather data includes:

[0033] S1: extracting weather data; the weather data includes rainfall forecast, severe weather forecast, temperature, humidity and wind speed;

[0034] S2: Add the current time to the predicted travel time to obtain the predicted transport arrival time; determine whether there is bad weather between the current time and the predicted transport arrival time; if so, delay the transport; if not, jump to S3;

[0035] S3: Set a rainfall threshold; determine whether the rainfall between the current time and the predicted transport arrival time is greater than the rainfall threshold; if so, delay the transport; if not, jump to S4; the rainfall threshold is set according to the rainfall when the vehicle can travel normally;

[0036] S4: Setting a comfortable weather range; the comfortable weather range includes a comfortable temperature range, a comfortable humidity range, and a comfortable wind speed range; the comfortable weather range is set according to the weather during normal driving;

[0037] Determine whether the temperature meets the comfortable temperature range; if yes, mark the temperature state as comfortable; if not, mark the temperature state as uncomfortable;

[0038] Determine whether the humidity meets the comfortable humidity range; if yes, mark the humidity state as comfortable; if not, mark the humidity state as uncomfortable;

[0039] Determine whether the wind speed meets the comfortable wind speed range; if yes, mark the wind speed state as comfortable; if not, mark the wind speed state as uncomfortable;

[0040] Combining the temperature state, humidity state and wind speed state to obtain the weather state;

[0041] If the weather conditions at the current time are not compatible with the predicted arrival time, transportation will be delayed and a time that does not include the unfavorable conditions will be selected for transportation.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] 1. The present invention collects heavy truck data, road data, and weather data, and screens driving routes based on the road data and heavy truck data. The weight limit, height limit, and transportation type in the road data are compared with the corresponding sub-data in the heavy truck data to obtain the road status. The roads are preliminarily screened based on the road status to prevent overloaded or unsuitable vehicles from entering unsuitable roads, reduce accident risks, and improve transportation efficiency. Based on the data of speed-limited sections and congested sections in the road data, the passing time of speed-limited sections and the passing time of congested sections are respectively calculated, and planning is carried out in advance to avoid driving in high-risk time periods or sections, thereby improving transportation safety and avoiding unnecessary waiting. and detours, saving fuel and reducing operating costs; the predicted driving time of the road is obtained by combining the passing time of the speed-limited section and the passing time of the congested section, and the driving route is obtained by screening the roads according to the predicted driving time, which helps drivers and logistics companies make more informed decisions, thereby improving economic benefits and ensuring driving safety; the weather data during transportation is compared with the preset threshold range, and the departure time is optimized and changed according to the comparison results, which can significantly reduce the risk of traffic accidents caused by severe weather conditions, reduce the impact of the environment on vehicle performance, reduce transportation time, improve logistics efficiency, and ensure driving safety.

[0044] 2. The present invention predicts the estimated time to pass through speed-limited sections and congested sections of the road. Knowing the estimated time to pass through congested sections can help drivers prepare themselves mentally and improve traffic safety. Based on the predicted time, they can choose the fastest or most economical route to avoid severely congested areas, saving time and costs. Avoiding unnecessary congestion can reduce the time vehicles spend idling, thereby reducing fuel consumption and exhaust emissions, and having a positive impact on environmental protection. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0046] Figure 1 The following is a flowchart of an embodiment of the present invention.

[0047] Figure 2 It is a system composition diagram of the present invention.

[0048] Figure 3 The following is a complete flowchart for obtaining road status in one embodiment of the present invention.

[0049] Figure 4The following is a complete flow chart for obtaining weather conditions in one embodiment of the present invention. DETAILED DESCRIPTION

[0050] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0051] See also Figures 1-4 , a first embodiment of the present invention provides a heavy truck road driving path optimization system, including: a database, a data collection module, a path selection module and a path optimization module;

[0052] Data collection module: used to collect heavy truck data, road data and weather data.

[0053] For example, in this embodiment, a heavy truck needs to transport 15 tons of steel from City A to City B. The heavy truck weighs 5 tons, has a vehicle height of 4 meters, and a travel speed of 80 km / h. There are three road options, namely Road 1, which is 215 kilometers long, has a height limit of 5 meters, a weight limit of 30 tons, and can transport ordinary goods and material goods, including 3 speed-limited sections and 2 congested sections; Road 2 is 234 kilometers long, has a height limit of 4.5 meters, a weight limit of 28 tons, and can transport ordinary goods and material goods, including 1 speed-limited section and 2 congested sections; Road 3 is 220 kilometers long, has a height limit of 5 meters, a weight limit of 30 tons, and can transport ordinary goods and material goods, including 2 speed-limited sections and 1 congested section; the historical expected passing time of each congested section of the three roads in different time periods and different traffic volumes is extracted from the database; future rainfall forecast, severe weather forecast, temperature, humidity and wind speed are collected through weather forecasts.

[0054] It is understandable that the order of speed-limited sections and congested sections on each road is set based on actual conditions. The traffic volume on congested sections is different at each time point every day. The current passing time can be roughly predicted based on the time points and traffic volume in historical data.

[0055] Path selection module: used to filter and obtain the driving path based on heavy truck data and road data.

[0056] For example, it is determined whether the vehicle weight is greater than the road weight limit, and the weight status of Road 1, Road 2 and Road 3 is normal; it is further determined whether the vehicle height is greater than the road height limit, and the height status of Road 1, Road 2 and Road 3 is normal; it is further determined whether the road transport type includes the transport cargo type, and the cargo status of Road 1, Road 2 and Road 3 is normal; the pre-selected roads are Road 1, Road 2 and Road 3.

[0057] The three speed limit sections in the pre-selected road 1 are speed limit section 1, speed limit section 2 and speed limit section 3. The speed limit of speed limit section 1 is 60 kilometers per hour and the section length is 15 kilometers. The speed limit of speed limit section 2 is 70 kilometers per hour and the section length is 10 kilometers. The speed limit of speed limit section 3 is 90 kilometers per hour and the section length is 20 kilometers. It is judged whether the driving speed of the heavy truck is greater than the speed limit of the speed limit section. If the driving speed of the heavy truck is greater than the speed limit of speed limit section 1 and speed limit section 2, then the heavy truck is in the speed limit section. The heavy truck needs to slow down to the speed limit in speed limit section one and speed limit section two; the driving time XZT1 of the heavy truck in speed limit section one is calculated to be 0.25 hours, and the driving time XZT2 of the heavy truck in speed limit section two is calculated to be 0.14 hours; if the driving speed of the heavy truck is lower than the speed limit of speed limit section three, the heavy truck will travel at the driving speed in speed limit section three; the driving time XZT3 of the heavy truck in speed limit section three is calculated to be 0.22 hours through the formula XZTp = ZLp / DV.

[0058] Pre-selected road two includes one speed-limited section with a speed limit of 85 kilometers per hour and a section length of 20 kilometers. It is determined whether the heavy truck's speed is greater than the speed limit of the speed-limited section. If the heavy truck's speed is less than the speed limits of speed-limited sections one and two, the heavy truck travels at the speed limit within the speed-limited section. The driving time XZT1 of the heavy truck in the speed-limited section is calculated using the formula XZTp=ZLp / DV to obtain 0.24 hours.

[0059] The pre-selected road three includes two speed-limited sections. It is determined that the heavy truck travels for a time XZT1 = 0.3 hours in the speed-limited section one and a time XZT2 = 0.2 hours in the speed-limited section two.

[0060] The driving distance to the first congested section in the pre-selected road 1 is 120 kilometers, and it passes through the speed limit section 1 in the middle. The speed limit section is 5 kilometers long. The current time is 8:00 am. According to the formula The calculated arrival time at the congested road section 1 is YJT1=1.56 hours, so the estimated arrival time at the congested road section 1 is 9:33.

[0061] Extract the historical traffic volume and historical arrival time of the congested road section from the database;

[0062] The historical traffic volume, historical arrival time and corresponding historical passing time of the congested road section are used as training data and test data. The training data is used to train the neural network model, and the test data is used to test the trained neural network model. The parameters of the neural network model are adjusted according to the test results to obtain a passing time prediction model with the input data being the arrival time, congested road section and traffic volume, and the output data being the corresponding passing time.

[0063] The traffic volume at this time is 5 vehicles per minute. The estimated arrival time of 9:33 and the traffic volume of 5 vehicles per minute are input into the through time prediction model, and the estimated passing time is 17 minutes. The time after passing the speed limit section is predicted to be 9:50. Then, after 50 kilometers, it arrives at the congested section 2. The time at this time is 10:28. The traffic volume of the congested section 2 is 7 vehicles per minute and the length is 5 kilometers. The input into the through time prediction model gives an estimated passing time of 22 minutes.

[0064] By formula The predicted driving time for pre-selected road one, YCT1, is calculated to be 3.29 hours, the predicted driving time for pre-selected road two, YCT2, is calculated to be 3.34 hours, and the predicted driving time for pre-selected road three, YCT3, is calculated to be 3.12 hours. The pre-selected roads are sorted according to the size of the predicted driving time, and pre-selected road three with the smallest ranking is marked as the driving path.

[0065] Route optimization module: used to optimize the driving route and select the driving time based on weather data.

[0066] For example, in this embodiment, the rainfall threshold is set to 40 mm of rainfall in 24 hours, the comfortable temperature range is set to 10 degrees to 30 degrees, the comfortable humidity range is 30% to 65%, and the comfortable wind speed range is 5 meters per second to 18 meters per second; it is judged whether there is bad weather between the current time and the predicted transportation arrival time. If it is judged that there is no bad weather between the current time and the predicted transportation arrival time, it is further judged whether the rainfall between the current time and the predicted transportation arrival time is greater than the rainfall threshold. If it is judged that the rainfall between the current time and the predicted transportation arrival time is less than the rainfall threshold; the current temperature is 18 degrees, the humidity is 35%, and the wind speed is 5 meters per second, judge whether the temperature meets the comfortable temperature range, and if it is, mark the temperature state as comfortable; judge whether the humidity meets the comfortable humidity range, and if it is, mark the humidity state as comfortable; judge whether the wind speed meets the comfortable wind speed range, and if it is, mark the wind speed state as comfortable; the weather state at the current time does not contain an uncomfortable state; judge whether the weather state at the current time and the predicted transport arrival time include an uncomfortable state, and if it is judged that it does not include an uncomfortable state, the heavy truck can immediately set off along Road Three.

[0067] It should be noted that the weather will also affect the actual driving speed of heavy trucks. When it rains or snows, the ground is slippery and needs to be driven at a low speed. The driving speed of heavy trucks and the speed limit in the speed limit area will also change due to changes in weather.

[0068] Some of the data in the above formula are calculated by removing the dimensions and taking their numerical values. The formula is a formula that is closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0069] Working principle of the present invention:

[0070] The present invention collects vehicle and heavy truck data, road data and weather data, screens roads according to the heavy truck data and road data, obtains road status by comparing corresponding sub-data, and preliminarily screens roads according to the road status to obtain pre-selected roads, predicts the predicted driving time of heavy trucks on each pre-selected road based on the road data of restricted sections and congested sections in the road data, sorts and screens the pre-selected roads according to the predicted driving time to obtain a driving route; obtains a predicted transportation arrival time according to the predicted driving time, compares weather data during transportation with a preset threshold range to obtain weather status, and optimizes the departure time of the heavy truck according to the weather status and the comparison result.

[0071] The above embodiments are only used to illustrate the technical method of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A heavy truck driving route optimization system, characterized in that: include: Database, data collection module, path selection module and path optimization module; Data collection module: used to collect heavy truck data, road data and weather data; Path selection module: used to filter and obtain the driving path based on heavy truck data and road data; Route optimization module: used to optimize the driving route and select the driving time based on weather data.

2. A heavy truck driving path optimization system according to claim 1, characterized in that: The step of obtaining the driving route by screening the heavy truck data and the road data includes: Extracting heavy truck data and road data; the heavy truck data includes vehicle weight, vehicle height, driving speed, and type of transported goods; the road data includes road length, road height limit, road weight limit, road transport type, speed limit section, and traffic volume; Determine whether the vehicle weight is greater than the road weight limit; if yes, mark the weight status of the corresponding road as abnormal; if no, mark the weight status of the corresponding road as normal; Determine whether the vehicle height is greater than the road height limit; if yes, mark the height state of the corresponding road as abnormal; if no, mark the height state of the corresponding road as normal; Determine whether the road transport type includes the transport cargo type; if yes, mark the cargo status of the corresponding road as normal; if no, mark the cargo status of the corresponding road as abnormal; The weight status, the height status and the cargo status are combined to obtain the road status, and the roads without abnormal status are marked as pre-selected roads; The predicted travel time of the pre-selected roads is calculated based on the traffic volume, driving speed, road length, speed limit of restricted sections and length of restricted sections; the pre-selected roads are sorted from small to large according to the predicted travel time, and the pre-selected road with the highest ranking is marked as the travel route.

3. A heavy truck driving path optimization system according to claim 2, characterized in that: The predicted travel time of the pre-selected road is calculated based on the traffic volume, the travel speed, the road length, the speed limit of the restricted road section and the length of the restricted road section, including: Extract traffic volume, driving speed, speed limit, road length and restricted road section length; The speed limit is marked as ZVp, the length of the restricted road section is marked as ZLp, and the driving speed of the vehicle is marked as DV; determine whether the driving speed is greater than the speed limit of the speed limit section; if yes, the vehicle needs to travel at the speed limit in the speed limit section, and the speed limit section travel time XZTp of the speed limit section numbered as p is calculated by the formula XZTp=ZLp / ZVp; if no, the vehicle does not need to slow down to pass the speed limit section, and the speed limit section travel time XZTp of the speed limit section numbered as p is calculated by the formula XZTp=ZLp / DV; wherein p represents the number of the speed limit section in the pre-selected road, p=1, 2, 3…n, and n is a positive integer; The estimated arrival time is calculated based on the vehicle speed and the travel distance to the congested section; the estimated passing time of the congested section is calculated based on the traffic volume and the estimated arrival time; The road length is marked as DLi, the estimated passing time is marked as YTq, and the length of the congested section is marked as YLq; wherein q represents the number of the congested section in the road, q=1, 2, 3...m, m is a positive integer; i represents the number of the road, i=1, 2, 3...b, b is a positive integer; By formula The predicted travel time YCTi of the pre-selected road numbered i is calculated.

4. A heavy truck driving path optimization system according to claim 3, characterized in that: The estimated arrival time is calculated based on the vehicle's travel speed and the travel distance to the congested road section, including: Extract vehicle speed, travel distance to congested road section and current time; The driving length to reach the congested road section is marked as YDLq, the number of congested roads between the congested roads is marked as x, and the number of speed limit roads is marked as y; By formula The arrival time YJTq at the congested road section is calculated; where 0≤x≤q, 0≤y≤p; Add the current time to the arrival time to get the estimated arrival time.

5. The heavy truck driving path optimization system according to claim 3 is characterized in that: The estimated passing time of the congested road section is obtained according to the traffic volume and the estimated arrival time, including: Extract the traffic volume and estimated arrival time of the congested road section; extract the historical traffic volume and historical arrival time of the congested road section from the database; The historical traffic volume, historical arrival time and corresponding historical passing time of the congested road section are used as training data and test data, the neural network model is trained using the training data, and the trained neural network model is tested using the test data. The parameters of the neural network model are adjusted according to the test results to obtain a passing time prediction model whose input data is the arrival time, congested road section and traffic volume, and whose output data is the corresponding passing time. The traffic volume and corresponding time of the congested section of the road are input into the through time prediction model to obtain the estimated through time.

6. A heavy truck driving path optimization system according to claim 1, characterized in that: The step of optimizing the driving route and selecting the driving time based on the weather data includes: S1: extracting weather data; the weather data includes rainfall forecast, severe weather forecast, temperature, humidity and wind speed; S2: Add the current time to the predicted travel time to get the predicted transportation arrival time; determine whether there is bad weather between the current time and the predicted transportation arrival time; if yes, delay the transportation; if no, jump to S3; S3: Set the rainfall threshold; determine whether the rainfall between the current time and the predicted transportation arrival time is greater than the rainfall threshold; if yes, delay the transportation; if no, jump to S4; S4: Setting a comfortable weather range; the comfortable weather range includes a comfortable temperature range, a comfortable humidity range and a comfortable wind speed range; Determine whether the temperature meets the comfortable temperature range; if yes, mark the temperature state as a comfortable state; if no, mark the temperature state as an uncomfortable state; Determine whether the humidity meets the comfortable humidity range; if yes, mark the humidity state as a comfortable state; if no, mark the humidity state as an uncomfortable state; Determine whether the wind speed meets the comfortable wind speed range; if yes, mark the wind speed state as a comfortable state; if no, mark the wind speed state as an uncomfortable state; The temperature state, humidity state and wind speed state are combined to obtain the weather state; If the weather conditions at the current time and the predicted arrival time are not compatible, transportation will be delayed and a time that does not include the uncomfortability will be selected for transportation.