Real-time alighting point recommendation method, device, computer equipment and storage medium

By collecting user historical order data and real-time traffic information, genetic algorithms are used to screen out the drop-off point that arrives at the destination at the shortest time, solving the problem of time waste caused by road congestion in the online car-hailing industry and improving the efficiency of users and drivers.

CN118366303BActive Publication Date: 2024-11-19BEIJING BAILONG MAYUN TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410499203.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-04-24
Publication Date
2024-11-19
Estimated Expiration
2044-04-24

AI Technical Summary

Technical Problem

In the online car-hailing industry, when the user's destination is located on a road with narrow width and many intersections, drivers are prone to scratches, collisions and congestion due to complex road conditions, resulting in wasted time. The existing method of modifying the exit point is not efficient enough and cannot Meet the urgent needs of users and affect the driver's single utilization rate.

Method used

By collecting users' historical order data, the average pace speed is calculated, and a congestion index is generated based on real-time traffic and road conditions information. The genetic algorithm is used to filter out the alternative drop-off point and driving path with the shortest total time, and provide personalized recommendations.

Benefits of technology

It realizes the shortest time to arrive at the destination when roads are congested, improves system applicability, meets users' urgent needs, and improves drivers' single-use efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118366303B_ABST
    Figure CN118366303B_ABST
Patent Text Reader

Abstract

The present invention provides a real-time alighting point recommendation method, device, computer equipment and storage medium, and relates to the technical field of alighting point recommendation methods for online car-hailing. The present invention understands the user's average walking speed by collecting the user's historical order information, and can predict the congestion of the road where the user's preset alighting point is located, and generates different alternative alighting points and driving routes according to whether the road is congested, and selects the alternative alighting points according to the user's average walking speed. The plan with the shortest total time required to reach the preset alighting point, thereby realizing personalized recommendations for different users, enabling users to reach their destination in the shortest time, and being more in line with the user's actual needs when the user is pressed for time, thereby improving the applicability of the system.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of methods for recommending alighting points for online ride-hailing services, and in particular to a real-time alighting point recommendation method, device, computer equipment and storage medium. Background Art

[0002] In the online car-hailing industry, when the user's destination is on a narrow road with many intersections, due to the complex road conditions, the driver is more likely to have accidents such as scratches and collisions on the road, wasting the user's time. And this kind of road is also more prone to congestion, and the movement speed of the vehicle is not even as fast as the user's walking speed. Under the premise that the user is in a hurry and is willing to get off at other drop-off points and walk a distance, other drop-off points close to the destination can be recommended to the user to meet the user's actual needs. However, in actual applications, usually when the vehicle is already stuck on the road, the user manually modifies the drop-off point or the system automatically modifies the drop-off point, and then walks to the destination by himself. This method not only wastes a lot of time and fails to meet the actual needs of users, but also makes it difficult for drivers to leave the vehicle and start the next order, resulting in low applicability of this method.

[0003] 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

[0004] The purpose of the present invention is to provide a real-time alighting point recommendation method, device, computer equipment and storage medium to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A real-time alighting point recommendation method, the specific steps comprising:

[0007] S1: Based on the user's historical orders, the starting distance and boarding time between the user's order starting point and the boarding point are collected to calculate the user's average walking speed;

[0008] S2: Based on the user's real-time order, the traffic flow information and road condition information of the road where the user's preset drop-off point is located are collected, and the congestion index of the road is generated according to the traffic flow information and road condition information;

[0009] S3: Compare the congestion index with a preset index threshold. If the congestion index is less than the preset index threshold, use the preset alighting point as the actual alighting point and the corresponding driving path as the first optimal path. If the congestion index is greater than or equal to the preset index threshold, execute step S4.

[0010] S4: Generate a predicted average vehicle speed according to the congestion index, and then generate a selection radius for screening candidate alighting points according to the predicted average vehicle speed and the average walking speed of the user, and set all road intersections within the selection radius as candidate alighting points with the preset alighting point as the center of the circle;

[0011] S5: Construct a fitness function with the shortest total time as a condition, use a genetic algorithm to generate a driving path for each alternative alighting point, and use the driving path and alternative alighting point with the highest fitness as the second optimal path and actual alighting point.

[0012] Preferably, the starting distance between the order starting point and the boarding point is calibrated as l i , the corresponding boarding time is calibrated as t i , average pace The calculation method is:

[0013]

[0014] In the formula, the subscript i represents the number of the historical order, i = 1, 2, 3,…, n.

[0015] Preferably, the traffic flow information includes historical traffic flow, predicted traffic flow, historical average vehicle speed, predicted average vehicle speed, and the road condition information includes road length, number of lanes, weather conditions, and construction conditions.

[0016] Preferably, the logic for generating the congestion index based on the traffic flow information and road condition information is:

[0017] The historical traffic volume and historical average speed of vehicles in the traffic flow information are divided according to the preset time interval t′, and an autoregressive moving average model is constructed to analyze the historical traffic volume to generate the predicted traffic volume after n times the time interval nt′;

[0018] The first priority coefficient and the second priority coefficient are generated according to the weather conditions and construction conditions respectively, and then the congestion index is jointly generated according to the predicted traffic volume, road length, number of lanes, the first priority coefficient and the second priority coefficient. The calculation method is:

[0019]

[0020] When the congestion index When , it is considered that the road where the preset drop-off point is located will be in a congested state after the time interval nt′;

[0021] Where μ1 and μ2 represent the first priority coefficient and the second priority coefficient respectively, L represents the road length, M represents the predicted traffic flow, and N represents the number of lanes. Indicates the preset index threshold.

[0022] Preferably, the weather conditions are divided into four categories: good, general, poor, and extremely poor. Good weather is sunny, general weather is cloudy, light rain, and light fog with visibility between 200m and 500m, poor weather is heavy rain, light snow, and moderate fog with visibility between 50m and 200m, and extremely poor weather is heavy rain, heavy snow, and dense fog with visibility below 50m.

[0023] When the weather condition is good, the first priority coefficient μ1=1;

[0024] When the weather condition is normal, the first priority coefficient μ1=2;

[0025] When the weather condition is bad, the first priority coefficient μ1=3;

[0026] When the weather condition is extremely bad, the first priority coefficient μ1=4;

[0027] The construction status is divided into unconstructed and under construction;

[0028] When the construction status is not under construction, the second priority coefficient μ2=0;

[0029] When the construction status is under construction, the second priority coefficient μ2=1.

[0030] Preferably, the logic of generating a predicted average vehicle speed according to the congestion coefficient, and then generating a selection radius according to the predicted average vehicle speed and the average walking speed of the user is:

[0031] Substituting several groups of historical traffic flows in turn for the predicted traffic flows into the calculation formula of the congestion coefficient, the congestion coefficients corresponding to several groups of time periods are generated;

[0032] A linear regression model is constructed based on the congestion coefficients and historical vehicle average speeds corresponding to several groups of time periods to generate a fitting curve between the congestion coefficient and the historical vehicle average speed. The congestion coefficient generated based on the predicted traffic flow is substituted into the fitting curve to obtain the corresponding predicted vehicle average speed.

[0033] The distance between the preset drop-off point and the corresponding road intersection in the first optimal path is calibrated as d, and the average speed of the vehicle is predicted according to the distance d. Calculate the vehicle congestion time T, According to the congestion time T and the average walking speed of the user Calculate the selection radius R,

[0034] A real-time alighting point recommendation device, the recommendation device is used to execute the above-mentioned recommendation method, comprising:

[0035] A first data collection module, which is in communication with the data processing module and is used to collect information on the starting distance, boarding time, starting point, boarding point, and preset alighting point contained in the user's historical orders and real-time orders;

[0036] A second data collection module, the second data collection module is in communication with the data processing module and is used to collect traffic flow information and road condition information of the road where the preset drop-off point is located;

[0037] A data processing module, wherein the data processing module is used to generate several groups of alternative alighting points according to the starting distance, boarding time, starting point, boarding point, preset alighting point, traffic information and road condition information, and use a genetic algorithm to select the driving path and alternative alighting points with the highest fitness as the final optimal path and actual alighting point.

[0038] A real-time alighting point recommendation computer device, the recommendation computer device comprising:

[0039] Storage media for storing computer programs;

[0040] A processor is used to execute the computer program to implement the above-mentioned recommended method.

[0041] A real-time alighting point recommendation storage medium is provided, wherein the storage medium is used to store a computer program, and the computer program implements the above-mentioned recommendation method when executed by a processor.

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

[0043] The present invention collects the user's historical order information to understand the user's average walking speed, and can predict the congestion of the road where the user's preset alighting point is located, generate different alternative alighting points and driving routes according to whether the road is congested, and select the alternative alighting points according to the user's average walking speed. The plan with the shortest total time required to reach the preset alighting point, thereby realizing personalized recommendations for different users, enabling users to reach their destination in the shortest time, and being more in line with the user's actual needs when the user is short on time, thereby improving the applicability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a schematic diagram of the overall method flow of the present invention;

[0045] Figure 2 It is a schematic diagram of the module structure of the present invention. DETAILED DESCRIPTION

[0046] 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.

[0047] 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.

[0048] Example:

[0049] See also Figure 1 , the present invention provides a technical solution:

[0050] A real-time alighting point recommendation method, the specific steps comprising:

[0051] S1: Based on the user's historical orders, collect the starting distance and boarding time between the user's order starting point and the boarding point, calculate the user's average walking speed, and calibrate the starting distance between the order starting point and the boarding point as l i , the corresponding boarding time is calibrated as t i , average pace The calculation method is:

[0052]

[0053] In the formula, the subscript i represents the number of the historical order, i=1,2,3,…,n. By calculating the user's average walking speed, we can understand the user's walking speed, which is convenient for personalized recommendation of other get-off points for users when the road is congested.

[0054] S2: Based on the user's real-time order, the traffic flow information and road condition information of the road where the user's preset get-off point is located are collected, and the congestion index of the road is generated based on the traffic flow information and road condition information. The traffic flow information includes historical traffic flow, predicted traffic flow, historical vehicle average speed, and predicted vehicle average speed. The road condition information includes road length, number of lanes, weather conditions, and construction conditions. The information on historical traffic flow, historical vehicle average speed, road length, and number of lanes can be collected through various map software, and the weather conditions and construction conditions can be obtained by online search on meteorological websites and municipal websites.

[0055] S3: Compare the congestion index with the preset index threshold. If the congestion index is less than the preset index threshold, the preset get-off point is used as the actual get-off point, and the corresponding driving path is used as the first optimal path. The first driving path is the recommended path when there is no congestion on the road. If the congestion index is greater than or equal to the preset index threshold, execute step S4.

[0056] S4: Generate a predicted average vehicle speed based on the congestion index, and then generate a selection radius for screening alternative alighting points based on the predicted average vehicle speed and the average walking speed of the user. With the preset alighting point as the center of the circle, all road intersections within the selection radius are set as alternative alighting points.

[0057] The road intersection selected here refers to other intersections on the road where the preset drop-off point is located. The movement trajectory of the vehicle to the drop-off point is mainly composed of two parts. The first part is from the boarding point to a certain intersection on the road where the drop-off point is located, and the second part is driving on the road and reaching the drop-off point from the intersection. Since when the road where the preset drop-off point is located is a complex road with a narrow width and many intersections, in order to reduce the driving time of the vehicle on the road, when the total time is the same, it is usually chosen to enter from the intersection closer to the preset drop-off point. For example, there are two intersections A and B near the drop-off point P, and the drop-off point P is closer to the intersection A. In plan 1, it takes 50 minutes for the vehicle to reach the intersection A from the boarding point and 10 minutes from the intersection A to the drop-off point P. In plan 2, it takes 40 minutes for the vehicle to reach the intersection B from the boarding point and 20 minutes from the intersection B to the drop-off point P. Then, although the total driving time is the same, the priority of plan 1 is also higher, and plan 1 is taken as the first optimal path.

[0058] S5: Construct a fitness function with the shortest total time as a condition, use a genetic algorithm to generate a driving path for each alternative alighting point, and use the driving path and alternative alighting point with the highest fitness as the second optimal path and actual alighting point.

[0059] Taking the above scheme as an example, when the road where the drop-off point P is located is congested, the driving time from intersection A or intersection B to the drop-off point P is greatly extended, even lower than the user's walking speed. If the user is in a hurry and is willing to accept the recommended drop-off point, then scheme one becomes that it takes 50 minutes for the vehicle to reach intersection A from the boarding point, and the user walks from intersection A to the drop-off point P. Similarly, scheme two becomes that it takes 40 minutes for the vehicle to reach intersection N from the boarding point, and the user walks from intersection B to the drop-off point P. Assuming that the time it takes for the user to walk from intersections A and B to the drop-off point P is 5 minutes and 10 minutes respectively, then the total time of scheme two is lower than that of scheme one, so intersection B is more recommended as the drop-off point rather than intersection A, and scheme two is the second best path. By determining whether the road where the drop-off point P is located is congested, and recommending different drop-off points and driving paths according to different determination results, personalized recommendations for different users can be achieved to better meet the actual needs of each user.

[0060] The logic of generating the congestion index based on traffic flow information and road condition information is:

[0061] The historical traffic volume and historical vehicle average speed in the traffic flow information are divided according to the preset time interval t′, and the autoregressive moving average model is constructed to analyze the historical traffic volume, and the predicted traffic volume after n times the time interval nt′ is generated. Then, the first priority coefficient and the second priority coefficient are generated according to the weather conditions and construction conditions respectively, and then the congestion index is jointly generated according to the predicted traffic volume, road length, number of lanes, the first priority coefficient, and the second priority coefficient. The calculation method is:

[0062]

[0063] When the congestion index When , it is considered that the road where the preset drop-off point is located will be in a congested state after the time interval nt′;

[0064] Where μ1 and μ2 represent the first priority coefficient and the second priority coefficient respectively, L represents the road length, M represents the predicted traffic flow, and N represents the number of lanes. Indicates the preset index threshold. The weather conditions are divided into four categories: good, general, poor, and extremely poor. Good weather refers to sunny days, general weather refers to cloudy days, light rain, and light fog with visibility between 200m and 500m, poor weather refers to heavy rain, light snow, and moderate fog with visibility between 50m and 200m, and extremely poor weather refers to heavy rain, heavy snow, and dense fog with visibility below 50m.

[0065] When the weather condition is good, the first priority coefficient μ1=1;

[0066] When the weather condition is normal, the first priority coefficient μ1=2;

[0067] When the weather condition is bad, the first priority coefficient μ1=3;

[0068] When the weather condition is extremely bad, the first priority coefficient μ1=4;

[0069] The construction status is divided into unconstructed and under construction;

[0070] When the construction status is not under construction, the second priority coefficient μ2=0;

[0071] When the construction status is under construction, the second priority coefficient μ2=1.

[0072] It is not difficult to see that the size of the congestion index is proportional to the traffic volume and inversely proportional to the road length and the number of lanes. The greater the traffic volume, the more likely congestion will occur. The longer the road length and the more lanes there are, the larger the road scale will be and the less likely congestion will occur. The first priority coefficient and the second priority coefficient are used for adjustment. Bad weather or road construction will increase the values ​​of the first priority coefficient and the second priority coefficient, which will cause the congestion index to increase sharply. This is reflected in real life, which means that congestion is more likely to occur. Correspondingly, when the weather is good and the road is not under construction, the first priority coefficient and the second priority coefficient will not affect the congestion index. The main factors causing road congestion are still traffic volume, road length and the number of lanes.

[0073] The logic of generating the predicted average vehicle speed based on the congestion coefficient and then generating the selection radius based on the predicted average vehicle speed and the user's average walking speed is as follows:

[0074] Substituting several groups of historical traffic flows in turn for the predicted traffic flows into the calculation formula of the congestion coefficient, the congestion coefficients corresponding to several groups of time periods are generated;

[0075] A linear regression model is constructed based on the congestion coefficients and historical vehicle average speeds corresponding to several groups of time periods to generate a fitting curve between the congestion coefficient and the historical vehicle average speed. The congestion coefficient generated based on the predicted traffic flow is substituted into the fitting curve to obtain the corresponding predicted vehicle average speed.

[0076] The distance between the preset drop-off point and the corresponding road intersection in the first optimal path is calibrated as d, and the average speed of the vehicle is predicted according to the distance d. Calculate the vehicle congestion time T, According to the congestion time T and the average walking speed of the user Calculate the selection radius R,

[0077] Still taking the above scheme as an example, when the road is not congested, the first optimal path is scheme 1, and the corresponding intersection is A. The distance between intersection A and the drop-off point P is a standard length d=1. Assuming that when the vehicle is congested on the road, the congestion time required to reach the drop-off point P from intersection A is T=20 minutes, then the user's average walking speed is The selected radius R=4, that is, four standard lengths. The actual meaning of the selected radius is equivalent to: when the road is congested, the time spent walking from any road intersection within the selected radius to the drop-off point P is less than the time spent driving from intersection A to the drop-off point P. Therefore, when the user urgently needs to walk a distance, all intersections within the selected radius can be used as alternative drop-off points, such as intersection A, intersection B, intersection C, intersection D... Naturally, each alternative drop-off point also corresponds to a different driving path and plan, such as plan 1, plan 2, plan 3, plan 4... After finding the plan with the shortest total time through the genetic algorithm, the driving path and alternative drop-off point corresponding to the plan are used as the second optimal path and actual drop-off point. In this embodiment, intersection B is used as the actual drop-off point, and driving from the boarding point to intersection B is used as the second optimal path to achieve the purpose of the shortest total time, so that the recommended actual drop-off point is more in line with user needs.

[0078] See also Figure 2 The present invention also provides a real-time alighting point recommendation device, which is used to execute the above-mentioned recommendation method, including:

[0079] A first data collection module, which is in communication with the data processing module and is used to collect information on the starting distance, boarding time, starting point, boarding point, and preset alighting point contained in the user's historical orders and real-time orders;

[0080] A second data collection module, the second data collection module is in communication with the data processing module and is used to collect traffic flow information and road condition information of the road where the preset drop-off point is located;

[0081] A data processing module, wherein the data processing module is used to generate several groups of alternative alighting points according to the starting distance, boarding time, starting point, boarding point, preset alighting point, traffic information and road condition information, and use a genetic algorithm to select the driving path and alternative alighting points with the highest fitness as the final optimal path and actual alighting point.

[0082] A real-time alighting point recommendation computer device, the recommendation computer device comprising:

[0083] Storage media for storing computer programs;

[0084] A processor is used to execute the computer program to implement the above-mentioned recommended method.

[0085] A real-time alighting point recommendation storage medium is provided, wherein the storage medium is used to store a computer program, and the computer program implements the above-mentioned recommendation method when executed by a processor.

[0086] 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.

[0087] 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.

[0088] 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.

[0089] 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 real-time alighting point recommendation method, characterized in that: The specific steps include: S1: Based on the user's historical orders, the starting distance and boarding time between the user's order starting point and the boarding point are collected to calculate the user's average walking speed; S2: Based on the user's real-time order, the traffic flow information and road condition information of the road where the user's preset drop-off point is located are collected, and the congestion index of the road is generated according to the traffic flow information and road condition information. The traffic flow information includes historical traffic flow, predicted traffic flow, historical average vehicle speed, and predicted average vehicle speed. The road condition information includes road length, number of lanes, weather conditions, and construction conditions. The logic of generating the congestion index based on traffic flow information and road condition information is: The historical traffic volume and historical vehicle average speed in the traffic flow information are recorded at preset time intervals. Divide and construct an autoregressive moving average model to analyze historical traffic flow and generate Times the time interval The predicted traffic volume after The first priority coefficient and the second priority coefficient are generated according to the weather conditions and construction conditions respectively, and then the congestion index is jointly generated according to the predicted traffic volume, road length, number of lanes, the first priority coefficient and the second priority coefficient. , calculated as: When the congestion index When the preset drop-off point is located on a road within the time interval It will be in congestion later; In the formula , Represent the first priority coefficient and the second priority coefficient respectively, represents the length of the road, represents the predicted traffic flow, represents the number of lanes, Indicates the preset index threshold; S3: Compare the congestion index with a preset index threshold. If the congestion index is less than the preset index threshold, use the preset alighting point as the actual alighting point and the corresponding driving path as the first optimal path. If the congestion index is greater than or equal to the preset index threshold, execute step S4. S4: Generate a predicted average vehicle speed according to the congestion index, and then generate a selection radius for screening candidate alighting points according to the predicted average vehicle speed and the average walking speed of the user, and set all road intersections within the selection radius as candidate alighting points with the preset alighting point as the center of the circle; The logic of generating the predicted average vehicle speed based on the congestion coefficient and then generating the selection radius based on the predicted average vehicle speed and the user's average walking speed is as follows: Substituting several groups of historical traffic flows in turn for the predicted traffic flows into the calculation formula of the congestion coefficient, the congestion coefficients corresponding to several groups of time periods are generated; A linear regression model is constructed based on the congestion coefficients and historical vehicle average speeds corresponding to several groups of time periods to generate a fitting curve between the congestion coefficient and the historical vehicle average speed. The congestion coefficient generated based on the predicted traffic flow is substituted into the fitting curve to obtain the corresponding predicted vehicle average speed. ; The distance between the preset drop-off point and the corresponding road intersection in the first optimal path is calibrated as , according to the distance and predicted vehicle average speed Calculate vehicle congestion time , , and then according to the congestion time and the user's average walking speed Calculate selection radius , ; S5: Construct a fitness function with the shortest total time as a condition, use a genetic algorithm to generate a driving path for each alternative alighting point, and use the driving path and alternative alighting point with the highest fitness as the second optimal path and actual alighting point.

2. The real-time alighting point recommendation method according to claim 1, characterized in that: The starting distance between the order starting point and the pickup point is marked as , the corresponding boarding time is calibrated as , average pace The calculation method is: Subscript Indicates the number of the historical order, .

3. The method for real-time alighting point recommendation according to claim 1, characterized in that: The weather conditions are divided into four categories: good, general, poor, and extremely poor. Good weather refers to sunny days; general weather refers to cloudy days, light rain, and light fog with visibility between 200m and 500m; poor weather refers to heavy rain, light snow, and moderate fog with visibility between 50m and 200m; and extremely poor weather refers to heavy rain, heavy snow, and dense fog with visibility below 50m. When the weather is good, the first priority factor ; When the weather condition is normal, the first priority coefficient ; When the weather condition is bad, the first priority factor ; When the weather conditions are extremely bad, the first priority coefficient ; The construction status is divided into unconstructed and under construction; When the construction status is not under construction, the second priority coefficient ; When the construction status is under construction, the second priority coefficient .

4. A real-time alighting point recommendation device, characterized in that: The recommendation device is used to execute the recommendation method according to any one of claims 1 to 3, including: A first data collection module, which is in communication with the data processing module and is used to collect information on the starting distance, boarding time, starting point, boarding point, and preset alighting point contained in the user's historical orders and real-time orders; A second data collection module, the second data collection module is in communication with the data processing module and is used to collect traffic flow information and road condition information of the road where the preset drop-off point is located; A data processing module, wherein the data processing module is used to generate several groups of alternative alighting points according to the starting distance, boarding time, starting point, boarding point, preset alighting point, traffic information and road condition information, and use a genetic algorithm to select the driving path and alternative alighting points with the highest fitness as the final optimal path and actual alighting point.

5. A computer device for real-time alighting point recommendation, characterized in that: The recommended computer equipment includes: Storage media for storing computer programs; A processor, configured to execute the computer program to implement the recommendation method according to any one of claims 1 to 3.

6. A real-time alighting point recommendation storage medium, characterized in that: The storage medium is used to store a computer program, and when the computer program is executed by a processor, the recommendation method according to any one of claims 1 to 3 is implemented.