Ride-hailing matching optimization methods, devices, electronic equipment and storage media

Abstract

This invention relates to a method, apparatus, electronic device, and storage medium for optimizing ride-sharing matching, belonging to the field of ride-sharing matching technology. The method includes: performing density clustering on multiple groups of origin-destination (OD) locations to obtain a first clustering result; optimizing the first clustering result based on the directed line segment formed by the origin and destination of each OD within each cluster and its destination location to obtain a second clustering result; optimizing the second clustering result based on the origin and destination locations of each OD within each cluster to obtain a third clustering result, and using the third clustering result as the ride-sharing matching result. This invention performs ride-sharing matching based on actual OD locations, ensuring the effectiveness of ride-sharing matching and improving the user's ride-sharing experience.

Description

Technical Field

[0001] This invention relates to the field of vehicle ride-sharing matching technology, and in particular to a ride-hailing ride-sharing matching optimization method, device, electronic device, and storage medium. Background Technology

[0002] With the continuous development and improvement of modern urban transportation systems, ride-hailing services, as a new mode of transportation, have become widely popular and applied. Ride-sharing, as an important means to improve vehicle utilization efficiency, reduce empty mileage, and lower carbon emissions, has received increasing attention and research in recent years.

[0003] With the increasing severity of urban traffic congestion, the impact of road congestion on ride-hailing matching is becoming more and more significant. Traditional matching methods often overlook actual conditions such as road congestion, resulting in matching results that fail to meet expectations in real-world urban traffic environments. Therefore, improving the accuracy of ride-hailing matching and enhancing user experience has become an urgent technical challenge. Summary of the Invention

[0004] In view of this, it is necessary to provide a ride-hailing carpooling matching optimization method, device, electronic device and storage medium to solve the problem that traditional ride-hailing carpooling matching methods are difficult to achieve the expected results in actual urban traffic environments.

[0005] To address the aforementioned problems, in a first aspect, the present invention provides a ride-hailing carpooling matching optimization method, comprising:

[0006] Based on the starting positions of multiple groups of ODs, density clustering is performed on the multiple groups of ODs to obtain the first clustering result;

[0007] Based on the directed line segments formed by the start and end points of each OD group within each cluster in the first clustering result, and the position of the end point, the first clustering result is optimized to obtain the second clustering result.

[0008] Based on the start and end positions of each OD group within each cluster in the second clustering result, the second clustering result is optimized to obtain a third clustering result, and the third clustering result is used as the multiplication matching result.

[0009] In one possible implementation, the second clustering result is optimized based on the start and end positions of each OD group within each cluster to obtain a third clustering result, including:

[0010] Based on the start and end points of each OD group within each cluster, determine the shortest travel time from the start point to the end point of each OD group.

[0011] Based on the shortest travel time from the start point to the end point of each OD group, and a preset time coefficient, determine the allowable travel time for each OD group, and determine all feasible paths for each OD group within the allowable travel time.

[0012] Based on all feasible paths for each OD group within the allowable passage time, determine the path similarity of each OD group;

[0013] Based on the path similarity of each OD group, the second clustering result is optimized to obtain the third clustering result.

[0014] In one possible implementation, determining the path similarity of each OD group based on all feasible paths within the permissible passage time includes:

[0015] The path similarity of each feasible path in each OD group within the allowable passage time is determined, and the maximum path similarity of all feasible paths in each OD group within the allowable passage time is determined as the path similarity of each OD group.

[0016] In one possible implementation, determining the path similarity of each feasible path for each group of ODs within the permissible passage time includes:

[0017] Determine the path similarity between each feasible path of each OD group within the allowable passage time and each feasible path of other OD groups within the allowable passage time;

[0018] The maximum value of the path similarity between each feasible path of each OD group within the allowable passage time and each feasible path of other OD groups within the allowable passage time is determined as the path similarity of each feasible path of each OD group within the allowable passage time.

[0019] In one possible implementation, the path similarity between each feasible path of each OD group within the permissible passage time and each feasible path of other ODs within the permissible passage time is determined based on the following formula:

[0020]

[0021] in, This represents the path similarity between any feasible path of each OD group within the allowable passage time and any feasible path of other OD groups within the allowable passage time. This represents the length of any feasible path for each OD group within the permissible passage time. This represents the length of any feasible path for other ODs within the permissible passage time. This represents the length of the overlapping path between any feasible path of each OD group within the allowable passage time and any feasible path of other OD groups within the allowable passage time. This indicates the shortest travel time from the start point to the end point of other ODs. This indicates the preset time for accommodation.

[0022] In one possible implementation, the step of performing density clustering on the multiple groups of ODs based on their starting positions to obtain a first clustering result includes:

[0023] The cluster radius is determined based on the number of the multiple groups of ODs;

[0024] Based on the cluster radius and the DBSCAN algorithm, density clustering is performed on the multiple groups of OD to obtain the first clustering result.

[0025] In one possible implementation, the optimization of the first clustering result based on the directed line segments and endpoint positions formed by the start and end points of each group of ODs within each cluster in the first clustering result to obtain a second clustering result includes:

[0026] Based on the first clustering result, the angle between the directed line segments formed by the start and end points of every two groups of OD within each cluster, and the distance between the end points, the first clustering result is optimized to obtain the second clustering result.

[0027] On the other hand, the present invention also provides a ride-hailing carpooling matching optimization device, comprising:

[0028] The clustering module is used to perform density clustering on the multiple groups of ODs based on their starting positions to obtain a first clustering result;

[0029] The first optimization module is used to optimize the first clustering result based on the directed line segment formed by the start and end points of each OD group in each cluster and the position of the end point in the first clustering result, so as to obtain the second clustering result.

[0030] The second optimization module is used to optimize the second clustering result based on the start and end positions of each OD group in each cluster in the second clustering result to obtain a third clustering result, and use the third clustering result as the multiplication matching result.

[0031] In a second aspect, the present invention also provides an electronic device, including a memory and a processor, wherein,

[0032] The memory is used to store programs;

[0033] The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the ride-hailing carpooling matching optimization method described in any of the above implementations.

[0034] Thirdly, the present invention also provides a computer-readable storage medium for storing a computer-readable program or instruction, which, when executed by a processor, can implement the steps in the ride-hailing carpooling matching optimization method described in any of the above implementations.

[0035] The beneficial effects of this invention are as follows: The ride-hailing carpooling matching optimization method, device, electronic device, and storage medium provided by this invention first perform density clustering on multiple groups of origin-destination (OD) locations to achieve preliminary clustering. Then, the clustering results are further optimized by using the directed line segments formed by the origin and destination of each OD group and the destination location, as well as the origin and destination locations of each OD group, to improve the carpooling matching effect and thus enhance the user's carpooling experience. This invention performs carpooling matching based on actual OD locations, ensuring the effectiveness of carpooling matching and improving the user's carpooling experience. Attached Figure Description

[0036] Figure 1 This is a schematic flowchart of an embodiment of the ride-hailing carpooling matching optimization method provided by the present invention;

[0037] Figure 2 This is a schematic flowchart of an embodiment of the opening and closing constraint calculation process of the present invention;

[0038] Figure 3 This is a schematic flowchart of an embodiment of the path similarity calculation process of the present invention;

[0039] Figure 4 This is a schematic diagram of an embodiment of the ride-hailing matching optimization device provided by the present invention;

[0040] Figure 5 A schematic diagram of an embodiment of the electronic device provided by the present invention. Detailed Implementation

[0041] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0042] In the description of the embodiments of the present invention, unless otherwise stated, "multiple" means two or more. "And / or" describes the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0043] The terms "first," "second," etc., used in the embodiments of this invention are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a technical feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature.

[0044] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0045] Before demonstrating the embodiments, the following terms will be explained.

[0046] OD stands for Origin and Destination in transportation.

[0047] This invention provides a method, apparatus, electronic device, and storage medium for optimizing ride-hailing carpooling matching, which will be described below.

[0048] Figure 1 This is a schematic flowchart of an embodiment of the ride-hailing carpooling matching optimization method provided by the present invention, as shown below. Figure 1 As shown, the ride-hailing carpooling matching optimization method includes:

[0049] S101. Based on the starting positions of multiple groups of ODs, perform density clustering on the multiple groups of ODs to obtain the first clustering result.

[0050] It should be noted that the origin and destination locations of each Origin-Destination (OD) can be obtained from the user's order information in the ride-hailing app. After the user initiates an order through a mobile device such as a smartphone, the backend physical server or cloud server can obtain the user's order information through the operator's base station, and then obtain the origin and destination locations of each OD from the user's order information.

[0051] In some embodiments of the present invention, step S101 includes:

[0052] The cluster radius is determined based on the number of the multiple groups of ODs;

[0053] Based on the cluster radius and the DBSCAN algorithm, density clustering is performed on the multiple groups of OD to obtain the first clustering result.

[0054] Specifically, when performing density clustering on multiple groups of originating points (ODs) based on their starting positions, the cluster radius can first be determined according to the number of ODs. For example, when the number of ODs is less than 340, the cluster radius can be set to 2500 meters; when the number of ODs is between 340 and 505, the cluster radius can be set to 2000 meters; and when the number of ODs is greater than 505, the cluster radius can be set to 1500 meters. Furthermore, during density clustering, each sample must contain at least one point. Then, based on the determined cluster radius, the DBSCAN algorithm is used to perform density clustering on the multiple ODs, obtaining the first clustering result. Compared to the traditional K-means algorithm, the DBSCAN algorithm can identify clusters of arbitrary shapes, making it more advantageous when handling complex data structures.

[0055] S102. Based on the directed line segments and endpoint positions formed by the start and end points of each OD group within each cluster in the first clustering result, the first clustering result is optimized to obtain the second clustering result.

[0056] It should be noted that by using the angle between the directed line segments formed by the start and end points of every two ODs within each cluster, as well as the position of the end point, the proximity between the paths corresponding to the two ODs can be determined, thereby further optimizing the preliminary clustering results.

[0057] In some embodiments of the present invention, step S102 includes:

[0058] Based on the first clustering result, the angle between the directed line segments formed by the start and end points of every two groups of OD within each cluster, and the distance between the end points, the first clustering result is optimized to obtain the second clustering result.

[0059] Specifically, when optimizing the first clustering result based on the directed line segment formed by the start and end points of each OD group within each cluster and the position of the end point, the first clustering result can be optimized based on the included angle between the directed line segments formed by the start and end points of each pair of OD groups within each cluster and the distance between the end point positions, to obtain the second clustering result.

[0060] Combination Figure 2 Let's take a look. Figure 2This is a schematic flowchart of an embodiment of the opening / closing constraint calculation process of the present invention. When optimizing the first clustering result based on the angle between the directed line segments formed by the start and end points of every two ODs within each cluster, and the distance between the end points, the opening / closing degree between every two ODs within each cluster can be determined based on the angle between the start and end points of every two ODs within each cluster, and the distance between the end points. Then, ODs within each cluster whose opening / closing degree with any other OD is greater than a preset threshold are removed to obtain the second clustering result. By setting the opening / closing degree, the proximity between the paths corresponding to two ODs can be accurately reflected, thereby improving the multiplication matching effect.

[0061] The degree of opening between any two ODs within each cluster can be calculated using the following formula:

[0062]

[0063]

[0064] in, Indicates the degree of opening / closing between two sets of OD. and For weight parameters, This represents the angle between the directed line segments formed by the start and end points of two sets of origin (OD). This represents the distance between the endpoints of two sets of ODs. For the preset distance, The angle between the directed line segment formed by the start and end points of one of the two sets of ODs and the due north direction. It represents the angle between the direction of due north and the direction formed by the starting and ending points of the other OD in two OD groups.

[0065] S103. Based on the starting and ending positions of each OD group within each cluster in the second clustering result, optimize the second clustering result to obtain a third clustering result, and use the third clustering result as the multiplication matching result.

[0066] In some embodiments of the present invention, step S103 includes:

[0067] Based on the start and end points of each OD group within each cluster, determine the shortest travel time from the start point to the end point of each OD group.

[0068] Based on the shortest travel time from the start point to the end point of each OD group, and a preset time coefficient, determine the allowable travel time for each OD group, and determine all feasible paths for each OD group within the allowable travel time.

[0069] Based on all feasible paths for each OD group within the allowable passage time, determine the path similarity of each OD group;

[0070] Based on the path similarity of each OD group, the second clustering result is optimized to obtain the third clustering result.

[0071] Specifically, when optimizing the second clustering result based on the start and end points of each OD group within each cluster, the following steps are taken: First, the shortest travel time from the start point to the end point of each OD group can be determined based on the start and end points of each OD group within each cluster. Then, the allowable travel time of each OD group is determined based on the shortest travel time from the start point to the end point of each OD group and a preset time coefficient. All feasible paths of each OD group within the allowable travel time are then determined. Next, the path similarity of each OD group is determined based on all feasible paths within the allowable travel time. Finally, the second clustering result can be optimized based on the path similarity of each OD group to obtain the third clustering result. For example, OD pairs with road similarity less than a similarity threshold can be removed from the second clustering result to obtain the third clustering result.

[0072] In some embodiments of the present invention, determining the path similarity of each group of ODs based on all feasible paths of each group of ODs within the permissible passage time includes:

[0073] The path similarity of each feasible path in each OD group within the allowable passage time is determined, and the maximum path similarity of all feasible paths in each OD group within the allowable passage time is determined as the path similarity of each OD group.

[0074] Specifically, when determining the path similarity of each group of ODs, the path similarity of each feasible path of each group of ODs within the allowable passage time can be determined first, and then the maximum path similarity of all feasible paths of each group of ODs within the allowable passage time can be determined as the path similarity of each group of ODs.

[0075] In some embodiments of the present invention, determining the path similarity of each feasible path for each group of ODs within the permissible passage time includes:

[0076] Determine the path similarity between each feasible path of each OD group within the allowable passage time and each feasible path of other OD groups within the allowable passage time;

[0077] The maximum value of the path similarity between each feasible path of each OD group within the allowable passage time and each feasible path of other OD groups within the allowable passage time is determined as the path similarity of each feasible path of each OD group within the allowable passage time.

[0078] Specifically, in combination Figure 3 Let's take a look. Figure 3 This is a schematic flowchart of an embodiment of the path similarity calculation process of the present invention. When determining the path similarity of each feasible path in each group of ODs within the allowable travel time, the feasible paths of each group of ODs can first be filtered. The shortest travel time from the starting point Om to the ending point Dm is calculated as shortest_time_ODm, where m is a random number between 1 and n, inclusive of 1 and n. Next, the allowable running time is calculated: allowed_time_ODm = shortest_time_ODm * time_factor. Subsequently, all simple paths from Om to Dm are generated. At the same time, an ellipse with Om and Dm as foci is defined, and paths outside the range of the ellipse are filtered out. Only the path time (travel_time) of the path that does not exceed the range of the ellipse is calculated to reduce the amount of computation. Finally, paths that exceed the allowable running time allowed_time_ODm are filtered out again, resulting in all feasible paths within the allowable time.

[0079] Next, path similarity is calculated. For a selected path, the method for calculating the similarity of paths to be run within the cluster is as follows: First, extract all nodes of each group of OD paths and combine them randomly to calculate the path length corresponding to their common nodes, i.e., the overlapping path length common_length; then, calculate the similarity of a single path.

[0080] In some embodiments of the present invention, the path similarity between each feasible path of each OD group within the permissible passage time and each feasible path of other ODs within the permissible passage time is determined based on the following formula:

[0081]

[0082] in, This represents the path similarity between any feasible path of each OD group within the allowable passage time and any feasible path of other OD groups within the allowable passage time. This represents the length of any feasible path for each OD group within the permissible passage time. This represents the length of any feasible path for other ODs within the permissible passage time. This represents the length of the overlapping path between any feasible path of each OD group within the allowable passage time and any feasible path of other OD groups within the allowable passage time. This indicates the shortest travel time from the start point to the end point of other ODs. This indicates the preset time for accommodation.

[0083] Furthermore, when the route similarity calculation results indicate that a passenger is suitable for ride-sharing, it is necessary to further determine whether they meet the time window requirements. The time window refers to the longest waiting time a passenger can accept. If the time difference between the vehicle's arrival at the passenger's departure point and the time the passenger places the order is less than or equal to the time window set by the passenger, then the time window condition is considered met. The size of the time window is set by the passenger based on their own needs.

[0084] When passengers seeking ridesharing meet the path similarity and time window conditions, route planning is required to ensure smooth pick-up and drop-off for each passenger and maximize travel efficiency for all. First, the current vehicle location is used as the new starting point, and the destination points (ODs) of the passengers seeking ridesharing are used as new waypoints. The possible arrival order of waypoints is traversed, and the shortest path with the shortest total travel time is found under the constraint that "each passenger's OD must be visited before their D."

[0085] In summary, the ride-sharing matching optimization method provided in this embodiment of the invention first performs density clustering on multiple groups of origin-destination (OD) locations to achieve preliminary clustering. Then, it further optimizes the clustering results by using the directed line segments formed by the origin and destination of each OD and their destination locations, as well as the origin and destination locations of each OD, to improve the ride-sharing matching effect and thus enhance the user's ride-sharing experience. This invention performs ride-sharing matching based on actual OD locations, ensuring the effectiveness of ride-sharing matching and improving the user's ride-sharing experience.

[0086] To better implement the ride-hailing carpooling matching optimization method in this embodiment of the invention, based on the ride-hailing carpooling matching optimization method, correspondingly, as follows: Figure 4 As shown, this embodiment of the invention also provides a ride-hailing carpooling matching optimization device, the ride-hailing carpooling matching optimization device 400 including:

[0087] Clustering module 401 is used to perform density clustering on the multiple groups of ODs based on the starting positions of the multiple groups of ODs to obtain a first clustering result;

[0088] The first optimization module 402 is used to optimize the first clustering result based on the directed line segment formed by the start and end points of each OD group in each cluster and the position of the end point in the first clustering result, so as to obtain the second clustering result.

[0089] The second optimization module 403 is used to optimize the second clustering result based on the start and end positions of each OD group in each cluster in the second clustering result to obtain a third clustering result, and use the third clustering result as the multiplication matching result.

[0090] The ride-hailing carpooling matching optimization device 400 provided in the above embodiments can realize the technical solutions described in the above ride-hailing carpooling matching optimization method embodiments. The specific implementation principles of each module or unit can be found in the corresponding content in the above ride-hailing carpooling matching optimization method embodiments, and will not be repeated here.

[0091] like Figure 5 As shown, the present invention also provides an electronic device 500. The electronic device 500 includes a processor 501, a memory 502, and a display 503. Figure 5 Only some components of the electronic device 500 are shown, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead.

[0092] In some embodiments, processor 501 may be a central processing unit (CPU), microprocessor, or other data processing chip, used to run program code stored in memory 502 or process data, such as the magnetic resonance image optimization method of the present invention.

[0093] In some embodiments, processor 501 may be a single server or a group of servers. The server group may be centralized or distributed. In some embodiments, processor 501 may be local or remote. In some embodiments, processor 501 may be implemented on a cloud platform. In one embodiment, the cloud platform may include a private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, inter-cloud, multi-cloud, or any combination thereof.

[0094] In some embodiments, memory 502 may be an internal storage unit of electronic device 500, such as a hard disk or memory of electronic device 500. In other embodiments, memory 502 may also be an external storage device of electronic device 500, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. equipped on electronic device 500.

[0095] Furthermore, the memory 502 may include both internal storage units of the electronic device 500 and external storage devices. The memory 502 is used to store application software and various types of data installed on the electronic device 500.

[0096] In some embodiments, display 503 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an organic light-emitting diode (OLED) touchscreen. Display 503 is used to display information from electronic device 500 and to display a visual user interface. Components 501-503 of electronic device 500 communicate with each other via a system bus.

[0097] In one embodiment, when the processor 501 executes the ride-hailing matching optimization program in the memory 502, the following steps can be implemented:

[0098] Based on the starting positions of multiple groups of ODs, density clustering is performed on the multiple groups of ODs to obtain the first clustering result;

[0099] Based on the directed line segments formed by the start and end points of each OD group within each cluster in the first clustering result, and the position of the end point, the first clustering result is optimized to obtain the second clustering result.

[0100] Based on the start and end positions of each OD group within each cluster in the second clustering result, the second clustering result is optimized to obtain a third clustering result, and the third clustering result is used as the multiplication matching result.

[0101] It should be understood that when the processor 501 executes the ride-hailing matching optimization program in the memory 502, in addition to the functions mentioned above, it can also perform other functions, as detailed in the description of the corresponding method embodiments above.

[0102] Furthermore, this embodiment of the invention does not specifically limit the type of electronic device 500 mentioned. Electronic device 500 can be a mobile phone, tablet computer, personal digital assistant (PDA), wearable device, laptop computer, or other portable electronic device. Exemplary embodiments of portable electronic devices include, but are not limited to, portable electronic devices running iOS, Android, Microsoft, or other operating systems. The aforementioned portable electronic device can also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the invention, electronic device 500 may not be a portable electronic device, but rather a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0103] Accordingly, this application also provides a computer-readable storage medium for storing computer-readable programs or instructions. When the programs or instructions are executed by a processor, they can implement the steps or functions of the ride-hailing matching optimization methods provided in the above-described method embodiments.

[0104] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.), and the computer program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0105] The above provides a detailed description of the ride-hailing carpooling matching optimization method, device, electronic device, and storage medium provided by the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for optimizing a ride-hailing carpooling match, characterized in that, The method comprises the following steps: Based on the origin positions of multiple groups of ODs, the multiple groups of ODs are subjected to density clustering to obtain a first clustering result; Based on the directed line segments formed by the origin and destination of each group of ODs in each clustering cluster in the first clustering result and the destination positions, the first clustering result is optimized to obtain a second clustering result; Based on the origin and destination positions of each group of ODs in each clustering cluster in the second clustering result, the second clustering result is optimized to obtain a third clustering result, and the third clustering result is taken as a carpool matching result, comprising: based on the origin and destination positions of each group of ODs in each clustering cluster, the shortest travel time from the origin position to the destination position of each group of ODs is determined; The product of the shortest travel time from the origin position to the destination position of each group of ODs and a preset time coefficient is determined as the allowable travel time of each group of ODs, and all feasible paths of each group of ODs within the allowable travel time are determined; The path similarity between each feasible path of each group of ODs within the allowable travel time and each feasible path of other groups of ODs within the allowable travel time is determined; The maximum value of the path similarity between each feasible path of each group of ODs within the allowable travel time and each feasible path of other groups of ODs within the allowable travel time is determined as the path similarity of each feasible path of each group of ODs within the allowable travel time, and the maximum value of the path similarity of all feasible paths of each group of ODs within the allowable travel time is determined as the path similarity of each group of ODs; Based on the path similarity of each group of ODs, the second clustering result is optimized to obtain a third clustering result. 2.The method of claim 1, wherein, The path similarity between each feasible path of each group of ODs within the allowable travel time and each feasible path of other groups of ODs within the allowable travel time is determined based on the following formula: wherein, represents a path similarity between any feasible path of the OD group within the allowable travel time and any feasible path of the other OD within the allowable travel time, represents a length of any feasible path of the OD group within the allowable travel time, represents a length of any feasible path of the other OD within the allowable travel time, represents a coincident path length between any feasible path of the OD group within the allowable travel time and any feasible path of the other OD within the allowable travel time, represents a shortest travel time from the origin location to the destination location of the other OD, represents a preset accommodation time. 3.The method of claim 1, wherein, The method comprises the following steps: Based on the number of the multiple groups of ODs, a clustering cluster radius is determined; Based on the clustering cluster radius and a DBSCAN algorithm, the multiple groups of ODs are subjected to density clustering to obtain a first clustering result. 4.The method of Claim 1, wherein, The method comprises the following steps: Based on the angle between the directed line segments formed by the origin and destination of each two groups of ODs in each clustering cluster in the first clustering result and the distance between the destination positions, the first clustering result is optimized to obtain a second clustering result. 5.A device for optimizing a ride-hailing carpooling match, characterized in that, The method comprises the following steps: A clustering module is configured to perform density clustering on multiple groups of ODs based on the origin positions of the multiple groups of ODs to obtain a first clustering result; A first optimization module is configured to optimize the first clustering result based on the directed line segments formed by the origin and destination of each group of ODs in each clustering cluster in the first clustering result and the destination positions to obtain a second clustering result; A second optimization module is configured to optimize the second clustering result based on the origin and destination positions of each group of ODs in each clustering cluster in the second clustering result to obtain a third clustering result, and the third clustering result is taken as a carpool matching result. The second optimization module is configured to optimize the second clustering result based on the start and end locations of each group of ODs in each cluster of the second clustering result, to obtain a third clustering result, and take the third clustering result as the carpooling matching result, and comprises the following steps: determining the shortest travel time from the start location to the end location of each group of ODs in each cluster based on the start and end locations of each group of ODs in each cluster; multiplying the shortest travel time from the start location to the end location of each group of ODs by a preset time coefficient to determine the allowable travel time of each group of ODs, and determining all feasible paths of each group of ODs within the allowable travel time; determining the path similarity between each feasible path of each group of ODs within the allowable travel time and each feasible path of other groups of ODs within the allowable travel time; determining the maximum value of the path similarity between each feasible path of each group of ODs within the allowable travel time and each feasible path of other groups of ODs within the allowable travel time as the path similarity of each feasible path of each group of ODs within the allowable travel time, and determining the maximum value of the path similarity of all feasible paths of each group of ODs within the allowable travel time as the path similarity of each group of ODs; optimizing the second clustering result based on the path similarity of each group of ODs to obtain a third clustering result.

6. An electronic device, comprising: comprising a memory and a processor, wherein the memory is configured to store a program; the processor is coupled to the memory and is configured to execute the program stored in the memory to implement the steps of the carpooling matching optimization method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, a computer readable program or instruction for storing, which can implement the steps of the carpooling matching optimization method according to any one of claims 1 to 4 when executed by a processor.

Images