Passenger distribution method, device and equipment and storage medium

Abstract

The invention discloses a passenger distribution method, device and equipment and a storage medium, relates to the field of vehicle passenger distribution, and solves the technical problem of low passenger matching rationality in an existing shared passenger scheme, and the method comprises the steps: obtaining a first path point set of a first passenger according to the destination of the current first passenger; acquiring a plurality of second passengers with the same starting point as the first passenger and a corresponding second path point set according to the current vehicle passenger carrying rate; obtaining a plurality of optimal passing points corresponding to a second waypoint set of the plurality of second passengers according to the first waypoint set; and obtaining a second passenger which is optimally matched with the first passenger according to the plurality of optimal passing points. According to the invention, the passenger matching efficiency can be improved, the passenger matching reasonability is improved, and the utilization rate of vehicle sharing passenger carrying is further improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle passenger allocation, and in particular to a passenger allocation method, device, equipment and storage medium. Background Art

[0002] During holidays, major transportation hubs such as train stations, airports, and long-distance bus stations welcome a large number of passengers with different destinations. Since the supply of online ride-hailing cars and taxis is far from meeting the number of passengers, when public transportation is suspended, passengers who need to take online ride-hailing cars or taxis will have to wait in line for too long. In this case, there are still many vehicles that only carry one passenger, which further exacerbates the contradiction between vehicle supply and demand and causes unnecessary waste of resources.

[0003] In response to the above problems, the existing methods of shared passenger transportation, such as carpooling or hitchhiking, are usually used to alleviate the problem of insufficient supply of vehicles. However, in the existing shared passenger transportation solutions, firstly, when the vehicle is carrying the rear passenger, the path overlap with the front passenger is not considered, resulting in unreasonable path planning; secondly, when the vehicle is matching the shared passengers, the vehicle passenger rate at the current departure point and the waiting time of the rear passenger are not considered, resulting in unreasonable passenger matching and low matching efficiency, which leads to low utilization rate of shared passenger transportation of vehicles, making it difficult to alleviate the problem of insufficient supply of vehicles at holiday transportation hubs. Therefore, how to improve the rationality of passenger matching during shared rides remains to be solved. Summary of the invention

[0004] The present application provides a passenger allocation method, device, equipment and storage medium to solve the technical problem of low rationality of passenger matching in existing shared passenger solutions.

[0005] According to a first aspect of an embodiment of the present application, there is provided a passenger allocation method, comprising:

[0006] According to the current destination of the first passenger, obtaining a first path point set of the first passenger;

[0007] According to the current vehicle passenger carrying rate, obtaining a plurality of second passengers having the same starting point as the first passenger and a corresponding second path point set;

[0008] A second set of path points corresponding to the plurality of second passengers, and obtaining a plurality of optimal waypoints according to the first set of path points;

[0009] Based on the multiple optimal waypoints, a second passenger who is the best match for the first passenger is obtained.

[0010] The present application first obtains a corresponding first path point set according to the destination of the first passenger, and then obtains multiple second passengers with the same starting point as the first passenger and the corresponding second path point set according to the vehicle passenger carrying rate, so that the second passengers who are more reasonably matched with the first passenger can be screened out first, thereby improving the rationality of passenger matching; then multiple optimal waypoints are obtained corresponding to the second path point sets of the multiple second passengers, so that the optimal waypoints of each second passenger can be matched for the first passenger at the same time, thereby improving the matching efficiency, and then the best matched second passenger is obtained according to the multiple optimal waypoints, so that the rationality of passenger matching can be improved, thereby improving the utilization rate of vehicle sharing.

[0011] In certain embodiments of the present application, the second path point set corresponding to the plurality of second passengers obtains a plurality of optimal waypoints according to the first path point set, specifically including:

[0012] A second path point set corresponding to the plurality of second passengers, and a plurality of waypoint sets are obtained according to the first path point set;

[0013] According to the plurality of waypoint sets, in combination with idle vehicle data, a plurality of optimal waypoints are obtained.

[0014] The present application first obtains multiple waypoint sets corresponding to the second path point sets of multiple second passengers, and can simultaneously match the waypoint set of each second passenger for the first passenger, thereby improving the matching efficiency. Then, multiple optimal waypoints are obtained by combining the idle vehicle data, and the influence of the idle vehicles on the selection of the optimal waypoints is considered, thereby improving the rationality of the optimal waypoints.

[0015] In certain embodiments of the present application, the second path point set corresponding to the plurality of second passengers obtains a plurality of waypoint sets according to the first path point set, specifically including:

[0016] Selecting one second passenger in turn as the current passenger, and obtaining a waypoint set of the current passenger according to a preset waypoint matching method, until the plurality of second passengers all obtain corresponding waypoint sets;

[0017] Wherein, the waypoint matching method comprises:

[0018] Obtaining an initial waypoint set according to the first waypoint set and the second waypoint set of the current passenger;

[0019] The path distances of all the initial waypoints in the initial waypoint set are calculated respectively, and the initial waypoints whose path distances fall within a preset distance interval are included in the waypoint set of the current passenger.

[0020] The present application sequentially selects the second passenger as the current passenger and obtains a waypoint set according to a waypoint matching method. During the matching, an initial waypoint set is first obtained according to the first path point set and the second path point set, while taking into account the paths of the first passenger and the second passenger, which can improve the path overlap and thus improve the rationality of path planning. Then, the path distances of all initial waypoints in the initial waypoint set are calculated and a waypoint set is obtained according to the path distances, which can exclude initial waypoints whose path distances are in an unreasonable range and improve the rationality of waypoint selection.

[0021] In certain embodiments of the present application, the step of obtaining multiple optimal waypoints based on the multiple waypoint sets and in combination with idle vehicle data specifically includes:

[0022] Selecting one waypoint set in turn as the current waypoint set, and obtaining the optimal waypoint in the current waypoint set according to a preset waypoint selection method, until the optimal waypoint is selected from all the waypoint sets;

[0023] The method for selecting a waypoint includes:

[0024] According to the idle vehicle data, a plurality of idle vehicle clusters are obtained based on a clustering algorithm;

[0025] Calculating the priority of each waypoint according to the number of idle vehicles in the plurality of idle vehicle clusters;

[0026] The waypoint with the highest priority is used as the optimal waypoint of the current waypoint set.

[0027] The present application sequentially selects a set of waypoints as the current set of waypoints and obtains the optimal waypoint according to the waypoint selection method. When selecting, multiple idle vehicle clusters are first obtained based on the idle vehicle data based on the clustering algorithm, and then the priority of each waypoint is calculated according to the number of idle vehicles in the multiple idle vehicle clusters, and the waypoint with the largest priority is used as the optimal waypoint. The influence of idle vehicles on the selection of the optimal waypoint is taken into account, and the rationality of the selection of the optimal waypoint is improved.

[0028] In certain embodiments of the present application, the calculating the priority of each waypoint according to the number of idle vehicles of the plurality of idle vehicle clusters specifically includes:

[0029]

[0030] Among them, p i is the priority of the i-th waypoint, d ij is the distance between the cluster center of the jth idle vehicle cluster and the i-th waypoint, q is the number of idle vehicle clusters, N j is the total number of idle vehicles included in the jth idle vehicle cluster, E i ={j|dij ≥d max} is the idle vehicle cluster set whose distance from the cluster center of the idle vehicle cluster to the i-th waypoint exceeds the upper limit of the idle vehicle scheduling distance, d max The upper limit of the dispatch distance for idle vehicles.

[0031] The present application obtains the priority of each waypoint based on the distance from the cluster center of each idle vehicle cluster to the waypoint, the total number of idle vehicles and the upper limit of the idle vehicle scheduling distance, takes into account the influence of the scheduling distance, scheduling time and scheduling amount of idle vehicles on the selection of the optimal waypoint, and improves the rationality of the selection of the optimal waypoint.

[0032] In certain embodiments of the present application, obtaining a second passenger who is the best match for the first passenger according to the multiple optimal waypoints specifically includes:

[0033] According to the plurality of optimal waypoints and the vehicle passenger carrying rate, based on a first passenger matching function, obtaining a second passenger who is the best match for the first passenger;

[0034] The first passenger matching function is specifically:

[0035]

[0036] Among them, a and b are the first passenger and the bth second passenger respectively, r b is the position of the bth second passenger among multiple second passengers, υ is the current vehicle passenger carrying rate, is the priority of the optimal waypoints for the first passenger a and the bth second passenger.

[0037] The present application calculates the best matching second passenger based on the position sequence of the second passengers, the current vehicle passenger load rate and the priority of the best waypoints for each second passenger. This multi-factor consideration can improve the rationality of passenger matching.

[0038] In certain embodiments of the present application, obtaining a second passenger who is the best match for the first passenger according to the multiple optimal waypoints specifically includes:

[0039] According to the plurality of optimal waypoints, the vehicle passenger loading rate and a preset fare allocation coefficient, based on a second passenger matching function, obtaining a second passenger who is the best match for the first passenger;

[0040]

[0041] Among them, a and b are the first passenger and the bth second passenger respectively, r b is the position of the bth second passenger among multiple second passengers, γ is the cost allocation coefficient, v is the current vehicle passenger carrying rate, is the priority of the optimal waypoints for the first passenger a and the bth second passenger.

[0042] The present application calculates the best matching second passenger based on the second passenger's position order, fare allocation coefficient, current vehicle passenger load rate and priority of the best waypoints for each second passenger, and can simultaneously consider fare allocation among shared passengers. Such multi-factor considerations can improve the rationality of passenger matching.

[0043] According to a second aspect of the embodiment of the present application, there is provided a passenger allocation device, including a first path acquisition module, a second path acquisition module, an optimal path acquisition module, and a second passenger matching module;

[0044] The first path acquisition module is used to acquire a first path point set of the first passenger according to the current destination of the first passenger;

[0045] The second path acquisition module is used to acquire a plurality of second passengers having the same starting point as the first passenger and a corresponding second path point set according to the current vehicle passenger carrying rate;

[0046] The optimal path acquisition module is used to obtain a plurality of optimal path points according to the first path point set corresponding to the second path point set of the plurality of second passengers;

[0047] The second passenger matching module is used to obtain a second passenger who is the best match with the first passenger based on the multiple optimal waypoints.

[0048] In certain embodiments of the present application, the optimal path acquisition module includes a path point set acquisition submodule and an optimal path point acquisition submodule;

[0049] The waypoint set acquisition submodule is used to obtain a plurality of waypoint sets according to the first waypoint set, corresponding to the second waypoint sets of the plurality of second passengers;

[0050] The optimal waypoint acquisition submodule is used to obtain multiple optimal waypoints based on the multiple waypoint sets and in combination with idle vehicle data.

[0051] In certain embodiments of the present application, the waypoint set acquisition submodule includes a waypoint set acquisition unit;

[0052] The waypoint set acquisition unit is used to select one of the second passengers as the current passenger in turn, and obtain the waypoint set of the current passenger according to a preset waypoint matching method, until the plurality of second passengers all obtain corresponding waypoint sets;

[0053] Wherein, the waypoint matching method comprises:

[0054] Obtaining an initial waypoint set according to the first waypoint set and the second waypoint set of the current passenger;

[0055] The path distances of all the initial waypoints in the initial waypoint set are calculated respectively, and the initial waypoints whose path distances fall within a preset distance interval are included in the waypoint set of the current passenger.

[0056] In certain embodiments of the present application, the optimal waypoint acquisition submodule includes an optimal waypoint acquisition unit;

[0057] The optimal waypoint acquisition unit is used to select one waypoint set as the current waypoint set in turn, and obtain the optimal waypoint in the current waypoint set according to a preset waypoint selection method, until the optimal waypoint is selected from all the waypoint sets;

[0058] The method for selecting a waypoint includes:

[0059] According to the idle vehicle data, a plurality of idle vehicle clusters are obtained based on a clustering algorithm;

[0060] Calculating the priority of each waypoint according to the number of idle vehicles in the plurality of idle vehicle clusters;

[0061] The waypoint with the highest priority is used as the optimal waypoint of the current waypoint set.

[0062] In certain embodiments of the present application, the calculating the priority of each waypoint according to the number of idle vehicles of the plurality of idle vehicle clusters specifically includes:

[0063]

[0064] Among them, p i is the priority of the i-th waypoint, d ij is the distance between the cluster center of the jth idle vehicle cluster and the i-th waypoint, q is the number of idle vehicle clusters, N j is the total number of idle vehicles included in the jth idle vehicle cluster, E i ={j|d ij ≥d max} is the idle vehicle cluster set whose distance from the cluster center of the idle vehicle cluster to the i-th waypoint exceeds the upper limit of the idle vehicle scheduling distance, d max The upper limit of the dispatch distance for idle vehicles.

[0065] In certain embodiments of the present application, the second passenger matching module includes a first optimal matching submodule;

[0066] The first optimal matching submodule is configured to obtain a second passenger who is the best match with the first passenger based on the first passenger matching function according to the multiple optimal waypoints and the vehicle passenger carrying rate;

[0067] The first passenger matching function is specifically:

[0068]

[0069] Among them, a and b are the first passenger and the bth second passenger respectively, r b is the position of the bth second passenger among multiple second passengers, v is the current vehicle passenger carrying rate, is the priority of the optimal waypoints for the first passenger a and the bth second passenger.

[0070] In certain embodiments of the present application, the second passenger matching module further includes a second optimal matching submodule;

[0071] The second optimal matching submodule is used to obtain a second passenger who is the best match with the first passenger based on the second passenger matching function according to the multiple optimal waypoints, the vehicle passenger carrying rate and the preset fare allocation coefficient;

[0072]

[0073] Among them, a and b are the first passenger and the bth second passenger respectively, r b is the position of the bth second passenger among multiple second passengers, γ is the cost allocation coefficient, v is the current vehicle passenger carrying rate, is the priority of the optimal waypoints for the first passenger a and the bth second passenger.

[0074] According to a third aspect of an implementation of the present application, a computer device is provided, comprising: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor; wherein, when the processor executes the computer program, a passenger allocation method of the present application is implemented.

[0075] According to a fourth aspect of the implementation of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a plurality of instructions, wherein the instructions are suitable for loading by a processor to execute a passenger allocation method of the present application.

[0076] The present application first obtains a corresponding first path point set according to the destination of the first passenger, and then obtains multiple second passengers with the same starting point as the first passenger and the corresponding second path point set according to the vehicle passenger carrying rate, so that the second passengers who are more reasonably matched with the first passenger can be screened out first, thereby improving the rationality of passenger matching; then multiple optimal waypoints are obtained corresponding to the second path point sets of the multiple second passengers, so that the optimal waypoints of each second passenger can be matched for the first passenger at the same time, thereby improving the matching efficiency, and then the best matched second passenger is obtained according to the multiple optimal waypoints, so that the rationality of passenger matching can be improved, thereby improving the utilization rate of vehicle sharing. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] Figure 1 : A flow chart of a passenger allocation method shown in certain embodiments of the present application;

[0078] Figure 2 : A module structure diagram of a passenger allocation device shown in certain embodiments of the present application. DETAILED DESCRIPTION

[0079] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals represent the same or similar elements or elements having the same or similar functions from beginning to end. The embodiments described below in conjunction with the accompanying drawings are exemplary and are only used to explain some embodiments of the present application, and should not be construed as limitations on the embodiments of the present application. Based on the embodiments shown in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0080] In the description of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, unless otherwise clearly and specifically defined, "multiple" and "several" mean two or more.

[0081] Existing shared passenger transportation methods usually include carpooling and ride-sharing, and the matching shared passenger transportation algorithms include carpooling algorithms and ride-sharing algorithms. However, the current shared passenger transportation methods and their algorithms have the following shortcomings: (1) After the vehicle picks up the first passenger, when matching the second passenger, the path overlap between the second passenger and the first passenger is not considered, resulting in unreasonable path planning, more detours, and increased vehicle travel time, which reduces the vehicle passenger carrying efficiency and low vehicle passenger utilization rate; (2) After the vehicle picks up the first passenger, when matching the second passenger, the vehicle passenger carrying rate at the current departure point and the waiting time of the second passenger are not considered, resulting in unreasonable passenger matching and low matching efficiency, which may cause some passengers who have been waiting for a long time to still have to wait for a long time before they can get on the vehicle, resulting in low vehicle shared passenger utilization rate. The existence of the above shortcomings makes it difficult to alleviate the problem of vehicle supply and demand near transportation hubs during holidays. How to improve the rationality of passenger matching during shared rides and thus improve the utilization rate of shared vehicles remains an urgent problem to be solved.

[0082] Based on the above technical background, please refer to Figure 1 The embodiment of the present application provides a passenger allocation method, including steps S101 to S104, each of which is as follows:

[0083] Step S101: According to the current destination of the first passenger, a first path point set of the first passenger is obtained.

[0084] In some optional implementations of the present application, acquiring the first path point set of the first passenger according to the current destination of the first passenger specifically includes:

[0085] Based on a preset first path-finding algorithm, a first path point set of the first passenger is obtained according to the current destination and departure point of the first passenger.

[0086] In certain optional embodiments of the present application, the first path-finding algorithm includes but is not limited to Dijkstra algorithm, A* algorithm and simulated annealing algorithm.

[0087] Exemplarily, the first path point set of the first passenger is marked as S a = {u1, u2, ..., u n}, where u1, u2, ..., u n for each path point.

[0088] Step S102: According to the current vehicle passenger carrying rate, a plurality of second passengers having the same starting point as the first passenger and a corresponding second path point set are obtained.

[0089] In some optional implementations of the present application, obtaining a plurality of second passengers having the same starting point as the first passenger and corresponding second path point sets according to the current vehicle passenger carrying rate specifically includes:

[0090] According to the current vehicle passenger carrying rate, obtaining a plurality of second passengers having the same starting point as the first passenger;

[0091] Based on a preset second pathfinding algorithm, a plurality of second path point sets are obtained corresponding to the respective departure points and destinations of the plurality of second passengers.

[0092] In certain optional embodiments of the present application, the second path-finding algorithm includes but is not limited to Dijkstra algorithm, A* algorithm and simulated annealing algorithm.

[0093] It should be understood that based on the consistency of the problem solved in this application, the first path-finding algorithm and the second path-finding algorithm should generally be set to the same algorithm.

[0094] Exemplarily, the second path point set of the b-th second passenger is marked as S b = {v b1 , v b2 , ..., v bn}, where v b1 , v b2 , ..., v bn are the path points of the path of the b-th second passenger.

[0095] Step S103: Corresponding to the second path point set of the plurality of second passengers, a plurality of optimal waypoints are obtained according to the first path point set.

[0096] In certain embodiments of the present application, the second path point set corresponding to the plurality of second passengers obtains a plurality of optimal waypoints according to the first path point set, specifically including:

[0097] A second path point set corresponding to the plurality of second passengers, and a plurality of waypoint sets are obtained according to the first path point set;

[0098] According to the plurality of waypoint sets, in combination with idle vehicle data, a plurality of optimal waypoints are obtained.

[0099] In certain embodiments of the present application, the second path point set corresponding to the plurality of second passengers obtains a plurality of waypoint sets according to the first path point set, specifically including:

[0100] Selecting one second passenger in turn as the current passenger, and obtaining a waypoint set of the current passenger according to a preset waypoint matching method, until the plurality of second passengers all obtain corresponding waypoint sets;

[0101] Wherein, the waypoint matching method comprises:

[0102] Obtaining an initial waypoint set according to the first waypoint set and the second waypoint set of the current passenger;

[0103] The path distances of all the initial waypoints in the initial waypoint set are calculated respectively, and the initial waypoints whose path distances fall within a preset distance interval are included in the waypoint set of the current passenger.

[0104] In some optional implementations of the present application, obtaining the initial waypoint set according to the first waypoint set and the second waypoint set of the current passenger specifically includes:

[0105] Match each path point in the first path point set and the second path point set in turn. When the position sequence of the path point in the first path point set and the second path point set is the same, classify the path point into the initial path point set until any point set in the first path point set or the second path point set is matched.

[0106] Exemplarily, the initial waypoint set is obtained according to the first waypoint set and the second waypoint set of the current passenger, and the specific steps are:

[0107] For the first path point set S a = {u1, u2, ..., u n} and the second path point set S of the current passenger (assuming it is the b-th second passenger) b = {v b1 , v b2 , ..., v bn}, at the same starting point, that is, u1=v b1 In the case of, find the index k such that u h =v bh ;

[0108] Will u1,u2,...,u h , ..., u k As the initial waypoint set I = {u1, u2, ..., u h , ..., u k}.

[0109] In some optional implementations of the present application, respectively calculating the path distances of all initial waypoints in the initial waypoint set, and classifying the initial waypoints whose path distances fall within a preset distance interval into the waypoint set of the current passenger, specifically includes:

[0110] Calculating the waypoint distances between all the initial waypoints in the initial waypoint set according to a preset waypoint distance algorithm;

[0111] According to the waypoint distances, the path distances of all initial waypoints are obtained;

[0112] Initial waypoints whose path distances fall within a preset distance interval are included in the waypoint set of the current passenger.

[0113] In certain optional embodiments of the present application, the waypoint distance algorithm includes but is not limited to the Haversine algorithm.

[0114] Exemplarily, the steps of respectively calculating the path distances of all the initial waypoints in the initial waypoint set and classifying the initial waypoints whose path distances fall within a preset distance interval into the waypoint set of the current passenger are as follows:

[0115] For the initial set of waypoints I = {u1, u2, ..., u h , ..., u k}, calculate the waypoint distances d(u1, u2), d(u2, u3), ..., d(u k-1 ,u k );

[0116] According to the distance of the waypoints, the path distance of all initial waypoints is obtained as:

[0117] dist (u1, u2) = d (u1, u2); dist (u1, u3) = dist (u1, u2) + d (u2, u3); ...; dist (u1, u k )=dist(u1,u k-1 )+d(u k-1 ,u k );

[0118] If D min ≤dist(u α ,u β )≤D max , then the initial waypoint u β A set of waypoints included in the current passenger's waypoints;

[0119] The distance of the waypoints is specifically:

[0120]

[0121] Where r is the radius of the earth, Δφ=|φ α -φ β | is the initial waypoint uα ,u β The absolute value of the latitude difference, Δλ=|λ α -λ β | is the initial waypoint u α ,u β The absolute value of the longitude difference, λ α ,φ α is the initial waypoint u α The longitude and latitude, λ β ,φ β is the initial waypoint u β longitude and latitude.

[0122] Considering that this application needs to solve the problem of long waiting time for passengers due to the shortage of vehicles at transportation hubs during holidays, when the waypoint is too far from the transportation hub, the difficulty of passenger matching is too great; when the waypoint is too close to the transportation hub, the passenger flow at the transportation hub is not alleviated. Based on the above facts, those skilled in the art can make D according to the historical implementation of this application near the transportation hub and the actual situation. min , D max The value of is set to ensure that the passenger flow of the transportation hub is effectively alleviated without increasing the difficulty of passenger matching. The preferred solution is D min =2km, D max =5km.

[0123] The present application sequentially selects the second passenger as the current passenger and obtains a waypoint set according to a waypoint matching method. During the matching, an initial waypoint set is first obtained according to the first path point set and the second path point set, while taking into account the paths of the first passenger and the second passenger, which can improve the path overlap and thus improve the rationality of path planning. Then, the path distances of all initial waypoints in the initial waypoint set are calculated and a waypoint set is obtained according to the path distances, which can exclude initial waypoints whose path distances are in an unreasonable range and improve the rationality of waypoint selection.

[0124] In certain embodiments of the present application, the step of obtaining multiple optimal waypoints based on the multiple waypoint sets and in combination with idle vehicle data specifically includes:

[0125] Selecting one waypoint set in turn as the current waypoint set, and obtaining the optimal waypoint in the current waypoint set according to a preset waypoint selection method, until the optimal waypoint is selected from all the waypoint sets;

[0126] The method for selecting a waypoint includes:

[0127] According to the idle vehicle data, a plurality of idle vehicle clusters are obtained based on a clustering algorithm;

[0128] Calculating the priority of each waypoint according to the number of idle vehicles in the plurality of idle vehicle clusters;

[0129] The waypoint with the highest priority is used as the optimal waypoint of the current waypoint set.

[0130] In certain optional embodiments of the present application, preferred categories of the idle vehicle data include, but are not limited to, vehicle operating status and vehicle location information; wherein the vehicle location information is obtained through GPS positioning.

[0131] In some optional implementations of the present application, the idle vehicle data is obtained in the following manner:

[0132] Each waypoint queries the server for vehicles within a preset radius of the corresponding waypoint to obtain corresponding vehicle operation data; wherein the vehicle operation data is obtained by each vehicle sending the corresponding latest vehicle operation status and vehicle location information to the server when the vehicle operation status of each vehicle changes and the server stores the information;

[0133] Each waypoint filters the vehicle operation data according to the vehicle operation status of each vehicle to obtain idle vehicle data.

[0134] In some optional implementations of the present application, obtaining a plurality of idle vehicle clusters based on the idle vehicle data and a clustering algorithm specifically includes:

[0135] According to the location information of the idle vehicles, multiple idle vehicle clusters are obtained based on the clustering algorithm.

[0136] In certain optional embodiments of the present application, the clustering algorithm includes but is not limited to a K-means clustering algorithm, a mean shift clustering algorithm, a DBSCAN (Density-Based Spatial Clustering of Applications with Noise) clustering algorithm, and a hierarchical clustering algorithm.

[0137] Exemplarily, the plurality of idle vehicles are clustered into a set C = {c1, c2, ..., c q}, where c1, c2, ..., c j , ..., c q Each idle vehicle is clustered, and each idle vehicle cluster c j The corresponding total number of idle vehicles is N j .

[0138] The present application sequentially selects a set of waypoints as the current set of waypoints and obtains the optimal waypoint according to the waypoint selection method. When selecting, multiple idle vehicle clusters are first obtained based on the idle vehicle data based on the clustering algorithm, and then the priority of each waypoint is calculated according to the number of idle vehicles in the multiple idle vehicle clusters, and the waypoint with the largest priority is used as the optimal waypoint. The influence of idle vehicles on the selection of the optimal waypoint is taken into account, and the rationality of the selection of the optimal waypoint is improved.

[0139] In certain embodiments of the present application, the calculating the priority of each waypoint according to the number of idle vehicles of the plurality of idle vehicle clusters specifically includes:

[0140]

[0141] Among them, p i is the priority of the i-th waypoint, d ij is the distance between the cluster center of the jth idle vehicle cluster and the i-th waypoint, q is the number of idle vehicle clusters, N j is the total number of idle vehicles included in the jth idle vehicle cluster, E i ={j|d ij ≥d max} is the idle vehicle cluster set whose distance from the cluster center of the idle vehicle cluster to the i-th waypoint exceeds the upper limit of the idle vehicle scheduling distance, d max The upper limit of the dispatch distance for idle vehicles.

[0142] In some optional embodiments of the present application, d is calculated ij The preferred scheme of the distance algorithm is the great circle distance algorithm, which is as follows:

[0143]

[0144] Where r is the radius of the earth, Δφ ij =|φ i -φ j | is the absolute value of the latitude difference between the i-th waypoint and the cluster center of the j-th idle vehicle cluster, Δλ ij =|λ i -λ j | is the absolute value of the longitude difference between the i-th waypoint and the cluster center of the j-th idle vehicle cluster, λ i ,φ i is the longitude and latitude of the jth waypoint, λ j ,φ j are the longitude and latitude of the cluster center of the jth idle vehicle cluster.

[0145] Considering that this application needs to solve the problem of long waiting time for passengers due to the shortage of vehicles at transportation hubs during holidays, when the distance from the cluster center of a cluster to a certain waypoint is too far (i.e., exceeds the upper limit of the idle vehicle dispatch distance), the time for the idle vehicles of the cluster to reach the waypoint will be relatively increased. For this waypoint, if the priority of the cluster is not lowered, there is a possibility of unnecessary increase in passenger waiting time (or vehicle en route time). Based on the above facts, those skilled in the art can make an assessment based on the historical implementation of this application near transportation hubs and the actual situation. max The value of is set to ensure that the passenger waiting time (or vehicle en route time) is reasonable. The preferred solution is d max =5km.

[0146] The present application obtains the priority of each waypoint based on the distance from the cluster center of each idle vehicle cluster to the waypoint, the total number of idle vehicles and the upper limit of the idle vehicle scheduling distance, takes into account the influence of the scheduling distance, scheduling time and scheduling amount of idle vehicles on the selection of the optimal waypoint, and improves the rationality of the selection of the optimal waypoint.

[0147] By first obtaining multiple waypoint sets corresponding to multiple second passengers' second path point sets, the waypoint set of each second passenger can be matched for the first passenger at the same time, thereby improving the matching efficiency. Then, multiple optimal waypoints are obtained by combining the idle vehicle data, and the influence of the idle vehicles on the selection of the optimal waypoints is taken into consideration, thereby improving the rationality of the optimal waypoints.

[0148] Step S104: Obtaining a second passenger who is the best match for the first passenger based on the multiple optimal waypoints.

[0149] For example, the first passenger is marked as a, and the total number of second passengers that need to be matched with the first passenger a is z. Each optimal waypoint corresponds to a second passenger, and the priority marks corresponding to the multiple optimal waypoints are set as r b is the position order of the bth second passenger among multiple second passengers.

[0150] In some optional embodiments of the present application, the bit sequence r b The preferred solution is the position order of the b-th second passenger among multiple second passengers sorted by waiting time.

[0151] In certain embodiments of the present application, obtaining a second passenger who is the best match for the first passenger according to the multiple optimal waypoints specifically includes:

[0152] According to the plurality of optimal waypoints and the vehicle passenger carrying rate, based on a first passenger matching function, obtaining a second passenger who is the best match for the first passenger;

[0153] The first passenger matching function is specifically:

[0154]

[0155] Among them, a and b are the first passenger and the bth second passenger respectively, r b is the position of the bth second passenger among multiple second passengers, v is the current vehicle passenger carrying rate, is the priority of the optimal waypoints for the first passenger a and the bth second passenger.

[0156] The present application calculates the best matching second passenger based on the position sequence of the second passengers, the current vehicle passenger load rate and the priority of the best waypoints for each second passenger. This multi-factor consideration can improve the rationality of passenger matching.

[0157] In certain embodiments of the present application, obtaining a second passenger who is the best match for the first passenger according to the multiple optimal waypoints specifically includes:

[0158] According to the plurality of optimal waypoints, the vehicle passenger loading rate and a preset fare allocation coefficient, based on a second passenger matching function, obtaining a second passenger who is the best match for the first passenger;

[0159]

[0160] Among them, a and b are the first passenger and the bth second passenger respectively, r b is the position of the bth second passenger among multiple second passengers, γ is the cost allocation coefficient, v is the current vehicle passenger carrying rate, is the priority of the optimal waypoints for the first passenger a and the bth second passenger.

[0161] The present application calculates the best matching second passenger based on the second passenger's position order, fare allocation coefficient, current vehicle passenger load rate and priority of the best waypoints for each second passenger, and can simultaneously consider fare allocation among shared passengers. Such multi-factor considerations can improve the rationality of passenger matching.

[0162] Considering that this application needs to solve the problem of long waiting time for passengers due to the shortage of vehicles at transportation hubs during holidays, the setting of the vehicle passenger load rate will first affect the difficulty of passenger matching and secondly affect the waiting time of passengers. Under the premise that the current vehicle passenger load rate is not set or obtained, the default vehicle passenger load rate is too fast or too slow, which will lead to distortion of passenger matching. Based on the above facts, those skilled in the art can set the default vehicle passenger load rate v according to the historical implementation and actual situation of this application near the transportation hub when the current vehicle passenger load rate is not set or obtained, so as to ensure that the impact of the vehicle passenger load rate on passenger matching is reasonable. The preferred solution is v = 2.5 people / min.

[0163] The present application first obtains a corresponding first path point set according to the destination of the first passenger, and then obtains multiple second passengers with the same starting point as the first passenger and the corresponding second path point set according to the vehicle passenger carrying rate, so that the second passengers who are more reasonably matched with the first passenger can be screened out first, thereby improving the rationality of passenger matching; then multiple optimal waypoints are obtained corresponding to the second path point sets of the multiple second passengers, so that the optimal waypoints of each second passenger can be matched for the first passenger at the same time, thereby improving the matching efficiency, and then the best matched second passenger is obtained according to the multiple optimal waypoints, so that the rationality of passenger matching can be improved, thereby improving the utilization rate of vehicle sharing.

[0164] Corresponding to the previous method, see Figure 2 , the embodiment of the present application provides a passenger allocation device, including a first path acquisition module 210, a second path acquisition module 220, an optimal path acquisition module 230 and a second passenger matching module 240;

[0165] The first path acquisition module 210 is used to acquire a first path point set of the first passenger according to the current destination of the first passenger;

[0166] The second path acquisition module 220 is used to acquire a plurality of second passengers having the same starting point as the first passenger and a corresponding second path point set according to the current vehicle passenger carrying rate;

[0167] The optimal path acquisition module 230 is used to obtain a plurality of optimal path points according to the first path point set corresponding to the second path point set of the plurality of second passengers;

[0168] The second passenger matching module 240 is used to obtain a second passenger who is the best match with the first passenger based on the multiple optimal waypoints.

[0169] In certain embodiments of the present application, the optimal path acquisition module 230 includes a path point set acquisition submodule 231 and an optimal path point acquisition submodule 232;

[0170] The waypoint set acquisition submodule 231 is used to obtain a plurality of waypoint sets corresponding to the second waypoint sets of the plurality of second passengers according to the first waypoint set;

[0171] The optimal waypoint acquisition submodule 232 is used to obtain multiple optimal waypoints based on the multiple waypoint sets and the idle vehicle data.

[0172] In some embodiments of the present application, the waypoint set acquisition submodule 231 includes a waypoint set acquisition unit 2311;

[0173] The waypoint set acquisition unit 2311 is used to select one second passenger as the current passenger in turn, and obtain the waypoint set of the current passenger according to a preset waypoint matching method, until the plurality of second passengers all obtain corresponding waypoint sets;

[0174] Wherein, the waypoint matching method comprises:

[0175] Obtaining an initial waypoint set according to the first waypoint set and the second waypoint set of the current passenger;

[0176] The path distances of all the initial waypoints in the initial waypoint set are calculated respectively, and the initial waypoints whose path distances fall within a preset distance interval are included in the waypoint set of the current passenger.

[0177] In certain embodiments of the present application, the optimal waypoint acquisition submodule 232 includes an optimal waypoint acquisition unit 2321;

[0178] The optimal waypoint acquisition unit 2321 is used to select one waypoint set as the current waypoint set in turn, and obtain the optimal waypoint in the current waypoint set according to a preset waypoint selection method, until the optimal waypoint is selected from the multiple waypoint sets;

[0179] The method for selecting a waypoint includes:

[0180] According to the idle vehicle data, a plurality of idle vehicle clusters are obtained based on a clustering algorithm;

[0181] Calculating the priority of each waypoint according to the number of idle vehicles in the plurality of idle vehicle clusters;

[0182] The waypoint with the highest priority is used as the optimal waypoint of the current waypoint set.

[0183] In certain embodiments of the present application, the calculating the priority of each waypoint according to the number of idle vehicles of the plurality of idle vehicle clusters specifically includes:

[0184]

[0185] Among them, p i is the priority of the i-th waypoint, d ij is the distance between the cluster center of the jth idle vehicle cluster and the i-th waypoint, q is the number of idle vehicle clusters, N j is the total number of idle vehicles included in the jth idle vehicle cluster, E i ={j|d ij ≥d max} is the idle vehicle cluster set whose distance from the cluster center of the idle vehicle cluster to the i-th waypoint exceeds the upper limit of the idle vehicle scheduling distance, d max The upper limit of the dispatch distance for idle vehicles.

[0186] In certain embodiments of the present application, the second passenger matching module 240 includes a first optimal matching submodule 241;

[0187] The first optimal matching submodule 241 is configured to obtain a second passenger who is optimally matched with the first passenger based on the first passenger matching function according to the multiple optimal waypoints and the vehicle passenger carrying rate;

[0188] The first passenger matching function is specifically:

[0189]

[0190] Among them, a and b are the first passenger and the bth second passenger respectively, r b is the position of the bth second passenger among multiple second passengers, v is the current vehicle passenger carrying rate, is the priority of the optimal waypoints for the first passenger a and the bth second passenger.

[0191] In certain embodiments of the present application, the second passenger matching module 240 further includes a second optimal matching submodule 242;

[0192] The second optimal matching submodule 242 is configured to obtain a second passenger who is the best match with the first passenger based on the second passenger matching function according to the plurality of optimal waypoints, the vehicle passenger loading rate and a preset fare allocation coefficient;

[0193]

[0194] Among them, a and b are the first passenger and the bth second passenger respectively, r b is the position of the bth second passenger among multiple second passengers, γ is the cost allocation coefficient, υ is the current vehicle passenger carrying rate, is the priority of the optimal waypoints for the first passenger a and the bth second passenger.

[0195] The present application first obtains a corresponding first path point set according to the destination of the first passenger, and then obtains multiple second passengers with the same starting point as the first passenger and the corresponding second path point set according to the vehicle passenger carrying rate, so that the second passengers who are more reasonably matched with the first passenger can be screened out first, thereby improving the rationality of passenger matching; then multiple optimal waypoints are obtained corresponding to the second path point sets of the multiple second passengers, so that the optimal waypoints of each second passenger can be matched for the first passenger at the same time, thereby improving the matching efficiency, and then the best matched second passenger is obtained according to the multiple optimal waypoints, so that the rationality of passenger matching can be improved, thereby improving the utilization rate of vehicle sharing.

[0196] It should be understood that the device provided in the embodiments of the present application corresponds to the aforementioned method, and a passenger allocation device provided in the embodiments of the present application can implement a passenger allocation method provided in any embodiment of the present application.

[0197] Adaptively, the embodiments of the present application also provide a computer device and a computer-readable storage medium.

[0198] The computer device comprises: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor;

[0199] Wherein, when the processor executes the computer program, a passenger allocation method of the present application is implemented.

[0200] The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute a passenger allocation method of the present application.

[0201] The above are some implementation methods of the present application, and the purpose, technical scheme and beneficial effects of the present application are further described in detail. It should be clear that the above-mentioned partial implementation methods of the present application cannot be understood as limiting the present application. It is particularly pointed out that for those skilled in the art, any changes, modifications, equivalent substitutions and variations made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A passenger allocation method, characterized in that: include: According to the current destination of the first passenger, obtaining a first path point set of the first passenger; According to the current vehicle passenger carrying rate, obtaining a plurality of second passengers having the same starting point as the first passenger and a corresponding second path point set; A second set of path points corresponding to the plurality of second passengers, and obtaining a plurality of optimal waypoints according to the first set of path points; Based on the multiple optimal waypoints, a second passenger who is the best match for the first passenger is obtained.

2. A passenger allocation method according to claim 1, characterized in that: The second path point set corresponding to the plurality of second passengers obtains a plurality of optimal waypoints according to the first path point set, specifically comprising: A second path point set corresponding to the plurality of second passengers, and a plurality of waypoint sets are obtained according to the first path point set; According to the plurality of waypoint sets, in combination with idle vehicle data, a plurality of optimal waypoints are obtained.

3. A passenger allocation method according to claim 2, characterized in that: The second path point set corresponding to the plurality of second passengers obtains a plurality of waypoint sets according to the first path point set, specifically comprising: Selecting one second passenger in turn as the current passenger, and obtaining a waypoint set of the current passenger according to a preset waypoint matching method, until the plurality of second passengers all obtain corresponding waypoint sets; Wherein, the waypoint matching method comprises: Obtaining an initial waypoint set according to the first waypoint set and the second waypoint set of the current passenger; The path distances of all the initial waypoints in the initial waypoint set are calculated respectively, and the initial waypoints whose path distances fall within a preset distance interval are included in the waypoint set of the current passenger.

4. A passenger allocation method according to claim 2, characterized in that: The step of obtaining a plurality of optimal waypoints according to the plurality of waypoint sets and in combination with idle vehicle data specifically includes: Selecting one waypoint set in turn as the current waypoint set, and obtaining the optimal waypoint in the current waypoint set according to a preset waypoint selection method, until the optimal waypoint is selected from all the waypoint sets; The method for selecting a waypoint includes: According to the idle vehicle data, a plurality of idle vehicle clusters are obtained based on a clustering algorithm; Calculating the priority of each waypoint according to the number of idle vehicles in the plurality of idle vehicle clusters; The waypoint with the highest priority is used as the optimal waypoint of the current waypoint set.

5. A passenger allocation method according to claim 4, characterized in that: The calculating the priority of each waypoint according to the number of idle vehicles clustered by the plurality of idle vehicles specifically includes: Among them, p i is the priority of the i-th waypoint, d ij is the distance between the cluster center of the jth idle vehicle cluster and the i-th waypoint, q is the number of idle vehicle clusters, N j is the total number of idle vehicles included in the jth idle vehicle cluster, E i ={j|d ij ≥d max } is the idle vehicle cluster set whose distance from the cluster center of the idle vehicle cluster to the i-th waypoint exceeds the upper limit of the idle vehicle scheduling distance, d max The upper limit of the dispatch distance for idle vehicles.

6. A passenger allocation method according to claim 1, characterized in that: The obtaining, according to the plurality of optimal waypoints, a second passenger who is the best match for the first passenger specifically includes: According to the plurality of optimal waypoints and the vehicle passenger carrying rate, based on a first passenger matching function, obtaining a second passenger who is the best match for the first passenger; The first passenger matching function is specifically: Among them, a and b are the first passenger and the bth second passenger respectively, r b is the position of the bth second passenger among multiple second passengers, v is the current vehicle passenger carrying rate, is the priority of the optimal waypoints for the first passenger a and the bth second passenger.

7. A passenger allocation method according to claim 1, characterized in that: The obtaining, according to the plurality of optimal waypoints, a second passenger who is the best match for the first passenger specifically includes: According to the plurality of optimal waypoints, the vehicle passenger loading rate and a preset fare allocation coefficient, based on a second passenger matching function, obtaining a second passenger who is the best match for the first passenger; Among them, a and b are the first passenger and the bth second passenger respectively, r b is the position of the bth second passenger among multiple second passengers, γ is the cost allocation coefficient, v is the current vehicle passenger carrying rate, is the priority of the optimal waypoints for the first passenger a and the bth second passenger.

8. A passenger distribution device, characterized in that: It includes a first path acquisition module, a second path acquisition module, an optimal route acquisition module and a second passenger matching module; The first path acquisition module is used to acquire a first path point set of the first passenger according to the current destination of the first passenger; The second path acquisition module is used to acquire a plurality of second passengers having the same starting point as the first passenger and a corresponding second path point set according to the current vehicle passenger carrying rate; The optimal path acquisition module is used to obtain a plurality of optimal path points according to the first path point set corresponding to the second path point set of the plurality of second passengers; The second passenger matching module is used to obtain a second passenger who is the best match with the first passenger based on the multiple optimal waypoints.

9. A computer device, characterized in that: include: processor; Memory; a computer program stored in the memory and configured to be executed by the processor; When the processor executes the computer program, a passenger allocation method as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute a passenger allocation method as described in any one of claims 1 to 7.

Images