Passenger flow evacuation method and device for online car-hailing demand abnormal aggregation

Abstract

The invention relates to a passenger flow evacuation method and device for abnormal gathering of online car-hailing demands, and belongs to the technical field of traffic, and the method comprises the steps: obtaining the current online car-hailing order information and historical online car-hailing order information of a target region, and judging whether the online car-hailing demands are gathered abnormally or not; and the passenger destinations are clustered by using an improved k-means algorithm, the transfer positions and number of transport vehicles in the evacuation scheme are determined, and bus and online car-hailing resources are reasonably allocated to evacuate the passengers. According to the method and the device, the technical effects of efficiently identifying the demand anomaly aggregation region, optimizing resource configuration and improving evacuation efficiency are achieved.

Description

Technical Field

[0001] The present invention relates to the field of transportation technologies, and particularly to a passenger flow evacuation method and device for abnormal aggregation of online car-hailing demands. Background Art

[0002] With the acceleration of the urbanization process and the rapid development of Internet technologies, online car-hailing, as a new travel mode, has quickly won the favor of a large number of passengers with its convenience and flexibility. However, during specific times (such as peak commuting hours, holidays, etc.) and in specific areas (such as commercial centers, transportation hubs, etc.), the demands for online car-hailing often show abnormal aggregation phenomena. Such demand aggregation will not only significantly prolong the waiting time of passengers and reduce travel efficiency, but may also trigger traffic congestion and further exacerbate the urban traffic pressure.

[0003] Traditional countermeasures, such as simply increasing the supply of online car-hailing, although can relieve the demand pressure to a certain extent, are often difficult to quickly and effectively solve the problem of abnormal aggregation of online car-hailing demands due to limitations in vehicle numbers, road capacities, and traffic conditions. In addition, solely relying on online car-hailing for evacuation may also exacerbate traffic congestion due to the frequent entry and exit of vehicles in the aggregation area, forming a vicious cycle.

[0004] Therefore, there is an urgent need for a solution that can efficiently identify the abnormal aggregation of online car-hailing demands and quickly evacuate the aggregated passengers. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide a passenger flow evacuation method and device for abnormal aggregation of online car-hailing demands, aiming to solve at least one of the above technical problems.

[0006] The technical solution of the present invention to solve the above technical problems is as follows: In the first aspect, the present application provides a passenger flow evacuation method for abnormal aggregation of online car-hailing demands, adopting the following technical solution: A passenger flow evacuation method for abnormal aggregation of online car-hailing demands includes: Obtaining the current online car-hailing order information and historical online car-hailing order information of a target area corresponding to the current time; Based on the current online car-hailing order information and historical online car-hailing order information of the target area, determining whether the online car-hailing demand in the target area has an abnormal aggregation; If the online car-hailing demand in the target area has an abnormal aggregation, then based on the current online car-hailing order information, determining an evacuation plan for the target area and evacuating the passengers in the target area according to the evacuation plan.

[0007] The beneficial effects of the present invention are as follows: By combining historical order data and current order information, this method can effectively determine the occurrence of abnormal aggregation of online car-hailing demand in the target area, ensuring that measures are taken in a timely manner to alleviate the problems of passenger waiting and traffic congestion. At the same time, an evacuation plan is formulated based on the current order information to achieve the rapid and orderly evacuation of the aggregated passengers.

[0008] Based on the above technical solutions, the present invention can be further improved as follows.

[0009] Further, determining whether there is abnormal aggregation of online car-hailing demand in the target area based on the historical online car-hailing order information of the target area includes: Based on the historical online car-hailing order information, determining the mean and standard deviation of the order volume in the target area; Based on the mean and standard deviation of the order volume, determining an order volume threshold; If the current online car-hailing order information is greater than the order volume threshold, it is determined that there is abnormal aggregation of online car-hailing demand in the target area; Otherwise, it is determined that there is no abnormal aggregation of online car-hailing demand in the target area.

[0010] The beneficial effects of adopting the above further solution are as follows: It is possible to statistically analyze the mean and standard deviation of the order volume in the target area based on historical data, thereby setting the order volume threshold. When the current online car-hailing order information exceeds this threshold, it can be accurately determined that abnormal aggregation has occurred in the target area. This method realizes the efficient identification of abnormal aggregation of online car-hailing demand, provides a reliable basis for subsequent activation of the evacuation plan, and effectively avoids the problems of excessive passenger waiting time and traffic congestion caused by abnormal demand.

[0011] Further, the current online car-hailing order information includes the destinations of multiple passengers. Determining the evacuation plan for the target area based on the current online car-hailing order information includes: Based on a preset improved k-means algorithm, clustering the destinations of all passengers to obtain multiple clusters, where one cluster represents a transfer location of multiple transport vehicles in the evacuation plan, and the transport vehicles are any one or more of online cars and buses; Based on the destinations of the passengers corresponding to each cluster and a preset transport vehicle allocation rule, determining the number of transport vehicles departing from the target area to each of the transfer locations; Based on the number of transport vehicles departing from the target area to each transfer location, determining the evacuation plan for the target area.

[0012] The beneficial effects of adopting the above further scheme are as follows: By clustering the destinations of all passengers using an improved k-means algorithm, multiple clusters are obtained, and each cluster represents the transfer location of the transport vehicle, thus realizing a reasonable grouping of the passengers' destinations and ensuring the optimization of the evacuation route. Based on the destinations of the passengers corresponding to each cluster, the number of passengers at each transfer location is determined, making the subsequent resource allocation more accurate and avoiding resource waste. According to the number of passengers at the transfer location and the preset bus allocation rules, the number of buses dispatched from the target area to each transfer point is determined, effectively utilizing the advantage of large passenger capacity of buses and improving the evacuation efficiency. At the same time, according to the number of passengers at each transfer point and the online car-hailing allocation rules, the number of required online car-hailing vehicles is determined, giving full play to the flexible characteristics of online car-hailing vehicles and ensuring that passengers can quickly reach their final destinations. By comprehensively considering the number of buses and online car-hailing vehicles, the evacuation plan for the target area is determined, achieving the optimal allocation of resources, significantly shortening the waiting time of passengers, improving the service quality, and at the same time reducing the possibility of traffic congestion.

[0013] Further, clustering all the said destinations based on the preset improved k-means algorithm to obtain multiple clusters includes: Step S31, obtaining multiple clustering numbers; Step S32, for each of the said clustering numbers, based on this clustering number, determining the current center of each cluster in the current iteration. The clustering number represents the number of clusters in the clustering process, and the current center represents the location of the cluster; Step S33, for each of the said clustering numbers, respectively calculating the distance information between the destination of each of the said passengers in the current iteration and the current centers of each cluster; Step S34, for each of the said clustering numbers, based on the respective distance information, allocating multiple passengers to each of the said clusters to obtain the number of passengers in each cluster; Step S35, for each of the said clustering numbers, based on the set bus information, the number of passengers in each cluster, and the number of available online car-hailing vehicles corresponding to the current center of each cluster, determining whether each of the said clusters meets the set constraint conditions; Step S36, for each of the said clustering numbers, if each of the said clusters meets the set constraint conditions, obtaining the iteration result. The iteration result includes multiple current clusters, the destinations of the passengers corresponding to each current cluster, and the clustering number, and calculating the objective value of the iteration result based on the preset objective function and multiple distance information; Step S37, execute steps S32 to S36 until the iteration times are met, and take the iteration result corresponding to the minimum objective value in the current iteration cycle as the current clustering result of this clustering number; Step S38: For each of the number of clusters, if any of the clusters does not meet the set constraint conditions, then based on the respective distance information, determine the new center of each cluster, and use the new center as the current center in the next iteration, and execute Steps S32 to S36 until the number of iterations is met, and use the iteration result with the minimum objective value in the current iteration cycle as the current clustering result for this number of clusters; Step S39: Based on the current clustering results corresponding to each of the number of clusters and the preset elbow method, determine the target clustering result, where the target clustering result includes multiple clusters, the passenger destinations corresponding to each cluster, and the optimal number of clusters.

[0014] The beneficial effects of adopting the above further solution are as follows: This method not only ensures that passengers within each cluster can be effectively assigned to the nearest transfer point, but also takes into account the bus passenger capacity efficiency and the sufficiency of online car-hailing resources, avoiding problems of resource waste and insufficient transport capacity. In addition, by determining the optimal number of clusters through the elbow method, the scientificity and rationality of the clustering result are further improved, providing a reliable basis for formulating subsequent evacuation plans.

[0015] Further, the determining whether each cluster meets the set constraint conditions based on the set bus information, the number of passengers in each cluster, and the available number of online car-hailing corresponding to the current center of each cluster includes: For each cluster, based on the set bus information and the number of passengers in the cluster, determine whether the passenger capacity of each bus corresponding to the cluster is greater than the set quantity threshold; and, For each cluster, determine whether the available number of online car-hailing corresponding to the current center of the cluster is not less than the number of passengers in the cluster; For each cluster, if the passenger capacity of each bus corresponding to the cluster is greater than the set quantity threshold, and if the available number of online car-hailing corresponding to the current center of the cluster is not less than the number of passengers in the cluster, then determine that each cluster meets the set constraint conditions, otherwise determine that each cluster does not meet the set constraint conditions.

[0016] The beneficial effects of adopting the above further solution are as follows: For each cluster, by determining whether the bus passenger capacity is greater than the set quantity threshold, the efficient use of bus resources is ensured, and resource waste is avoided. For each cluster, by ensuring that the available number of online car-hailing corresponding to the current center is not less than the number of passengers, the smooth evacuation of passengers from the transfer point to the final destination is effectively guaranteed. Through the setting of the above dual constraint conditions, it is ensured that each cluster meets the evacuation requirements, thereby improving the feasibility and reliability of the overall evacuation plan and realizing the efficient evacuation of passengers in areas with abnormal aggregation of online car-hailing demands.

[0017] Second aspect, the present application provides a passenger flow evacuation device for abnormal aggregation of online car-hailing demands, and adopts the following technical solutions: A passenger flow evacuation device for abnormal aggregation of online car-hailing demands, comprising: An acquisition module, configured to acquire the current online car-hailing order information and historical online car-hailing order information of a target area corresponding to the current time; A judgment module, configured to judge whether the online car-hailing demand in the target area has an abnormal aggregation based on the historical online car-hailing order information of the target area; An evacuation plan determination module, if the online car-hailing demand in the target area has an abnormal aggregation, then determine an evacuation plan for the target area based on the current online car-hailing order information, and evacuate the passengers in the target area according to the evacuation plan.

[0018] Further, the judgment module is specifically configured to: Based on the historical online car-hailing order information, determine the mean and standard deviation of the order volume in the target area; Based on the mean and standard deviation of the order volume, determine an order volume threshold; If the current online car-hailing order information is greater than the order volume threshold, it is determined that the online car-hailing demand in the target area has an abnormal aggregation; Otherwise, it is determined that the online car-hailing demand in the target area has not had an abnormal aggregation.

[0019] Further, the evacuation plan determination module includes: A clustering sub-module, configured to cluster the destinations of all passengers based on a preset improved k-means algorithm to obtain multiple clusters, and one cluster represents a transfer position of multiple transport vehicles in the evacuation plan, and the transport vehicle is any one or more of online car-hailing vehicles and buses; A first determination sub-module, configured to determine the number of transport vehicles sent from the target area to each of the transfer positions based on the destinations of the passengers corresponding to each cluster and a preset transport vehicle allocation rule; A second determination sub-module, configured to determine the evacuation plan for the target area based on the number of transport vehicles sent from the target area to each transfer position.

[0020] Further, the clustering sub-module is specifically configured to perform the following steps: Step S31, obtain multiple clustering numbers; Step S32, for each of the clustering numbers, based on the clustering number, determine the current center of each cluster in the current iteration, the clustering number represents the number of clusters in the clustering process, and the current center represents the position of the cluster; Step S33: For each of the number of clusters, calculate the distance information between the destination of each passenger in the current iteration and the current centers of each cluster respectively. Step S34: For each of the number of clusters, based on the respective distance information, allocate multiple passengers to each of the clusters respectively to obtain the number of passengers in each cluster. Step S35: For each of the number of clusters, based on the set bus information, the number of passengers in each cluster, and the available online car-hailing vehicle quantity corresponding to the current center of each cluster, determine whether each cluster meets the set constraint conditions. Step S36: For each of the number of clusters, if each cluster meets the set constraint conditions, obtain the iteration result. The iteration result includes multiple current clusters, the passenger destinations corresponding to each current cluster, and the number of clusters, and calculate the objective value of the iteration result based on a preset objective function and multiple distance information. Step S37: Execute Steps S32 to S36 until the number of iterations is met, and take the iteration result corresponding to the minimum objective value in the current iteration cycle as the current clustering result for this number of clusters. Step S38: For each of the number of clusters, if there is any cluster that does not meet the set constraint conditions, determine the new center of each cluster based on the respective distance information, and take the new center as the current center in the next iteration. Then execute Steps S32 to S36 until the number of iterations is met, and take the iteration result with the minimum objective value in the current iteration cycle as the current clustering result for this number of clusters. Step S39: Based on the current clustering results corresponding to each of the number of clusters and the preset elbow method, determine the target clustering result. The target clustering result includes multiple clusters, the passenger destinations corresponding to each cluster, and the optimal number of clusters.

[0021] Further, the clustering sub-module determines whether each cluster meets the set constraint conditions based on the set bus information, the number of passengers in each cluster, and the available online car-hailing vehicle quantity corresponding to the current center of each cluster, including: For each cluster, based on the set bus information and the number of passengers in the cluster, determine whether the passenger capacity of each bus corresponding to the cluster is greater than the set quantity threshold; and For each cluster, determine whether the available online car-hailing vehicle quantity corresponding to the current center of the cluster is not less than the number of passengers in the cluster; For each cluster, if the passenger capacity of each bus corresponding to the cluster is greater than the set quantity threshold and if the available online car-hailing vehicle quantity corresponding to the current center of the cluster is not less than the number of passengers in the cluster, determine that each cluster meets the set constraint conditions; otherwise, determine that each cluster does not meet the set constraint conditions.

[0022] Additional aspects and advantages of the present application will be given in part in the following description, become apparent from the following description, or be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 Schematic flowchart of a passenger flow evacuation method for abnormal aggregation of online car-hailing demands provided for an embodiment of the present invention; Figure 2 Schematic diagram for determining the optimal number of clusters by the elbow method provided for an embodiment of the present invention; Figure 3 Schematic diagram showing the clustering result provided for an embodiment of the present invention; Figure 4 Schematic structural diagram of a passenger flow evacuation device for abnormal aggregation of online car-hailing demands provided for an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying Figures 1 to 4 drawings in the embodiments of the present application. Apparently, the described embodiments are some but not all of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the scope of protection of the present application.

[0025] In addition, the term "and / or" in this document is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this document generally represents an "or" relationship between the associated objects before and after unless otherwise specified.

[0026] The embodiments of the present application provide a passenger flow evacuation method for abnormal aggregation of online car-hailing demands. This method can be executed by an electronic device, which can be a server or a mobile terminal device. The server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services; the mobile terminal device can be a laptop computer, a desktop computer, etc., but is not limited thereto.

[0027] As Figure 1 shown, a passenger flow evacuation method for abnormal aggregation of online car-hailing demands includes: Step S1, obtaining the current online car-hailing order information and historical online car-hailing order information of the target area corresponding to the current time; In the embodiments of the present application, the target area may be an area or a specific location. The current online car-hailing order information can obtain all the online car-hailing orders within the target area at the current time through the real-time data interface of the online car-hailing platform. The online car-hailing order includes the order ID, the passenger location, and the passenger's destination. For example, the order volume in the current online car-hailing order information corresponding to the current time is 420.

[0028] The historical online car-hailing order information can obtain the online car-hailing order information within the target area in a previous period of time, such as in the past week, ten days, or a month, through the data interface or database of the online car-hailing platform.

[0029] Step S2: Based on the current online car-hailing order information and the historical online car-hailing order information of the target area, determine whether there is an abnormal aggregation of the online car-hailing demand in the target area; In the embodiments of the present application, specifically, step S2 includes: Based on the historical online car-hailing order information, determine the mean and standard deviation of the order volume in the target area; Based on the mean and standard deviation of the order volume, determine the order volume threshold; If the current online car-hailing order information is greater than the order volume threshold, it is determined that there is an abnormal aggregation of the online car-hailing demand in the target area; Otherwise, it is determined that there is no abnormal aggregation of the online car-hailing demand in the target area.

[0030] In the embodiments of the present application, taking the XX area as an example, for the current time window [8:00, 8:30], using the online car-hailing order volume data of the past 100 days, calculate the mean of the order volume within this time window and the standard deviation .

[0031] Calculate the standard deviation of the order volume within this time window The formula is as follows: ; Among them, is the standard deviation, is the mean, is the historical online car-hailing order information of the past t days, t is the number of days, and the value of t is t = 1, 2, ……, T.

[0032] If the current online car-hailing order information of the current time window is greater than the order volume threshold, it is determined that there is an abnormal demand aggregation in this area, that is, ; Among them, O is the current online car-hailing order information of the current time window, is a parameter. In the embodiments of the present application, is set to 3.

[0033] Step S3. If the online car-hailing demand in the target area shows abnormal aggregation, based on the current online car-hailing order information, determine the evacuation plan for the target area, and evacuate the passengers in the target area according to the evacuation plan.

[0034] In the embodiment of the present application, the current online car-hailing order information includes the destinations of multiple passengers. Specifically, the determination of the evacuation plan for the target area based on the current online car-hailing order information includes steps Sa to Sd: Step Sa. Based on the preset improved k-means algorithm, cluster the destinations of all passengers to obtain multiple clusters. Each cluster represents the transfer location of the transport vehicle in the evacuation plan. The transport vehicle can be any one or more of online cars and buses. The center of each cluster serves as the transfer point for buses and online cars. In the embodiment of the present application, step Sa specifically includes: Step S31. Obtain multiple numbers of clusters. In the embodiment of the present application, set the range of the number of clusters according to historical data or experience, for example, from 2 to 10.

[0035] Step S32. For each number of clusters, based on this number of clusters, determine the current center of each cluster in the current iteration. The number of clusters represents the number of clusters in the clustering process, and the current center represents the location of the cluster. In the embodiment of the present application, randomly select the corresponding number of data points as the current centers of the respective clusters for the initial clustering.

[0036] Step S33. For each number of clusters, calculate the distance information between the destination of each passenger and the current center of each cluster respectively. In the embodiment of the present application, based on the set distance formula, calculate the distance information between the destination of each passenger and the current center of each cluster respectively, such as Euclidean distance, Manhattan distance, and Chebyshev distance, etc.

[0037] Step S34. For each number of clusters, based on the respective distance information, allocate multiple passengers to each cluster respectively to obtain the number of passengers in each cluster. In the embodiment of the present application, allocate each passenger to the cluster with the current center of the cluster closest to its destination, and count the number of passengers allocated to each cluster.

[0038] Step S35. For each number of clusters, based on the set bus information, the number of passengers in each cluster, and the number of available online cars corresponding to the current center of each cluster, determine whether each cluster meets the set constraint conditions. In the embodiments of the present application, in step S35, based on the set bus information, the number of passengers in each cluster, and the number of available online car-hailing vehicles corresponding to the current center of each cluster, it is determined whether each cluster meets the set constraint conditions, which specifically includes: For each cluster, based on the set bus information and the number of passengers in the cluster, it is determined whether the passenger capacity of each bus corresponding to the cluster is greater than the set quantity threshold; and, For each cluster, it is determined whether the number of available online car-hailing vehicles corresponding to the current center of the cluster is not less than the number of passengers in the cluster; For each cluster, if the passenger capacity of each bus corresponding to the cluster is greater than the set quantity threshold, and if the number of available online car-hailing vehicles corresponding to the current center of the cluster is not less than the number of passengers in the cluster, it is determined that each cluster meets the set constraint conditions, otherwise it is determined that each cluster does not meet the set constraint conditions.

[0039] In the above embodiments, for each cluster, the following two conditions are required to be met: (1) The remainder of the number of passengers divided by the bus capacity should be greater than the threshold, that is: ; Wherein, is the number of passengers, is the bus capacity, is the set quantity threshold, that is, it represents the minimum number of passengers assigned to a bus to ensure the effective utilization of the capacity of each bus.

[0040] (2) There are enough available online car-hailing vehicles near the current center (transfer point) of the cluster, and the number of available online car-hailing vehicles can meet the passenger demand assigned to this transfer point , that is: .

[0041] In step S36, for each number of clusters, if each cluster meets the set constraint conditions, an iteration result is obtained. The iteration result includes multiple current clusters, the passenger destinations corresponding to each current cluster, and the number of clusters, and based on a preset objective function and multiple distance information, the objective value of the iteration result is calculated; In step S37, steps S32 to S36 are executed until the iteration times are met, and the iteration result corresponding to the minimum objective value in the current iteration period is used as the current clustering result for this number of clusters; Step S38: For each of the number of clusters, if any of the clusters does not meet the set constraint conditions, then based on the respective distance information, determine the new center of each cluster, and use the new center as the current center in the next iteration, and execute steps S32 to S36 until the number of iterations is met, and use the iteration result with the minimum objective value in the current iteration cycle as the current clustering result for this number of clusters; In the embodiments of the present application, the goal of clustering is to minimize the sum of the squares of the distances from each passenger's destination to the current center of the cluster to which it belongs. Therefore, the preset objective function is: ; where, is the passenger's destination, is the current center of the cluster, is the cluster the mean vector of all passenger destinations within.

[0042] Step S39: Based on the current clustering results corresponding to each of the number of clusters and the preset elbow method, determine the target clustering result, where the target clustering result includes multiple clusters, the passenger destinations corresponding to each cluster, and the optimal number of clusters.

[0043] In the embodiments of the present application, based on the objective values under different numbers of clusters, a line graph is drawn, where the horizontal axis represents the number of clusters and the vertical axis represents the corresponding objective value; select the number of clusters corresponding to the position where the decrease rate of the objective value on the line graph significantly slows down, and use this number of clusters as the optimal number of clusters.

[0044] For example, as Figure 2 shown, when the number of clusters is 6, the sum of squared errors significantly decreases. Therefore, the optimal number of clusters is 6. The finally obtained target clustering result is as Figure 3 shown. A total of 6 clusters are obtained, and the center of each cluster is used as the transfer point for buses and online car-hailing. Figure 3 In, the large dots of different colors represent the centers of each cluster, the small dots of different colors represent the positions of passengers, and the small dots of the same color represent the passenger positions that need to be assigned to the transfer points corresponding to the large dots of the same color.

[0045] Step Sb: Based on the destinations of the passengers corresponding to each cluster and the preset transportation vehicle allocation rules, determine the number of transportation vehicles departing from the target area to each of the transfer positions; Step Sc: Based on the number of transportation vehicles departing from the target area to each transfer position, determine the evacuation plan for the target area.

[0046] In the embodiments of the present application, based on the number of passengers corresponding to each transfer location and a preset bus allocation rule, the number of buses dispatched from the target area to each transfer location is determined, and / or, based on the number of passengers at each transfer location and a preset online car-hailing allocation rule, the number of online car-hailing vehicles dispatched from the target area to each transfer location is determined; subsequently, based on the number of buses and / or online car-hailing vehicles at each transfer point, an evacuation plan for the target area is determined.

[0047] In the embodiments of the present application, the centers of the 6 clusters obtained in step Sa are used as transfer points for buses and online car-hailing vehicles, and passengers are assigned to each transfer point according to the cluster to which the passenger destination belongs.

[0048] For example, the number of passengers assigned to transfer point 1 is 62; the number of passengers assigned to transfer point 2 is 111; the number of passengers assigned to transfer point 3 is 56; the number of passengers assigned to transfer point 4 is 56; the number of passengers assigned to transfer point 5 is 73; the number of passengers assigned to transfer point 6 is 62.

[0049] According to the number of passengers assigned to each transfer point , estimate the number of buses dispatched from the gathering area to each transfer point : ; Finally, it is obtained that the number of buses to be dispatched from the gathering area to transfer point 1, transfer point 3, transfer point 4, transfer point 5, and transfer point 6 is 2; the number of buses to be dispatched from the gathering area to transfer point 2 is 3.

[0050] According to the number of passengers assigned to each transfer point , estimate the number of online car-hailing vehicles required for each transfer point : ; Among them, is the average number of passengers carried by a single online car-hailing vehicle. In the embodiments of the present application is 1.4. Finally, it is obtained that the number of online car-hailing vehicles to be dispatched to transfer point 1 is 45; the number of online car-hailing vehicles to be dispatched to transfer point 2 is 80; the number of online car-hailing vehicles to be dispatched to transfer point 3 is 40; the number of online car-hailing vehicles to be dispatched to transfer point 4 is 40; the number of online car-hailing vehicles to be dispatched to transfer point 5 is 53; the number of online car-hailing vehicles to be dispatched to transfer point 6 is 45.

[0051] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions of the present invention or make equivalent replacements, and these modifications or equivalent replacements cannot make the modified technical solutions deviate from the spirit and scope of the technical solutions of the present invention.

[0052] This method combines historical order data and current order information to effectively judge the occurrence of abnormal aggregation of online car-hailing demand in the target area, and quickly activates the evacuation plan to ensure that measures are taken immediately to alleviate the problems of passenger waiting and traffic congestion. At the same time, an evacuation plan is formulated based on the current order information, and a two-level transportation method of "bus + online car-hailing" is adopted. This combination method not only improves the evacuation efficiency, but also reduces traffic congestion and resource waste, realizing the rapid and orderly evacuation of the aggregated passengers.

[0053] Figure 4 The structural schematic diagram of a passenger flow evacuation device 200 for abnormal aggregation of online car-hailing demand is shown. As Figure 4 shown, a passenger flow evacuation device 200 for abnormal aggregation of online car-hailing demand mainly includes: An acquisition module 201, configured to acquire the current online car-hailing order information and historical online car-hailing order information of the target area corresponding to the current time; A judgment module 202, configured to judge whether the online car-hailing demand in the target area has abnormal aggregation based on the historical online car-hailing order information of the target area; An evacuation plan determination module 203, if the online car-hailing demand in the target area has abnormal aggregation, determines the evacuation plan for the target area based on the current online car-hailing order information, and evacuates the passengers in the target area according to the evacuation plan.

[0054] Optionally, the judgment module 202 is specifically configured to: Determine the mean and standard deviation of the order volume of the target area based on the historical online car-hailing order information; Determine the order volume threshold based on the mean and standard deviation of the order volume; If the current online car-hailing order information is greater than the order volume threshold, it is determined that the online car-hailing demand in the target area has abnormal aggregation; Otherwise, it is determined that the online car-hailing demand in the target area has not had abnormal aggregation.

[0055] Optionally, the evacuation plan determination module 203 includes: A clustering sub-module, which is used to cluster the destinations of all passengers based on a preset improved k-means algorithm to obtain multiple clusters, where one cluster represents a transfer location of multiple transport vehicles in the evacuation plan, and the transport vehicle is any one or more of online car-hailing vehicles and buses; A first determination sub-module, which is used to determine the number of transport vehicles departing from the target area to each of the transfer locations based on the destinations of the passengers corresponding to each cluster and a preset transport vehicle allocation rule; A second determination sub-module, which is used to determine the evacuation plan of the target area based on the number of transport vehicles departing from the target area to each transfer location.

[0056] Step S31: Obtain multiple numbers of clusters; Step S32: For each number of clusters, based on this number of clusters, determine the current center of each cluster in the current iteration. The number of clusters represents the number of clusters in the clustering process, and the current center represents the position of the cluster; Step S33: For each number of clusters, calculate the distance information between the destination of each passenger in the current iteration and the current center of each cluster respectively; Step S34: For each number of clusters, based on the respective distance information, allocate multiple passengers to each cluster respectively to obtain the number of passengers in each cluster; Step S35: For each number of clusters, based on the set bus information, the number of passengers in each cluster, and the number of available online car-hailing vehicles corresponding to the current center of each cluster, determine whether each cluster meets the set constraint conditions; Step S36: For each number of clusters, if each cluster meets the set constraint conditions, obtain an iteration result. The iteration result includes multiple current clusters, the passenger destinations corresponding to each current cluster, and the number of clusters, and calculate the objective value of the iteration result based on a preset objective function and multiple distance information; Step S37: Execute steps S32 to S36 until the number of iterations is satisfied, and use the iteration result corresponding to the minimum objective value in the current iteration cycle as the current clustering result of this number of clusters; Step S38: For each number of clusters, if there is any cluster that does not meet the set constraint conditions, determine the new center of each cluster based on the respective distance information, and use the new center as the current center in the next iteration. Execute steps S32 to S36 until the number of iterations is satisfied, and use the iteration result corresponding to the minimum objective value in the current iteration cycle as the current clustering result of this number of clusters; Step S39: Based on the current clustering results corresponding to each of the number of clusters and the preset elbow method, determine the target clustering result, where the target clustering result includes multiple clusters, the passenger destination corresponding to each cluster, and the optimal number of clusters.

[0057] Optionally, the clustering sub-module determines whether each cluster meets the set constraint conditions based on the set bus information, the number of passengers in each cluster, and the number of available online car-hailing vehicles corresponding to the current center of each cluster, including: For each cluster, based on the set bus information and the number of passengers in the cluster, determine whether the passenger capacity of each bus corresponding to the cluster is greater than the set quantity threshold; and, For each cluster, determine whether the number of available online car-hailing vehicles corresponding to the current center of the cluster is not less than the number of passengers in the cluster; For each cluster, if the passenger capacity of each bus corresponding to the cluster is greater than the set quantity threshold, and if the number of available online car-hailing vehicles corresponding to the current center of the cluster is not less than the number of passengers in the cluster, then determine that each cluster meets the set constraint conditions, otherwise determine that each cluster does not meet the set constraint conditions.

[0058] In an example, the modules in any of the above devices can be one or more integrated circuits configured to implement the above methods. For example: one or more application specific integrated circuits (ASICs), or, one or more digital signal processors (DSPs), or, one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0059] Again, when the modules in the device can be implemented in the form of a processing element scheduler, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processors that can call programs. Again, these modules can be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0060] In this application, names are given to various objects such as various messages / information / devices / network elements / systems / devices / actions / operations / processes / concepts, etc. It can be understood that these specific names do not constitute limitations on the relevant objects, and the given names can be changed according to factors such as scenarios, contexts, or usage habits. The understanding of the technical meanings of the technical terms in this application should be mainly determined from the functions and technical effects reflected / executed in the technical solutions.

[0061] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, devices, and modules described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0062] Those of ordinary skill in the art can realize that the modules and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0063] The term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device.

[0064] The above description is only a preferred embodiment of this application and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of the application involved in this application is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the foregoing application concept. For example, a technical solution formed by mutually replacing the above features with (but not limited to) technical features having similar functions applied in this application.

Claims

1. A passenger evacuation method for abnormal concentration of online car-hailing demand, characterized in that: include: Get the current online taxi order information and historical online taxi order information for the target area corresponding to the current time; Based on the current online car-hailing order information and the historical online car-hailing order information of the target area, determining whether the online car-hailing demand in the target area is abnormally concentrated; If there is an abnormal concentration of online ride-hailing demand in the target area, an evacuation plan for the target area is determined based on the current online ride-hailing order information, and passengers in the target area are evacuated according to the evacuation plan.

2. According to claim 1, a passenger evacuation method for abnormal concentration of online car-hailing demand is characterized in that: The determining whether abnormal concentration of online car-hailing demand in the target area occurs based on historical online car-hailing order information in the target area includes: Based on the historical online car-hailing order information, determine the mean and standard deviation of the order volume in the target area; Determining an order volume threshold based on the mean and standard deviation of the order volume; If the current online car-hailing order information is greater than the order volume threshold, it is determined that the online car-hailing demand in the target area is abnormally concentrated; Otherwise, it is determined that there is no abnormal concentration of online car-hailing demand in the target area.

3. According to claim 1, a passenger evacuation method for abnormal concentration of online car-hailing demand is characterized in that: The current online car-hailing order information includes destinations of multiple passengers, and determining the evacuation plan of the target area based on the current online car-hailing order information includes: Based on the preset improved k-means algorithm, the destinations of all passengers are clustered to obtain multiple clusters, where one cluster represents a transfer location of multiple transport vehicles in the evacuation plan, and the transport vehicles are any one or more of online-hailing cars and buses; Determining the number of transport vehicles sent from the target area to each of the transfer locations based on the destination of the passengers corresponding to each of the clusters and a preset transport vehicle allocation rule; An evacuation plan for the target area is determined based on the number of transport vehicles sent from the target area to each transfer location.

4. A passenger evacuation method for abnormal concentration of online car-hailing demand according to claim 3, characterized in that: The preset improved k-means algorithm is used to cluster all the destinations to obtain multiple clusters, including: Step S31, obtaining multiple cluster numbers; Step S32, for each of the cluster numbers, based on the cluster number, determining the current center of each cluster in the current iteration number, wherein the cluster number represents the number of clusters in the clustering process, and the current center represents the position of the cluster; Step S33, for each of the cluster numbers, respectively calculating the distance information between the destination of each of the passengers in the current iteration number and the current center of each cluster; Step S34, for each of the cluster numbers, based on each of the distance information, multiple passengers are respectively allocated to each of the clusters to obtain the number of passengers in each cluster; Step S35, for each of the cluster numbers, based on the set bus information, the number of passengers in each cluster and the number of available online-hailing vehicles corresponding to the current center of each cluster, determine whether each cluster satisfies the set constraint conditions; Step S36, for each of the cluster numbers, if each of the clusters satisfies the set constraint conditions, an iteration result is obtained, the iteration result including multiple current clusters, the passenger destination corresponding to each current cluster and the cluster number, and based on a preset objective function and multiple distance information, a target value of the iteration result is calculated; Step S37, executing steps S32 to S36 until the number of iterations is met, and taking the iteration result corresponding to the minimum target value in the current iteration cycle as the current clustering result of the cluster number; Step S38, for each of the cluster numbers, if there is any cluster that does not meet the set constraint condition, then based on the distance information, determine the new center of each cluster, and use the new center as the current center in the next iteration number, and execute steps S32 to S36 until the iteration number is met, and use the iteration result with the minimum target value in the current iteration cycle as the current clustering result of the cluster number; Step S39, based on the current clustering results corresponding to each of the clustering numbers and the preset elbow rule, a target clustering result is determined, wherein the target clustering result includes a plurality of clusters, a passenger destination corresponding to each cluster, and an optimal clustering number.

5. A passenger evacuation method for abnormal concentration of online car-hailing demand according to claim 4, characterized in that: The determining whether each cluster satisfies the set constraint condition based on the set bus information, the number of passengers in each cluster, and the number of available online-hailing vehicles corresponding to the current center of each cluster includes: For each of the clusters, based on the set bus information and the number of passengers in the cluster, determining whether the passenger capacity of each bus corresponding to the cluster is greater than a set number threshold; and, For each of the clusters, determining whether the number of available online-hailing vehicles corresponding to the current center of the cluster is not less than the number of passengers in the cluster; For each of the clusters, if the passenger capacity of each bus corresponding to the cluster is greater than the set quantity threshold, and if the number of available online-hailing taxis corresponding to the current center of the cluster is not less than the number of passengers in the cluster, then it is determined that each of the clusters meets the set constraints; otherwise, it is determined that each of the clusters does not meet the set constraints.

6. A passenger evacuation device for abnormal concentration of online car-hailing demand, characterized in that: include: An acquisition module is used to obtain the current online car-hailing order information and historical online car-hailing order information of the target area corresponding to the current time; A judgment module, used to judge whether the demand for online ride-hailing in the target area is abnormally concentrated based on the historical online ride-hailing order information of the target area; The evacuation plan determination module determines the evacuation plan of the target area based on the current online ride-hailing order information if the demand for online ride-hailing vehicles in the target area is abnormally concentrated, and evacuates the passengers in the target area according to the evacuation plan.

7. A passenger flow evacuation device for abnormal concentration of online car-hailing demand according to claim 6, characterized in that: The judgment module is specifically used for: Based on the historical online car-hailing order information, determine the mean and standard deviation of the order volume in the target area; Determining an order volume threshold based on the mean and standard deviation of the order volume; If the current online car-hailing order information is greater than the order volume threshold, it is determined that the online car-hailing demand in the target area is abnormally concentrated; Otherwise, it is determined that there is no abnormal concentration of online car-hailing demand in the target area.

8. The passenger flow evacuation device for abnormal concentration of online car-hailing demand according to claim 6, characterized in that: The evacuation plan determination module includes: A clustering submodule, for clustering the destinations of all passengers based on a preset improved k-means algorithm to obtain multiple clusters, where one cluster represents a transfer location of multiple transport vehicles in the evacuation plan, and the transport vehicles are any one or more of online-hailing cars and buses; A first determination submodule, configured to determine the number of transport vehicles sent from the target area to each of the transfer locations based on the destination of the passengers corresponding to each of the clusters and a preset transport vehicle allocation rule; The second determination submodule is used to determine the evacuation plan of the target area based on the number of transport vehicles sent from the target area to each transfer location.

9. A passenger flow evacuation device for abnormal concentration of online car-hailing demand according to claim 8, characterized in that: The clustering submodule is specifically used to perform the following steps: Step S31, obtaining multiple cluster numbers; Step S32, for each of the cluster numbers, based on the cluster number, determining the current center of each cluster in the current iteration number, wherein the cluster number represents the number of clusters in the clustering process, and the current center represents the position of the cluster; Step S33, for each of the cluster numbers, respectively calculating the distance information between the destination of each of the passengers in the current iteration number and the current center of each cluster; Step S34, for each of the cluster numbers, based on each of the distance information, multiple passengers are respectively allocated to each of the clusters to obtain the number of passengers in each cluster; Step S35, for each of the cluster numbers, based on the set bus information, the number of passengers in each cluster and the number of available online-hailing vehicles corresponding to the current center of each cluster, determine whether each cluster satisfies the set constraint conditions; Step S36, for each of the cluster numbers, if each of the clusters satisfies the set constraint conditions, an iteration result is obtained, the iteration result including multiple current clusters, the passenger destination corresponding to each current cluster and the cluster number, and based on a preset objective function and multiple distance information, a target value of the iteration result is calculated; Step S37, executing steps S32 to S36 until the number of iterations is met, and taking the iteration result corresponding to the minimum target value in the current iteration cycle as the current clustering result of the cluster number; Step S38, for each of the cluster numbers, if there is any cluster that does not meet the set constraint condition, then based on the distance information, determine the new center of each cluster, and use the new center as the current center in the next iteration number, and execute steps S32 to S36 until the iteration number is met, and use the iteration result with the minimum target value in the current iteration cycle as the current clustering result of the cluster number; Step S39, based on the current clustering results corresponding to each of the clustering numbers and the preset elbow rule, a target clustering result is determined, wherein the target clustering result includes a plurality of clusters, a passenger destination corresponding to each cluster, and an optimal clustering number.

10. A passenger flow evacuation device for abnormal concentration of online car-hailing demand according to claim 9, characterized in that: The clustering submodule determines whether each cluster meets the set constraint conditions based on the set bus information, the number of passengers in each cluster, and the number of available online-hailing vehicles corresponding to the current center of each cluster, including: For each of the clusters, based on the set bus information and the number of passengers in the cluster, determining whether the passenger capacity of each bus corresponding to the cluster is greater than a set number threshold; and, For each of the clusters, determining whether the number of available online-hailing vehicles corresponding to the current center of the cluster is not less than the number of passengers in the cluster; For each of the clusters, if the passenger capacity of each bus corresponding to the cluster is greater than the set quantity threshold, and if the number of available online-hailing taxis corresponding to the current center of the cluster is not less than the number of passengers in the cluster, then it is determined that each of the clusters meets the set constraints; otherwise, it is determined that each of the clusters does not meet the set constraints.

Images