Elastic bus operation scheduling method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of bus scheduling, and provides an elastic bus operation scheduling method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining elastic bus operation parameters, static passenger demand data and dynamic passenger demand data; substituting the static passenger demand data into a first operation scheduling model taking operation cost as a target, and generating an initial scheduling plan including an initial path and an initial charging plan; any dynamic passenger demand data and all static passenger demand data are substituted into a second operation scheduling model with the operation cost as the target, and an adjustment scheduling plan of a scene corresponding to any dynamic passenger demand data is generated; a target scheduling plan is determined based on the initial scheduling plan and each adjusted scheduling plan. The dynamic passenger demand is considered in the adjustment of the scheduling plan, so that the operation cost of the elastic public transportation system achieves a better effect under the condition of meeting the dynamic passenger demand, and the flexibility of the whole elastic public transportation system is also improved.

Description

Technical Field

[0001] The present invention relates to the technical field of public transportation scheduling, and in particular to a flexible public transportation operation scheduling method, device, electronic equipment and storage medium. Background Art

[0002] In the era of low-carbon and shared transportation, the application scenarios of electric buses are gradually innovating, introducing flexible, efficient and diversified flexible bus service models. Flexible buses can comprehensively consider passenger reservation needs and real-time demand information, provide more flexible service models, and thus reduce the negative impact of electric vehicle range anxiety, break the time and space restrictions of traditional buses such as fixed points, fixed routes and fixed times, and enhance the competitiveness of public transportation services.

[0003] At present, the existing flexible buses analyze the vehicle operation and line passenger flow patterns based on artificial intelligence, Internet of Things and big data technologies to achieve static operation scheduling of flexible buses, that is, to plan the operation path of flexible buses (including driving nodes and routes between driving nodes) according to the pre-acquired static passenger demand data. However, with the widespread popularization of smart mobile terminals, public transportation travelers have more convenient ways to express their travel needs in real time, but the existing technology does not consider the optimization of dynamic passenger demand (demand other than static passenger demand, in practical applications, usually refers to passenger demand obtained after the static operation scheduling plan is determined). Flexible buses only operate according to the stations (i.e. driving nodes) and routes planned by static operation scheduling, and have poor flexibility. In addition, the existing static operation scheduling does not consider the charging plan, which may lead to insufficient power during the operation of flexible buses.

[0004] Therefore, how to combine dynamic passenger demand to implement an operational scheduling plan that includes flexible bus operation routes and charging plans is a technical problem that needs to be solved urgently. Summary of the invention

[0005] The present invention provides a flexible public transportation operation scheduling method, device, electronic equipment and storage medium, which are used to solve the above-mentioned technical problems existing in the prior art.

[0006] The present invention provides a flexible public transportation operation scheduling method, comprising: Obtain flexible bus operation parameters, static passenger demand data and dynamic passenger demand data; Substituting the static passenger demand data into a first operation scheduling model with operation cost as a target to generate an initial scheduling plan including an initial path and an initial charging plan, wherein the first operation scheduling model is constructed based on the flexible bus operation parameters; Substitute any of the dynamic passenger demand data and all the static passenger demand data into the second operation scheduling model with the operation cost as the objective, to generate an adjusted scheduling plan corresponding to the scenario of any of the dynamic passenger demand data. The adjusted scheduling plan includes an adjusted route and an adjusted charging plan. The second operation scheduling model is constructed based on the initial scheduling plan and the dynamic passenger demand data; Based on the initial scheduling plan and each adjusted scheduling plan, determine the final target scheduling plan.

[0007] According to a flexible bus operation scheduling method provided by the present invention, the first operation scheduling model includes: a first total utility objective function of the flexible bus constructed based on flexible bus operation parameters and a first set of constraint conditions; the first total utility objective function is used to represent the total cost of any scheduling plan of all flexible buses that meet the static passenger demand data; the first set of constraint conditions includes: The first bus route constraint: ensure that the boarding point should be visited before the alighting point; The first time constraint: ensure the continuity of the flexible bus time; The first bus capacity constraint: ensure that the flexible bus is not overloaded; The first bus power constraint: ensure that the power of the flexible bus meets the power required by the initial scheduling plan.

[0008] According to a flexible bus operation scheduling method provided by the present invention, the first total utility objective function is: ; Wherein, is the value of the first total utility objective function; is the usage cost of the flexible bus; is the charging cost of the flexible bus; is the detour cost of the passenger; is the penalty cost for the passenger waiting for the flexible bus; is the set of driving nodes of the flexible bus; is the set of passenger boarding points; is the set of electric flexible bus charging stations; is the set of flexible bus vehicles; is the set of scenarios corresponding to the dynamic passenger demand data; is two driving nodes and the driving duration between; is the average maximum waiting time of all passengers at the boarding point i in the static passenger demand data; is the scenario the occurrence probability of; is a variable taking a value of 0 or 1, indicating the flexible bus Whether passing through the driving node To the driving node ; Is an integer variable representing the charging duration of the flexible bus At the charging station ; Is an integer variable representing the average value of the additional detour duration for all passengers boarding at the boarding point When taking the flexible bus compared to directly driving or taking a taxi to reach the destination; Is an integer variable representing the flexible bus Starting from the departure time to reach the driving node ; Is the expected cost considering scenario s, and min() is the function to find the minimum value.

[0009] According to a flexible bus operation and scheduling method provided by the present invention, the second operation and scheduling model includes: a second total utility objective function of the flexible bus and a second constraint condition set. The second total utility objective function is constructed based on the initial scheduling plan and the dynamic passenger demand data, and is used to represent the total cost of any scheduling plan of all flexible buses in the scenario that meets the dynamic passenger demand data; the second constraint condition set includes: Second bus path constraint: Ensure that the boarding and alighting points in the static passenger demand data must be served, and the boarding and alighting points in the dynamic passenger demand data must also be served; Second time constraint: Ensure that the line detour duration generated by adjusting the path of the flexible bus is not greater than the additional detour duration of passengers in the scenario corresponding to the dynamic passenger demand data; Second bus capacity constraint: Ensure that the flexible bus is not overloaded; Second bus power constraint: Ensure that the power of the flexible bus meets the power required for adjusting the scheduling plan.

[0010] According to a flexible bus operation and scheduling method provided by the present invention, the second total utility objective function is: ; Wherein, Is the usage cost of the flexible bus; Is the charging cost of the flexible bus; Is the passenger detour cost; Is the penalty cost for passengers waiting for the flexible bus; Is the set of driving nodes of the flexible bus in the scenario corresponding to the dynamic passenger demand data; Is the set of passenger boarding points in the scenario corresponding to the dynamic passenger demand data; Is the set of charging stations for electric flexible buses; is a set of flexible bus vehicles; are two driving nodes and the driving duration between; is the average maximum waiting time of all passengers at boarding point i in the scenario corresponding to the dynamic passenger demand data; is a variable taking values of 0 or 1, indicating whether the path of flexible bus k from driving node i to j is added in the scenario s corresponding to the dynamic passenger demand data; is a variable taking values of 0 or 1, indicating whether the path of flexible bus k from driving node i to j is deleted in the scenario s corresponding to the dynamic passenger demand data; is an integer variable representing the charging duration of flexible bus k at charging station c in the scenario s corresponding to the dynamic passenger demand data; is an integer variable representing the average additional detour duration of all passengers boarding at boarding point taking the flexible bus relative to driving directly or taking a taxi to reach the destination in the scenario corresponding to the dynamic passenger demand data; is an integer variable representing the duration from the departure time when flexible bus starts to reach driving node in the scenario s corresponding to the dynamic passenger demand data; min() is the minimum value function.

[0011] According to a flexible bus operation scheduling method provided by the present invention, based on the initial scheduling plan and each of the adjusted scheduling plans, a final target scheduling plan is determined, including: For each scenario, calculate the similarity matrix between the adjusted scheduling plan of each scenario and the initial scheduling plan, and establish the association relationship between the adjusted path and the initial path in the scenario according to the similarity matrix; Generate a membership matrix according to the similarity matrix, the association relationship and the initial path of the initial scheduling plan, and allocate the driving nodes in the static passenger demand data to the initial path according to the membership matrix; Based on the membership matrix, the scenario probability and the positions of the driving nodes in the static passenger demand data in the adjusted paths corresponding to different scenarios, calculate a position matrix, and determine the order of the driving nodes in the static passenger demand data in the path of the final target scheduling plan based on the position matrix, so as to determine the final target scheduling plan.

[0012] The present invention also provides a flexible bus operation scheduling device, including: A data acquisition module for acquiring flexible bus operation parameters, static passenger demand data and dynamic passenger demand data; An initial scheduling plan generation module, configured to substitute the static passenger demand data into a first operation scheduling model with the operation cost as the objective, and generate an initial scheduling plan including an initial route and an initial charging plan, where the first operation scheduling model is constructed based on the flexible bus operation parameters; An adjusted scheduling plan generation module, configured to substitute any of the dynamic passenger demand data and all the static passenger demand data into a second operation scheduling model with the operation cost as the objective, and generate an adjusted scheduling plan corresponding to the scenario of any of the dynamic passenger demand data, where the adjusted scheduling plan includes an adjusted route and an adjusted charging plan, and the second operation scheduling model is constructed based on the initial scheduling plan and the dynamic passenger demand data; A target scheduling plan determination module, configured to determine a final target scheduling plan based on the initial scheduling plan and each of the adjusted scheduling plans.

[0013] The present invention further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and running on the processor, where when the processor executes the program, the flexible bus operation scheduling method as described in any of the above is implemented.

[0014] The present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the flexible bus operation scheduling method as described in any of the above is implemented.

[0015] The present invention further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the flexible bus operation scheduling method as described in any of the above is implemented.

[0016] The flexible bus operation scheduling method, device, electronic device, and storage medium provided by the present invention generate an initial scheduling plan through the first operation scheduling model and the static passenger demand data, and consider the randomly occurring dynamic demands in actual applications. Based on the initial scheduling plan and the dynamic passenger demand data, a second operation scheduling model with the operation cost as the objective is constructed to generate an adjusted scheduling plan corresponding to the scenario of any of the dynamic passenger demand data, and then the final target scheduling plan with better robustness is determined according to the initial scheduling plan and each adjusted scheduling plan. Since the adjusted scheduling plan takes into account the dynamic passenger demand, the final target scheduling plan considering the dynamic passenger demand is realized, so that the operation cost of the flexible bus system reaches a better effect, and when dynamic passenger demands occur, it can also be switched to the corresponding adjusted scheduling plan at low cost, thereby improving the flexibility of the entire flexible bus system. Description of the Drawings

[0017] To more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0018] Figure 1 It is a schematic flowchart of the elastic bus operation scheduling method provided by the present invention.

[0019] Figure 2 It is the initial path and charging plan diagram of the initial scheduling plan in the elastic bus operation scheduling method provided by the present invention.

[0020] Figure 3 It is the path and charging plan diagram of the adjusted scheduling plan corresponding to the first scenario in the elastic bus operation scheduling method provided by the present invention.

[0021] Figure 4 It is the path and charging plan diagram of the adjusted scheduling plan corresponding to the second scenario in the elastic bus operation scheduling method provided by the present invention.

[0022] Figure 5 It is the path and charging plan diagram of the adjusted scheduling plan corresponding to the third scenario in the elastic bus operation scheduling method provided by the present invention.

[0023] Figure 6 It is the initial path and charging plan diagram of the target scheduling plan in the elastic bus operation scheduling method provided by the present invention.

[0024] Figure 7 It is a schematic diagram of matrix calculation when determining the final target scheduling plan in the elastic bus operation scheduling method provided by the present invention.

[0025] Figure 8 It is a schematic structural diagram of the elastic bus operation scheduling device provided by the present invention.

[0026] Figure 9 It is a schematic structural diagram of the electronic device provided by the present invention. Detailed implementation manners

[0027] To make the objectives, technical solutions and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions in the present invention in conjunction with the drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments in the present invention belong to the scope of protection of the present invention.

[0028] The elastic bus operation scheduling method according to the embodiments of the present invention is as follows Figure 1 shown, and includes the following steps S110 to S140.

[0029] Step S110: Obtain elastic bus operation parameters, static passenger demand data, and dynamic passenger demand data. The elastic bus operation parameters include: 1) The usage cost of the elastic bus, for example: ¥5 / period.

[0030] 2) The charging cost of the elastic bus, for example: ¥25 / period.

[0031] 3) The detour cost of passengers, for example: ¥5 / period.

[0032] 4) The penalty cost for passengers waiting for the elastic bus, for example: ¥25 / period.

[0033] 5) The maximum passenger capacity of the elastic bus, for example: 24 people.

[0034] 6) The maximum power of the electric elastic bus, for example: 50 kWh.

[0035] 7) The minimum power of the electric elastic bus, for example: 15 kWh.

[0036] 8) The charging rate, for example: 5 kWh / period.

[0037] 9) The service duration (the duration of stopping for passengers to get on and off) is 1 period.

[0038] The above period is a period of a preset duration, for example: 1 - 5 minutes. If it is less than the length of one period, it is calculated as one period. All duration concepts in this article can be counted in units of the said period.

[0039] The static passenger demand data and dynamic passenger demand data can be obtained from online car-hailing orders, mainly including information such as the boarding point, alighting point, and the maximum waiting time (the duration from the departure time of the elastic bus to the passenger's boarding point). The static passenger demand data and dynamic passenger demand data obtained from the online car-hailing orders in a certain area are shown in Table 1 below.

[0040] Table 1 Static Passenger Demand Data and Dynamic Passenger Demand Data

[0041] In Table 1 above, the boarding and alighting points corresponding to each static passenger demand data are the driving nodes that the flexible bus needs to pass through (i.e., the stations where passengers get on and off the bus on the flexible bus route). The maximum waiting time is based on the defined time period above. For example, if the time period is 5 minutes and the maximum waiting time is 10, then 10×5 = 50 minutes, which means that the passenger expects the departure time of the flexible bus to be 50 minutes from the start to reach the passenger's boarding point.

[0042] Step S120: Substitute the static passenger demand data into the first operation scheduling model with the operation cost as the objective to generate an initial scheduling plan including an initial route and an initial charging plan. The first operation scheduling model is constructed based on the flexible bus operation parameters. In this step, by pre - constructing the first operation scheduling model with the operation cost as the objective and solving the first operation scheduling model according to the static passenger demand data, the operation cost is minimized, and the scheduling plan corresponding to the minimum operation cost is used as the initial scheduling plan. That is, the flexible bus is scheduled according to the initial route and the initial charging plan in the initial scheduling plan, so that the operation cost of the entire flexible bus system is minimized.

[0043] It should be noted that: the initial route and the initial charging plan are the initial routes and initial charging plans of each flexible bus in the flexible bus system.

[0044] It can be understood that: the initial charging plan includes charging or not charging. When the initial route contains the node of the charging station, it means charging is required; when the initial route does not contain the node of the charging station, it means charging is not required.

[0045] Step S130: Substitute any of the dynamic passenger demand data and all the static passenger demand data into the second operation scheduling model with the operation cost as the objective to generate an adjusted scheduling plan corresponding to the scenario of any of the dynamic passenger demand data. The adjusted scheduling plan includes an adjusted route and an adjusted charging plan. The second operation scheduling model is constructed based on the initial scheduling plan and the dynamic passenger demand data.

[0046] Each dynamic passenger demand data and all the static passenger demand data correspond to a scenario, that is, a dynamic demand scenario. That is, each dynamic passenger demand data corresponds to a scenario. As shown in Table 1 above, there are three dynamic demand scenarios. The dynamic passenger demands 8, 9, and 10 respectively form three dynamic demand scenarios with the static passenger demand data 1 - 7.

[0047] In this step, by using the pre-constructed second operation scheduling model with the operation cost as the objective, and solving the second operation scheduling model according to the dynamic passenger demand data and all static passenger demand data, the operation cost is minimized under the corresponding scenario. The scheduling plan corresponding to the minimum operation cost is used as the adjusted scheduling plan. That is, the flexible bus is scheduled according to the adjusted path and adjusted charging plan in the adjusted scheduling plan, so that the operation cost of the entire flexible bus system is minimized under the corresponding scenario.

[0048] Step S140: Based on the initial scheduling plan and each adjusted scheduling plan, determine the final target scheduling plan.

[0049] In the flexible bus operation scheduling method of this embodiment, an initial scheduling plan is generated through the first operation scheduling model and static passenger demand data. Considering the randomly occurring dynamic demands in actual applications, based on the initial scheduling plan and dynamic passenger demand data, a second operation scheduling model with the operation cost as the objective is constructed to generate adjusted scheduling plans corresponding to each scenario of the dynamic passenger demand data. Then, according to the initial scheduling plan and each adjusted scheduling plan, a final target scheduling plan with better robustness is determined. Since the adjusted scheduling plan takes into account the dynamic passenger demand, the final scheduling plan considering the dynamic passenger demand is realized, enabling the operation cost of the flexible bus system to achieve a better effect. Moreover, when dynamic passenger demands occur, it can also be switched to the corresponding adjusted scheduling plan at low cost, thereby improving the flexibility of the entire flexible bus system.

[0050] In some embodiments, the first operation scheduling model includes: a first total utility objective function of the flexible bus constructed based on flexible bus operation parameters and a first set of constraint conditions. The first total utility objective function is used to represent the total cost of any scheduling plan of all flexible buses that meets the static passenger demand data. Among them, the first set of constraint conditions includes the following constraint conditions.

[0051] The first bus path constraint: Ensure that the boarding point should be visited before the alighting point.

[0052] The first time constraint: Ensure the continuity of the flexible bus time.

[0053] The first bus capacity constraint: Ensure that the flexible bus is not overloaded.

[0054] The first bus power constraint: Ensure that the power of the flexible bus meets the power required by the initial scheduling plan.

[0055] Specifically, the formula of the first total utility objective function is as follows: (1).

[0056] Wherein, is the first total utility objective function value; is the flexible bus usage cost; is the flexible bus charging cost; is the passenger detour cost; is the penalty cost for passengers waiting for the flexible bus; is the set of flexible bus driving nodes (i.e., the set of flexible bus stops); is the set of passenger boarding points; is the set of electric flexible bus charging stations; is the set of flexible bus vehicles; is the set of scenarios corresponding to the dynamic passenger demand data; are two driving nodes and the driving duration between; is the average maximum waiting duration of passengers at boarding point i in the static passenger demand data; is the scenario appearance probability; is a variable taking values of 0 or 1, indicating whether the flexible bus passes through the driving node to the driving node , if so, takes the value of 1, otherwise 0; is an integer variable, indicating the flexible bus charging duration at the charging station ; is an integer variable, indicating the average additional detour duration of all passengers boarding at boarding point taking the flexible bus relative to directly driving or taking a taxi to the destination; is an integer variable, indicating the flexible bus from the departure time as the starting point to reach the driving node duration; is the expected cost considering scenario s, and min() is the minimum value function. Among them, the set V includes the nodes in the sets P and C, as well as the flexible bus yard stops.

[0057] It should be noted that: since the dynamic passenger demand data is not considered temporarily when generating the initial scheduling plan, the last term in the first total utility objective function can take the value of 0.

[0058] In this embodiment, the above first total utility objective function includes this term, that is, the average maximum waiting duration of all passengers at boarding point i in the static passenger demand data, and also includes , that is, the flexible bus at the charging station The charging duration, adding multiple objective items such as charging duration and waiting duration, makes the time window of the first total utility objective function more flexible, more in line with the actual situation, and also improves the operation efficiency and accuracy of the model.

[0059] The first set of constraint conditions is used to impose relevant restrictions on the planned path based on objective conditions such as bus routes, time, bus capacity, and bus power during the scheduling planning with the goal of minimizing the first total utility objective function.

[0060] Specifically, the formula expressions of the constraint conditions in the first set of constraint conditions are as follows: The first bus route constraint is used to ensure that the boarding point should be visited before the alighting point: (2).

[0061] In the formula, is the set of passenger boarding points, represents the flexible bus The duration from the departure time to the boarding point, The duration, represents the flexible bus The duration from the departure time to the alighting point, The duration, is the service duration of the flexible bus at the driving node, are two driving nodes and The driving duration between.

[0062] The first time constraint is used to ensure the continuity of the flexible bus time, initialize the departure time of the flexible bus, and calculate the bus arrival time according to the following formula to achieve bus time continuity: (3); (4); (5); (6).

[0063] Among them, is the set of boarding and alighting points in the static passenger demand data, is the set of flexible bus stations, is an integer variable representing the flexible bus Departure time from the station , is the flexible bus Waiting duration at the station (it should be noted that: the flexible bus Departure from the station The departure time is not determined by the moment, but by the flexible bus departing from the station The departure time is determined by the waiting duration before departure, and both are calculated by time periods. For example, if one time period is 5 minutes, there are 12 time periods in one hour), is an integer variable, representing the flexible bus from the departure time to the duration of reaching the driving node of, is the service duration of the flexible bus at the driving node, is a value of infinity.

[0064] The first bus capacity constraint is used to ensure that the flexible bus is not overloaded. The number of passengers is calculated according to the following formula to meet the first bus capacity constraint: (7); (8).

[0065] Among them, represents the number of people on the flexible bus at the driving node of, represents the number of people on the flexible bus at the driving node of, is the number of people getting on / off at the driving node of. If the driving node is the boarding point, then takes a positive value. If the driving node is the alighting point, then takes a negative value.

[0066] The first bus power constraint is used to ensure that the power of the flexible bus meets the power required by the initial scheduling plan. The charging duration is calculated according to the following formula: (9); (10).

[0067] Among them, is the driving duration between the driving node and the charging station of, represents the flexible bus from the departure time to the duration of reaching the charging station of, is a variable with a value of 0 or 1, representing the flexible bus whether from the charging station to the driving node .

[0068] The above formulas (1)-(10) are the first operation and scheduling model. In this embodiment, the static passenger demand data is substituted into the above formulas, and Python is used to call Cplex to solve the first operation and scheduling model, obtaining an initial scheduling plan including an initial path and an initial charging plan. The initial scheduling plan obtained by solving based on the static passenger demand data in Table 1 above is as Figure 2 shown. Figure 2 Among them, taking two flexible buses as an example, the initial scheduling plan of the two flexible buses is shown. Among them, the boarding point locations are 1-7 (corresponding to boarding points 1-7 in Table 1), the alighting point locations are 11-17 (corresponding to alighting points 11-17 in Table 1), D represents the bus station, and S1 and S2 respectively represent two charging stations.

[0069] In some embodiments, the second operation and scheduling model includes: a second total utility objective function of the flexible bus and a second set of constraint conditions. The second total utility objective function is constructed based on the initial scheduling plan and the dynamic passenger demand data, and is used to represent the total cost of any scheduling plan of all flexible buses in a scenario that meets the dynamic passenger demand data; the second set of constraint conditions includes: Second bus path constraint: Ensure that the boarding points and alighting points in the static passenger demand data must be served, and the boarding points and alighting points in the dynamic passenger demand data must also be served.

[0070] Second time constraint: Ensure that the line detour duration generated by the flexible bus adjusting the path is not greater than the additional detour duration of passengers in the scenario corresponding to the dynamic passenger demand data.

[0071] Second bus capacity constraint: Ensure that the flexible bus is not overloaded.

[0072] Second bus power constraint: Ensure that the power of the flexible bus meets the power required for adjusting the scheduling plan.

[0073] Specifically, the formula of the second total utility objective function is as follows: (11).

[0074] Among them, is the usage cost of the flexible bus; is the charging cost of the flexible bus; is the passenger detour cost; is the penalty cost for passengers waiting for the flexible bus; is the set of driving nodes of the flexible bus in the scenario corresponding to the dynamic passenger demand data; is the set of passenger boarding points in the scenario corresponding to the dynamic passenger demand data; is the set of charging stations for electric flexible buses; is a set of flexible bus vehicles; are two driving nodes and the driving duration between them; is the average maximum waiting time of all passengers at boarding point i in the scenario corresponding to the dynamic passenger demand data; is a variable taking values of 0 or 1, indicating whether the path of flexible bus k from driving node i to j is added in the scenario s corresponding to the dynamic passenger demand data; is a variable taking values of 0 or 1, indicating whether the path of flexible bus k from driving node i to j is deleted in the scenario s corresponding to the dynamic passenger demand data; is an integer variable representing the charging duration of flexible bus k at charging station c in the scenario s corresponding to the dynamic passenger demand data; is an integer variable representing the average additional detour duration of all passengers taking the flexible bus relative to driving directly or taking a taxi to the destination at boarding point in the scenario s corresponding to the dynamic passenger demand data; is an integer variable representing the flexible bus in the scenario s corresponding to the dynamic passenger demand data starting from the departure time to reach the driving node duration; min() is the function to find the minimum value. Among them, the set contains the nodes in the set and C, as well as the depot stations of the flexible buses. The variables and represent the adjustment of the driving route. For example: in scenario 1 corresponding to Figure 3 , in the initial route, boarding point 8 and alighting point 18 in the dynamic passenger demand data are inserted between boarding point 2 and boarding point 6, then , , and , when obtaining the dynamic passenger demand data, any unserved driving nodes on the initial route can be adjusted.

[0075] Specifically, the formula expressions of the constraints in the second set of constraints are as follows.

[0076] The second bus path constraint is used to ensure that the boarding points and alighting points in the static passenger demand data must be served, and the boarding points and alighting points in the dynamic passenger demand data must also be served. The formula is as follows: (12).

[0077] Among them, is the set of passenger boarding points and alighting points in the dynamic passenger demand data, It is a set of boarding points and alighting points in static passenger demand data.

[0078] The second time constraint is used to ensure that the line detour duration generated by the flexible bus adjustment path is not greater than the additional detour duration of passengers in the corresponding scenario of the dynamic passenger demand data. Calculate the line detour duration generated by the flexible bus adjustment path according to the following formula and compare it with the additional detour duration of passengers in the corresponding scenario of the dynamic passenger demand data: (13).

[0079] Among them, represents the average value of the additional detour duration of all passengers boarding at the boarding point in the corresponding scenario s of the dynamic passenger demand data when taking the flexible bus compared with directly driving or taking a taxi to the destination. is the set of dynamic demand boarding points. In the corresponding scenario s of the dynamic passenger demand data, for the flexible bus starting from the departure time to reach the corresponding alighting point the duration. is the service duration of the flexible bus at the driving node in the corresponding scenario s of the dynamic passenger demand data. is the driving duration between two driving nodes and

[0080] The second bus capacity constraint is used to ensure that the flexible bus is not overloaded. The formula is as follows: (14).

[0081] Among them, is a variable with a value of 0 or 1, indicating the number of people on the flexible bus at the driving node in the corresponding scenario s of the dynamic passenger demand data. is the rated passenger capacity of the flexible bus.

[0082] The second bus power constraint is used to ensure that the power of the flexible bus meets the power required for the adjustment and scheduling plan.

[0083] (15).

[0084] (16).

[0085] Among them, is the power consumption of the flexible bus k from the driving node to the charging station is the charging rate of the flexible bus. is the rated capacity of the flexible bus battery.​​ is an integer variable representing the flexible bus in scenario s corresponding to the dynamic passenger demand data when reaching the driving node the battery level, is an integer variable representing the flexible bus in scenario s corresponding to the dynamic passenger demand data when arriving at the charging station the battery level, is the set of stations of the flexible bus, is a variable taking values of 0 or 1, representing whether the flexible bus from the charging station to the driving node ; is a variable taking values of 0 or 1, representing that in scenario s corresponding to the dynamic passenger demand data, whether the path of flexible bus k from the charging station to driving node j is added; is a variable taking values of 0 or 1, representing that in scenario s corresponding to the dynamic passenger demand data, whether the path of flexible bus k from the charging station to driving node j is deleted.

[0086] The above formulas (11)-(16) are the second operation and scheduling model. In this embodiment, substituting the static passenger demand data and the dynamic passenger demand data into the above formulas, and using Python to call Cplex to solve the second operation and scheduling model, an adjusted scheduling plan including adjusted paths and adjusted charging plans is obtained. The adjusted scheduling plan solved based on the dynamic passenger demand data in Table 1 above is as Figures 3 - 5 shown, Figures 3 - 5 in which, taking two flexible buses as an example, the initial scheduling plans of the two flexible buses are shown. Figure 3 The adjusted scheduling plan diagram corresponding to the dynamic scenario formed by the dynamic passenger demand data corresponding to demand number 8 in Table 1 and the static passenger demand data 1-7, Figure 4 The adjusted scheduling plan diagram corresponding to the dynamic scenario formed by the dynamic passenger demand data corresponding to demand number 9 in Table 1 and the static passenger demand data 1-7, Figure 5 The adjusted scheduling plan diagram corresponding to the dynamic scenario formed by the dynamic passenger demand data corresponding to demand number 10 in Table 1 and the static passenger demand data 1-7.

[0087] In some embodiments, step S140 specifically includes the following steps 1 to 3.

[0088] Step 1: For each scenario, calculate the similarity matrix between the adjusted scheduling plan of each scenario and the initial scheduling plan, and establish the association relationship between the adjusted path and the initial path in the scenario. Specifically, as Figure 7As shown in (a), obtain the adjusted path for each dynamic passenger demand data corresponding to scenario s and the adjusted charging plan (the path including the charging station node in the adjusted path includes the adjusted charging plan), and obtain the initial path and the initial charging plan, where represents the adjusted path of flexible bus k under scenario s, represents the initial path of flexible bus k. For the data in Table 1, as Figure 7 shown in (b), for each scenario, calculate the similarity matrix between the adjusted scheduling plan and the initial scheduling plan of each scenario, that is, compare the number of nodes with the same position and the same order in the two scheduling plans, and construct the similarity matrix of the two scheduling plans based on the number of nodes with the same position and the same order. Establish the association relationship between the path in the scenario and the initial path . Specifically, the adjusted path corresponding to the larger element in each row of the similarity matrix and the initial path establish an association relationship. For example: in the similarity matrix, the adjusted path in the adjusted scheduling plan and the initial path in the initial scheduling plan have two driving nodes (i.e., station D and boarding point 2) with the same position and the same order (the elements corresponding to and in the similarity matrix are 2, while the elements corresponding to and are 1), so the adjusted path is associated with the initial path . That is, in the similarity matrix, for each corresponding row, is associated with the in the column where the largest element in this row is located.

[0089] Step 2: Generate the membership degree matrix (MDM) according to the similarity matrix, the association relationship, and the initial path of the initial scheduling plan. As Figure 7 shown in (c), allocate the driving nodes (boarding points and corresponding alighting points) in the static passenger demand data to the initial path according to the membership degree matrix. For example: the adjusted path is associated with the initial path , that is, the driving node i in is likely to be allocated to the initial path according to the following formula (17).

[0090] A entry in the membership degree matrix contains a score (0 and 1 in the membership degree matrix), and this score is obtained through the scenario path associated with ​ Scene probability is calculated by summation. The scene probability is a preset value. For example, the probabilities of three scenes are all 1 / 3.

[0091] (17).

[0092] Among them, if , and is associated with , then . According to the similarity matrix and the membership matrix, the driving node i in each static passenger demand data is assigned to the path . As shown in (c) of Figure 7 , in the membership matrix, an element of 1 indicates that the corresponding boarding point and alighting point are assigned to the corresponding initial path. For example, the boarding point 1 and the alighting point 11 are assigned to the initial path .

[0093] Step 3: As shown in (d) of Figure 7 , based on the membership matrix, the scene probability, and the positions of the driving nodes in the static passenger demand data in the adjusted paths corresponding to different scenes, calculate the position matrix, and determine the order of the driving nodes in the static passenger demand data in the path of the final target scheduling plan based on the position matrix, so as to determine the final target scheduling plan, that is, a robust scheduling plan with a better service order. Specifically, the formula for calculating the position matrix is as follows: (18).

[0094] represents the position of the driving node i in the static passenger demand data in when the driving node i in the static passenger demand data belongs to .

[0095] Based on the data of the corresponding region in Table 1, the scheduling plans obtained in the above steps S120 to S140 are shown in Table 2 below, and the final target scheduling plan is as shown in Figure 6 .

[0096] Table 2 Test results of online car-hailing data in a certain region

[0097] In Table 2, the detour cost, operation cost, charging cost, and waiting cost are all time costs, calculated based on the above-mentioned preset time period. For the monetary cost, it can be obtained by multiplying the amount per unit time by the time cost. Specifically, in different scenarios, the flexible bus fleet plans to adopt different adjustment methods. In Scenario 1, the bus uses additional charging costs to serve real-time demand, while in Scenario 2, the fleet switches to mutual cooperation to meet all demands. According to the solution of this embodiment, the final target scheduling plan is obtained. The final total target cost (Formula (1)) is 1853, and the average target value gap is less than 6.38%. That is, the total target cost of the two scheduling paths V1 and V2 of the final target scheduling plan obtained in step S140 in Table 2 is 1853, with a relatively low cost, and it can switch to the corresponding adjusted scheduling plan at a relatively low cost in any of Scenarios 1-3.

[0098] The flexible bus operation scheduling device provided by the present invention will be described below. The flexible bus operation scheduling device described below can be correspondingly referred to the flexible bus operation scheduling method described above.

[0099] The flexible bus operation scheduling device according to an embodiment of the present invention, as Figure 8 shown, includes the following modules 810 to 840.

[0100] A data acquisition module 810, configured to acquire flexible bus operation parameters, static passenger demand data, and dynamic passenger demand data.

[0101] An initial scheduling plan generation module 820, configured to substitute the static passenger demand data into a first operation scheduling model with operation cost as the target, and generate an initial scheduling plan including an initial path and an initial charging plan, where the first operation scheduling model is constructed based on the flexible bus operation parameters.

[0102] An adjusted scheduling plan generation module 830, configured to substitute any one of the dynamic passenger demand data and all static passenger demand data into a second operation scheduling model with operation cost as the target, and generate an adjusted scheduling plan corresponding to the scenario of any one of the dynamic passenger demand data, where the adjusted scheduling plan includes an adjusted path and an adjusted charging plan, and the second operation scheduling model is constructed based on the initial scheduling plan and the dynamic passenger demand data.

[0103] A target scheduling plan determination module 840, configured to determine a final target scheduling plan based on the initial scheduling plan and each adjusted scheduling plan.

[0104] The flexible bus operation scheduling device of this embodiment generates an initial scheduling plan through the first operation scheduling model and static passenger demand data, and considers the randomly occurring dynamic demands in actual applications. Based on the initial scheduling plan and dynamic passenger demand data, a second operation scheduling model with the operation cost as the objective is constructed to generate an adjusted scheduling plan corresponding to any scenario of the dynamic passenger demand data. Then, according to the initial scheduling plan and each adjusted scheduling plan, the final target scheduling plan with better robustness is determined. Since the adjusted scheduling plan takes into account the dynamic passenger demand, the final scheduling plan considering the dynamic passenger demand is realized, enabling the operation cost of the flexible bus system to achieve a better effect. Moreover, when dynamic passenger demands occur, it can also be switched to the corresponding adjusted scheduling plan at low cost, thereby improving the flexibility of the entire flexible bus system.

[0105] In some embodiments, the first operation scheduling model includes: a first total utility objective function of the flexible bus constructed based on flexible bus operation parameters and a first set of constraint conditions; the first total utility objective function is used to represent the total cost of any scheduling plan of all flexible buses that meet the static passenger demand data; the first set of constraint conditions includes: First bus route constraint: Ensure that the boarding point should be visited before the alighting point.

[0106] First time constraint: Ensure the continuity of the flexible bus time.

[0107] First bus capacity constraint: Ensure that the flexible bus is not overloaded.

[0108] First bus power constraint: Ensure that the power of the flexible bus meets the power required for the initial scheduling plan.

[0109] In some embodiments, the first total utility objective function is: ; Wherein, is the value of the first total utility objective function; is the flexible bus usage cost; is the flexible bus charging cost; is the passenger detour cost; is the penalty cost for passengers waiting for the flexible bus; is the set of flexible bus driving nodes; is the set of passenger boarding points; is the set of electric flexible bus charging stations; is the set of flexible bus vehicles; is the set of scenarios corresponding to the dynamic passenger demand data; is two driving nodes and the driving duration between them; is the average maximum waiting time of all passengers at boarding point i in the static passenger demand data; is for the scenario occurrence probability; is a variable taking values of 0 or 1, indicating whether the flexible bus passes through the driving node to the driving node ; is an integer variable, indicating the charging duration of the flexible bus at the charging station ; is an integer variable, indicating the average additional detour duration of all passengers boarding at boarding point when taking the flexible bus compared to directly driving or taking a taxi to the destination; is an integer variable, indicating the duration from the departure time for the flexible bus to reach the driving node ; is the expected cost considering scenario s, and min() is the minimum function.

[0110] In some embodiments, the second operation and dispatch model includes: a second total utility objective function of the flexible bus and a second set of constraint conditions. The second total utility objective function is constructed based on the initial dispatch plan and the dynamic passenger demand data, and is used to characterize the total cost of any dispatch plan of all flexible buses in meeting the scenarios corresponding to the dynamic passenger demand data; the second set of constraint conditions includes: Second bus path constraint: Ensure that the boarding and alighting points in the static passenger demand data must be served, and the boarding and alighting points in the dynamic passenger demand data must also be served.

[0111] Second time constraint: Ensure that the line detour duration generated by adjusting the path of the flexible bus is not greater than the additional detour duration of passengers in the scenarios corresponding to the dynamic passenger demand data.

[0112] Second bus capacity constraint: Ensure that the flexible bus is not overloaded.

[0113] Second bus power constraint: Ensure that the power of the flexible bus meets the power required for the adjusted dispatch plan.

[0114] In some embodiments, the second total utility objective function is: ; where is the usage cost of the flexible bus; is the charging cost of the flexible bus; is the passenger detour cost; is the penalty cost for passengers waiting for the flexible bus; is the set of driving nodes of the flexible bus in the scenario corresponding to the dynamic passenger demand data; is the set of passenger boarding points in the scenario corresponding to the dynamic passenger demand data; is the set of charging stations for electric flexible buses; is the set of flexible bus vehicles; are two driving nodes and is the driving duration between them; is the average value of the maximum waiting durations of all passengers at boarding point i in the scenario corresponding to the dynamic passenger demand data; is a variable taking values of 0 or 1, indicating whether the path of the flexible bus k from driving node i to j is added in the scenario s corresponding to the dynamic passenger demand data; is a variable taking values of 0 or 1, indicating whether the path of the flexible bus k from driving node i to j is deleted in the scenario s corresponding to the dynamic passenger demand data; is an integer variable representing the charging duration of the flexible bus k at the charging station c in the scenario s corresponding to the dynamic passenger demand data; is an integer variable representing the average additional detour duration of all passengers boarding at boarding point in the flexible bus relative to directly driving or taking a taxi to reach the destination in the scenario s corresponding to the dynamic passenger demand data; is an integer variable representing the flexible bus in the scenario s corresponding to the dynamic passenger demand data is the duration from the departure time to reach the driving node ; min() is the function to find the minimum value.

[0115] In some embodiments, the target scheduling plan determination module 840 specifically includes: For each scenario, calculate the similarity matrix between the adjusted scheduling plan and the initial scheduling plan of each scenario, and establish the association relationship between the adjusted path and the initial path in the scenario according to the similarity matrix.

[0116] Generate the membership matrix according to the similarity matrix, the association relationship and the initial path of the initial scheduling plan, and allocate the driving nodes in the static passenger demand data to the initial path according to the membership matrix.

[0117] Calculate the position matrix based on the membership matrix, the scenario probability and the positions of the driving nodes in the static passenger demand data in the adjusted paths corresponding to different scenarios, and determine the order of the driving nodes in the static passenger demand data in the path of the final target scheduling plan based on the position matrix, so as to determine the final target scheduling plan.

[0118] Figure 9Illustrates a schematic diagram of the physical structure of an electronic device, as Figure 9 shown. The electronic device may include: a processor 910, a communications interface 920, a memory 930, and a communication bus 940. Among them, the processor 910, the communications interface 920, and the memory 930 communicate with each other through the communication bus 940. The processor 910 may call the logical instructions in the memory 930 to execute the flexible bus operation scheduling method, which includes: Obtain flexible bus operation parameters, static passenger demand data, and dynamic passenger demand data.

[0119] Substitute the static passenger demand data into the first operation scheduling model with the operation cost as the target to generate an initial scheduling plan including an initial path and an initial charging plan. The first operation scheduling model is constructed based on the flexible bus operation parameters.

[0120] Substitute any of the dynamic passenger demand data and all the static passenger demand data into the second operation scheduling model with the operation cost as the target to generate an adjusted scheduling plan corresponding to the scenario of any of the dynamic passenger demand data. The adjusted scheduling plan includes an adjusted path and an adjusted charging plan. The second operation scheduling model is constructed based on the initial scheduling plan and the dynamic passenger demand data.

[0121] Determine the final target scheduling plan based on the initial scheduling plan and each adjusted scheduling plan.

[0122] In addition, when the logical instructions in the above-mentioned memory 930 are implemented in the form of software functional units and sold or used as an independent product, they may be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, may be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs, etc., which can store program codes.

[0123] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the flexible bus operation scheduling method provided by the above-mentioned various methods, and the method includes: Obtain flexible bus operation parameters, static passenger demand data, and dynamic passenger demand data.

[0124] Substitute the static passenger demand data into a first operation scheduling model with the operation cost as the objective to generate an initial scheduling plan including an initial path and an initial charging plan, and the first operation scheduling model is constructed based on the flexible bus operation parameters.

[0125] Substitute any one of the dynamic passenger demand data and all the static passenger demand data into a second operation scheduling model with the operation cost as the objective to generate an adjusted scheduling plan corresponding to the scenario of any one of the dynamic passenger demand data, and the adjusted scheduling plan includes an adjusted path and an adjusted charging plan, and the second operation scheduling model is constructed based on the initial scheduling plan and the dynamic passenger demand data.

[0126] Determine the final target scheduling plan based on the initial scheduling plan and each of the adjusted scheduling plans.

[0127] On another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it realizes the flexible bus operation scheduling method provided by the above-mentioned various methods, and the method includes: Obtain flexible bus operation parameters, static passenger demand data, and dynamic passenger demand data.

[0128] Substitute the static passenger demand data into a first operation scheduling model with the operation cost as the objective to generate an initial scheduling plan including an initial path and an initial charging plan, and the first operation scheduling model is constructed based on the flexible bus operation parameters.

[0129] Substitute any one of the dynamic passenger demand data and all the static passenger demand data into a second operation scheduling model with the operation cost as the objective to generate an adjusted scheduling plan corresponding to the scenario of any one of the dynamic passenger demand data, and the adjusted scheduling plan includes an adjusted path and an adjusted charging plan, and the second operation scheduling model is constructed based on the initial scheduling plan and the dynamic passenger demand data.

[0130] Determine the final target scheduling plan based on the initial scheduling plan and each of the adjusted scheduling plans.

[0131] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0132] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0133] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A flexible public transportation operation scheduling method, characterized in that: include: Obtain flexible bus operation parameters, static passenger demand data and dynamic passenger demand data; Substituting the static passenger demand data into a first operation scheduling model with operation cost as a target to generate an initial scheduling plan including an initial path and an initial charging plan, wherein the first operation scheduling model is constructed based on the flexible bus operation parameters; Substituting any of the dynamic passenger demand data and all the static passenger demand data into a second operation scheduling model with operation cost as a target, generating an adjustment scheduling plan for a scenario corresponding to any of the dynamic passenger demand data, the adjustment scheduling plan including an adjustment route and an adjustment charging plan, the second operation scheduling model being constructed based on the initial scheduling plan and the dynamic passenger demand data; Based on the initial scheduling plan and each of the adjusted scheduling plans, a final target scheduling plan is determined.

2. The flexible public transportation operation scheduling method according to claim 1, characterized in that: The first operation scheduling model includes: a first total utility objective function of the flexible bus constructed based on the flexible bus operation parameters and a first constraint condition set; the first total utility objective function is used to characterize the total cost of any scheduling plan of all flexible buses that meets the static passenger demand data; the first constraint condition set includes: The first bus route constraint: ensure that the boarding point should be visited before the alighting point; The first time constraint: ensuring the continuity of flexible bus time; The first bus capacity constraint: ensure that flexible buses are not overloaded; The first bus power constraint: ensure that the flexible bus power meets the power required by the initial scheduling plan.

3. The flexible public transportation operation scheduling method according to claim 2, characterized in that: The first total utility objective function is: ； in, is the first total utility objective function value; To make public transport use more flexible; the cost of charging resilient public transportation; detour costs for passengers; Penalty costs for passengers waiting for flexible transit; is a collection of flexible bus driving nodes; Gather passengers at the boarding point; a collection of charging stations for electric resilient buses; A collection of flexible public transport vehicles; A set of scenarios corresponding to dynamic passenger demand data; For two driving nodes and The driving time between is the average maximum waiting time of all passengers at boarding point i in the static passenger demand data; For the scene The probability of occurrence; is a variable with a value of 0 or 1, indicating flexible public transportation Whether it passes through the driving node To the driving node ; is an integer variable, indicating flexible bus At the charging station Charging time; An integer variable representing the boarding point The average of the extra detour time for all passengers taking flexible public transportation compared to driving or taking a taxi to their destination; is an integer variable, indicating flexible bus Arrive at the driving node starting from the departure time Length of time; To consider the expected cost of scene s, min() is the minimum function.

4. The flexible public transportation operation scheduling method according to claim 1, characterized in that: The second operation scheduling model includes: a second total utility objective function of the flexible bus and a second set of constraints, the second total utility objective function is constructed based on the initial scheduling plan and the dynamic passenger demand data, and the second total utility objective function is used to characterize the total cost of any scheduling plan of all flexible buses that meets the scenario corresponding to the dynamic passenger demand data; the second set of constraints includes: The second bus route constraint: ensure that the pick-up and drop-off points in the static passenger demand data must be served, and the pick-up and drop-off points in the dynamic passenger demand data must also be served; Second time constraint: ensure that the detour time generated by the flexible bus adjustment route is not greater than the additional detour time of passengers in the scenario corresponding to the dynamic passenger demand data; The second bus capacity constraint: ensure that flexible buses are not overloaded; The second bus power constraint: ensure that the flexible bus power meets the power required to adjust the scheduling plan.

5. The flexible public transportation operation scheduling method according to claim 4, characterized in that: The second total utility objective function is: ； in, To make public transport use more flexible; the cost of charging resilient public transportation; detour costs for passengers; Penalty costs for passengers waiting for flexible transit; The driving node set of the flexible bus in the scenario corresponding to the dynamic passenger demand data; The set of passenger boarding points in the scenario corresponding to the dynamic passenger demand data; a collection of charging stations for electric resilient buses; A collection of flexible public transport vehicles; For two driving nodes and The driving time between is the average maximum waiting time of all passengers at boarding point i in the scenario corresponding to dynamic passenger demand data; is a variable with a value of 0 or 1, indicating whether the path of flexible bus k from driving node i to j is added in the scenario s corresponding to the dynamic passenger demand data; is a variable with a value of 0 or 1, indicating whether the path of flexible bus k from driving node i to j is deleted in the scenario s corresponding to the dynamic passenger demand data; is an integer variable, which represents the charging time of flexible bus k at charging station c in scenario s corresponding to dynamic passenger demand data; is an integer variable, representing the boarding point in scenario s corresponding to the dynamic passenger demand data The average of the extra detour time for all passengers taking flexible public transportation compared to driving or taking a taxi to their destination; is an integer variable, indicating the dynamic passenger demand data corresponding to the flexible bus in scenario s Arrive at the driving node starting from the departure time duration; min() is the minimum value function.

6. The flexible public transportation operation scheduling method according to any one of claims 1 to 5, characterized in that: Determining a final target scheduling plan based on the initial scheduling plan and each of the adjusted scheduling plans includes: For each scenario, a similarity matrix between the adjusted scheduling plan of each scenario and the initial scheduling plan is calculated, and a correlation relationship between the adjusted path and the initial path in the scenario is established according to the similarity matrix; Generate a membership matrix according to the similarity matrix, the association relationship and the initial path of the initial scheduling plan, and assign the driving nodes in the static passenger demand data to the initial path according to the membership matrix; Based on the membership matrix, scenario probability and the positions of the driving nodes in the static passenger demand data in the adjustment paths corresponding to different scenarios, a position matrix is ​​calculated, and based on the position matrix, the order of the driving nodes in the static passenger demand data in the path of the final target scheduling plan is determined to determine the final target scheduling plan.

7. A flexible public transportation operation dispatching device, characterized in that: include: A data acquisition module, used to acquire flexible bus operation parameters, static passenger demand data and dynamic passenger demand data; An initial dispatch plan generating module, used for substituting the static passenger demand data into a first operation dispatch model with operation cost as a target, to generate an initial dispatch plan including an initial path and an initial charging plan, wherein the first operation dispatch model is constructed based on the flexible bus operation parameters; an adjustment scheduling plan generating module, used for respectively substituting any of the dynamic passenger demand data and all the static passenger demand data into a second operation scheduling model with operation cost as the target, and generating an adjustment scheduling plan for a scenario corresponding to any of the dynamic passenger demand data, wherein the adjustment scheduling plan includes an adjustment path and an adjustment charging plan, and the second operation scheduling model is constructed based on the initial scheduling plan and the dynamic passenger demand data; The target scheduling plan determination module is used to determine the final target scheduling plan based on the initial scheduling plan and each of the adjusted scheduling plans.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the flexible public transportation operation scheduling method according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the flexible public transportation operation scheduling method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the flexible public transportation operation scheduling method according to any one of claims 1 to 6 is implemented.

Images