WO2022138164A1 - シミュレーション装置 - Google Patents
シミュレーション装置 Download PDFInfo
- Publication number
- WO2022138164A1 WO2022138164A1 PCT/JP2021/045111 JP2021045111W WO2022138164A1 WO 2022138164 A1 WO2022138164 A1 WO 2022138164A1 JP 2021045111 W JP2021045111 W JP 2021045111W WO 2022138164 A1 WO2022138164 A1 WO 2022138164A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- port
- time
- vehicle
- calculation unit
- information
- Prior art date
Links
- 238000004088 simulation Methods 0.000 title claims abstract description 118
- 238000004364 calculation method Methods 0.000 claims abstract description 166
- 230000008707 rearrangement Effects 0.000 claims description 67
- 238000012423 maintenance Methods 0.000 claims description 31
- 230000006870 function Effects 0.000 claims description 23
- 230000032258 transport Effects 0.000 claims description 20
- 238000010801 machine learning Methods 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 238000011084 recovery Methods 0.000 claims description 4
- 238000000034 method Methods 0.000 description 70
- 230000008569 process Effects 0.000 description 47
- 238000010586 diagram Methods 0.000 description 35
- 238000011156 evaluation Methods 0.000 description 23
- 238000012545 processing Methods 0.000 description 10
- 238000009826 distribution Methods 0.000 description 9
- 238000003860 storage Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 239000000284 extract Substances 0.000 description 8
- 238000006243 chemical reaction Methods 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000009795 derivation Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 239000006249 magnetic particle Substances 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Definitions
- This disclosure relates to a simulation device.
- the sharing transportation service has multiple ports for parking vehicles.
- Each user rents a vehicle from a desired port and returns the vehicle to the desired port. Since the number of vehicles rented out and the number of vehicles returned at each port do not always match, the number of vehicles parked in the port may be biased. In this case, the vehicles are rearranged from the port with a large number of vehicles to the port with a small number of vehicles.
- the number of vehicles parked in each port can change over time. Therefore, it is required to predict changes in the number of vehicles at each port.
- Patent Document 1 the number of parking slots and the number of initially arranged vehicles for each station in the car sharing system are determined, and the state transition when the car sharing system is operated with the number of parking slots and the number of initially arranged vehicles by a state transition simulation is described. An operation plan creation system that evaluates business feasibility by reproducing it is described.
- Patent Document 1 considers the personnel for forwarding (relocating) the vehicle to another station and relocating the vehicle when the arrangement of the vehicle is biased. However, there is room for improvement in the rearrangement simulation.
- This disclosure describes a simulation device capable of improving the simulation accuracy of vehicle movement.
- the simulation device is a device that simulates the movement of a vehicle between a plurality of ports in a sharing traffic service.
- This simulation device includes a calculation unit that calculates the working time at the relocation port, which is the port to be relocated of the vehicle, and simulates the relocation based on the working time.
- relocation is simulated based on the working time at the relocation port. Since the working time may vary depending on the relocation port, the relocation simulation can be realized with high accuracy by considering the working time at the relocation port. As a result, it becomes possible to improve the simulation accuracy of the movement of the vehicle.
- FIG. 1 is a schematic configuration diagram of a simulation system including a simulation device according to an embodiment.
- FIG. 2 is a diagram for explaining a divided area.
- FIG. 3A is a diagram showing an example of port information.
- FIG. 3B is a diagram showing an example of vehicle information.
- FIG. 3C is a diagram showing an example of carrier vehicle information.
- FIG. 4 is a diagram showing an example of lending number information.
- FIG. 5 is a diagram showing an example of movement information.
- FIG. 6 is a diagram showing an example of battery usage information.
- FIG. 7 is a diagram showing an example of usage time information.
- FIG. 8 is a block diagram showing a functional configuration of the simulation apparatus shown in FIG.
- FIG. 9 is a flowchart showing a series of processes of the simulation method performed by the simulation apparatus shown in FIG.
- FIG. 10 is a flowchart showing the simulation process of the target area in detail.
- FIG. 11 is a flowchart showing the rearrangement process in detail.
- FIG. 12 is a flowchart showing the lending process in detail.
- FIG. 13 is a diagram for explaining a process of selecting a target area.
- FIG. 14 is a diagram showing an example of rental unit information used in the simulation of the target area.
- FIG. 15 is a diagram showing an example of movement information used in the simulation of the target area.
- FIG. 16 is a diagram showing an example of battery usage information used in the simulation of the target area.
- FIG. 17 is a diagram showing an example of usage time information used in the simulation of the target area.
- FIG. 18 is a diagram showing an example of a list of available vehicles.
- FIG. 19 is a diagram showing a hardware configuration of the simulation apparatus shown in FIG.
- FIG. 1 is a schematic configuration diagram of a simulation system including a simulation device according to an embodiment.
- FIG. 2 is a diagram for explaining a divided area.
- FIG. 3A is a diagram showing an example of port information.
- FIG. 3B is a diagram showing an example of vehicle information.
- FIG. 3C is a diagram showing an example of carrier vehicle information.
- FIG. 4 is a diagram showing an example of lending number information.
- FIG. 5 is a diagram showing an example of movement information.
- FIG. 6 is a diagram showing an example of battery usage information.
- FIG. 7 is a diagram showing an example of usage time information.
- the simulation system 1 shown in FIG. 1 is a system for simulating the movement of a vehicle in a sharing traffic service.
- the sharing transportation service is a sharing service in which a plurality of users jointly use a vehicle, and is, for example, a one-way type MEV (Micro Electric Vehicle) sharing system. Examples of vehicles include bicycles, cars, motorcycles, and scooters.
- the sharing transportation service has multiple ports. A port is a space (parking lot) for parking a vehicle. Ports are also referred to as stations.
- Each user rents a vehicle at the desired port and returns the vehicle at the desired port.
- the port on which the vehicle is returned may be different or the same as the port on which the vehicle was rented. Therefore, in each port, the number of vehicles to be rented and the number of vehicles to be returned do not always match, so that the number of vehicles parked in the port (number of parked vehicles) may be biased.
- the rearrangement of vehicles between the ports is simulated so that the number of vehicles available at each port is not insufficient and the number of vehicles that can be parked is not exceeded. The rearrangement is performed, for example, by a transport vehicle such as a truck transporting the vehicle between the ports.
- the relocation area is set in the sharing transportation service.
- the rearrangement area is an area where the vehicle is rearranged and includes a plurality of ports. That is, the vehicle is rearranged between the ports included (provided) in the rearrangement area.
- the rearrangement area is divided into a plurality of divided areas.
- the rearrangement area R is divided into a division area Ra, a division area Rb, a division area Rc, and a division area Rd.
- the rearrangement area is divided so that each divided area includes a plurality of ports P.
- the rearrangement area is divided by an arbitrary method. For example, the relocation area is divided by administrative district or business operator.
- the simulation system 1 includes a simulation device 10 and a management device 20.
- the simulation device 10 and the management device 20 are configured to be able to communicate with each other via the network NW.
- the network NW may be configured by either wired or wireless. Examples of network NWs include mobile communication networks, the Internet, and WAN (Wide Area Network).
- the simulation device 10 is a device (simulator) that simulates the movement of a vehicle between a plurality of ports included in the rearrangement area in the sharing traffic service.
- An example of the simulation device 10 is an information processing device such as a server device.
- the management device 20 is a device that manages the sharing transportation service.
- the management device 20 manages information about ports and vehicles used in the sharing transportation service.
- the management device 20 stores, for example, port information, vehicle information, and carrier information.
- the port information (each record) includes a port ID (identifier), an area ID, location information, a number of cars that can be parked, and a number of cars that can be used.
- the port ID is information that can uniquely identify the port.
- the area ID is information that can uniquely identify the divided area, and indicates the divided area to which the port indicated by the port ID belongs.
- the position information is information indicating the position of the port indicated by the port ID. For example, latitude and longitude are used as the position information.
- the number of vehicles that can be parked indicates the number of vehicles that can be parked in the port indicated by the port ID.
- the number of parkable cars is set to a value obtained by, for example, multiplying the number of racks by the permissible rate.
- the permissible rate is a value indicating the degree to which parking is permissible with respect to the number of racks.
- the number of available vehicles is the number of vehicles available in the port indicated by the port ID, for example, the number of vehicles parked in the
- the vehicle information (each record) includes the vehicle ID, the vehicle status, the port ID, and the battery level.
- the vehicle ID is information that can uniquely identify the vehicle.
- the vehicle state indicates the state of the vehicle indicated by the vehicle ID. Examples of vehicle conditions include “moving", “parking”, and “relocating”.
- the port ID indicates a port in which the vehicle indicated by the vehicle ID is parked.
- the remaining battery level indicates the remaining battery level of the vehicle indicated by the vehicle ID. As the remaining battery level, for example, SOC (State Of Charge) [%] can be used.
- the vehicle information may further include type information indicating the type of vehicle. Examples of vehicle types include bicycles, automobiles, motorcycles, and scooters.
- the carrier information (each record) includes the carrier ID, the number of vehicles that can be accommodated, the state of the carrier, the position information, the collection port ID, and the placement port ID. Including the number of relocations.
- the carrier ID is information that can uniquely identify the carrier.
- the number of vehicles that can be accommodated is the number of vehicles that can be accommodated by the vehicle indicated by the vehicle ID.
- the carrier state indicates the state of the carrier indicated by the carrier ID. Examples of the carrier state include "collecting", "moving", and "arranging”. "Recovering” means that the transport vehicle is stopped near the collection port in order to collect the vehicle.
- the collection port is a port where the vehicle to be rearranged (target vehicle) is collected.
- "During placement” is a state in which the carrier is stopped near the placement port in order to place the vehicle.
- the placement port is the port on which the recovered vehicle is placed.
- the position information is information indicating the position of the carrier indicated by the carrier ID.
- the collection port ID is the port ID of the collection port.
- the placement port ID is the port ID of the placement port.
- the number of rearranged vehicles is the number of vehicles rearranged (moved) from the collection port to the placement port, and is the number of vehicles rearranged by the transport vehicle indicated by the transport vehicle ID.
- the management device 20 further stores statistical information regarding the usage record of the vehicle. Examples of statistical information include rental unit information, movement information, battery usage information, and usage time information.
- the rental number information is information showing the average value of the number of vehicles rented at the same time (time zone) on the same type of usage date at each port.
- the lending number information (each record) includes a port ID, a usage date type, a time, and an average lending number.
- the usage date type indicates the usage date type.
- the type of usage date is set, for example, for each usage date in which the usage status of the vehicle is similar. Examples of usage day types include weekdays and holidays.
- the average number of rented vehicles is the average value of the number of rented vehicles at the same time on the day of the usage date type indicated by the usage day type information in the port indicated by the port ID.
- the average number of units lent is calculated from past usage records.
- the record of the rental number information is generated every 3 minutes. For example, when the time is 7:00, the average number of rented vehicles may be the average value of the number of rented vehicles between 7:00 and 7:00:03.
- the movement information is information indicating the number of times that movement is performed between two ports at the same time (time zone) on the same type of usage date.
- the movement information (each record) includes a lending port ID, a usage date type, a time, a return port ID, and the number of movements.
- the lending port ID is the port ID of the lending port.
- the rental port is the port on which the vehicle is rented.
- the return port ID is the port ID of the return port.
- the return port is the port on which the vehicle is returned.
- the number of movements indicates the number of times the vehicle has moved from the lending port to the return port at the same time (time zone) on the same day of use.
- the time when the vehicle moves may be the time when the vehicle is rented (rental time), the time when the vehicle is returned (return time), or the time between the rental time and the return time.
- the number of moves is calculated from the past usage record.
- the number of movements may be a cumulative value or an average value.
- the movement information record is generated every hour.
- the number of movements may be the number of times the vehicle has moved from the rental port to the return port between 7:00 and 8:00.
- battery usage information is information indicating the average battery usage when moving between two ports.
- the battery usage information (each record) includes a lending port ID, a return port ID, and a battery usage amount.
- Battery usage is the average battery usage between the time the vehicle is rented at the port indicated by the rental port ID and the time the vehicle is returned to the port indicated by the return port ID. SOC [%] can be used as the battery usage. Battery usage is calculated from past usage records.
- the usage time information is information indicating the average time (usage time) that the user has been using the vehicle for moving between the two ports.
- the usage time information indicates the average time required to move between the two ports.
- the usage time information (each record) includes a lending port ID, a return port ID, and a usage time.
- the usage time is the average time from when the vehicle is rented at the port indicated by the rental port ID until the vehicle is returned to the port indicated by the return port ID.
- the usage time may be expressed in units of 1 hour.
- the usage time is calculated from the past usage record.
- FIG. 8 is a block diagram showing a functional configuration of the simulation apparatus shown in FIG.
- the simulation apparatus 10 functionally includes an acquisition unit 11, a selection unit 12, an adjustment unit 13, a calculation unit 14, and an evaluation unit 15. Since the functions (operations) of each functional unit will be described in detail in the description of the simulation method described later, the functions of each functional unit will be briefly described here.
- the acquisition unit 11 is a functional unit that acquires various types of information.
- the acquisition unit 11 acquires port information, vehicle information, carrier vehicle information, rental number information, movement information, battery usage information, and usage time information from the management device 20.
- the selection unit 12 is a functional unit that selects a target area.
- the target area is a simulation target divided area among a plurality of divided areas generated by dividing the rearranged area.
- the calculation unit 14 is a functional unit that virtually treats all ports included in the non-target area as one virtual port and simulates the movement of a vehicle between a plurality of target ports and one virtual port. ..
- the non-target area is a divided area other than the target area among the plurality of divided areas.
- the target port is a port included in the target area.
- the simulated vehicle movement includes the movement of the vehicle by the user and the rearrangement of the vehicle by the carrier.
- the calculation unit 14 simulates the relocation of the vehicle between a plurality of target ports by performing the relocation recommendation process (recommendation algorithm).
- the rearrangement recommendation process is a process for recommending the rearrangement of the vehicle. Specifically, the calculation unit 14 determines the relocation port and the number of relocations by the relocation recommendation process.
- the rearrangement port is a port that is the target of vehicle rearrangement, and includes a collection port and a rearrangement port. For example, the calculation unit 14 calculates the working time at the relocation port and simulates the relocation based on the working time.
- the adjustment unit 13 is a functional unit that adjusts weights for each of a plurality of parameters used in the rearrangement recommendation process.
- the weight is, for example, a value of 0 to 1.
- the adjusting unit 13 selects a weight pattern from a plurality of predetermined weight patterns.
- the weight pattern is a combination of weights for each parameter.
- the evaluation unit 15 is a functional unit that evaluates weights.
- the evaluation unit 15 generates an evaluation result for the weight pattern.
- FIG. 9 is a flowchart showing a series of processes of the simulation method performed by the simulation apparatus shown in FIG.
- FIG. 10 is a flowchart showing the simulation process of the target area in detail.
- FIG. 11 is a flowchart showing the rearrangement process in detail.
- FIG. 12 is a flowchart showing the lending process in detail.
- FIG. 13 is a diagram for explaining a process of selecting a target area.
- FIG. 14 is a diagram showing an example of rental unit information used in the simulation of the target area.
- FIG. 15 is a diagram showing an example of movement information used in the simulation of the target area.
- FIG. 16 is a diagram showing an example of battery usage information used in the simulation of the target area.
- FIG. 17 is a diagram showing an example of usage time information used in the simulation of the target area.
- FIG. 18 is a diagram showing an example of a list of available vehicles.
- the series of processes shown in FIG. 9 is started by, for example, the user of the simulation device 10 transmitting an optimization command to the simulation device 10.
- the optimization command is a command for optimizing the weight for each of a plurality of parameters used in the rearrangement recommendation process.
- the acquisition unit 11 acquires various information (step S11).
- the acquisition unit 11 acquires port information, vehicle information, carrier vehicle information, rental unit information, movement information, battery usage information, and usage time information at a certain time from the management device 20. Any time can be used as the above time.
- the acquisition unit 11 outputs various acquired information to the calculation unit 14, and causes the selection unit 12 to select the target area.
- the selection unit 12 selects the target area (step S12).
- the selection unit 12 selects an unselected divided area as the target area from the plurality of divided areas generated by dividing the rearranged area. In the example shown in FIG. 13, the divided area Ra is selected as the target area.
- the selection unit 12 outputs the area information indicating the target area to the calculation unit 14, and causes the adjustment unit 13 to select the weight pattern.
- the adjusting unit 13 selects a weight pattern (step S13).
- the adjusting unit 13 selects an unselected weight pattern from a plurality of predetermined weight patterns. Then, the adjusting unit 13 outputs the selected weight pattern to the calculation unit 14.
- the calculation unit 14 carries out a simulation process of the target area (step S14).
- the calculation unit 14 performs port information, vehicle information, carrier vehicle information, rental vehicle unit information, movement information, battery usage information, and usage time information. Is received from the acquisition unit 11 and the area information is received from the selection unit 12, and the initial setting is performed (step S21).
- the calculation unit 14 virtually treats all the ports included in the non-target area as one virtual port in the simulation of the target area. Therefore, as an initial setting, the calculation unit 14 converts each of the rental unit information, the movement information, the battery usage information, and the usage time information received from the acquisition unit 11 into information for simulation of the target area.
- the calculation unit 14 extracts a record including the port ID of the target port from the rental unit information received from the acquisition unit 11. Then, the calculation unit 14 generates a virtual port record from the remaining records (records including the port ID of the non-target port) included in the lending number information. For example, the calculation unit 14 sets the average value of the average number of lending units included in the records of the same usage date type and the same time among the remaining records as the average number of lending units of the virtual port at the relevant usage date type and time. Generates a record for the virtual port. Then, as shown in FIG. 14, the calculation unit 14 generates the loaned number information including the record of the target port and the record of the virtual port as the loaned number information for the simulation of the target area.
- the calculation unit 14 extracts a record whose lending port and return port are both target ports from the movement information received from the acquisition unit 11.
- the calculation unit 14 uses a record in which the lending port is the target port and the return port is the port in the non-target area, and the average value of the number of moves included in the record of the same lending port, the same usage date type, and the same time. Is calculated, and the calculated average value is set as the number of movements from the lending port to the virtual port in the usage date type and time. This process creates a record where the lending port is the target port and the return port is the virtual port.
- the calculation unit 14 uses a record in which the lending port is a port in the non-target area and the return port is the target port, and the number of movements included in the same return port, the same usage date type, and the same time record. Calculate the average value of, and set the calculated average value to the number of movements from the virtual port to the return port in the usage date type and time. By this process, a record is generated in which the lending port is a virtual port and the returning port is the target port. Further, the calculation unit 14 calculates and calculates the average value of the number of movements included in the records of the same usage date type and the same time using the records in which the lending port and the returning port are both ports in the non-target area. The average value is set to the number of moves from the virtual port to the virtual port in the relevant usage date type and time. This process produces a record in which both the lending port and the returning port are virtual ports.
- the calculation unit 14 has a record in which the lending port and the return port are both target ports, a record in which the lending port is the target port, and a return port is a virtual port, and a lending port.
- a record in which the lending port is the target port, and a return port is a virtual port Is a virtual port, and a record including a record in which the return port is the target port and a record in which both the lending port and the return port are virtual ports are generated as movement information for simulation of the target area.
- the battery usage information conversion process and the usage time information conversion process are the same as the movement information conversion process. By these conversion processes, the battery usage information for the simulation of the target area shown in FIG. 16 and the usage time information for the simulation of the target area shown in FIG. 17 are generated.
- the calculation unit 14 extracts the record of the port (target port) included in the target area indicated by the area information from the port information received from the acquisition unit 11. Then, the calculation unit 14 sets the time t to 0 (initial value).
- step S22 the calculation unit 14 changes the vehicle state included in the vehicle information of each vehicle returned at time t from "moving" to "parking", and the port ID is the port where the vehicle is returned. Set the port ID. Then, the calculation unit 14 increases the number of available port information of the port where the vehicle is returned by the number of vehicles returned to the port.
- the calculation unit 14 changes the vehicle state included in the vehicle information of the vehicle collected by the collection operation started at time t from "parking" to "relocating", and changes the port ID to the port of the collection port. Change from ID to invalid value. Then, the calculation unit 14 reduces the number of available port information of the collection port by the number of vehicles collected from the port (rearrangement number) at time t. Similarly, the calculation unit 14 changes the vehicle state included in the vehicle information of the vehicle placed by the placement work ending at time t from "relocating" to "parking", and sets the port ID to the port of the placement port. Set to ID. Then, the calculation unit 14 increases the number of available port information of the arrangement port by the number of vehicles arranged in the port (relocation number) at time t.
- the calculation unit 14 carries out the rearrangement process (step S23).
- the calculation unit 14 first determines whether or not it is the timing to calculate the relocation (step S31).
- the relocation calculation is performed, for example, at the timing when the carrier (worker) finishes the relocation work.
- the calculation unit 14 ends the relocation process.
- the calculation unit 14 specifies the carrier to be rearranged. For example, the calculation unit 14 identifies the carrier that has completed the rearrangement work as the carrier that performs the rearrangement. Then, the calculation unit 14 determines the collection port (step S32).
- step S32 the calculation unit 14 determines the collection port by using the parameters X i and j for determining the collection port.
- the variable i represents the index number of the port. An integer value is assigned to the target port in order from 1 as an index number. The total number of target ports is Np. Therefore, the variable i can take an integer value from 1 to Np.
- the variable j is an index number of a parameter for determining the collection port. An integer value is assigned as an index number in order from 1 to the parameter for determining the collection port.
- the parameters X i, j are the integral value X i, 1 , the priority X i, 2 , the normalized value X i, 3 , the access degree X i, 4 , the increase rate X i, 5 , and the number of vehicles.
- X i, 6 and the number of vehicles X i, 7 are used.
- the integrated values X i and 1 are the total value of the surplus units generated at the i-th port by the future time Ta.
- the surplus number is the number of vehicles (surplus vehicles) that exceed the number of cars that can be parked at the port, and is also called the overflow number.
- the integrated values X i and 1 are the total value of the surplus units generated between x hours before the time Ta and the time Ta.
- the surplus number is calculated based on the available number ct, i , the demand number dt, i , and the number of racks Ri .
- the number of available vehicles ct and i represents the number of vehicles predicted to be available on the i-th port at time t .
- the demanded number dt and i represent the demanded number at the i-th port at time t.
- the demand units dt and i are the number of vehicles predicted to be rented from the i-th port at time t (the number of vehicles rented) and the number of vehicles predicted to be returned to the i-th port at time t (the number of vehicles rented). This is the difference from the number of returned units).
- the demand units dt and i are positive values, and when the number of rented units is smaller than the number of returned units, the demand units dt and i are negative values.
- the available units ct, i and the demand units dt, i can be obtained by performing the same calculation as the lending process described later.
- the number of racks R i represents the number of racks in the i-th port.
- the permissible rate ⁇ is a value indicating the degree to which parking can be tolerated with respect to the number of racks Ri. For example, when the permissible rate ⁇ is 2, the remaining number obtained by subtracting the demand number dt, i from the available number ct, i exceeds twice the number of racks Ri . It is judged that an overflow (surplus vehicle) has occurred.
- the number of racks Ri and the permissible rate ⁇ are predetermined. For example, the number of parkable cars that is the result of multiplying the number of racks Ri and the permissible rate ⁇ may be obtained from the port information.
- the port information may include the number of racks Ri and the tolerance ⁇ .
- Priority X i and 2 are values indicating the degree to which the vehicle is preferentially collected. The larger the value of priority Xi , 2 , the higher the priority.
- the priorities X i and 2 are set in four stages of, for example, high, medium, low, and none. Priority Xi and 2 are preset for each port.
- the normalized values X i and 3 are values obtained by normalizing the integrated values X i and 1 with the number of racks R i as shown in the equation (3).
- the access degrees X i and 4 are values indicating the ease with which the carrier can access the i-th port. The larger the access degree Xi and 4 , the easier it is for the carrier to access the i-th port.
- the access degrees X i and 4 decrease as the distance from the position of the carrier at time t to the i-th port increases.
- the access degrees X i and 4 are, for example, values obtained by multiplying the distance from the position of the carrier to the i-th port at time t by -1.
- the rate of increase X i, 5 is the rate at which vehicles increase at the i-th port between time t and future time Ta.
- the rate of increase X i, 5 is calculated by, for example, the equation (4).
- the number of vehicles X i, 6 is the number of vehicles whose battery level is exhausted at the i-th port at time t. For example, when the remaining battery level is equal to or less than a preset first threshold value, it is determined that there is no remaining battery level.
- the number of vehicles X i, 7 is the number of vehicles whose remaining battery power is low at the i-th port at time t. For example, when the remaining battery level is equal to or less than a preset second threshold value and larger than the first threshold value, it is determined that the remaining battery level is low.
- the calculation unit 14 extracts the weight for each parameter from the weight pattern selected by the adjustment unit 13. Then, as shown in the equation (5), the calculation unit 14 calculates the weighted sum of each parameter for each port, and sets the calculation result to the collection priority Xi of the i -th port. Then, the calculation unit 14 determines the port having the highest collection priority Xi as the collection port.
- step S33 the calculation unit 14 first calculates the recommended number of collection ports determined in step S32.
- the calculation unit 14 calculates the recommended collection number based on, for example, the surplus number at time Ta. For example, the surplus number at time Ta is calculated as the recommended collection number.
- the calculation unit 14 extracts the number of transport vehicles that can be rearranged from the transport vehicle information. Then, the calculation unit 14 determines which of the recommended collection number and the accommodable number, whichever is smaller, as the temporary rearrangement number.
- the calculation unit 14 determines the placement port (step S34).
- step S34 the calculation unit 14 determines the placement port using the parameters Y i and k for determining the placement port.
- the variable k is an index number of a parameter for determining the placement port. Integer values are assigned to the parameters for determining the placement port in order from 1 as the index number.
- the parameters Y i, k are integrated values Y i, 1 , priority Y i, 2 , normalized values Y i, 3 , access degrees Y i, 4 , reduction rate Y i, 5 , and number of vehicles.
- Y i, 6 the number of vehicles Y i, 7 , the number of deployable units Y i, 8 , and the opportunity loss Y i, 9 are used.
- the integrated values Y i and 1 are the total values of the shortages that occur at the i-th port by the time Ta in the future.
- the shortage is the number of vehicles (insufficient vehicles) that were in demand for lending but could not be used.
- the integrated values Y i and 1 are the total values of the shortages generated between y hours before the time Ta and the time Ta.
- the shortage is calculated based on the available units ct, i and the demand units dt, i .
- the minimum number ⁇ is a value representing the minimum number of vehicles that are desired to be parked in the port so that there is no shortage of vehicles.
- the remaining number obtained by subtracting the demand number dt and i from the available number ct and i is less than the minimum number ⁇ , it is determined that the vehicle shortage has occurred. Since the demand units dt and i may be larger than the available units ct and i , the remaining units may take a negative value. For example, when the minimum number ⁇ is 3, it is determined that a shortage has occurred when the remaining number is less than 3.
- the minimum number ⁇ is predetermined.
- the port information may include the minimum number ⁇ .
- Priority Yi and 2 are values indicating the degree to which vehicles are preferentially arranged. The larger the value of priority Yi, 2 , the higher the priority.
- the priorities Yi and 2 are set in four stages of, for example, high, medium, low, and none.
- the priorities Yi and 2 are preset for each port.
- the normalized values Y i and 3 are values obtained by normalizing the integrated values Y i and 1 with the number of racks R i as shown in the equation (8).
- the access degrees Yi and 4 are values indicating the ease with which the carrier can access the i-th port from the collection port. The larger the access degree Yi and 4 , the easier it is for the carrier to access the i-th port from the collection port.
- the access degrees Yi and 4 decrease as the distance from the collection port to the i-th port increases.
- the access degrees Yi and 4 are, for example, values obtained by multiplying the distance from the collection port to the i-th port by -1.
- the rate of decrease Y i, 5 is the rate at which vehicles decrease at the i-th port between the time t and the future time Ta.
- the reduction rates Y i and 5 are calculated by, for example, the equation (9).
- the number of vehicles Y i, 6 is the number of vehicles whose remaining battery power is exhausted at the i-th port at time t.
- the number of vehicles Y i, 6 is obtained in the same manner as the number of vehicles X i, 6 .
- the number of vehicles Y i, 7 is the number of vehicles whose remaining battery power is low at the i-th port at time t.
- the number of vehicles Y i, 7 is obtained in the same manner as the number of vehicles X i, 7 .
- the number of vehicles that can be arranged Y i, 8 is the number of vehicles that can be arranged at the i-th port at time t.
- Opportunity loss Yi , 9 is a value indicating the possibility of losing the opportunity for the vehicle to be rented.
- the opportunity loss Y i, 9 is, for example, an integral value Y i, 1 , a priority Y i, 2 , a normalized value Y i, 3 , a reduction rate Y i, 5 , a number of vehicles Y i, 6 , and a number of vehicles Y. It is the total value of i and 7 .
- the calculation unit 14 extracts the weight for each parameter from the weight pattern selected by the adjustment unit 13. Then, as shown in the equation (10), the calculation unit 14 calculates the weighted sum of each parameter for each port, and sets the calculation result to the arrangement priority Yi of the i -th port.
- the calculation unit 14 determines the port having the highest placement priority Y i as the placement port. At this time, the calculation unit 14 calculates the recommended number of placement ports. The calculation unit 14 calculates the recommended number of placements based on, for example, the number of shortages at time Ta. For example, the shortage number at time Ta is calculated as the recommended placement number. Then, the calculation unit 14 compares the number of temporary rearrangements with the recommended number of arrangements, and if the recommended number of arrangements is equal to or greater than the number of recommended temporary rearrangements, determines the number of temporary rearrangements as the number of units to be rearranged.
- the calculation unit 14 recalculates the placement priority Yi for each port other than the placement port (first placement port).
- the calculation method of the placement priority Y i described above is described above, except that the access degrees Y i and 4 are values indicating the ease with which the carrier can access the i-th port from the first placement port. It is the same as the calculation method of the arrangement priority Y i of.
- the access degrees Yi and 4 decrease as the distance from the first placement port to the i-th port increases.
- the access degrees Yi and 4 are, for example, values obtained by multiplying the distance from the first placement port to the i-th port by -1.
- the calculation unit 14 determines the port having the highest placement priority Y i as the second placement port. At this time, the calculation unit 14 calculates the recommended number of placements for the second placement port in the same manner as for the first placement port.
- the calculation unit 14 compares the sum of the recommended number of placement of the first placement port and the recommended number of placement of the second placement port with the number of temporary rearrangements, and when the sum is equal to or greater than the number of temporary rearrangements. Determines the number of temporary relocations as the number of relocations. In this case, the recommended number of vehicles for placement of the first placement port is placed on the first placement port, and the recommended placement number of the first placement port is subtracted from the number of rearranged ports for the second placement port. The number of vehicles obtained by this is arranged.
- the calculation unit 14 determines the sum as the number of rearrangements.
- the recommended number of vehicles for placement of the first placement port is arranged in the first placement port, and the recommended number of vehicles for placement of the second placement port is placed in the second placement port.
- the calculation unit 14 calculates the time required for the rearrangement (step S35).
- the required time is the travel time of the carrier from the current location to the collection port, the work time at the collection port (collection time), and the time required from the collection port to the placement port. Includes travel time and working time (deployment time) at the deployment port. If two ports are determined as placement ports, the required time is the travel time of the carrier from the current location to the collection port, the work time at the collection port (collection time), and the time required from the collection port to the first placement port.
- the travel time, the working time at the first deployment port (deployment time), the travel time from the first deployment port to the second deployment port, and the working time at the second deployment port (deployment time). include.
- the calculation unit 14 calculates the travel time between the two ports by a known method. For example, the calculation unit 14 calculates the travel time between the two ports by dividing the distance between the two ports by the assumed speed of the carrier.
- the working time Tpi at the port includes the basic working time Tbi , the transport time Tc i , and the maintenance time Tmi .
- the basic work time Tbi is the time required for the basic work at the i -th port.
- An example of basic work is stopping work of a transport vehicle.
- the basic working time Tbi is a fixed value and may vary from port to port.
- the basic work time Tbi is calculated and set in advance from the past work record (time actually required for the basic work) at the i -th port.
- the transportation time Tc i is the time required for the worker to carry the vehicle to be relocated (target vehicle) between the transport vehicle stopped to perform the work at the i-th port and the i-th port. Is.
- the calculation unit 14 has the number of target vehicles Nri in the i -th port, the number Ns that the worker can carry in one transportation operation, and the i-th port.
- the transportation time Tc i is calculated based on the time f (Mi ) required for one transportation operation. Specifically, the calculation unit 14 calculates the transportation time Tc i by multiplying the division result obtained by dividing the number Nri by the number Ns and the time f (Mi ) .
- the number Nri in the collection port and the placement port is the number of rearrangements determined in step S34.
- the number Nri in the collection port is the number of rearrangements determined in step S34
- the number Nri in each placement port is the placement determined in step S34. It is the number of units.
- the number Ns is a value determined according to the number of workers and the like, and is set in advance for each carrier.
- the time f ( Mi ) is calculated based on the map image data Mi.
- the map image data Mi is image data showing a map around the i -th port (within a certain range including the i-th port).
- the map image data Mi includes environmental information within a certain range including the i -th port. Examples of environmental information include road shapes, traffic light positions, road signs, building shapes, and building types.
- the calculation unit 14 calculates the transportation time Tc i based on the map image data Mi.
- the function f is a function that defines the relationship between the time required for one transportation operation and the map image data Mi.
- a machine learning model can be used as such a function f.
- the map image data around the port (within a certain range including the port) is used as an explanatory variable, and the past work record (time required for one transportation work) at the port is used as the objective variable, and the explanatory variables related to a plurality of ports are used.
- a machine learning model is trained using the combination of and the objective variable. In such a machine learning model, the feature amount is extracted by vectorizing the input map image data.
- Maintenance time Tmi is the time required to maintain the i -th port. Examples of work for maintenance include leaflet allocation work and cleaning work.
- the calculation unit 14 calculates the maintenance time Tmi based on the elapsed time ⁇ ti that has elapsed since the worker who relocated the i -th port last visited. Specifically, as shown in the equation (13), the calculation unit 14 calculates the maintenance time Tmi using the function g.
- the function g is a function that defines the relationship between the maintenance time Tmi and the elapsed time ⁇ ti . That is, the maintenance time Tmi changes according to the elapsed time ⁇ ti . As the elapsed time ⁇ ti increases, the maintenance time Tmi increases.
- the function g is obtained and stored in advance from the past work results (maintenance time actually required for the maintenance work) at the plurality of ports.
- the function g is set in common to all ports, for example.
- step S36 the calculation unit 14 changes the transport vehicle state included in the transport vehicle information of the transport vehicle to "moving", sets the collection port ID to the port ID of the collection port determined in step S32, and arranges the collection port ID.
- the port ID is set to the port ID of the arrangement port determined in step S34, and the number of rearrangements is set to the number of rearrangements determined in step S34.
- the calculation unit 14 starts the collection work at the collection port at the first time obtained by adding the travel time from the current location of the carrier to the collection port to the time t, and sets the work time at the collection port as the first time.
- the collection work at the collection port is completed at the second time obtained by adding to the time, and the placement work at the placement port is completed at the third time obtained by adding the movement time from the collection port to the placement port to the second time. It is stored (stacked) that it is started and that the placement work at the placement port ends at the fourth time obtained by adding the work time at the placement port to the third time. The same applies when two ports are determined as the placement ports. As a result, the calculation unit 14 ends the rearrangement process.
- the calculation unit 14 carries out the lending process (step S24).
- the calculation unit 14 first determines the number of lending units in each port (step S41). Specifically, the calculation unit 14 determines the number of vehicles rented out at the port at time t (the number of rented vehicles) for each of the target port and the virtual port. In the following description, the vehicle rented at the port may be referred to as "rental vehicle at the port", “rental vehicle” or the like.
- the calculation unit 14 determines the number of rented units at each port according to the probability distribution of the number of rented units, for example, using the information on the number of rented units for simulation in the target area.
- an example of a method for determining the number of rented units will be described using the information on the number of rented units for simulation of the target area shown in FIG.
- the number of rented vehicles rented at a port whose port ID is "Pa1" (hereinafter referred to as "port Pa1", etc.) at 7:00 on Monday is the average number of rented vehicles at 7:00 on weekdays at port Pa1. It is determined by generating a random number (integer value) that follows a Poisson distribution with the peak of "7", which is the number of units. That is, the generated random number is determined as the number of loans.
- the calculation unit 14 determines a vehicle (rental vehicle) to be rented at each target port (step S42).
- the calculator 14 extracts a record of vehicles parked in the target port from the vehicle information updated in step S22, thereby listing the available vehicles (vehicles) as shown in FIG. List) is generated.
- the calculation unit 14 selects the vehicles for the number of rented vehicles determined in step S41 from the vehicle list as the rented vehicles.
- the calculation unit 14 determines the rental vehicle based on, for example, the remaining battery level of each vehicle parked in the target port. Specifically, the usage probability of each vehicle is calculated so that the vehicle having a larger battery level has a higher probability of being selected.
- the utilization probability of a vehicle having a battery remaining amount equal to or higher than the remaining amount threshold value is expressed by the equation (14) using the number n a , the number n b , the constant C a , and the constant C b .
- the number na is the number of available vehicles having a battery remaining amount equal to or higher than the remaining amount threshold value.
- the number n b is the number of available vehicles having a battery remaining amount less than the remaining amount threshold value.
- the constant C a is used to determine the utilization probability of a vehicle having a battery remaining amount equal to or higher than the remaining amount threshold value.
- the constant C b is used to determine the utilization probability of a vehicle having a battery remaining amount less than the remaining amount threshold.
- the constant C a is larger than the constant C b .
- the constant C a , the constant C b , and the remaining amount threshold value are set in advance based on the past usage record and the like.
- the utilization probability of a vehicle having a battery remaining amount less than the remaining amount threshold value is expressed by the equation (15) using the number n a , the number n b , the constant C a , and the constant C b .
- the calculation unit 14 selects rental vehicles for the number of rental vehicles based on the usage probability of each available vehicle.
- the calculation unit 14 determines the remaining battery level of the rental vehicle at the virtual port (step S43). Since the virtual port is a port that virtually represents all the ports included in the non-target area, the available vehicle list is not generated for the virtual port. Therefore, the rented vehicle is not selected in the virtual port, but the remaining battery level of the rented vehicle is determined. That is, the virtual port assumes that a virtual vehicle with a determined battery level is selected as the rental vehicle.
- step S43 the calculation unit 14 determines, for example, the battery level of the rental vehicle at the virtual port based on the battery level of the vehicle existing in the non-target area. Specifically, the calculation unit 14 extracts the vehicle information of the vehicle existing in the non-target area from the vehicle information updated in step S22. Then, the calculation unit 14 uses the extracted vehicle information to count the number of vehicles having the battery remaining amount among all the vehicles existing in the non-target area for each battery remaining amount. Then, the calculation unit 14 calculates the usage probability of each battery remaining amount by dividing the number of vehicles having each battery remaining amount by the total number of vehicles existing in the non-target area. Then, the calculation unit 14 determines the battery remaining amount of each rental vehicle in the virtual port based on the usage probability of each battery remaining amount. The calculation unit 14 may calculate the battery level of the rented vehicle at the virtual port based on the battery level of all the vehicles existing in the rearrangement area.
- the calculation unit 14 determines the return port (destination) in which the rental vehicle at each port is returned (step S44).
- the calculation unit 14 determines the return port of each rented vehicle according to the probability distribution of the return port, for example, using the movement information for simulation of the target area.
- the movement information for simulation of the target area shown in FIG.
- the probability that port Pa3 will be selected as the return port is 0.1
- the probability that port Pa4 will be selected is 0.3
- the probability that virtual port VPa will be selected is 0.2.
- the calculation unit 14 determines the return port based on the above probability. That is, the calculation unit 14 determines one of the return ports as the return port on which the rented vehicle is returned, according to the distribution of the probability that the vehicle will be returned at each return port (multinomial distribution).
- the calculation unit 14 determines the battery usage of the rental vehicle at each port (step S45).
- the calculation unit 14 determines the battery usage of the rented vehicle, for example, based on the rented port and the return port of each rented vehicle.
- the calculation unit 14 determines the battery usage amount of each rental vehicle by using the battery usage information for simulation in the target area.
- an example of a method for determining the battery usage amount will be described using the battery usage information for simulation of the target area shown in FIG. For example, if the lending port is port Pa1 and the returning port is port Pa3, the battery usage is determined to be 0.3.
- the calculation unit 14 determines the usage time of the rental vehicle at each port (step S46).
- the calculation unit 14 determines the usage time based on, for example, the rental port and the return port of each rental vehicle.
- the calculation unit 14 determines the usage time of each rented vehicle according to the probability distribution of the usage time using the usage time information for simulation of the target area.
- an example of a method of determining the usage time will be described using the usage time information for simulation of the target area shown in FIG.
- the vehicle usage time is obtained by generating a random number (integer value) that follows a Poisson distribution with a peak of "0.6" (hours). It is determined. That is, the generated random number is determined as the usage time.
- step S47 the calculation unit 14 changes the vehicle state included in the vehicle information of each vehicle rented out at time t at the target port from "parking" to "moving”, and changes the port ID to an invalid value.
- the remaining battery power is subtracted by the calculated battery usage.
- the calculation unit 14 newly generates a vehicle information record for each rental vehicle in the virtual port. Specifically, the calculation unit 14 assigns a new vehicle ID to each vehicle, sets the vehicle status to "moving”, sets the port ID to an invalid value, and determines the remaining battery level in step S43. The remaining battery level is set to a value obtained by subtracting the battery usage amount determined in step S45 from the above.
- the calculation unit 14 reduces the number of available port information of the target port on which the vehicle is rented by the number of rented ports. Then, the calculation unit 14 stores (stacks) that the vehicle is returned to the return port at a time obtained by adding the usage time of each vehicle to the time t. The port information of the ports included in the non-target area is not changed. As a result, the calculation unit 14 ends the lending process.
- End time Tend is the end time of the simulation.
- the end time Tend is set to, for example, a value indicating that 24 hours have passed from the time 0.
- the calculation unit 14 determines that the time t has not reached the end time Tend (step S25; NO), and adds 1 to the time t (step). S26). Then, the calculation unit 14 performs the processes of steps S22 to S25 again at the next time t.
- the calculation unit 14 determines that the time t has reached the end time Tend (step S25; YES), and ends the simulation process of the target area.
- the evaluation unit 15 evaluates the weight pattern (step S15).
- step S15 the evaluation unit 15 generates an evaluation result for the weight (weight pattern) based on the surplus number and the shortage number generated in each port when the rearrangement is performed using the weight pattern. For example, as shown in the equation (16), the evaluation unit 15 calculates the sum of the surplus units ai , t and the shortage units bi, t generated in each port in a predetermined period as the evaluation result E.
- the number of ports Np is the total number of target ports.
- the predetermined period is a period from time 0 to the end time Tend.
- the surplus number ai, t is the surplus number generated at time t at the i-th port.
- the shortage units bi and t are the shortage units that occurred at time t at the i-th port.
- the evaluation unit 15 outputs the evaluation result to the adjustment unit 13.
- the adjusting unit 13 determines whether or not all the weight patterns have been selected (step S16). When it is determined that not all the weight patterns have been selected (step S16; NO), the adjusting unit 13 selects an unselected weight pattern (step S13). Then, steps S14 to S16 are performed again. When it is determined in step S16 that all the weight patterns have been selected (step S16; YES), the adjusting unit 13 determines the optimum weight pattern for the target area (step S17).
- step S17 the adjusting unit 13 determines the optimum weight pattern from all the weight patterns based on the evaluation result. In other words, the adjusting unit 13 determines the optimum weight for each of the plurality of parameters based on the evaluation result. For example, the adjusting unit 13 determines the weight pattern having the smallest evaluation result E among all the weight patterns as the optimum weight pattern for the target area.
- the selection unit 12 determines whether or not all the divided areas have been selected as the target area (step S18). When it is determined that not all the divided areas have been selected as the target area (step S18; NO), the selection unit 12 selects the unselected divided area as the target area (step S12). Then, steps S13 to S18 are performed again. When it is determined in step S18 that all the divided areas have been selected as the target areas (step S18; YES), the adjusting unit 13 outputs the optimum weight pattern for each target area to the calculation unit 14. Then, when the calculation unit 14 receives the optimum weight pattern from the adjustment unit 13, the calculation unit 14 simulates the rearrangement by performing the rearrangement recommendation process in each target area using the optimum weight pattern.
- step S24 may be performed before step S23, or may be performed in parallel with step S23.
- steps S42 to S44 may be performed in any order or may be performed in parallel with each other.
- Step S46 may be performed before step S45, or may be performed in parallel with step S45. Steps S45 and S46 may be performed after step S44.
- the optimization command may include area information indicating the divided area to be optimized.
- the selection unit 12 determines whether or not all the division areas to be optimized have been selected.
- the rearrangement of the vehicle is simulated based on the working time Tpi at the rearrangement ports (collection port and placement port).
- the transport time Tci may vary depending on the surrounding environment of the rearranged port. Specifically, if the relocation port is adjacent to a large road, the carrier can be stopped near the relocation port, so the work of transporting the vehicle between the carrier and the relocation port. It is considered that (transportation work) does not take time. On the other hand, if the relocation port is located in a place where the carrier cannot enter, the stop position of the carrier may be separated from the relocation port. In such a case, the transportation work may take time.
- the working time Tpi may vary depending on the relocation port. Therefore, by considering the working time Tpi at the rearrangement port, the simulation of the rearrangement of the vehicle can be realized with high accuracy. As a result, it becomes possible to improve the simulation accuracy of the movement of the vehicle.
- the calculation unit 14 calculates the transportation time Tc i based on the map image data Mi showing the map around the rearranged port.
- the transport time Tci may vary depending on the surrounding environment of the rearranged port. Therefore, by using the map image data Mi , the surrounding environment of the rearranged port can be taken into consideration. As a result, the calculation accuracy of the transportation time Tc i can be improved, and by extension, the calculation accuracy of the working time Tpi can be improved.
- the calculation unit 14 calculates the transportation time Tci using a machine learning model learned using the map image data around the port as an explanatory variable and the time required for one transportation operation at the port as the objective variable. It is conceivable to calculate the transport time Tci using the actual value of the past transport time in one rearrangement port. However, if the number of past actual values is small, the calculation accuracy of the transportation time Tci may decrease. On the other hand, the transport time at the rearranged port having a similar surrounding environment is considered to have a similar tendency. According to the above configuration, by using the machine learning model, the transportation time Tci is calculated in consideration of the actual value of the past transportation time in the rearranged port having a similar surrounding environment. Therefore, even when the number of the actual values of the past transportation time in the rearrangement port is small, the calculation accuracy of the transportation time Tc i can be improved, and the calculation accuracy of the working time Tpi can be improved.
- the calculation unit 14 performs the number Nri of the target vehicles to be relocated at the relocation port, the number Ns that the worker can carry in one transportation work, and one transportation work at the relocation port.
- the transportation time Tc i is calculated based on the required time f (Mi ) .
- the transportation time Tc i is calculated by multiplying the division result obtained by dividing the number Nri by the number Ns and the time f (Mi ) . According to this configuration, the transportation time Tci can be calculated even when the worker cannot carry all the target vehicles in one transportation operation.
- the calculation unit 14 calculates the maintenance time Tmi based on the elapsed time ⁇ ti that has elapsed since the worker visited the relocation port last time. According to this configuration, the calculation accuracy of the maintenance management time Tmi can be improved, and by extension, the calculation accuracy of the working time Tpi can be improved.
- the calculation unit 14 calculates the maintenance time Tmi using the function g that defines the relationship between the maintenance time Tmi and the elapsed time ⁇ ti.
- the function g is obtained from the past maintenance time in a plurality of ports. It is conceivable to calculate the maintenance time Tmi using the actual value of the past maintenance time in one relocation port. However, if the number of past actual values is small, the calculation accuracy of the maintenance time Tmi may decrease. On the other hand, the maintenance time is considered to have the same tendency in all ports. According to the above configuration, by using the function g, the maintenance time Tmi is calculated in consideration of the actual value of the past maintenance time not only in the rearranged port but also in other ports. Therefore, even when the number of the actual values of the past maintenance time in the relocation port is small, the calculation accuracy of the maintenance time Tmi can be improved, and the calculation accuracy of the work time Tpi can be improved. ..
- the calculation unit 14 determines the recovery port and the placement port by using the relocation recommendation process (recommendation algorithm). According to this configuration, it is possible to determine the optimum recovery port and placement port for effective relocation.
- the calculation unit 14 determines the number of relocated vehicles based on the surplus number generated at the collection port, the number of vehicles that can be accommodated for relocation, and the shortage number generated at the placement port. For example, the number of rearrangement vehicles may be determined so as to reduce the number of surplus vehicles and the number of shortage vehicles within the range of the number of vehicles that can be accommodated. According to this configuration, it is possible to effectively suppress the excess or deficiency of the vehicle at each port by using the transport vehicle.
- the adjustment unit 13 adjusts the weights for each of the plurality of parameters used in the rearrangement recommendation process.
- the calculation unit 14 simulates the rearrangement by performing the rearrangement recommendation process using the weight. According to this configuration, it is possible to simulate the rearrangement while adjusting the influence degree of each parameter.
- the evaluation unit 15 generates an evaluation result for the weight of each parameter based on the surplus number and the shortage number generated in each port when the rearrangement is performed. According to this configuration, the weight of each parameter is evaluated according to the effect of the rearrangement. Therefore, the validity of the parameter weight can be judged from the evaluation result.
- the evaluation unit 15 determines the optimum weight for each of the plurality of parameters based on the evaluation result.
- the calculation unit 14 simulates the rearrangement by performing the rearrangement recommendation process using the optimum weight. With this configuration, the relocation can be simulated with the weights that achieved the most effective relocation. In other words, effective rearrangement recommendation processing (recommendation algorithm) can be realized. As a result, it is possible to improve the simulation accuracy.
- all the ports included in the non-target area are virtually treated as one virtual port, and the movement of the vehicle between the plurality of target ports included in the target area and the virtual ports is simulated.
- Ru a vehicle that moves from a target port in a target area to a port in a non-target area is considered to be a vehicle that is rented out at the target port and returned at the virtual port.
- a vehicle that moves from a port in a non-target area to a target port in the target area is considered to be a vehicle that is rented out at the virtual port and returned at the target port.
- the calculation unit 14 determines the number of rented vehicles and the return port on which each rented vehicle is returned for each of the plurality of target ports and virtual ports. According to this configuration, it is possible to simulate the movement of the vehicle between the ports by the user.
- the calculation unit 14 determines the rental vehicle based on the remaining battery level of each vehicle parked in the target port. According to this configuration, the simulation can be performed in consideration of the remaining battery level, so that the simulation accuracy can be improved.
- the simulation device 10 vehicles parked in ports in non-target areas are excluded from the calculation target. That is, the port information of the port of the non-target area and the vehicle information of the vehicle existing in the non-target area are not used for the simulation of the target area. Therefore, the rental vehicle in the virtual port is not selected from the vehicles existing in the non-target area, but is newly generated as a virtual vehicle. Since this virtual vehicle does not have information on the remaining battery level, the calculation unit 14 determines the remaining battery level of the rental vehicle at the virtual port based on the remaining battery level of the vehicle existing in the non-target area. do. With this configuration, it is possible to determine the battery level of the rental vehicle at the virtual port. As a result, it is possible to improve the simulation accuracy.
- the calculation unit 14 determines the battery usage of the rental vehicle based on the rental port and the return port. Since the battery usage of the rental vehicle can be predicted from the combination of the rental port and the return port, the battery usage can be accurately determined according to the above configuration. Then, for example, by subtracting the battery usage amount from the battery remaining amount of the rented vehicle, the battery remaining amount after the rented vehicle is returned can be calculated. Therefore, since it is possible to simulate the change over time in the remaining battery level of each vehicle, it is possible to improve the simulation accuracy.
- the simulation of the movement of the vehicle between a plurality of ports in the sharing traffic service can be performed at high speed, and it is possible to bring it closer to reality.
- the simulation device 10 may be configured by one device physically or logically coupled, or may be configured by a plurality of devices physically or logically separated from each other.
- the simulation device 10 may be realized by a plurality of computers distributed on a network such as cloud computing.
- the configuration of the simulation device 10 may include any configuration that can realize the function of the simulation device 10.
- the simulation device 10 may simulate the movement of the vehicle between a plurality of ports included in the rearrangement area, and it is not necessary to select the target area.
- the rearrangement area may not be divided into division areas, and the simulation device 10 may not include the selection unit 12.
- the simulation device 10 does not have to optimize the weights for each of the plurality of parameters used in the rearrangement recommendation process.
- the calculation unit 14 may perform the rearrangement recommendation process using the weight specified by the user of the simulation device 10. In these cases, the simulation device 10 does not have to include the adjusting unit 13 and the evaluation unit 15.
- the user of the simulation device 10 may evaluate the weight.
- the adjusting unit 13 may determine the optimum weight for each parameter based on the evaluation result by the user. In this case, the simulation device 10 does not have to include the evaluation unit 15.
- the working time Tp i includes at least the transportation time Tc i .
- the working time Tp i may not include at least one of the basic working time Tbi and the maintenance time Tmi .
- the working time Tpi may include yet another time.
- the calculation unit 14 may calculate the time required for one transportation operation based on another information indicating the surrounding environment of the rearranged port.
- the parameters X i, j for determining the recovery port may include parameters relating to the working time Tpi at the i -th port. For example, the smaller the working time Tpi , the larger the value of this parameter. In this case, the collection port that can effectively collect the vehicle can be determined in consideration of the working time Tpi .
- the parameters Y i, k for determining the placement port may include a parameter relating to the working time Tpi at the i -th port. For example, the smaller the working time Tpi , the larger the value of this parameter. In this case, the placement port on which the vehicle can be effectively placed can be determined in consideration of the working time Tpi .
- Battery usage information may be set for each user with the same attributes. For example, gender and age are used as user attributes.
- the calculation unit 14 determines the attributes of the user who rents the rental vehicle by a known method. Then, the calculation unit 14 may determine the battery usage of the rental vehicle based on the attributes of the user in addition to the rental port and the return port.
- the usage time may vary depending on the purpose of use of the vehicle. For example, the usage time when a vehicle is used for sightseeing may be significantly different from the usage time when a vehicle is used on a daily basis.
- the calculation unit 14 may determine the usage time of each rental vehicle according to the mixed Poisson distribution of the usage time. For example, the calculation unit 14 estimates the parameters of the mixed Poisson distribution from the past usage time for each combination of the lending port and the returning port by using a method such as an EM (Expectation-Maximization) algorithm. Then, the calculation unit 14 calculates the usage time from the probability model using the estimated parameters.
- EM Extractation-Maximization
- each functional block may be realized using one physically or logically coupled device, or two or more physically or logically separated devices can be directly or indirectly (eg, for example). , Wired, wireless, etc.) and may be realized using these plurality of devices.
- the functional block may be realized by combining the software with the one device or the plurality of devices.
- Functions include judgment, decision, judgment, calculation, calculation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, solution, selection, selection, establishment, comparison, assumption, expectation, and assumption. These include broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assigning. Not limited to functions.
- a functional block (configuration unit) that makes transmission function is called a transmitting unit (transmitting unit) or a transmitter (transmitter).
- the realization method is not particularly limited.
- the simulation device 10 in one embodiment of the present disclosure may function as a computer that performs the processing of the present disclosure.
- the hardware configuration of the simulation device 10 will be described.
- FIG. 19 is a diagram showing an example of the hardware configuration of the simulation device 10 according to the embodiment of the present disclosure.
- the simulation device 10 described above may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like.
- the word “device” can be read as a circuit, a device, a unit, or the like.
- the hardware configuration of the simulation device 10 may be configured to include one or more of each of the devices shown in the figure, or may be configured not to include some of the devices.
- the processor 1001 For each function in the simulation device 10, the processor 1001 performs calculations by loading predetermined software (programs) on hardware such as the processor 1001 and the memory 1002, and controls communication by the communication device 1004, or the memory 1002. And by controlling at least one of reading and writing of data in the storage 1003.
- predetermined software programs
- the processor 1001 operates, for example, an operating system to control the entire computer.
- the processor 1001 may be configured by a central processing unit (CPU: Central Processing Unit) including an interface with peripheral devices, a control device, an arithmetic unit, a register, and the like.
- CPU Central Processing Unit
- each function of the simulation device 10 described above may be realized by the processor 1001.
- the processor 1001 reads a program (program code), a software module, data, and the like from at least one of the storage 1003 and the communication device 1004 into the memory 1002, and executes various processes according to these.
- a program program code
- a program that causes a computer to execute at least a part of the operations described in the above-described embodiment is used.
- each function of the simulation device 10 may be realized by a control program stored in the memory 1002 and operating in the processor 1001.
- Processor 1001 may be mounted by one or more chips.
- the program may be transmitted from the network via a telecommunication line.
- the memory 1002 is a computer-readable recording medium, for example, by at least one of ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), and the like. It may be configured.
- the memory 1002 may be referred to as a register, a cache, a main memory (main storage device), or the like.
- the memory 1002 can store a program (program code), a software module, and the like that can be executed to carry out the simulation method according to the embodiment of the present disclosure.
- the storage 1003 is a computer-readable recording medium, and is, for example, an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, an optical magnetic disk (for example, a compact disk, a digital versatile disk, or a Blu-ray). It may consist of at least one such as a (registered trademark) disk), a smart card, a flash memory (eg, a card, stick, key drive), a floppy (registered trademark) disk, and a magnetic strip.
- the storage 1003 may be referred to as an auxiliary storage device.
- the storage medium described above may be, for example, a database, server, or other suitable medium containing at least one of memory 1002 and storage 1003.
- the communication device 1004 is hardware (transmission / reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as, for example, a network device, a network controller, a network card, or a communication module.
- the communication device 1004 includes, for example, a high frequency switch, a duplexer, a filter, a frequency synthesizer, and the like in order to realize at least one of frequency division duplex (FDD: Frequency Division Duplex) and time division duplex (TDD: Time Division Duplex). It may be configured to include.
- FDD Frequency Division Duplex
- TDD Time Division Duplex
- the input device 1005 is an input device (for example, a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that accepts an input from the outside.
- the output device 1006 is an output device (for example, a display, a speaker, an LED lamp, etc.) that performs output to the outside.
- the input device 1005 and the output device 1006 may be integrally configured like, for example, a touch panel.
- Each device such as the processor 1001 and the memory 1002 is connected by a bus 1007 for communicating information.
- the bus 1007 may be configured by using a single bus, or may be configured by using a different bus for each device.
- the simulation device 10 includes hardware such as a microprocessor, a digital signal processor (DSP: Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), and an FPGA (Field Programmable Gate Array).
- DSP Digital Signal Processor
- ASIC Application Specific Integrated Circuit
- PLD Programmable Logic Device
- FPGA Field Programmable Gate Array
- the hardware may implement some or all of each functional block.
- processor 1001 may be implemented using at least one of these hardware.
- Information notification is not limited to the embodiments / embodiments described in the present disclosure, and may be performed by other methods.
- Information and the like may be output from the upper layer to the lower layer, or may be output from the lower layer to the upper layer. Information and the like may be input / output via a plurality of network nodes.
- the input / output information and the like may be stored in a specific place (for example, a memory) or may be managed using a management table. Information to be input / output may be overwritten, updated, or added. The output information and the like may be deleted. The input information or the like may be transmitted to another device.
- the determination may be made by a value represented by 1 bit (0 or 1), by a boolean value (Boolean: true or false), or by comparing numerical values (for example, a predetermined value). It may be done by comparison with the value).
- Notification of predetermined information is not limited to explicit notification, and may be implicitly (for example, by not notifying the predetermined information). ..
- Software whether called software, firmware, middleware, microcode, hardware description language, or other names, is an instruction, instruction set, code, code segment, program code, program, subprogram, software module.
- Applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, features, etc. should be broadly interpreted.
- Software, instructions, information, etc. may be transmitted and received via a transmission medium.
- the software uses at least one of wired technology (coaxial cable, fiber optic cable, twist pair, digital subscriber line (DSL: Digital Subscriber Line), etc.) and wireless technology (infrared, microwave, etc.) to create a website.
- wired technology coaxial cable, fiber optic cable, twist pair, digital subscriber line (DSL: Digital Subscriber Line), etc.
- wireless technology infrared, microwave, etc.
- the information, signals, etc. described in this disclosure may be represented using any of a variety of different techniques.
- data, instructions, commands, information, signals, bits, symbols, and chips that may be referred to throughout the above description are voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, light fields or photons, or theirs. It may be represented by any combination.
- system and “network” used in this disclosure are used interchangeably.
- the information, parameters, etc. described in the present disclosure may be expressed using absolute values, relative values from a predetermined value, or other corresponding information. It may be represented.
- determining and “determining” used in this disclosure may include a wide variety of actions.
- “Judgment” and “decision” are, for example, judgment (judging), calculation (calculating), calculation (computing), processing (processing), derivation (deriving), investigation (investigating), search (looking up, search, inquiry). It may be considered as (eg, searching in a table, database or another data structure), and ascertaining.
- “Judgment” and “decision” are receiving (eg, receiving information), transmitting (eg, transmitting information), input, output, and access (eg, transmitting information). It may be considered as (accessing) (for example, accessing data in memory).
- “Judgment” and “decision” may be regarded as resolving, selecting, choosing, establishing, and comparing. That is, “judgment” and “decision” may be regarded as some action related to “judgment” and “decision”. “Judgment (decision)” may be read as “assuming", “expecting”, “considering”, or the like.
- connection means any direct or indirect connection or connection between two or more elements and each other. It can include the presence of one or more intermediate elements between two “connected” or “combined” elements.
- the connection or connection between the elements may be performed physically, logically, or may be realized by a combination thereof. For example, “connection” may be read as "access”.
- connection may be read as "access”.
- connection or “coupling” is used in the present disclosure, the two elements are “connected” or “coupled” to each other using at least one of one or more wires, cables and printed electrical connections.
- electromagnetic energy having wavelengths in the radio frequency region, microwave region and light (both visible and invisible) region may be used. It may be considered to be “connected” or “bonded” to each other.
- references to elements using designations such as “first” and “second” as used in this disclosure does not generally limit the quantity or order of those elements. These designations can be used in the present disclosure as a convenient way to distinguish between two or more elements. Therefore, references to the first and second elements do not mean that only two elements can be adopted and that the first element must somehow precede the second element.
- each of the above devices may be replaced with a "circuit", a “device” or the like.
- the term "A and B are different” may mean “A and B are different from each other”.
- the term may mean that "A and B are different from C”.
- Terms such as “separate” and “combined” may be interpreted in the same way as “different”.
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Primary Health Care (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Description
Claims (8)
- シェアリング交通サービスにおける複数のポート間での車両の移動をシミュレートするシミュレーション装置であって、
車両の再配置の対象となるポートである再配置ポートにおける作業時間を算出し、前記作業時間に基づいて前記再配置をシミュレートする計算部を備える、シミュレーション装置。 - 前記作業時間は、前記再配置の対象となる車両である対象車両を前記再配置ポートの間で運搬する運搬車と前記再配置ポートとの間で前記対象車両を作業員が運ぶのに要する運搬時間を含み、
前記計算部は、前記再配置ポートの周辺の地図を示す地図画像データに基づいて、前記運搬時間を算出する、請求項1に記載のシミュレーション装置。 - 前記計算部は、ポート周辺の地図画像データを説明変数とし、当該ポートにおける1回の運搬作業に要する時間を目的変数として学習された機械学習モデルを用いて、前記運搬時間を算出する、請求項2に記載のシミュレーション装置。
- 前記計算部は、前記対象車両の台数と、1回の運搬作業で運ぶことができる台数と、前記1回の運搬作業に要する時間と、に基づいて、前記運搬時間を算出する、請求項3に記載のシミュレーション装置。
- 前記作業時間は、前記再配置ポートを維持管理するための維持管理時間を含み、
前記計算部は、前記再配置ポートを作業員が前回訪れてから経過した経過時間に基づいて、前記維持管理時間を算出する、請求項1~請求項4のいずれか一項に記載のシミュレーション装置。 - 前記計算部は、前記維持管理時間と前記経過時間との関係を規定する関数を用いて、前記維持管理時間を算出し、
前記関数は、前記複数のポートにおける過去の維持管理時間から求められる、請求項5に記載のシミュレーション装置。 - 前記計算部は、再配置をレコメンドするためのレコメンドアルゴリズムを用いて、前記再配置の対象となる対象車両が回収される前記再配置ポートである回収ポート、及び回収された前記対象車両が配置される前記再配置ポートである配置ポートを決定する、請求項1~請求項6のいずれか一項に記載のシミュレーション装置。
- 前記計算部は、前記回収ポートにおいて生じる余剰台数と、前記再配置を行う運搬車が収容可能な車両の台数である収容可能台数と、前記配置ポートにおいて生じる不足台数と、に基づいて、再配置台数を決定する、請求項7に記載のシミュレーション装置。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US18/251,647 US20230409990A1 (en) | 2020-12-23 | 2021-12-08 | Simulation device |
JP2022572105A JP7478847B2 (ja) | 2020-12-23 | 2021-12-08 | シミュレーション装置 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2020213515 | 2020-12-23 | ||
JP2020-213515 | 2020-12-23 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022138164A1 true WO2022138164A1 (ja) | 2022-06-30 |
Family
ID=82157721
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2021/045111 WO2022138164A1 (ja) | 2020-12-23 | 2021-12-08 | シミュレーション装置 |
Country Status (3)
Country | Link |
---|---|
US (1) | US20230409990A1 (ja) |
JP (1) | JP7478847B2 (ja) |
WO (1) | WO2022138164A1 (ja) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2002304498A (ja) * | 2001-04-03 | 2002-10-18 | Honda Motor Co Ltd | 車両共同利用システム |
JP2014041475A (ja) * | 2012-08-22 | 2014-03-06 | Toyota Motor Corp | カーシェアリングシステムの運用管理システムおよび方法 |
KR101932608B1 (ko) * | 2017-09-21 | 2018-12-27 | 충남대학교산학협력단 | 자전거 대여 시스템 관리 방법, 자전거 대여 시스템의 관리 서버, 및 컴퓨터 판독가능 기록 매체 |
-
2021
- 2021-12-08 WO PCT/JP2021/045111 patent/WO2022138164A1/ja active Application Filing
- 2021-12-08 JP JP2022572105A patent/JP7478847B2/ja active Active
- 2021-12-08 US US18/251,647 patent/US20230409990A1/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2002304498A (ja) * | 2001-04-03 | 2002-10-18 | Honda Motor Co Ltd | 車両共同利用システム |
JP2014041475A (ja) * | 2012-08-22 | 2014-03-06 | Toyota Motor Corp | カーシェアリングシステムの運用管理システムおよび方法 |
KR101932608B1 (ko) * | 2017-09-21 | 2018-12-27 | 충남대학교산학협력단 | 자전거 대여 시스템 관리 방법, 자전거 대여 시스템의 관리 서버, 및 컴퓨터 판독가능 기록 매체 |
Non-Patent Citations (1)
Title |
---|
TAKEI, TOMOHISA: "Bike Share Virtuous Circle - Solving the Redeployment Problem with AI", NIKKEI COMPUTER, no. 981, 10 January 2019 (2019-01-10), JP , pages 56 - 57, XP009537886, ISSN: 0285-4619 * |
Also Published As
Publication number | Publication date |
---|---|
JP7478847B2 (ja) | 2024-05-07 |
JPWO2022138164A1 (ja) | 2022-06-30 |
US20230409990A1 (en) | 2023-12-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110264023B (zh) | 共享车辆管理服务器和存储共享车辆管理程序的非暂时性存储介质 | |
Zhang et al. | Route prediction for instant delivery | |
CN103134505B (zh) | 路径规划系统及其方法 | |
CN110188970B (zh) | 共享车辆管理装置以及共享车辆管理方法 | |
Chen et al. | Optimal deployment of electric bicycle sharing stations: model formulation and solution technique | |
Huang et al. | A bimodal Gaussian inhomogeneous Poisson algorithm for bike number prediction in a bike-sharing system | |
CN111950950A (zh) | 订单配送路径的规划方法、装置、计算机介质及电子设备 | |
CN113342418B (zh) | 基于区块链的分布式机器学习任务卸载方法 | |
CN112082566B (zh) | 电动汽车路径规划方法、装置、终端及存储介质 | |
Roh et al. | A block transportation scheduling system considering a minimisation of travel distance without loading of and interference between multiple transporters | |
Wang et al. | Record: Joint real-time repositioning and charging for electric carsharing with dynamic deadlines | |
Nair et al. | Equilibrium design of bicycle sharing systems: the case of Washington DC | |
Zhong et al. | The optimization of bus rapid transit route based on an improved particle swarm optimization | |
WO2023053684A1 (ja) | ゴミ収集システムおよび学習済みモデル | |
Kınay et al. | Charging station location and sizing for electric vehicles under congestion | |
WO2022138164A1 (ja) | シミュレーション装置 | |
WO2022138168A1 (ja) | シミュレーション装置 | |
CN114595026A (zh) | 在多平台即服务的系统中估计平台上运行的工作负载的属性 | |
JP7227862B2 (ja) | ポート開設場所提案装置 | |
CN116704783A (zh) | 一种基于cim的公交站点与快速路出口优化布局方法和装置 | |
CN114640619B (zh) | 基于平均通信距离的天基网络拓扑设计方法及相关设备 | |
Haider et al. | Optimizing the relocation operations of free-floating electric vehicle sharing systems | |
JP7441230B2 (ja) | 共用車両管理装置 | |
CN113222282B (zh) | 运送路径确定方法和装置、可读存储介质、电子设备 | |
Zhang et al. | Bidirectional k-nearest neighbor spatial crowdsourcing allocation protocol based on edge computing |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21910313 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2022572105 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 18251647 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 21910313 Country of ref document: EP Kind code of ref document: A1 |