WO2021042833A1 - 基于调度模型的车辆调度方法、装置、计算机设备及存储介质 - Google Patents

基于调度模型的车辆调度方法、装置、计算机设备及存储介质 Download PDF

Info

Publication number
WO2021042833A1
WO2021042833A1 PCT/CN2020/098464 CN2020098464W WO2021042833A1 WO 2021042833 A1 WO2021042833 A1 WO 2021042833A1 CN 2020098464 W CN2020098464 W CN 2020098464W WO 2021042833 A1 WO2021042833 A1 WO 2021042833A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
delivery
scheduling
delivery point
point
Prior art date
Application number
PCT/CN2020/098464
Other languages
English (en)
French (fr)
Inventor
程克喜
Original Assignee
平安科技（深圳）有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Publication of WO2021042833A1 publication Critical patent/WO2021042833A1/zh

Links

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
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
    • 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
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06315—Needs-based resource requirements planning or analysis
    • 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
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Definitions

  • This application relates to the field of smart transportation in smart cities, and in particular to a vehicle scheduling method, device, computer equipment, and storage medium based on a scheduling model.
  • this application proposes a vehicle scheduling method, device, computer equipment, and storage medium based on a scheduling model, which can optimize the placement strategy of the placement point based on the operational data and location of the existing placement point, thereby increasing the utilization rate. Maximize revenue.
  • this application proposes a vehicle scheduling method based on a scheduling model, the method including:
  • the specific dimensional data includes usage data of registered users and operation data of each placement point;
  • a vehicle scheduling strategy is generated according to the optimization data, wherein the vehicle scheduling strategy includes the number of changes in the amount of vehicle delivery at each delivery point.
  • this application also discloses a vehicle scheduling device for shared vehicles, which includes:
  • the obtaining module is adapted to obtain specific dimensional data, where the specific dimensional data includes usage data of registered users and operation data of each placement point;
  • the optimization module is adapted to calculate optimization data based on the specific dimensional data and a pre-built vehicle scheduling model, where the vehicle scheduling model takes car rental demand and rental car revenue as optimization targets;
  • the output module is adapted to generate a vehicle scheduling strategy according to the optimization data, wherein the vehicle scheduling strategy includes the number of changes in the amount of vehicle delivery at each delivery point.
  • this application also discloses a computer device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor.
  • the processor executes the computer program, the above scheduling-based The vehicle scheduling method of the model.
  • the present application also discloses a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the vehicle scheduling method based on the scheduling model is realized.
  • the vehicle scheduling method, device, computer equipment, and storage medium based on the scheduling model proposed in this application generate an optimized vehicle scheduling model combined with the operation data and location data of the vehicle delivery point through the pre-built vehicle scheduling model.
  • the placement strategy can assist in increasing the utilization rate of the placed vehicles, reducing idleness, making it convenient for users to rent cars and improving corporate efficiency.
  • Fig. 1 is a flowchart of a vehicle scheduling method based on a scheduling model in the first embodiment of the present application
  • FIG. 2 is a flowchart of calculating optimized data based on specific dimensional data and a pre-built vehicle scheduling model according to an embodiment of the present application
  • Figure 3 is a flow chart of the forecasted demand interval of an embodiment of the present application.
  • FIG. 4 is a flowchart of calculating optimized data according to specific dimensional data and a pre-built vehicle scheduling model in a further embodiment of the embodiment of the present application;
  • FIG. 5 is a flowchart of generating a vehicle scheduling strategy based on optimized data in a further embodiment of the embodiment of the present application
  • FIG. 6 is a schematic diagram of program modules of a vehicle dispatching device for shared vehicles in the second embodiment of the present application.
  • FIG. 7 is a schematic diagram of the hardware structure of the computer equipment of the third embodiment of the present application.
  • FIG. 1 shows a flowchart of a vehicle scheduling method based on a scheduling model in Embodiment 1 of the present application. It can be understood that the flowchart in this method embodiment is not used to limit the order of execution of the steps.
  • the following exemplarily describes the vehicle dispatching device of the shared vehicle as the execution subject.
  • the vehicle dispatching device of the shared vehicle may be applied to the server. details as follows:
  • Step S101 Obtain specific dimensional data, where the specific dimensional data includes usage data of registered users and operation data of each placement point;
  • the usage data of the registered user includes the rental time of the registered user, the delivery point when renting the car, the delivery point when returning the car, the rental duration, the consumption amount and other data.
  • the operating data of each delivery point includes the rental of each single car rental business. Data such as time, rental duration, delivery point and amount generated when returning the car.
  • step S102 calculate optimization data based on the specific dimension data and the pre-built vehicle scheduling model, where the vehicle scheduling model takes car rental demand and rental car revenue as optimization goals;
  • step S102 includes the following steps:
  • Step S201 Calculate the predicted demand interval of the placement point according to the specific dimension data
  • the predicted demand interval can be obtained according to the following steps S301-S303:
  • Step S301 Calculate the fixed demand interval according to the usage data of the registered users
  • the usage data of registered users can be used to calculate the usage time period, usage frequency, and commonly used distribution points of registered users with regular rentals (such as registered users who regularly rent at and off work, the rental point and return point of the car are relatively fixed) Based on this information, the fixed demand interval of each placement point can be calculated, that is, the minimum number of vehicles placed at the placement point.
  • Step A1 Obtain historical borrowing and repayment records in a certain period of operation (for example: 3 months) of the placement point;
  • Step A2 Obtain the borrowing record of the registered user in the historical borrowing record, and generating a user data table based on the registered user’s borrowing record; the user usage data table includes the user ID and the number of times the user has used it during the operation period , Use distribution status;
  • Step A3 Filter out user data with relatively regular usage distribution according to the user data table, and generate a second user data table;
  • the user’s weekly use of shared vehicles can be counted according to the calendar week, and it can be judged whether the user uses the shared vehicle every week and the number of uses per week is not less than the set number of times (e.g. 3 times) ), the user data that meets the condition is listed in the second user data table.
  • Step A4 According to the second data table, count the number of people whose use times are greater than or equal to the first specific value and the number of persons greater than or equal to the second specific value during the operation period as the upper and lower limits of the fixed demand interval to obtain the fixed demand interval.
  • Step S302 Calculate the floating demand interval according to the operating data of the delivery point
  • the operating data of the delivery point it is possible to count the use time period and the number of rentals of individual customers with randomness of the rental vehicle, and then the floating demand interval of each rental vehicle can be calculated.
  • Step S303 Calculate the sum of the fixed demand interval and the floating demand interval to obtain a predicted demand interval.
  • step S202 calculate the demand for the delivery point corresponding to the minimum cost according to the pre-built cost model, where the cost model relates to the transformation cost and the transportation cost of the delivery point.
  • the cost of renovation involves the rent of the site, construction costs and subsequent equipment maintenance costs
  • the cost of dispatch involves the wages of dispatch personnel, the dispatch capacity of the company operating the car rental business, etc., based on which the cost model is constructed, and the linear programming principle is used to calculate the satisfaction The demand for each delivery point corresponding to the demand interval and the minimum cost.
  • a cost model is as follows:
  • P represents the cost
  • A represents the area of land required for each additional shared vehicle
  • R i represents the rent per unit area of the i-th vehicle placement point
  • y i represents the optimized vehicle placement of the i-th vehicle placement point
  • Quantity y i'represents the current vehicle delivery volume of the i-th vehicle delivery point
  • B represents the construction cost required for each increase or decrease of a shared vehicle
  • C i represents the average maintenance of each shared vehicle at the i-th vehicle delivery point Cost
  • D i represents the number of dispatch personnel required for the i-th vehicle delivery point
  • h represents the salary of dispatch personnel.
  • the values of the above-mentioned parameters R i , C i , and D i can be obtained by statistics based on the historical operation data of each vehicle delivery point.
  • a number of constraints can be set, such as: the sum of the number of personnel cannot exceed a certain value, individual restrictions for each vehicle placement point (e.g., according to the limitations of the site, the i-th vehicle placement point can be placed The number of vehicles does not exceed 20 at most); according to this, combined with the forecasted demand interval, the demand for the delivery point corresponding to the minimum cost can be obtained.
  • step S102 further includes the following steps:
  • Step S401 finding the scheduling demand when the scheduling cost is the smallest according to the demand of each delivery point and the preset scheduling cost model
  • the preset scheduling cost model is as follows:
  • G represents the transportation cost
  • t represents the service cycle
  • an operation cycle is divided into M segments
  • n represents the number of delivery points
  • c ij represents the transportation cost per unit mileage from the delivery point i to the delivery point j
  • d ij represents the delivery from the delivery point.
  • the distance from the point i to the delivery point j, x ij represents the number of vehicles transferred from the delivery point i to the delivery point j, where i ⁇ j.
  • the scheduling cost model several constraints can be set as needed, such as the conservation of the total number of vehicles during the dispatch, the mileage of the vehicle is greater than the distance between the two delivery points, and the sufficient parking spaces for the dispatched vehicles when they reach the target delivery point, etc., according to the above The model can solve the dispatching demand between each delivery point.
  • Step S402 Calculate the vehicle scheduling route plan when the revenue is maximized according to the scheduling requirement and the preset revenue model.
  • the preset profit model is as follows:
  • Q means revenue
  • i ⁇ P means that the delivery point i needs to transfer the vehicle to another station at a certain time
  • j ⁇ D means that the delivery point j needs to dispatch the vehicle to the station at a certain time
  • s is the dispatcher number
  • S means The number of dispatchers
  • Rer represents the revenue of each dispatch task
  • O means the dispatch center
  • C means every shift The working hours of a dispatcher.
  • each scheduling task can only be executed once
  • the vehicle life of the dispatcher is greater than the distance between the two delivery points during the dispatching process
  • a dispatcher can only perform one dispatching task And so on, based on this, the best scheduling path can be found.
  • step S103 generating a vehicle scheduling strategy based on the optimization data, where the vehicle scheduling strategy includes the number of changes in the amount of vehicle delivery at each delivery point.
  • the vehicle scheduling strategy further includes the vehicle scheduling path plan obtained in step S402.
  • the generating a vehicle scheduling strategy according to the optimization data further includes the following steps:
  • a list of delivery points whose delivery volume variation index is greater than a preset first threshold is generated as a list of delivery points that need to be modified.
  • the quantity change index here can be calculated according to the difference between the demand quantity and the existing quantity, or it can be calculated according to the percentage change of the demand quantity to the existing quantity.
  • the first threshold can be set as the quantity according to different calculation methods. Or percentage.
  • the generating a vehicle scheduling strategy according to the optimization data further includes the following steps:
  • a list of placement points whose demand is lower than the preset second threshold is generated as a list of placement points to be cancelled.
  • the operating cost includes transportation cost, maintenance cost, and loss cost.
  • the method further includes the following steps S501-S503:
  • Step S501 generating a list of delivery points where the operating cost is higher than the revenue generated
  • Step S502 calculating the ratio of the difference between the operating cost and the revenue generated to the revenue generated;
  • step S503 the placement points whose ratio is higher than the preset third threshold are included in the list of placement points to be cancelled.
  • FIG. 6 shows a schematic diagram of program modules of a vehicle scheduling device 600 for shared vehicles in the second embodiment of the present application.
  • the vehicle scheduling device 600 for shared vehicles may include or be divided into one or more program modules, and the one or more program modules are stored in a storage medium and executed by one or more processors.
  • the program module referred to in the embodiments of the present application refers to a series of computer program instruction segments capable of completing specific functions, and is more suitable than the program itself to describe the execution process of the vehicle scheduling method based on the scheduling model in the storage medium.
  • the following description will specifically introduce the functions of each program module in this embodiment:
  • the obtaining module 601 is adapted to obtain specific dimensional data, where the specific dimensional data includes usage data of registered users and operation data of each placement point;
  • the usage data of the registered user includes the rental time of the registered user, the delivery point when renting the car, the delivery point when returning the car, the rental duration, the amount of consumption and other data.
  • the operating data of each delivery point includes the rental time of each single car rental business. , Rental duration, delivery point and amount generated when returning the car.
  • the optimization module 602 is adapted to calculate optimization data based on the specific dimension data and a pre-built vehicle scheduling model, where the vehicle scheduling model takes car rental demand and rental car revenue as optimization goals;
  • the optimization module 602 calculates optimized data according to the specific dimensional data and a pre-built vehicle scheduling model, including the following steps:
  • Step S201 The optimization module 602 calculates the predicted demand range of the placement point according to the specific dimension data
  • the predicted demand interval can be obtained according to the following steps S301-S303:
  • Step S301 the optimization module 602 calculates the fixed demand interval according to the usage data of the registered users
  • the usage data of registered users can be used to calculate the usage time period, usage frequency, and commonly used distribution points of registered users with regular rentals (such as registered users who regularly rent at and off work, the rental point and return point of the car are relatively fixed) Based on this information, the fixed demand interval of each placement point can be calculated, that is, the minimum number of vehicles placed at the placement point.
  • Step A1 the optimization module 602 obtains the historical loan and return records of a certain period of operation (for example: 3 months) of the placement point;
  • Step A2 The optimization module 602 obtains the borrowing records of the registered users in the historical borrowing records, and generates a user data table based on the registered users’ borrowing records; the user usage data table includes the user ID and the user’s operating period The number of uses and distribution of use;
  • Step A3 the optimization module 602 filters out user data with a relatively regular usage distribution according to the user data table, and generates a second user data table;
  • the user’s weekly use of shared vehicles can be counted according to the calendar week, and it can be judged whether the user uses the shared vehicle every week and the number of uses per week is not less than the set number of times (e.g. 3 times) ), the user data that meets the condition is listed in the second user data table.
  • Step A4 the optimization module 602 respectively counts the number of people whose use times are greater than or equal to the first specific value and the number of persons greater than or equal to the second specific value during the operation period according to the second data table as the upper and lower limits of the fixed demand interval to obtain the fixed demand Interval.
  • Step S302 the optimization module 602 calculates the floating demand interval according to the operating data of the delivery point
  • the operating data of the delivery point it is possible to count the use time period and the number of rentals of individual customers with randomness of the rental vehicle, and then the floating demand interval of each rental vehicle can be calculated.
  • step S303 the optimization module 602 calculates the sum of the fixed demand interval and the floating demand interval to obtain a predicted demand interval.
  • step S202 the optimization module 602 calculates the demand for the delivery point corresponding to the minimum cost according to the pre-built cost model, where the cost model relates to the transformation cost and the transportation cost of the delivery point.
  • the cost of renovation involves the rent of the site, construction costs and subsequent equipment maintenance costs
  • the cost of dispatch involves the wages of dispatch personnel, the dispatch capacity of the company operating the car rental business, etc., based on which the cost model is constructed, and the linear programming principle is used to calculate the satisfaction The demand for each delivery point corresponding to the demand interval and the minimum cost.
  • a cost model is as follows:
  • P represents the cost
  • A represents the area of land required for each additional shared vehicle
  • R i represents the rent per unit area of the i-th vehicle placement point
  • y i represents the optimized vehicle placement of the i-th vehicle placement point
  • Quantity y i'represents the current vehicle delivery volume of the i-th vehicle delivery point
  • B represents the construction cost required for each increase or decrease of a shared vehicle
  • C i represents the average maintenance of each shared vehicle at the i-th vehicle delivery point Cost
  • D i represents the number of dispatch personnel required at the i-th vehicle delivery point
  • h represents the salary of dispatch personnel.
  • the values of the above-mentioned parameters R i , C i , and D i can be obtained by statistics based on the historical operation data of each vehicle delivery point.
  • a number of constraints can be set, such as: the sum of the number of personnel cannot exceed a certain value, individual restrictions for each vehicle placement point (e.g., according to the limitations of the site, the i-th vehicle placement point can be placed The number of vehicles does not exceed 20 at most); according to this, combined with the forecasted demand interval, the demand for the delivery point corresponding to the minimum cost can be obtained.
  • the optimization module 602 calculates optimized data according to the specific dimensional data and a pre-built vehicle scheduling model, and further includes the following steps:
  • Step S401 finding the scheduling demand when the scheduling cost is the smallest according to the demand of each delivery point and the preset scheduling cost model
  • the preset scheduling cost model is as follows:
  • G represents the transportation cost
  • t represents the service cycle
  • an operation cycle is divided into M segments
  • n represents the number of delivery points
  • c ij represents the transportation cost per unit mileage from the delivery point i to the delivery point j
  • d ij represents the delivery from the delivery point.
  • the distance from the point i to the delivery point j, x ij represents the number of vehicles transferred from the delivery point i to the delivery point j, where i ⁇ j.
  • the scheduling cost model several constraints can be set as needed, such as the conservation of the total number of vehicles during the dispatch, the mileage of the vehicle is greater than the distance between the two delivery points, and the sufficient parking spaces for the dispatched vehicles when they reach the target delivery point, etc., according to the above The model can solve the dispatching demand between each delivery point.
  • Step S402 Calculate the vehicle scheduling route plan when the revenue is maximized according to the scheduling requirement and the preset revenue model.
  • the preset profit model is as follows:
  • Q means revenue
  • i ⁇ P means that the delivery point i needs to transfer the vehicle to another station at a certain time
  • j ⁇ D means that the delivery point j needs to dispatch the vehicle to the station at a certain time
  • s is the dispatcher number
  • S means The number of dispatchers
  • Rer represents the revenue of each dispatch task
  • O means the dispatch center
  • C means every shift The working hours of a dispatcher.
  • each scheduling task can only be executed once
  • the vehicle life of the dispatcher is greater than the distance between the two delivery points during the dispatching process
  • a dispatcher can only perform one dispatching task And so on, based on this, the best scheduling path can be found.
  • the output module 603 is adapted to generate a vehicle scheduling strategy according to the optimization data, where the vehicle scheduling strategy includes the number of changes in the amount of vehicle delivery at each delivery point.
  • the vehicle scheduling strategy further includes the vehicle scheduling path plan obtained in step S402.
  • the output module 603 generating a vehicle scheduling strategy according to the optimization data further includes the following steps:
  • a list of delivery points whose delivery volume variation index is greater than a preset first threshold is generated as a list of delivery points that need to be modified.
  • the quantity change index here can be calculated according to the difference between the demand quantity and the existing quantity, or it can be calculated according to the percentage change of the demand quantity to the existing quantity.
  • the first threshold can be set as the quantity according to different calculation methods. Or percentage.
  • the output module 603 generating a vehicle scheduling strategy according to the optimization data further includes the following steps:
  • a list of placement points whose demand is lower than the preset second threshold is generated as a list of placement points to be cancelled.
  • the operating cost includes transportation cost, maintenance cost, and loss cost.
  • the output module 603 generating a vehicle scheduling strategy based on the optimization data further includes the following steps S501-S503:
  • Step S501 generating a list of delivery points where the operating cost is higher than the revenue generated
  • Step S502 calculating the ratio of the difference between the operating cost and the revenue generated to the revenue generated;
  • step S503 the placement points whose ratio is higher than the preset third threshold are included in the list of placement points to be cancelled.
  • the computer device 700 is a device that can automatically perform numerical calculation and/or information processing according to pre-set or stored instructions.
  • the computer equipment 700 at least includes, but is not limited to, a memory 701, a processor 702, a network interface 703, and a vehicle scheduling device 704 that can share a vehicle through a system bus that can communicate with each other. among them:
  • the memory 701 includes at least one type of computer-readable storage medium.
  • the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory ( RAM), static random access memory (SRAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), magnetic memory, magnetic disks, optical disks, etc.
  • the memory 701 may be an internal storage unit of the computer device 700, such as a hard disk or memory of the computer device 700.
  • the memory 701 may also be an external storage device of the computer device 700, such as a plug-in hard disk, a smart media card (SMC), and a secure digital (Secure Digital, SD) card, flash card (Flash Card), etc.
  • the memory 701 may also include both an internal storage unit of the computer device 700 and an external storage device thereof.
  • the memory 701 is generally used to store an operating system and various application software installed in the computer device 700, for example, the program code of the vehicle scheduling device 704 for shared vehicles.
  • the memory 701 can also be used to temporarily store various types of data that have been output or will be output.
  • the processor 702 may be a central processing unit (Central Processing Unit, CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments.
  • the processor 702 is generally used to control the overall operation of the computer device 700.
  • the processor 702 is configured to run the program code or processing data stored in the memory 701, for example, to run the vehicle scheduling device 704 for sharing vehicles, so as to implement the vehicle scheduling method based on the scheduling model in the first embodiment.
  • the network interface 703 may include a wireless network interface or a wired network interface, and the network interface 703 is generally used to establish a communication connection between the computer device 700 and other electronic devices.
  • the network interface 703 is used to connect the computer device 700 to an external terminal through a network, and to establish a data transmission channel and a communication connection between the computer device 700 and the external terminal.
  • the network may be Intranet, Internet, Global System of Mobile Communication (GSM), Wideband Code Division Multiple Access (WCDMA), 4G network, 5G Network, Bluetooth (Bluetooth), Wi-Fi and other wireless or wired networks.
  • FIG. 7 only shows a computer device 700 with components 701-704, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead.
  • the vehicle scheduling device 704 for the shared vehicle stored in the memory 701 may also be divided into one or more program modules, and the one or more program modules are stored in the memory 701 and configured by One or more processors (processor 702 in this embodiment) are executed to complete the vehicle scheduling method based on the scheduling model of this application.
  • the computer-readable storage medium may be non-volatile or volatile, such as flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory). Etc.), random access memory (RAM), static random access memory (SRAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), magnetic memory, Disks, optical disks, servers, App application malls, etc., have computer programs stored thereon, and when the programs are executed by the processor, the above-mentioned vehicle scheduling method based on the scheduling model is implemented.
  • RAM random access memory
  • SRAM static random access memory
  • ROM read only memory
  • EEPROM electrically erasable programmable read only memory
  • PROM programmable read only memory
  • magnetic memory Disks, optical disks, servers, App application malls, etc.
  • the method of the above embodiments can be implemented by means of software plus the necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is better. ⁇
  • the technical solution of this application essentially or the part that contributes to the existing technology can be embodied in the form of a software product, and the computer software product is stored in a storage medium (such as ROM/RAM, magnetic disk, The optical disc) includes several instructions to enable a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the method described in each embodiment of the present application.

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Tourism & Hospitality (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种基于调度模型的车辆调度方法、装置、计算机设备及存储介质，方法包括：获取各投放点的特定维度数据，其中，特定维度数据包含车辆运营数据以及位置数据（S101）；根据特定维度数据与预先构建的车辆调度模型计算优化数据，其中，车辆调度模型以租车需求与租车收入为优化目标（S102）；根据优化数据生成车辆调度策略，其中，车辆调度策略包含各投放点的车辆投放量的变动数目（S103）。通过预先构建的车辆调度模型结合车辆投放点的运营数据与位置数据，生成了优化的投放策略，可辅助提高投放的车辆的使用率，减少闲置，方便用户租车且提高企业效益。

Description

基于调度模型的车辆调度方法、装置、计算机设备及存储介质
本申请要求于2019年9月6日提交中国专利局、申请号为201910841566.X，发明名称为“基于调度模型的车辆调度方法、装置、计算机设备及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及智慧城市智慧交通领域，尤其涉及一种基于调度模型的车辆调度方法、装置、计算机设备及存储介质。
背景技术
现今共享单车、共享汽车等共享车辆越来越方便了人们的生活，但是发明人意识到，当前市场上共享车辆的投放缺乏科学管理，投放点的设置与各投放点的投放数量均较为随意，未按照实际需求进行投放，使得各共享车辆投放点的需求关系不平衡，有的投放点供不应求，有的投放点车辆使用率很低，如此企业的运营成本较高，收益难以实现最大化。
发明内容
有鉴于此，本申请提出一种基于调度模型的车辆调度方法、装置、计算机设备及存储介质，能够根据现有投放点的运营数据与位置对投放点的投放策略进行优化，从而提高使用率，实现收益最大化。
首先，为实现上述目的，本申请提出一种基于调度模型的车辆调度方法，所述方法包括：
获取特定维度数据，其中，所述特定维度数据包含注册用户的使用数据以及各投放点的运营数据；
根据所述特定维度数据与预先构建的车辆调度模型计算优化数据，其中，所述车辆调度模型以租车需求与租车收入为优化目标；
根据所述优化数据生成车辆调度策略，其中，所述车辆调度策略包含各投放点的车辆投放量的变动数目。
为了实现上述目的，本申请还公开了一种共享车辆的车辆调度装置，其包括：
获取模块，适于获取特定维度数据，其中，所述特定维度数据包含注册用户的使用数据以及各投放点的运营数据；
优化模块，适于根据所述特定维度数据与预先构建的车辆调度模型计算优化数据，其中，所述车辆调度模型以租车需求与租车收入为优化目标；
输出模块，适于根据所述优化数据生成车辆调度策略，其中，所述车辆调度策略包含各投放点的车辆投放量的变动数目。
为了实现上述目的，本申请还公开了一种计算机设备，包括存储器、处理器以及存储在存储器上并可在处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现上述基 于调度模型的车辆调度方法。
为了实现上述目的，本申请还公开了一种计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时实现上述基于调度模型的车辆调度方法。
相较于现有技术，本申请所提出的基于调度模型的车辆调度方法、装置、计算机设备及存储介质，通过预先构建的车辆调度模型结合车辆投放点的运营数据与位置数据，生成了优化的投放策略，可辅助提高投放的车辆的使用率，减少闲置，方便用户租车且提高企业效益。
附图说明
图1是本申请实施例一之基于调度模型的车辆调度方法的流程图；
图2是本申请实施例之根据特定维度数据与预先构建的车辆调度模型计算优化数据的流程图；
图3是本申请实施例之预测需求量区间的流程图；
图4是本申请实施例之进一步的实施例中根据特定维度数据与预先构建的车辆调度模型计算优化数据的流程图；
图5是本申请实施例之进一步的实施例中根据优化数据生成车辆调度策略的流程图；
图6是本申请实施例二之共享车辆的车辆调度装置的程序模块示意图；
图7是本申请实施例三之计算机设备的硬件结构示意图。
具体实施方式
为了使本申请的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本申请进行进一步详细说明。应当理解，此处所描述的具体实施例仅用以解释本申请，并不用于限定本申请。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
需要说明的是，在本申请中涉及“第一”、“第二”等的描述仅用于描述目的，而不能理解为指示或暗示其相对重要性或者隐含指明所指示的技术特征的数量。由此，限定有“第一”、“第二”的特征可以明示或者隐含地包括至少一个该特征。另外，各个实施例之间的技术方案可以相互结合，但是必须是以本领域普通技术人员能够实现为基础，当技术方案的结合出现相互矛盾或无法实现时应当认为这种技术方案的结合不存在，也不在本申请要求的保护范围之内。
实施例一
参阅图1，示出了本申请实施例一之基于调度模型的车辆调度方法的流程图。可以理解，本方法实施例中的流程图不用于对执行步骤的顺序进行限定。下面以共享车辆的车辆调度装置为执行主体进行示例性描述，所述共享车辆的车辆调度装置可以应用于服务器中。具体如下：
步骤S101，获取特定维度数据，其中，所述特定维度数据包含注册用户的使用数据以 及各投放点的运营数据；
本步骤中，注册用户的使用数据包含注册用户的租用时间、租车时的投放点、还车时的投放点、租用时长、消费金额等数据，各投放点的运营数据包含每单租车业务的租用时间、租用时长、还车时的投放点与产生金额等数据。
请回到图1，步骤S102，根据所述特定维度数据与预先构建的车辆调度模型计算优化数据，其中，所述车辆调度模型以租车需求与租车收入为优化目标；
具体地，参阅图2，步骤S102包括如下步骤：
步骤S201，根据所述特定维度数据计算投放点的预测需求量区间；
参阅图3，本步骤中，预测需求量区间可根据如下步骤S301-S303得到：
步骤S301，根据注册用户的使用数据计算固定需求量区间；
由注册用户的使用数据可以统计出租用较为规律的注册用户(如上、下班正常租用的注册用户，其租用的投放点与还车的投放点较为固定)的使用时间段、使用频率、常用投放点等信息，据此可计算各投放点的固定需求量区间，也即投放点的最小车辆投放数量。
本步骤中，一种得到固定需求量区间的方法如下述步骤A1-A3：
步骤A1，获取投放点的某一段运营期间(如：3个月)内的历史借还记录；
步骤A2，获取所述历史借还记录中注册用户的借还记录，并根据注册用户的借还记录生成用户数据表；所述用户使用数据表包括用户ID、该用户在运营期间内的使用次数、使用分布状况；
步骤A3，根据用户数据表筛选出使用分布状况较为规律的用户数据，生成第二用户数据表；
本步骤中，判断用户的使用分布状况是否规律可按照自然周统计用户每周使用共享车辆的状况，并判断用户是否每周使用共享车辆且每周使用次数不少于设定次数(如3次)，将满足该条件的用户数据列入第二用户数据表。
步骤A4，根据第二数据表分别统计在运营期间内使用次数大于等于第一特定值的人数以及大于等于第二特定值的人数作为固定需求量区间的上限与下限，得到固定需求量区间。
本步骤中，通过将高频使用用户的数量作为区间上限，并将较高频用户的数量作为下限，可较好地照顾到统计的误差，也能使得出的需求量区间满足实际需求情形。
步骤S302，根据投放点的运营数据计算浮动需求量区间；
根据投放点的运营数据可统计租用车辆具有随机性的散客的使用时间段、租用次数等信息，进而可统计出各租车点的浮动需求量区间。
步骤S303，计算所述固定需求量区间与浮动需求量区间的总和得到预测需求量区间。
请回到图2，步骤S202，根据预先构建的成本模型计算成本最小时对应的投放点的需求量，其中，所述成本模型涉及投放点的改造成本与调运成本。
其中，改造成本涉及场地的租金、施工成本以及后续的设备维护成本，调运成本涉及调运人员的工资、运营租车业务的公司的调运能力等，据此构建成本模型，并利用线性规划原 理计算出满足需求量区间且成本最小时对应的各投放点的需求量。此处，一种成本模型如下：
Figure PCTCN2020098464-appb-000001
其中，P表示成本，A表示每增加一个共享车辆所需使用的土地的面积，R i表示第i个车辆投放点的单位面积租金；y i表示优化后的第i个车辆投放点的车辆投放量，y i’表示当前第i个车辆投放点的车辆投放量；B表示每增加或减少一个共享车辆所需的施工成本；C i表示第i个车辆投放点的平均每个共享车辆的维护成本；D i表示第i个车辆投放点所需配备的调运人员的数量，h表示调运人员的工资。上述参数R i、C i、D i的数值可根据各车辆投放点的历史运营数据进行统计得到。
根据上述成本模型，可设置若干约束条件，如：人员数量的总和不能超过一定数值、每个车辆投放点的单独限制条件(如：根据现场的场地的限制，第i个车辆投放点可投放的车辆的数量最多不超过20辆)；据此，结合预测需求量区间，可以求得成本最小时对应的投放点的需求量。
可选地，参阅图4，步骤S102还包括如下步骤：
步骤S401，根据各投放点的需求量以及预设的调度成本模型求出调度成本最小时的调度需求；
在一种实施例中，预设的调度成本模型如下：
Figure PCTCN2020098464-appb-000002
其中，G表示调运成本，t表示服务周期，将一个运营周期分为M段；n表示投放点的个数，c ij表示从投放点i到投放点j单位里程调运成本，d ij表示从投放点i到投放点j的距离，x ij表示从投放点i到投放点j调运车的数量，其中i≠j。
根据上述调度成本模型可按需要设置若干约束条件，如调运过程中车辆总数守恒，车辆续航里程大于两个投放点之间的距离，被调运车辆到达目标投放点时有足够的车位等，根据上述模型可求解出各投放点之间的调运需求。
步骤S402，根据所述调度需求与预设的收益模型计算收益最大化时的车辆调度路径方案。
在一种实施例中，预设的收益模型如下：
Figure PCTCN2020098464-appb-000003
其中，Q表示收益，i∈P表示投放点i在某时间需要调离车辆至别的站点；j∈D表示投放点j在某时间需要调配车辆到该站点；s为调度员编号，S表示调度人员数量；Rer表示每 个调度任务的收益；x ijs＝1表示调度员s从取车点i取车前往送车点j，否则x ijs＝0；O表示调度中心；C表示每班每个调度人员的工时费。
根据上述收益模型可按需要设置若干约束条件，如：每个调度任务只能执行一次，调度员在调度过程中车辆续航大于两个投放点之间的距离，一个调度员只能执行一个调度任务等，据此可求出最佳调度路径。
请回到图1，步骤S103，根据所述优化数据生成车辆调度策略，其中，所述车辆调度策略包含各投放点的车辆投放量的变动数目。
在进一步的实施例中，所述车辆调度策略还包含步骤S402求出的车辆调度路径方案。
可选地，所述根据所述优化数据生成车辆调度策略还包括如下步骤：
根据各投放点的车辆投放量的变动数目生成投放量变动指标大于预设的第一阈值的投放点的清单作为需改造投放点清单。
根据上述步骤可筛除投放车辆变动数目较小的投放点，节约改造成本与人力成本，主要将精力放到变动数目较大的投放点的扩建或缩减改造上，使得各投放点的投放量更好地满足用户的需求。此处的投放量变动指标可以按需求量与现有投放量的差值计算，也可以按照需求量现对于现有投放量的变动百分比计算，第一阈值可以根据计算方式的不同相应设置为数量或百分比。
可选地，所述根据所述优化数据生成车辆调度策略还包括如下步骤：
生成需求量低于预设的第二阈值的投放点的清单作为待撤销投放点清单。
据此可判断哪些投放点的供远大于求，没有继续投放车辆的价值，可建议将投放点拆除，停止该投放点的运营活动。
可选地，所述运营成本包含调运成本、维修成本以及损耗成本，参阅图5，所述方法还包括如下步骤S501-S503：
步骤S501，生成运营成本高于产生收入的投放点清单；
步骤S502，计算运营成本与产生收入的差值相对于产生收入的比例；
步骤S503，将所述比例高于预设的第三阈值的投放点纳入待撤销投放点清单。
这样可及时发现亏损严重的投放点，对亏损严重的投放点予以撤销处理，及时止损。
实施例二
请参阅图6，示出了本申请实施例二之共享车辆的车辆调度装置600的程序模块示意图。在本实施例中，共享车辆的车辆调度装置600可以包括或被分割成一个或多个程序模块，一个或者多个程序模块被存储于存储介质中，并由一个或多个处理器所执行，以完成本申请，并可实现上述基于调度模型的车辆调度方法。本申请实施例所称的程序模块是指能够完成特定功能的一系列计算机程序指令段，比程序本身更适合于描述基于调度模型的车辆调度方法在存储介质中的执行过程。以下描述将具体介绍本实施例各程序模块的功能：
获取模块601，适于获取特定维度数据，其中，所述特定维度数据包含注册用户的使用数据以及各投放点的运营数据；
此处，注册用户的使用数据包含注册用户的租用时间、租车时的投放点、还车时的投放点、租用时长、消费金额等数据，各投放点的运营数据包含每单租车业务的租用时间、租用时长、还车时的投放点与产生金额等数据。
请回到图6，优化模块602，适于根据所述特定维度数据与预先构建的车辆调度模型计算优化数据，其中，所述车辆调度模型以租车需求与租车收入为优化目标；
具体地，参阅图2，优化模块602根据所述特定维度数据与预先构建的车辆调度模型计算优化数据包括如下步骤：
步骤S201，优化模块602根据所述特定维度数据计算投放点的预测需求量区间；
参阅图3，本步骤中，预测需求量区间可根据如下步骤S301-S303得到：
步骤S301，优化模块602根据注册用户的使用数据计算固定需求量区间；
由注册用户的使用数据可以统计出租用较为规律的注册用户(如上、下班正常租用的注册用户，其租用的投放点与还车的投放点较为固定)的使用时间段、使用频率、常用投放点等信息，据此可计算各投放点的固定需求量区间，也即投放点的最小车辆投放数量。
本步骤中，一种得到固定需求量区间的方法如下述步骤A1-A3：
步骤A1，优化模块602获取投放点的某一段运营期间(如：3个月)内的历史借还记录；
步骤A2，优化模块602获取所述历史借还记录中注册用户的借还记录，并根据注册用户的借还记录生成用户数据表；所述用户使用数据表包括用户ID、该用户在运营期间内的使用次数、使用分布状况；
步骤A3，优化模块602根据用户数据表筛选出使用分布状况较为规律的用户数据，生成第二用户数据表；
本步骤中，判断用户的使用分布状况是否规律可按照自然周统计用户每周使用共享车辆的状况，并判断用户是否每周使用共享车辆且每周使用次数不少于设定次数(如3次)，将满足该条件的用户数据列入第二用户数据表。
步骤A4，优化模块602根据第二数据表分别统计在运营期间内使用次数大于等于第一特定值的人数以及大于等于第二特定值的人数作为固定需求量区间的上限与下限，得到固定需求量区间。
本步骤中，通过将高频使用用户的数量作为区间上限，并将较高频用户的数量作为下限，可较好地照顾到统计的误差，也能使得出的需求量区间满足实际需求情形。
步骤S302，优化模块602根据投放点的运营数据计算浮动需求量区间；
根据投放点的运营数据可统计租用车辆具有随机性的散客的使用时间段、租用次数等信息，进而可统计出各租车点的浮动需求量区间。
步骤S303，优化模块602计算所述固定需求量区间与浮动需求量区间的总和得到预测需求量区间。
请回到图2，步骤S202，优化模块602根据预先构建的成本模型计算成本最小时对应的投放点的需求量，其中，所述成本模型涉及投放点的改造成本与调运成本。
其中，改造成本涉及场地的租金、施工成本以及后续的设备维护成本，调运成本涉及调运人员的工资、运营租车业务的公司的调运能力等，据此构建成本模型，并利用线性规划原理计算出满足需求量区间且成本最小时对应的各投放点的需求量。此处，一种成本模型如下：
Figure PCTCN2020098464-appb-000004
其中，P表示成本，A表示每增加一个共享车辆所需使用的土地的面积，R i表示第i个车辆投放点的单位面积租金；y i表示优化后的第i个车辆投放点的车辆投放量，y i’表示当前第i个车辆投放点的车辆投放量；B表示每增加或减少一个共享车辆所需的施工成本；C i表示第i个车辆投放点的平均每个共享车辆的维护成本；D i表示第i个车辆投放点所需配备的调运人员的数量，h表示调运人员的工资。上述参数R i、C i、D i的数值可根据各车辆投放点的历史运营数据进行统计得到。
根据上述成本模型，可设置若干约束条件，如：人员数量的总和不能超过一定数值、每个车辆投放点的单独限制条件(如：根据现场的场地的限制，第i个车辆投放点可投放的车辆的数量最多不超过20辆)；据此，结合预测需求量区间，可以求得成本最小时对应的投放点的需求量。
可选地，参阅图4，优化模块602根据所述特定维度数据与预先构建的车辆调度模型计算优化数据还包括如下步骤：
步骤S401，根据各投放点的需求量以及预设的调度成本模型求出调度成本最小时的调度需求；
在一种实施例中，预设的调度成本模型如下：
Figure PCTCN2020098464-appb-000005
其中，G表示调运成本，t表示服务周期，将一个运营周期分为M段；n表示投放点的个数，c ij表示从投放点i到投放点j单位里程调运成本，d ij表示从投放点i到投放点j的距离，x ij表示从投放点i到投放点j调运车的数量，其中i≠j。
根据上述调度成本模型可按需要设置若干约束条件，如调运过程中车辆总数守恒，车辆续航里程大于两个投放点之间的距离，被调运车辆到达目标投放点时有足够的车位等，根据上述模型可求解出各投放点之间的调运需求。
步骤S402，根据所述调度需求与预设的收益模型计算收益最大化时的车辆调度路径方案。
在一种实施例中，预设的收益模型如下：
Figure PCTCN2020098464-appb-000006
其中，Q表示收益，i∈P表示投放点i在某时间需要调离车辆至别的站点；j∈D表示投放点j在某时间需要调配车辆到该站点；s为调度员编号，S表示调度人员数量；Rer表示每个调度任务的收益；x ijs＝1表示调度员s从取车点i取车前往送车点j，否则x ijs＝0；O表示调度中心；C表示每班每个调度人员的工时费。
根据上述收益模型可按需要设置若干约束条件，如：每个调度任务只能执行一次，调度员在调度过程中车辆续航大于两个投放点之间的距离，一个调度员只能执行一个调度任务等，据此可求出最佳调度路径。
请回到图6，输出模块603，适于根据所述优化数据生成车辆调度策略，其中，所述车辆调度策略包含各投放点的车辆投放量的变动数目。
在进一步的实施例中，所述车辆调度策略还包含步骤S402求出的车辆调度路径方案。
可选地，输出模块603根据所述优化数据生成车辆调度策略还包括如下步骤：
根据各投放点的车辆投放量的变动数目生成投放量变动指标大于预设的第一阈值的投放点的清单作为需改造投放点清单。
根据上述步骤可筛除投放车辆变动数目较小的投放点，节约改造成本与人力成本，主要将精力放到变动数目较大的投放点的扩建或缩减改造上，使得各投放点的投放量更好地满足用户的需求。此处的投放量变动指标可以按需求量与现有投放量的差值计算，也可以按照需求量现对于现有投放量的变动百分比计算，第一阈值可以根据计算方式的不同相应设置为数量或百分比。
可选地，输出模块603根据所述优化数据生成车辆调度策略还包括如下步骤：
生成需求量低于预设的第二阈值的投放点的清单作为待撤销投放点清单。
据此可判断哪些投放点的供远大于求，没有继续投放车辆的价值，可建议将投放点拆除，停止该投放点的运营活动。
可选地，所述运营成本包含调运成本、维修成本以及损耗成本，参阅图5，输出模块603根据所述优化数据生成车辆调度策略还包括如下步骤S501-S503：
步骤S501，生成运营成本高于产生收入的投放点清单；
步骤S502，计算运营成本与产生收入的差值相对于产生收入的比例；
步骤S503，将所述比例高于预设的第三阈值的投放点纳入待撤销投放点清单。
这样可及时发现亏损严重的投放点，对亏损严重的投放点予以撤销处理，及时止损。
实施例三
参阅图7，是本申请实施例三之计算机设备700的硬件架构示意图。在本实施例中，所述计算机设备700是一种能够按照事先设定或者存储的指令，自动进行数值计算和/或信息处理的设备。如图所示，所述计算机设备700至少包括，但不限于，可通过系统总线相互通信连接存储器701、处理器702、网络接口703、以及共享车辆的车辆调度装置704。其中：
本实施例中，存储器701至少包括一种类型的计算机可读存储介质，所述可读存储介质 包括闪存、硬盘、多媒体卡、卡型存储器(例如，SD或DX存储器等)、随机访问存储器(RAM)、静态随机访问存储器(SRAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、可编程只读存储器(PROM)、磁性存储器、磁盘、光盘等。在一些实施例中，存储器701可以是计算机设备700的内部存储单元，例如该计算机设备700的硬盘或内存。在另一些实施例中，存储器701也可以是计算机设备700的外部存储设备，例如该计算机设备700上配备的插接式硬盘，智能存储卡(Smart Media Card，SMC)，安全数字(Secure Digital，SD)卡，闪存卡(Flash Card)等。当然，存储器701还可以既包括计算机设备700的内部存储单元也包括其外部存储设备。本实施例中，存储器701通常用于存储安装于计算机设备700的操作系统和各类应用软件，例如共享车辆的车辆调度装置704的程序代码等。此外，存储器701还可以用于暂时地存储已经输出或者将要输出的各类数据。
处理器702在一些实施例中可以是中央处理器(Central Processing Unit，CPU)、控制器、微控制器、微处理器、或其他数据处理芯片。该处理器702通常用于控制计算机设备700的总体操作。本实施例中，处理器702用于运行存储器701中存储的程序代码或者处理数据，例如运行共享车辆的车辆调度装置704，以实现实施例一中的基于调度模型的车辆调度方法。
所述网络接口703可包括无线网络接口或有线网络接口，该网络接口703通常用于在所述计算机设备700与其他电子装置之间建立通信连接。例如，所述网络接口703用于通过网络将所述计算机设备700与外部终端相连，在所述计算机设备700与外部终端之间的建立数据传输通道和通信连接等。所述网络可以是企业内部网(Intranet)、互联网(Internet)、全球移动通讯系统(Global System of Mobile communication，GSM)、宽带码分多址(Wideband Code Division Multiple Access，WCDMA)、4G网络、5G网络、蓝牙(Bluetooth)、Wi-Fi等无线或有线网络。
需要指出的是，图7仅示出了具有部件701-704的计算机设备700，但是应理解的是，并不要求实施所有示出的部件，可以替代的实施更多或者更少的部件。
在本实施例中，存储于存储器701中的所述共享车辆的车辆调度装置704还可以被分割为一个或者多个程序模块，所述一个或者多个程序模块被存储于存储器701中，并由一个或多个处理器(本实施例为处理器702)所执行，以完成本申请基于调度模型的车辆调度方法。
实施例四
本实施例提供一种计算机可读存储介质，所述计算机可读存储介质可以是非易失性，也可以是易失性，如闪存、硬盘、多媒体卡、卡型存储器(例如，SD或DX存储器等)、随机访问存储器(RAM)、静态随机访问存储器(SRAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、可编程只读存储器(PROM)、磁性存储器、磁盘、光盘、服务器、App应用商城等等，其上存储有计算机程序，程序被处理器执行时实现上述的基于调度模型的车辆调度方法。
上述本申请实施例序号仅仅为了描述，不代表实施例的优劣。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借 助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，空调器，或者网络设备等)执行本申请各个实施例所述的方法。
以上仅为本申请的优选实施例，并非因此限制本申请的专利范围，凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本申请的专利保护范围内。

Claims (20)

  1. 一种基于调度模型的车辆调度方法，其中，所述方法包括：
    获取特定维度数据，其中，所述特定维度数据包含注册用户的使用数据以及各投放点的运营数据；
    根据所述特定维度数据与预先构建的车辆调度模型计算优化数据，其中，所述车辆调度模型以租车需求与租车收入为优化目标；
    根据所述优化数据生成车辆调度策略，其中，所述车辆调度策略包含各投放点的车辆投放量的变动数目。
  2. 由权利要求1所述的基于调度模型的车辆调度方法，其中，所述根据所述特定维度数据与预先构建的车辆调度模型计算优化数据包括：
    根据所述特定维度数据计算投放点的预测需求量区间；
    根据预先构建的成本模型计算成本最小时对应的投放点的需求量，其中，所述成本模型涉及投放点的改造成本与调运成本；所述成本模型如下：
    Figure PCTCN2020098464-appb-100001
    其中，P表示成本，A表示每增加一个共享，车辆所需使用的土地的面积，R i表示第i个车辆投放点的单位面积租金；y i表示优化后的第i个车辆投放点的车辆投放量，y i’表示当前第i个车辆投放点的车辆投放量；B表示每增加或减少一个共享车辆所需的施工成本；C i表示第i个车辆投放点的平均每个共享车辆的维护成本；D i表示第i个车辆投放点所需配备的调运人员的数量，h表示调运人员的工资。
  3. 由权利要求2所述的基于调度模型的车辆调度方法，其中，所述根据所述特定维度数据计算该投放点的预测需求量区间包括：
    根据注册用户的使用数据计算固定需求量区间；
    根据投放点的运营数据计算浮动需求量区间；
    计算所述固定需求量区间与浮动需求量区间的总和得到预测需求量区间。
  4. 由权利要求2所述的基于调度模型的车辆调度方法，其中，所述根据所述特定维度数据与预先构建的车辆调度模型计算优化数据还包括：
    根据各投放点的需求量以及预设的调度成本模型求出调度成本最小时的调度需求；所述调度成本模型如下：
    Figure PCTCN2020098464-appb-100002
    其中，G表示调运成本，t表示服务周期，将一个运营周期分为M段；n表示投放点的个数，c ij表示从投放点i到投放点j单位里程调运成本，d ij表示从投放点i到投放点j的距离， x ij表示从投放点i到投放点j调运车的数量，其中i≠j；
    根据所述调度需求与预设的收益模型计算收益最大化时的车辆调度路径方案；所述收益模型如下：
    Figure PCTCN2020098464-appb-100003
    其中，Q表示收益，i∈P表示投放点i在某时间需要调离车辆至别的站点；j∈D表示投放点j在某时间需要调配车辆到该站点；s为调度员编号，S表示调度人员数量；Rer表示每个调度任务的收益；x ijs＝1表示调度员s从取车点i取车前往送车点j，否则x ijs＝0；O表示调度中心；C表示每班每个调度人员的工时费。
  5. 由权利要求1所述的基于调度模型的车辆调度方法，其中，所述根据所述优化数据生成车辆调度策略包括：
    根据各投放点的车辆投放量的变动数目生成投放量变动指标大于预设的第一阈值的投放点的清单作为需改造投放点清单。
  6. 由权利要求1所述的基于调度模型的车辆调度方法，其中，所述根据所述优化数据生成车辆调度策略还包括：
    生成需求量低于预设的第二阈值的投放点的清单作为待撤销投放点清单。
  7. 由权利要求1所述的基于调度模型的车辆调度方法，其中，所述运营数据包含运营成本与产生收入，所述运营成本包含调运成本、维修成本以及损耗成本，所述方法还包括：
    生成运营成本高于产生收入的投放点清单；
    计算运营成本与产生收入的差值相对于产生收入的比例；
    将所述比例高于预设的第三阈值的投放点纳入待撤销投放点清单。
  8. 一种共享车辆的车辆调度装置，其中，其包括：
    获取模块，获取特定维度数据，其中，所述特定维度数据包含注册用户的使用数据以及各投放点的运营数据；
    优化模块，适于根据所述特定维度数据与预先构建的车辆调度模型计算优化数据，其中，所述车辆调度模型以租车需求与租车收入为优化目标；
    输出模块，适于根据所述优化数据生成车辆调度策略，其中，所述车辆调度策略包含各投放点的车辆投放量的变动数目。
  9. 一种设备，包括存储器、处理器以及存储在存储器上并可在处理器上运行的计算机程序，其中，所述处理器执行所述计算机程序时实现基于调度模型的车辆调度方法，所述方法具体包括如下步骤：
    获取特定维度数据，其中，所述特定维度数据包含注册用户的使用数据以及各投放点的运营数据；
    根据所述特定维度数据与预先构建的车辆调度模型计算优化数据，其中，所述车辆调度 模型以租车需求与租车收入为优化目标；
    根据所述优化数据生成车辆调度策略，其中，所述车辆调度策略包含各投放点的车辆投放量的变动数目。
  10. 由权利要求9所述的设备，其中，所述根据所述特定维度数据与预先构建的车辆调度模型计算优化数据包括：
    根据所述特定维度数据计算投放点的预测需求量区间；
    根据预先构建的成本模型计算成本最小时对应的投放点的需求量，其中，所述成本模型涉及投放点的改造成本与调运成本；所述成本模型如下：
    Figure PCTCN2020098464-appb-100004
    其中，P表示成本，A表示每增加一个共享车辆所需使用的土地的面积，R i表示第i个车辆投放点的单位面积租金；y i表示优化后的第i个车辆投放点的车辆投放量，y i’表示当前第i个车辆投放点的车辆投放量；B表示每增加或减少一个共享车辆所需的施工成本；C i表示第i个车辆投放点的平均每个共享车辆的维护成本；D i表示第i个车辆投放点所需配备的调运人员的数量，h表示调运人员的工资。
  11. 由权利要求10所述的设备，其中，所述根据所述特定维度数据计算该投放点的预测需求量区间包括：
    根据注册用户的使用数据计算固定需求量区间；
    根据投放点的运营数据计算浮动需求量区间；
    计算所述固定需求量区间与浮动需求量区间的总和得到预测需求量区间。
  12. 由权利要求10所述的设备，其中，所述根据所述特定维度数据与预先构建的车辆调度模型计算优化数据还包括：
    根据各投放点的需求量以及预设的调度成本模型求出调度成本最小时的调度需求；所述调度成本模型如下：
    Figure PCTCN2020098464-appb-100005
    其中，G表示调运成本，t表示服务周期，将一个运营周期分为M段；n表示投放点的个数，c ij表示从投放点i到投放点j单位里程调运成本，d ij表示从投放点i到投放点j的距离，x ij表示从投放点i到投放点j调运车的数量，其中i≠j；
    根据所述调度需求与预设的收益模型计算收益最大化时的车辆调度路径方案；所述收益模型如下：
    Figure PCTCN2020098464-appb-100006
    其中，Q表示收益，i∈P表示投放点i在某时间需要调离车辆至别的站点；j∈D表示投放点j在某时间需要调配车辆到该站点；s为调度员编号，S表示调度人员数量；Rer表示每个调度任务的收益；x ijs＝1表示调度员s从取车点i取车前往送车点j，否则x ijs＝0；O表示调度中心；C表示每班每个调度人员的工时费。
  13. 由权利要求9所述的设备，其中，所述根据所述优化数据生成车辆调度策略包括：
    根据各投放点的车辆投放量的变动数目生成投放量变动指标大于预设的第一阈值的投放点的清单作为需改造投放点清单。
  14. 由权利要求9所述的设备，其中，所述根据所述优化数据生成车辆调度策略还包括：
    生成需求量低于预设的第二阈值的投放点的清单作为待撤销投放点清单。
  15. 一种计算机可读存储介质，其上存储有计算机程序，其中，所述计算机程序被处理器执行时实现基于调度模型的车辆调度方法，所述方法具体包括如下步骤：
    获取特定维度数据，其中，所述特定维度数据包含注册用户的使用数据以及各投放点的运营数据；
    根据所述特定维度数据与预先构建的车辆调度模型计算优化数据，其中，所述车辆调度模型以租车需求与租车收入为优化目标；
    根据所述优化数据生成车辆调度策略，其中，所述车辆调度策略包含各投放点的车辆投放量的变动数目。
  16. 由权利要求15所述的计算机可读存储介质，其中，所述根据所述特定维度数据与预先构建的车辆调度模型计算优化数据包括：
    根据所述特定维度数据计算投放点的预测需求量区间；
    根据预先构建的成本模型计算成本最小时对应的投放点的需求量，其中，所述成本模型涉及投放点的改造成本与调运成本；所述成本模型如下：
    Figure PCTCN2020098464-appb-100007
    其中，P表示成本，A表示每增加一个共享车辆所需使用的土地的面积，R i表示第i个车辆投放点的单位面积租金；y i表示优化后的第i个车辆投放点的车辆投放量，y i’表示当前第i个车辆投放点的车辆投放量；B表示每增加或减少一个共享车辆所需的施工成本；C i表示第i个车辆投放点的平均每个共享车辆的维护成本；D i表示第i个车辆投放点所需配备的调运人员的数量，h表示调运人员的工资。
  17. 由权利要求16所述的计算机可读存储介质，其中，所述根据所述特定维度数据计算该投放点的预测需求量区间包括：
    根据注册用户的使用数据计算固定需求量区间；
    根据投放点的运营数据计算浮动需求量区间；
    计算所述固定需求量区间与浮动需求量区间的总和得到预测需求量区间。
  18. 由权利要求17所述的基于调度模型的车辆调度方法，其中，所述根据所述特定维度数据与预先构建的车辆调度模型计算优化数据还包括：
    根据各投放点的需求量以及预设的调度成本模型求出调度成本最小时的调度需求；所述调度成本模型如下：
    Figure PCTCN2020098464-appb-100008
    其中，G表示调运成本，t表示服务周期，将一个运营周期分为M段；n表示投放点的个数，c ij表示从投放点i到投放点j单位里程调运成本，d ij表示从投放点i到投放点j的距离，x ij表示从投放点i到投放点j调运车的数量，其中i≠j；
    根据所述调度需求与预设的收益模型计算收益最大化时的车辆调度路径方案；所述收益模型如下：
    Figure PCTCN2020098464-appb-100009
    其中，Q表示收益，i∈P表示投放点i在某时间需要调离车辆至别的站点；j∈D表示投放点j在某时间需要调配车辆到该站点；s为调度员编号，S表示调度人员数量；Rer表示每个调度任务的收益；x ijs＝1表示调度员s从取车点i取车前往送车点j，否则x ijs＝0；O表示调度中心；C表示每班每个调度人员的工时费。
  19. 由权利要求15所述的计算机可读存储介质，其中，所述根据所述优化数据生成车辆调度策略包括：
    根据各投放点的车辆投放量的变动数目生成投放量变动指标大于预设的第一阈值的投放点的清单作为需改造投放点清单。
  20. 由权利要求15所述的计算机可读存储介质，其中，所述根据所述优化数据生成车辆调度策略还包括：
    生成需求量低于预设的第二阈值的投放点的清单作为待撤销投放点清单。
PCT/CN2020/098464 2019-09-06 2020-06-28 基于调度模型的车辆调度方法、装置、计算机设备及存储介质 WO2021042833A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910841566.X 2019-09-06
CN201910841566.XA CN110705753B (zh) 2019-09-06 2019-09-06 基于调度模型的车辆调度方法、装置、计算机设备及存储介质

Publications (1)

Publication Number Publication Date
WO2021042833A1 true WO2021042833A1 (zh) 2021-03-11

Family

ID=69194323

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/098464 WO2021042833A1 (zh) 2019-09-06 2020-06-28 基于调度模型的车辆调度方法、装置、计算机设备及存储介质

Country Status (2)

Country Link
CN (1) CN110705753B (zh)
WO (1) WO2021042833A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113888000A (zh) * 2021-10-18 2022-01-04 支付宝(杭州)信息技术有限公司 一种共享单车的调度方法及装置
CN117910783A (zh) * 2024-03-19 2024-04-19 中国民用航空总局第二研究所 基于航班地面保障任务的地面保障人员排班方法

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110705753B (zh) * 2019-09-06 2024-05-03 平安科技（深圳）有限公司 基于调度模型的车辆调度方法、装置、计算机设备及存储介质
CN111553578B (zh) * 2020-04-22 2022-04-22 国电南瑞科技股份有限公司 移动电餐车群投放点选择方法、路线规划方法及系统
CN111612358B (zh) * 2020-05-25 2024-04-12 北京交通大学 共享汽车车辆调度及调度员路径优化方法
CN111915208A (zh) * 2020-08-11 2020-11-10 上海钧正网络科技有限公司 一种共享车辆智能调度收益评价的方法及装置
CN112101745A (zh) * 2020-08-27 2020-12-18 深圳市元征科技股份有限公司 车辆投放提示方法、装置、终端设备及存储介质
CN112418663B (zh) * 2020-11-20 2022-09-13 厦门大学 道路旅游客运车辆配置方法、系统、电子设备及存储介质
CN112580889A (zh) * 2020-12-25 2021-03-30 北京嘀嘀无限科技发展有限公司 服务资源预估方法、装置、电子设备及存储介质
CN113222348A (zh) * 2021-04-16 2021-08-06 深圳竹芒科技有限公司 共享物品的调度方法、装置、计算机设备和存储介质
CN113344336A (zh) * 2021-05-11 2021-09-03 中车唐山机车车辆有限公司 一种车辆调度方法、装置及存储介质
CN114596667B (zh) * 2022-03-08 2023-08-11 北京物资学院 一种数据共享方法、系统及计算机存储介质
CN114936886B (zh) * 2022-07-22 2023-02-03 北京阿帕科蓝科技有限公司 基于区块估值来控制共享车投放的方法、系统及存储介质

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107330586A (zh) * 2017-06-16 2017-11-07 东南大学 一种基于改进蚁群算法的公共自行车动态调度方法
CN107657353A (zh) * 2017-11-09 2018-02-02 东峡大通（北京）管理咨询有限公司 租赁物的调度方法及系统
CN108388999A (zh) * 2018-03-09 2018-08-10 北京摩拜科技有限公司 车辆调度方法、服务器、客户端及系统
CN108563717A (zh) * 2018-03-31 2018-09-21 东南大学 一种基于信息融合的共享单车故障识别与应用系统
CN108776852A (zh) * 2018-06-22 2018-11-09 北京京东金融科技控股有限公司 无桩车辆调度方法和系统
CN109583770A (zh) * 2018-11-28 2019-04-05 清华四川能源互联网研究院 车辆调度方法及装置
CN110705753A (zh) * 2019-09-06 2020-01-17 平安科技（深圳）有限公司 基于调度模型的车辆调度方法、装置、计算机设备及存储介质

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160027307A1 (en) * 2005-12-23 2016-01-28 Raj V. Abhyanker Short-term automobile rentals in a geo-spatial environment
US20100287073A1 (en) * 2009-05-05 2010-11-11 Exxonmobil Research And Engineering Company Method for optimizing a transportation scheme
CN107578199B (zh) * 2017-08-21 2021-02-26 南京航空航天大学 一种求解二维装载约束物流车辆调度问题的方法
CN108492546B (zh) * 2018-03-27 2021-12-24 汉海信息技术(上海)有限公司 车辆调度方法、系统、服务器及蓝牙扫描设备
CN109800896A (zh) * 2018-12-21 2019-05-24 浙江数链科技有限公司 车辆调度方法、装置、计算机设备和存储介质
CN110189006B (zh) * 2019-05-20 2023-07-04 深圳市众行网科技有限公司 车辆的调度方法、装置、计算机设备及其存储介质

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107330586A (zh) * 2017-06-16 2017-11-07 东南大学 一种基于改进蚁群算法的公共自行车动态调度方法
CN107657353A (zh) * 2017-11-09 2018-02-02 东峡大通（北京）管理咨询有限公司 租赁物的调度方法及系统
CN108388999A (zh) * 2018-03-09 2018-08-10 北京摩拜科技有限公司 车辆调度方法、服务器、客户端及系统
CN108563717A (zh) * 2018-03-31 2018-09-21 东南大学 一种基于信息融合的共享单车故障识别与应用系统
CN108776852A (zh) * 2018-06-22 2018-11-09 北京京东金融科技控股有限公司 无桩车辆调度方法和系统
CN109583770A (zh) * 2018-11-28 2019-04-05 清华四川能源互联网研究院 车辆调度方法及装置
CN110705753A (zh) * 2019-09-06 2020-01-17 平安科技（深圳）有限公司 基于调度模型的车辆调度方法、装置、计算机设备及存储介质

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113888000A (zh) * 2021-10-18 2022-01-04 支付宝(杭州)信息技术有限公司 一种共享单车的调度方法及装置
CN117910783A (zh) * 2024-03-19 2024-04-19 中国民用航空总局第二研究所 基于航班地面保障任务的地面保障人员排班方法
CN117910783B (zh) * 2024-03-19 2024-05-24 中国民用航空总局第二研究所 基于航班地面保障任务的地面保障人员排班方法

Also Published As

Publication number Publication date
CN110705753A (zh) 2020-01-17
CN110705753B (zh) 2024-05-03

Similar Documents

Publication Publication Date Title
WO2021042833A1 (zh) 基于调度模型的车辆调度方法、装置、计算机设备及存储介质
CN108090225B (zh) 数据库实例的运行方法、装置、系统及计算机可读存储介质
Banerjee et al. Pricing in ride-share platforms: A queueing-theoretic approach
CN104391737B (zh) 云平台中负载平衡的优化方法
US20120326893A1 (en) Method and system for coordinating permitted use of a parking space
JP6247388B2 (ja) バーストモード制御
Chang et al. Location design and relocation of a mixed car-sharing fleet with a CO2 emission constraint
US20140149164A1 (en) Scheduling management system and scheduling management method
TWI395163B (zh) 停車位分享與媒合方法與系統
CN104462432A (zh) 自适应的分布式计算方法
WO2020211455A1 (zh) 一种数据处理系统及方法
CN114926231A (zh) 利用费用设定装置、利用费用设定方法、记录介质
US20110010343A1 (en) Optimization and staging method and system
CN105359460A (zh) 云频谱管理系统
CN104407926A (zh) 一种云计算资源的调度方法
US20130261833A1 (en) Architecture for energy management of multi customer multi time zone distributed facilities
CN107241380A (zh) 用于基于时间调整的负载均衡的方法和设备
US20210217082A1 (en) Method and system for optimizing allocation of borrowing requests
WO2022116447A1 (zh) 公交车调度方法、装置、计算机设备及介质
CN107533676A (zh) 固定分配内容选择基础设施中的响应延迟减少
WO2019085459A1 (zh) 评估管理方法、应用服务器及计算机可读存储介质
WO2019071960A1 (zh) 金额预算的需求分析方法、应用服务器及计算机可读存储介质
CN112862319B (zh) 订单调度的方法、装置、设备及存储介质
TW201305948A (zh) 預約管理裝置、預約管理方法、預約管理程式、及記憶其程式之電腦可讀取之記錄媒體
US9514289B2 (en) License management methods

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: 20861441

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20861441

Country of ref document: EP

Kind code of ref document: A1