[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

CN114862115A - Shared vehicle scheduling method and device, electronic equipment and storage medium - Google Patents

Shared vehicle scheduling method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN114862115A
CN114862115A CN202210354952.8A CN202210354952A CN114862115A CN 114862115 A CN114862115 A CN 114862115A CN 202210354952 A CN202210354952 A CN 202210354952A CN 114862115 A CN114862115 A CN 114862115A
Authority
CN
China
Prior art keywords
beta
beta distribution
vehicle
distribution
initialized
Prior art date
Legal status (The legal status 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 status listed.)
Granted
Application number
CN202210354952.8A
Other languages
Chinese (zh)
Other versions
CN114862115B (en
Inventor
杨启航
董钊辰
林剑峰
石振旭
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Mobai Beijing Information Technology Co Ltd
Original Assignee
Mobai Beijing Information Technology Co Ltd
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 Mobai Beijing Information Technology Co Ltd filed Critical Mobai Beijing Information Technology Co Ltd
Priority to CN202210354952.8A priority Critical patent/CN114862115B/en
Publication of CN114862115A publication Critical patent/CN114862115A/en
Application granted granted Critical
Publication of CN114862115B publication Critical patent/CN114862115B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06Q10/06—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
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression 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
    • 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
    • G06Q10/06313—Resource planning in a project environment
    • 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
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G06Q30/0202—Market predictions or forecasting for commercial activities
    • 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

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Theoretical Computer Science (AREA)
  • Development Economics (AREA)
  • Data Mining & Analysis (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Educational Administration (AREA)
  • Mathematical Physics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Computational Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Pure & Applied Mathematics (AREA)
  • Quality & Reliability (AREA)
  • General Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • Evolutionary Biology (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Health & Medical Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Algebra (AREA)
  • Probability & Statistics with Applications (AREA)
  • Primary Health Care (AREA)
  • Traffic Control Systems (AREA)

Abstract

The application provides a shared vehicle scheduling method, a device, electronic equipment and a storage medium, which relate to the technical field of shared vehicle scheduling, wherein the method comprises the steps of obtaining beta distribution corresponding to the vehicle riding-out probability of each parking fence in a preset time period according to vehicle flow data; acquiring an initialized beta parameter of the beta distribution, and updating the initialized beta parameter to obtain a predicted beta distribution; randomly sampling based on the predicted beta distribution to obtain a target parking fence, wherein the target parking fence is configured as a parking fence that increases a vehicle dispatching amount.

Description

Shared vehicle scheduling method and device, electronic equipment and storage medium
Technical Field
The disclosed embodiments relate to the field of scheduling technologies of shared vehicles, and more particularly, to a scheduling method and apparatus of a shared vehicle, an electronic device, and a storage medium.
Background
In a business scenario of sharing a single vehicle, the number of riding orders of a user in a single vehicle drop-in location must not be greater than the number of vehicle supplies, subject to vehicle supply restrictions, but when the number of riding orders of a vehicle is equal to the number of supplies, there may be potential orders, that is, the demand in the location may be greater than the supply. In order to be able to exploit these potential order requirements as much as possible, it is necessary to explore possible orders by heuristically adding a certain adjustment amount to some point locations.
The current technical scheme for exploring possible orders is to manually select point locations according to the operation condition or randomly select hot point locations, then increase daily adjustment amount and evaluate the speed of the car to explore. However, the method for manually selecting point locations is limited by the manual cognition on operation, the point locations which can be explored are very limited, potential point locations cannot be fully excavated, and the workload is large. The randomness of the random point selection mode is too large, the exploration effect is not good, the cost is wasted, and the income is reduced. And the speed of the vehicle is influenced by various factors, so that the effect of exploration is difficult to accurately evaluate, and the scheme has insufficient sustainability.
Disclosure of Invention
An object of the present disclosure is to provide a new technical solution for a scheduling method, apparatus, electronic device and storage medium for a shared vehicle.
According to vehicle flow data, obtaining a beta distribution corresponding to the vehicle riding-out probability of each parking fence in a preset time period; acquiring an initialized beta parameter of the beta distribution, and updating the initialized beta parameter to obtain a predicted beta distribution; randomly sampling based on the predicted beta distribution to obtain a target parking fence, wherein the target parking fence is configured as a parking fence that increases a vehicle dispatching amount.
Optionally, before obtaining the initialized beta parameters of the beta distribution, the method includes: obtaining beta parameters of the beta distribution; and preprocessing the beta parameters according to a preset threshold value to obtain the initialized beta parameters of the beta distribution.
Optionally, the updating the initialization parameter to obtain the predicted beta distribution includes: acquiring the vehicle outflow and supply in the preset time period; and updating the initialized beta parameters according to a preset attenuation coefficient, the outflow quantity and the supply quantity to obtain a predicted beta distribution.
Optionally, the updating the initialized beta parameter according to the preset attenuation coefficient and the outflow and supply amounts includes: under the condition that the supply quantity is larger than zero, updating the initialized beta parameters according to a preset attenuation coefficient, the outflow quantity and the supply quantity; and updating the initialized beta parameter according to the outflow quantity and the supply quantity when the supply quantity is equal to zero.
Optionally, the vehicle flow data includes working day vehicle flow data and holiday vehicle flow data, and the obtaining, according to the vehicle flow data, a beta distribution corresponding to a vehicle ride-out probability of each parking fence within a preset time period further includes: obtaining a first beta distribution according to the vehicle flow data in the workday; obtaining a second beta distribution according to the holiday vehicle flow data; wherein the first beta distribution is used to obtain a target parking fence corresponding to a workday and the second beta distribution is used to obtain a target parking fence corresponding to a vacation.
Optionally, when the beta distribution includes a first beta distribution and a second beta distribution, the updating the initialized beta parameters to obtain a predicted beta distribution includes: and updating the initialized beta parameters of the first beta distribution and the second beta distribution respectively to obtain a first predicted beta distribution and a second predicted beta distribution, wherein when one of the first beta distribution and the second beta distribution is updated, the parameters of the other beta distribution are kept unchanged.
Optionally, the randomly sampling based on the predicted beta distribution to obtain the target parking fence includes: and for each parking fence, generating a random number by adopting a Topson sampling method in the preset time, and selecting N parking fences with the maximum random numbers as target parking fences.
In a second aspect, an embodiment of the present application provides a scheduling apparatus for sharing a vehicle, where the apparatus includes: the data processing module is used for obtaining the beta distribution of the vehicle riding-out probability corresponding to each parking fence in a preset time period according to the vehicle flow data; the parameter updating module is used for acquiring the initialized beta parameters of the beta distribution and updating the initialized beta parameters to obtain the predicted beta distribution; a target determination module configured to perform random sampling based on the predicted beta distribution to obtain a target parking fence, wherein the target parking fence is configured as a parking fence that increases a vehicle dispatching amount.
In a third aspect, an embodiment of the present application provides an electronic device, including a memory and a processor, where the memory is used for storing a computer program; the processor is adapted to execute the computer program to implement the steps of the shared vehicle scheduling method according to the first aspect.
In a fourth aspect, the present application provides a readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps of the scheduling method of shared vehicles according to any one of the first aspect.
The method has the advantages that the method obtains the beta distribution corresponding to the vehicle riding-out probability of each parking fence in the preset time period according to the vehicle flow data, and can perform exploratory scheduling on the single-vehicle fence by taking each parking fence as an exploration point; and acquiring initialized beta parameters of the beta distribution, updating the initialized beta parameters, updating the parameters in time according to daily vehicle flow data to obtain predicted beta distribution so as to improve exploration precision, randomly sampling based on the predicted beta distribution to explore possible unknown vehicle outflow to obtain a target parking fence with unknown orders, and exploring the unknown orders by increasing the vehicle dispatching amount of the target parking fence so as to realize reasonable dispatching of the vehicles of each parking fence.
Other features of the present description and advantages thereof will become apparent from the following detailed description of exemplary embodiments thereof, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the specification and together with the description, serve to explain the principles of the specification.
Fig. 1 is a schematic diagram of a system architecture that can be used to implement an embodiment of the present disclosure.
FIG. 2 is a flowchart illustrating a scheduling method for sharing vehicles according to an embodiment.
FIG. 3 is a block schematic diagram of a shared vehicle dispatcher, according to another embodiment.
FIG. 4 is a block schematic diagram of an electronic device according to one embodiment.
Detailed Description
Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of the components and steps, the numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.
The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.
Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.
In all examples shown and discussed herein, any particular value should be construed as merely illustrative, and not limiting. Thus, other examples of the exemplary embodiments may have different values.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.
The embodiment of the disclosure relates to an application scenario for vehicle scheduling of shared vehicles.
In a business scenario of sharing a single vehicle, the number of riding orders of a user in a single vehicle drop-in location must not be greater than the number of vehicle supplies, subject to vehicle supply restrictions, but when the number of riding orders of a vehicle is equal to the number of supplies, there may be potential orders, that is, the demand in the location may be greater than the supply. In order to be able to exploit these potential order requirements as much as possible, it is necessary to explore possible orders by heuristically adding a certain adjustment amount to some point locations.
Aiming at the requirements, the point locations can be selected manually according to the operation condition, or the hot point locations can be selected randomly, then the daily adjustment amount is increased, and the speed of the vehicle scattering is evaluated for exploration. However, the method for manually selecting point locations is limited by the manual cognition on operation, the point locations which can be explored are very limited, potential point locations cannot be fully excavated, and the workload is large. The randomness of the random point selection mode is too large, the exploration effect is not good, the cost is wasted, and the income is reduced. And the speed of the vehicle is influenced by various factors, so that the effect of exploration is difficult to accurately evaluate, and the scheme has insufficient sustainability.
In view of the technical problems of the foregoing embodiments, the present disclosure provides a scheduling method and apparatus for a shared vehicle, an electronic device, and a storage medium. The method comprises the steps of considering exploration scheduling as a problem of recommending the parking fence, selecting exploration point positions which are the point positions where the parking fence with the most possibility of being supplied with insufficient supply is recommended, depicting the conventional vehicle flow data by means of beta distribution, obtaining a target parking fence based on Topson sampling, and exploring unknown orders by continuously increasing the adjustment amount in the target parking fence.
< hardware configuration >
Fig. 1 is a schematic diagram of a system architecture for implementing an embodiment of the present disclosure.
As shown in fig. 1, the system includes a server 2000 and an electronic device 1000. The server 2000 and the electronic device 1000 perform information interaction through a network 3000, where the network 3000 may be a wireless network or a wired network.
The server 2000 provides a service point for processes, databases, and communications facilities. The server 2000 may be a monolithic server, a distributed server across multiple computers, a computer data center, a cloud server, or a cloud-deployed server cluster, etc. The server may be of various types, such as, but not limited to, a web server, a news server, a mail server, a message server, an advertisement server, a file server, an application server, an interaction server, a database server, or a proxy server. In some embodiments, each server may include hardware, software, or embedded logic components or a combination of two or more such components for performing the appropriate functions supported or implemented by the server.
The specific configuration of the server 2000 may include, but is not limited to, a processor 2100, a memory 2200, an interface device 2300, and a communication device 2400. Processor 2100 is used to execute computer programs written in an instruction set of an architecture such as x86, Arm, RISC, MIPS, SSE, and so on. The memory 2200 is, for example, a ROM (read only memory), a RAM (random access memory), a nonvolatile memory such as a hard disk, or the like. The interface device 2300 is, for example, a USB interface, a serial interface, a parallel interface, a network interface, or the like. The communication device 2400 is, for example, capable of wired communication or wireless communication, and may include, for example, WiFi communication, bluetooth communication, 2G/3G/4G/5G communication, and the like.
As applied to the disclosed embodiment, the memory 2200 of the server 2000 is configured to store a computer program for controlling the processor 2100 to operate so as to implement the method according to the disclosed embodiment. The skilled person can design the computer program according to the solution disclosed in the present disclosure. How the computer program controls the processor to operate is well known in the art and will not be described in detail here.
It will be understood by those skilled in the art that the server 2000 may include other devices besides the devices shown in fig. 1, and is not limited thereto.
The electronic device 1000 may include, but is not limited to, a processor 1100, a memory 1200, an interface device 1300, a communication device 1400, a display device 1500, an input device 1600, a speaker 1700, a microphone 1800, and the like. The processor 1100 may be a central processing unit CPU, a graphics processing unit GPU, a microprocessor MCU, or the like, and is configured to execute a computer program, and the computer program may be written by using an instruction set of architectures such as x86, Arm, RISC, MIPS, and SSE. The memory 1200 includes, for example, a ROM (read only memory), a RAM (random access memory), a nonvolatile memory such as a hard disk, and the like. The interface device 1300 includes, for example, a USB interface, a serial interface, a parallel interface, and the like. The communication device 1400 is capable of wired communication using an optical fiber or a cable, or wireless communication, and specifically may include WiFi communication, bluetooth communication, 2G/3G/4G/5G communication, and the like. The display device 1500 is, for example, a liquid crystal display panel, a touch panel, or the like. The input device 1600 may include, for example, a touch screen, a keyboard, a somatosensory input, and the like. The speaker 1700 is used to output an audio signal. The microphone 1800 is used to collect audio signals.
The electronic device 1000 may be a smart phone, a laptop, a desktop computer, a tablet computer, a wearable device, etc., and is not limited herein.
In this embodiment, the electronic device 1000 may be configured to obtain, according to the vehicle flow data, a beta distribution corresponding to a vehicle ride-out probability of each parking fence within a preset time period; acquiring an initialized beta parameter of the beta distribution, and updating the initialized beta parameter to obtain a predicted beta distribution; and carrying out random sampling based on the predicted beta distribution to obtain the target parking fence.
As applied to any embodiment of the present disclosure, the memory 1200 of the electronic device 1000 is configured to store a computer program that controls the processor 1100 to operate to implement a method according to any embodiment of the present disclosure. The skilled person can design the computer program according to the solution disclosed in the present disclosure. How the computer program controls the processor to operate is well known in the art and will not be described in detail here. The electronic device 1000 may be installed with an intelligent operating system (e.g., Windows, Linux, android, IOS, etc. systems) and application software.
It should be understood by those skilled in the art that although a plurality of means of the electronic device 1000 are shown in fig. 1, the electronic device 1000 of the embodiments of the present disclosure may refer only to some of the means therein, for example, only to the processor 1100, the memory 1200, and the like.
Various embodiments and examples according to the present invention are described below with reference to the accompanying drawings.
< method examples >
Fig. 2 is a flow diagram of a scheduling method of a shared vehicle according to one embodiment, which may be implemented by the electronic device or the server in fig. 1.
As shown in fig. 2, the scheduling method of the shared vehicle of the present embodiment may include the following steps:
s210, obtaining a beta distribution corresponding to the vehicle riding-out probability of each parking fence in a preset time period according to the vehicle flow data.
In this embodiment, the vehicle flow data may include data such as vehicle supply volume, outflow volume, inflow volume, and call-in volume in each parking fence. The preset time period may be set according to actual conditions, for example, the preset time period may be one hour. The vehicle ride-out probability refers to the probability that a vehicle within the parking fence is ridden out of the fence within a preset time period.
If one considers whether a single vehicle rides within one hour of a fence to be a bernoulli distribution, then the best way to characterize its ride probability from the bayesian statistics perspective is the Beta distribution, hereinafter referred to as the Beta distribution.
For one hour of one fence, the ride amount and supply amount of the past N days are selected, the ride amount outflow is summed as a parameter A of the Beta distribution, and after the supply amount supply is summed, the ride amount outflow is subtracted as a parameter B of the Beta distribution. The Beta distribution was obtained:
Beta(A，B)＝Beta(∑outflow,∑supply-∑outflow)
the distribution Beta (A, B) represents the probability that a single vehicle will be ridden within one hour of a fence.
S220, obtaining the initialized beta parameters of the beta distribution, and updating the initialized beta parameters to obtain the predicted beta distribution.
In one example, the Beta parameters directly obtained from the vehicle flow data may have the problem of too large parameters or too small parameters, and if the parameters are too large, the parameter updating speed may be too slow, and part of fences are continuously and repeatedly recommended. If the parameters are too small, the randomness is possibly too large, the actual order quantity of the determined target parking fence is not large, the exploration effect is not good, and the cost is wasted. Therefore, before obtaining the initialized Beta parameter of the Beta distribution, preprocessing is required, and the preprocessing method in this embodiment includes: acquiring beta parameters of beta distribution; and preprocessing the beta parameters according to a preset threshold value to obtain the initialized beta parameters of the beta distribution.
In one embodiment, preprocessing beta parameters according to a preset threshold includes preprocessing over-sized parameters. For example, the beta parameters of the beta distribution are A and B, and when either one of the A or B is greater than the preset threshold T max When it is greater than the preset threshold value T max The beta parameter of (a) is reduced to T in an equal ratio max . Thereby avoiding the influence caused by overlarge parameters.
In one embodiment, pre-processing beta parameters according to a preset threshold includes pre-processing parameters that are too small. For example, when the beta parameters of the beta distribution are A and B, when either one of the A or B is less than the preset threshold T min Then, a 30% quantile of the vehicle outflow rate of a preset region is obtained according to the vehicle flow data to obtain an initial parameter, wherein the preset region can be a city, a district or a county, for example, if the 30% quantile of the vehicle outflow rate of a city is p, and the updated initial parameter B 'is 20, the updated initial parameter a' is 20 p/(1-p). In the embodiment, the too small parameter is replaced by the overall average outflow rate of the preset area, so that the inaccurate prediction effect caused by the too small beta parameter can be avoided.
In this embodiment, updating the initialization parameter to obtain the predicted beta distribution includes: acquiring the outflow volume and the supply volume of the vehicle in a preset time period; and updating the initialized beta parameters according to the preset attenuation coefficient, the outflow quantity and the supply quantity to obtain the predicted beta distribution.
The supply amount in this embodiment includes a preliminary supply amount of the vehicle within a preset time period, an inflow amount of the vehicle into the parking fence within a preset time period, a call-in amount within a preset time period, and a call-out amount within a preset time period. It is understood that the maximum value of the supply amount in the preset time period is equal to the sum of the vehicle preliminary supply amount, the inflow amount into the parking fence in the preset time, and the call-in amount in the preset time, minus the call-out amount in the preset time. Since the outflow amount cannot be larger than the supply amount, the supply amount of the vehicle is the vehicle maximum outflow amount upper limit value within the preset time period. The vehicle outflow amount is an actual vehicle riding amount.
In one example, the newer data value is higher because the traffic data of the vehicle has a certain timeliness. Therefore, when updating the distribution parameters, it is necessary to give the parameters a certain forgetting capability. The present embodiment sets the attenuation coefficient c for the old parameter in the process of updating the parameter, and the magnitude of the attenuation coefficient c depends on the half-life of the attenuation of the desired coefficient. For example, assuming the desired half-life is h (unit: day), then c can be calculated h The attenuation coefficient was calculated as 0.5. For example, if the half-life is 7 days, then c is 0.9057.
In this embodiment, it is considered that if there is no vehicle supply at a location for a long period of time, in order to retain valid information as much as possible, the forgetting capability should be reduced. Therefore, the present solution provides a supply amount determination before multiplying by the attenuation factor. That is, in the process of updating the initialized beta parameters according to the preset attenuation coefficient, the outflow quantity and the supply quantity, the supply quantity needs to be judged, and in the case that the supply quantity is greater than zero, the initialized beta parameters are updated according to the preset attenuation coefficient, the outflow quantity and the supply quantity; and when the supply amount is equal to zero, updating the initialized beta parameters according to the outflow amount and the supply amount. That is, when the supply amount is greater than 0, the beta parameter is attenuated, and when the supply amount is equal to 0, no attenuation is performed.
In one example, assume that the vehicle outflow at the previous time is a t-1 To aboveThe vehicle supply amount at one time is b t-1 The Beta distribution in the preset time period before updating is Beta (A) t-1 ,B t-1 ) If the updated Beta distribution in the preset time period is Beta (A) t ,B t ) Updating the beta parameters:
A t ＝c·A t-1 +a t-1 ，
B t ＝c·B t-1 +max(b t-1 –a t-1 )，
where c is the attenuation coefficient, max (b) t-1 –a t-1 ) The largest remaining vehicle in the parking fence at the end of the previous time.
According to the method, the attenuation coefficient is introduced in the process of obtaining the predicted beta distribution, so that the timeliness of data can be guaranteed, and the obtained beta distribution is more accurate. It is understood that updating the initialized beta parameters to obtain the predicted beta distribution is persistent, for example, updating the beta distribution within a preset one-hour time period each day to obtain the predicted beta distribution of the current day until the preset distribution effect is achieved.
And S230, carrying out random sampling based on the predicted beta distribution to obtain the target parking fence.
Wherein the target parking fence is configured as a parking fence that increases the amount of vehicle dispatch. For example, if fence D is the target fence, then 5 vehicles can be called into fence D each day until the beta distribution of fence D is as expected.
In this embodiment, randomly sampling based on the predicted beta distribution to obtain the target parking fence includes: and for each parking fence, generating a random number by adopting a Thompson sampling method within preset time, and selecting N parking fences with the maximum random number as target parking fences.
For example, each fence generates a random number according to Beta distribution every hour, selects n corresponding fences with the maximum random number, repeats the operations for k times, obtains nk fences in total, and it should be noted that the nk fences may be repeated, obtains target fences according to the nk fences, and schedules d vehicles to each target fence for exploration. After d vehicles are dispatched to each target fence, obtaining the beta distribution of the vehicle riding-out probability corresponding to each parking fence in a preset time period according to the vehicle flow data of the day; updating the beta parameters of the beta distribution to obtain the predicted beta distribution of the next day; and (4) carrying out random sampling based on the predicted beta distribution to obtain a target parking fence, and circulating according to the steps, thereby realizing the determination of the target fence, assisting the dispatching of vehicles, exploring more unknown orders and increasing the traffic.
In addition, considering that the amount of traffic on the working day and the holiday is different, in order to cope with the business environment where the working day and the holiday are different, the embodiment separately calculates the working day and the holiday, and is described by using two distributions.
In this embodiment, the vehicle flow data includes working day vehicle flow data and holiday vehicle flow data, and the obtaining, according to the vehicle flow data, a beta distribution corresponding to a vehicle ride-out probability of each parking fence within a preset time period further includes: obtaining a first beta distribution according to the vehicle flow data in the working day; obtaining a second beta distribution according to the holiday vehicle flow data; wherein the first beta distribution is used to obtain a target parking fence corresponding to a workday and the second beta distribution is used to obtain a target parking fence corresponding to a vacation.
For example, the first Beta distribution is Beta1(A, B), the second Beta distribution is Beta2(A, B), and the working day is separated from the holiday parameters, so that the prediction result can be more accurate.
In this embodiment, when the beta distribution includes the first beta distribution and the second beta distribution, if the initialized beta parameter is updated, obtaining the predicted beta distribution includes: and updating the initialized beta parameters of the first beta distribution and the second beta distribution respectively to obtain a first predicted beta distribution and a second predicted beta distribution, wherein when one of the first beta distribution and the second beta distribution is updated, the parameters of the other beta distribution are kept unchanged. Therefore, the independence of the working day and the holiday is ensured, and the prediction result can be more accurate.
That is, when the beta distributions include a first beta distribution and a second beta distribution, it is necessary to determine whether the day before is a work or a holiday, and for example, if the day is a work day and the day before is a work day, the first beta distribution corresponding to the day before may be selected, the initialized beta parameter of the first beta distribution may be updated to obtain a first predicted beta distribution, and if the day is a holiday and the day before is a work day, the second beta distribution corresponding to the corresponding holiday may be selected, and the initialized beta parameter of the second beta distribution may be updated.
In one example, the implementation result of this embodiment may be: two weeks of trial runs were conducted in both city M and city N, with the predicted time of most target parking fences in both cities occurring at the early peak. On weekends, there are all time periods throughout the day. In M cities, whether working days or holidays, most of the target parking fences are located at subway exits or at places very close to ground iron exits. In actual performance, an average of 6M city target parking pens were obtained daily, adding 93 modulation amounts, with an additional growth of 1087 turnaround orders. On average, 10N city target parking pens were obtained daily, increasing the dispatch volume by 121, with additional growth in the turnaround order of 217. Therefore, the method and the device can realize the exploration of unknown orders, so that the vehicle scheduling guidance is tentatively carried out, and the vehicle riding orders are increased.
According to the method, the beta distribution corresponding to the vehicle riding-out probability of each parking fence in the preset time period is obtained according to vehicle flow data, and each parking fence can be used as an exploration point to perform exploratory scheduling on the single-vehicle fence; and acquiring initialized beta parameters of the beta distribution, updating the initialized beta parameters, updating the parameters in time according to daily vehicle flow data to obtain predicted beta distribution so as to improve exploration precision, randomly sampling based on the predicted beta distribution to explore possible unknown vehicle outflow to obtain a target parking fence with unknown orders, and exploring the unknown orders by increasing the vehicle dispatching amount of the target parking fence so as to realize reasonable dispatching of the vehicles of each parking fence.
< apparatus embodiment >
FIG. 3 is a functional block diagram of a shared vehicle dispatcher 300, according to one embodiment. As shown in fig. 3, the scheduling apparatus of the shared vehicle may include:
the data processing module 301 is configured to obtain a beta distribution corresponding to a vehicle ride-out probability of each parking fence within a preset time period according to the vehicle flow data.
A parameter updating module 302, configured to obtain an initialized beta parameter of the beta distribution, and update the initialized beta parameter to obtain a predicted beta distribution.
A target determination module 303, configured to perform random sampling based on the predicted beta distribution to obtain a target parking fence, where the target parking fence is configured as a parking fence that increases a vehicle dispatching amount.
In one embodiment, the data processing module 301 may be configured to obtain beta parameters of the beta distribution; and preprocessing the beta parameters according to a preset threshold value to obtain the initialized beta parameters of the beta distribution.
In one embodiment, the parameter update module 302 may be configured to obtain the vehicle outflow and supply during the preset time period; and updating the initialized beta parameters according to a preset attenuation coefficient, the outflow quantity and the supply quantity to obtain a predicted beta distribution.
In one embodiment, the parameter updating module 302 may be configured to update the initialized beta parameter according to a preset attenuation coefficient and the outflow and supply amounts when the supply amount is greater than zero; and when the supply quantity is equal to zero, updating the initialized beta parameter according to the outflow quantity and the supply quantity.
In one embodiment, the data processing module 301 may be configured to obtain a first beta distribution according to the vehicle flow data on the working day; obtaining a second beta distribution according to the holiday vehicle flow data; the first beta distribution is used for obtaining a target parking fence corresponding to a working day, and the second beta distribution is used for obtaining a target parking fence corresponding to a vacation.
In one embodiment, the parameter updating module 302 may update the initialized beta parameters of the first beta distribution and the second beta distribution to obtain a first predicted beta distribution and a second predicted beta distribution, respectively, wherein when one of the first beta distribution and the second beta distribution is updated, the parameters of the other beta distribution are kept unchanged.
In one embodiment, the target determining module 303 may be configured to generate a random number by using a thompson sampling method for each parking fence within a preset time, and select N parking fences with the largest random number as the target parking fence.
The apparatus of this embodiment may be the processor 1100 of fig. 1.
According to the vehicle flow data, obtaining a beta distribution corresponding to the vehicle riding-out probability of each parking fence in a preset time period; and then acquiring the initialized beta parameters of the beta distribution, updating the initialized beta parameters, updating the parameters in time to obtain a predicted beta distribution, randomly sampling based on the predicted beta distribution to obtain a target parking fence, and adding a vehicle transfer amount for the target parking fence for exploring possible unknown vehicle outflow so as to well guide the exploration of the next position order.
< electronic device embodiment >
Fig. 4 is a functional block diagram of an electronic device 400. As shown in fig. 4, the electronic device 400 includes: a processor 410, a memory 420 and a program or instructions stored on the memory 420 and executable on said processor 410, the program or instructions when executed by the processor implementing the steps of the shared vehicle scheduling method described above.
< storage Medium embodiment >
The present embodiments provide a computer-readable storage medium having stored therein an executable command, which when executed by a processor, performs the method described in any of the method embodiments of the present specification.
One or more embodiments of the present description may be a system, method, and/or computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied thereon for causing a processor to implement various aspects of the specification.
The computer readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or electrical signals transmitted through electrical wires.
The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or to an external computer or external storage device via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device.
The computer program instructions for carrying out operations for embodiments of the present description may be assembly instructions, Instruction Set Architecture (ISA) instructions, machine related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, an electronic circuit, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA), can execute computer-readable program instructions to implement various aspects of the present description by utilizing state information of the computer-readable program instructions to personalize the electronic circuit.
Aspects of the present description are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the description. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.
These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer-readable medium storing the instructions comprises an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.
The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present description. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions. It is well known to those skilled in the art that implementation by hardware, implementation by software, and implementation by a combination of software and hardware are equivalent.
The foregoing description of the embodiments of the present specification has been presented for purposes of illustration and description, but is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein. The scope of the application is defined by the appended claims.

Claims (10)

1. A method of scheduling shared vehicles, the method comprising:
obtaining beta distribution corresponding to the vehicle riding-out probability of each parking fence in a preset time period according to the vehicle flow data;
acquiring an initialized beta parameter of the beta distribution, and updating the initialized beta parameter to obtain a predicted beta distribution;
randomly sampling based on the predicted beta distribution to obtain a target parking fence, wherein the target parking fence is configured as a parking fence that increases a vehicle dispatching amount.
2. The method according to claim 1, wherein prior to obtaining the initialized beta parameters for the beta distribution, the method comprises:
obtaining beta parameters of the beta distribution;
and preprocessing the beta parameters according to a preset threshold value to obtain the initialized beta parameters of the beta distribution.
3. The method of claim 1, wherein the updating the initialization parameters to obtain the predicted beta distribution comprises:
acquiring the outflow volume and the supply volume of the vehicle in the preset time period;
and updating the initialized beta parameters according to a preset attenuation coefficient, the outflow quantity and the supply quantity to obtain a predicted beta distribution.
4. The method of claim 3, wherein the updating the initialized beta parameters according to the preset attenuation coefficient and the outflow and supply amounts comprises:
under the condition that the supply quantity is larger than zero, updating the initialized beta parameters according to a preset attenuation coefficient, the outflow quantity and the supply quantity;
and updating the initialized beta parameter according to the outflow quantity and the supply quantity when the supply quantity is equal to zero.
5. The method of claim 1, wherein the vehicle flow data comprises weekday vehicle flow data and vacation vehicle flow data, and the deriving a beta distribution corresponding to a vehicle ride-out probability for each parking fence over a preset time period from the vehicle flow data comprises:
obtaining a first beta distribution according to the vehicle flow data in the working day;
obtaining a second beta distribution according to the holiday vehicle flow data;
wherein the first beta distribution is used to obtain a target parking fence corresponding to a workday and the second beta distribution is used to obtain a target parking fence corresponding to a vacation.
6. The method according to claim 1, wherein in the case that the beta distribution includes a first beta distribution and a second beta distribution, the updating the initialized beta parameters to obtain a predicted beta distribution includes:
updating the initialized beta parameters of the first beta distribution and the second beta distribution respectively to obtain a first predicted beta distribution and a second predicted beta distribution,
wherein, when updating the parameter of one of the first beta distribution and the second beta distribution, the parameter of the other beta distribution is kept unchanged.
7. The method of claim 1, wherein randomly sampling based on the predicted beta distribution to obtain a target parking fence comprises:
and for each parking fence, generating a random number by adopting a Thompson sampling method within the preset time, and selecting N parking fences with the maximum random number as target parking fences.
8. A shared vehicle scheduling apparatus, the apparatus comprising:
the data processing module is used for obtaining the beta distribution of the vehicle riding-out probability corresponding to each parking fence in a preset time period according to the vehicle flow data;
the parameter updating module is used for acquiring the initialized beta parameters of the beta distribution and updating the initialized beta parameters to obtain the predicted beta distribution;
a target determination module configured to perform random sampling based on the predicted beta distribution to obtain a target parking fence, wherein the target parking fence is configured as a parking fence that increases a vehicle dispatching amount.
9. An electronic device comprising a memory and a processor, the memory for storing a computer program; the processor is adapted to execute the computer program to implement the method according to any of claims 1-7.
10. A readable storage medium, characterized in that the readable storage medium has stored thereon a computer program which, when being executed by a processor, carries out the method according to any one of claims 1-7.
CN202210354952.8A 2022-04-06 2022-04-06 Method and device for scheduling shared vehicle, electronic equipment and storage medium Active CN114862115B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210354952.8A CN114862115B (en) 2022-04-06 2022-04-06 Method and device for scheduling shared vehicle, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210354952.8A CN114862115B (en) 2022-04-06 2022-04-06 Method and device for scheduling shared vehicle, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN114862115A true CN114862115A (en) 2022-08-05
CN114862115B CN114862115B (en) 2024-10-15

Family

ID=82629097

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210354952.8A Active CN114862115B (en) 2022-04-06 2022-04-06 Method and device for scheduling shared vehicle, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN114862115B (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070174458A1 (en) * 2006-01-23 2007-07-26 Boyce Robert L Jr Method for modeling on-demand free pool of resources
WO2019072054A1 (en) * 2017-10-11 2019-04-18 北京摩拜科技有限公司 Vehicle scheduling method, server, client, and system
CN110019290A (en) * 2017-08-31 2019-07-16 腾讯科技（深圳）有限公司 Recommended method and device based on statistics priori
CN110533956A (en) * 2019-10-10 2019-12-03 南京创维信息技术研究院有限公司 The parking stall distribution method and system of the interim vehicle parking in intelligent residential district
CN111062629A (en) * 2019-12-20 2020-04-24 上海钧正网络科技有限公司 Vehicle scheduling method and device, computer equipment and storage medium
CN112418699A (en) * 2020-11-30 2021-02-26 腾讯科技（深圳）有限公司 Resource allocation method, device, equipment and storage medium
CN114282759A (en) * 2021-11-22 2022-04-05 摩拜(北京)信息技术有限公司 Vehicle demand estimation method and device, electronic equipment and storage medium

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070174458A1 (en) * 2006-01-23 2007-07-26 Boyce Robert L Jr Method for modeling on-demand free pool of resources
CN110019290A (en) * 2017-08-31 2019-07-16 腾讯科技（深圳）有限公司 Recommended method and device based on statistics priori
WO2019072054A1 (en) * 2017-10-11 2019-04-18 北京摩拜科技有限公司 Vehicle scheduling method, server, client, and system
CN110533956A (en) * 2019-10-10 2019-12-03 南京创维信息技术研究院有限公司 The parking stall distribution method and system of the interim vehicle parking in intelligent residential district
CN111062629A (en) * 2019-12-20 2020-04-24 上海钧正网络科技有限公司 Vehicle scheduling method and device, computer equipment and storage medium
CN112418699A (en) * 2020-11-30 2021-02-26 腾讯科技（深圳）有限公司 Resource allocation method, device, equipment and storage medium
CN114282759A (en) * 2021-11-22 2022-04-05 摩拜(北京)信息技术有限公司 Vehicle demand estimation method and device, electronic equipment and storage medium

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
HONGMAN WANG ET AL.: "A Full Service Model for Vehicle Scheduling in One-Way Electric Vehicle Car-Sharing Systems", SECOND INTERNATIONAL CONFERENCE, IOV 2015 CHENGDU, CHINA, 21 December 2015 (2015-12-21), pages 25 *
高楹;宋辞;舒华;裴韬;: "北京市摩拜共享单车源汇时空特征分析及空间调度", 地球信息科学学报, no. 08, 22 August 2018 (2018-08-22), pages 1123 - 1138 *

Also Published As

Publication number Publication date
CN114862115B (en) 2024-10-15

Similar Documents

Publication Publication Date Title
US20180101860A1 (en) Automated offer generation responsive to behavior attribute
US20200057918A1 (en) Systems and methods for training artificial intelligence to predict utilization of resources
US11068815B2 (en) Systems and methods for vehicle scheduling
US11574550B2 (en) Learning of policy for selection of associative topic in dialog system
US11157963B2 (en) Methods and systems for offering financial products
CN107948437B (en) Screen-off display method and device
CN113159453B (en) Resource data prediction method, device, equipment and storage medium
US10748095B2 (en) Automated teller machine flow network and control system
CN113721955A (en) Vehicle upgrading method, device, equipment and storage medium
US10528965B2 (en) Bundling application programming interfaces
CN114862115B (en) Method and device for scheduling shared vehicle, electronic equipment and storage medium
US9635188B1 (en) Mobile device data allocation system
US10764788B2 (en) Managing bandwidth in mobile telecommunications networks
CN114463050A (en) Vehicle demand estimation method, device, electronic equipment and storage medium
CN114282759A (en) Vehicle demand estimation method and device, electronic equipment and storage medium
CN111767290B (en) Method and apparatus for updating user portraits
CN111985967A (en) Article information generation method and device, electronic equipment and computer readable medium
CN117648167B (en) Resource scheduling method, device, equipment and storage medium
CN110874737A (en) Payment mode recommendation method and device, electronic equipment and storage medium
CN116149721A (en) Method, apparatus, device and computer readable medium for configuring service data
CN112579572B (en) Associated account maintenance method and device and electronic equipment
CN115689152A (en) Enterprise yield prediction method, enterprise yield prediction device, electronic equipment and medium
CN111260464A (en) Interest rate pricing method and device, electronic equipment and storage medium
CN113516466A (en) Request response method, request response device, electronic equipment and readable storage medium
CN117852807A (en) Scheduling method, scheduling device, electronic equipment and readable storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant