CN114168701A - Vehicle scheduling method, system, equipment and storage medium - Google Patents

Vehicle scheduling method, system, equipment and storage medium Download PDF

Info

Publication number
CN114168701A
CN114168701A CN202111512445.4A CN202111512445A CN114168701A CN 114168701 A CN114168701 A CN 114168701A CN 202111512445 A CN202111512445 A CN 202111512445A CN 114168701 A CN114168701 A CN 114168701A
Authority
CN
China
Prior art keywords
idle
driver
time point
demand
preset
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.)
Pending
Application number
CN202111512445.4A
Other languages
Chinese (zh)
Inventor
王磊
罗顺风
黎勇
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.)
Zhejiang Geely Holding Group Co Ltd
Hangzhou Youxing Technology Co Ltd
Original Assignee
Zhejiang Geely Holding Group Co Ltd
Hangzhou Youxing 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 Zhejiang Geely Holding Group Co Ltd, Hangzhou Youxing Technology Co Ltd filed Critical Zhejiang Geely Holding Group Co Ltd
Priority to CN202111512445.4A priority Critical patent/CN114168701A/en
Publication of CN114168701A publication Critical patent/CN114168701A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2457—Query processing with adaptation to user needs
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Artificial Intelligence (AREA)
  • Strategic Management (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Molecular Biology (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Educational Administration (AREA)
  • Development Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Remote Sensing (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention provides a vehicle scheduling method, a system, equipment and a storage medium, wherein the vehicle scheduling method comprises the following steps: according to the pre-trained prediction model corresponding to each geographic area, obtaining order demands and prediction values of idle drivers in a time period corresponding to the target starting time point; in a time period corresponding to the target starting time point, obtaining a difference value between the order demand corresponding to each geographic area and the predicted value of the idle driver, and taking the geographic area with the difference value reaching a preset difference value threshold value as a demand overflow area; and acquiring the actual numerical values of idle drivers in all the geographic areas at the target starting time point, and processing and acquiring the demand overflow area to which the idle drivers are to be dispatched aiming at each idle driver. According to the invention, not only are the personal income and the overall experience of a vehicle driver considered, but also the benefit maximization of an operation platform is ensured; and the global idle drivers are scheduled, so that global optimal scheduling is realized.

Description

Vehicle scheduling method, system, equipment and storage medium
Technical Field
The present invention relates to the field of vehicle control technologies, and in particular, to a vehicle scheduling method, system, device, and storage medium.
Background
The network appointment vehicle gradually becomes the first choice of modern people for the convenient, flexible and on-call service characteristics, and plays an important role in public transportation; the process that the network car booking travels on the road without load and waits for the passengers to get off orders is called as an empty car tour process, and in the actual operation process, the empty car tour process possibly accounts for more than 50% of the working time of a driver of the network car booking, so that the operation efficiency of the network car booking is greatly influenced.
In the prior art, although a vehicle dispatching system can dispatch and dispatch idle drivers in an area with overflowing demand (that is, the demand of a vehicle is greater than the amount of the idle drivers), if the idle drivers are far away from the area with overflowing demand, and a platform sends a dispatching instruction to the idle drivers, the idle drivers are likely to have the situation that oil expenses cannot be returned, and the dispatching process is not economic, so that the platform using experience of the drivers is greatly reduced, and meanwhile, the profit of the platform is lost; in addition, if a plurality of demand overflow areas occur simultaneously, the prior art cannot reasonably schedule idle drivers for the whole situation.
In conclusion, the vehicle scheduling method in the prior art has the problems that whether idle driver scheduling is reasonable or not cannot be checked, and reasonable scheduling of idle drivers cannot be carried out aiming at the whole situation.
Disclosure of Invention
In view of the above disadvantages of the prior art, an object of the present invention is to provide a vehicle scheduling method, a system, a device, and a storage medium, for solving the problem that the vehicle scheduling method in the prior art cannot account whether the idle driver scheduling is reasonable, and cannot perform reasonable idle driver scheduling for the whole situation.
To achieve the above and other related objects, the present invention provides a vehicle scheduling method, including:
inputting a target starting time point into a pre-trained prediction model corresponding to each geographic area to obtain order demands and prediction values of idle drivers in a time period corresponding to the target starting time point;
calculating the difference value between the order demand corresponding to each geographic area and the predicted value of the idle driver in the time period corresponding to the target starting time point, and taking the geographic area with the difference value reaching a preset difference value threshold value as a demand overflow area;
acquiring actual values of free drivers in all geographic areas at the target starting time point, and aiming at each free driver: and processing to obtain the required overflow area to which the driver is to be dispatched according to the preset speed, the preset duration and the actual distance between the current idle driver and each required overflow area.
In one embodiment of the invention, the driver with the idle time exceeding the preset time threshold is taken as the idle driver.
In an embodiment of the invention, the prediction model is obtained by training using an xgboost model.
In an embodiment of the present invention, the prediction model is represented as:
Figure BDA0003399735940000021
wherein t represents the input target start time point, Dt+pA predicted numerical value representing the order demand of the time period corresponding to the target starting time point; f represents the regression relationship between the target starting time point and the prediction value of the corresponding order demand; o ist+pA predicted value representing an idle driver for a time period corresponding to the target starting time point; g represents a regression relationship of the target starting time point and the predicted value of the corresponding idle driver.
In an embodiment of the present invention, the obtaining of the actual values of the idle drivers in all geographic areas at the target starting time point includes, for each idle driver: processing to obtain a demand overflow area to which the driver is to be dispatched according to a preset speed, a preset duration and an actual distance between a current idle driver and each demand overflow area;
according to the preset vehicle speed, the preset duration and the actual distance between the current idle driver and each demand overflow area, the following formula is constructed:
Figure BDA0003399735940000022
wherein n represents the actual number of free drivers for all geographic areas at the target starting time point; m represents the total number of the demand overflow areas;
Figure BDA0003399735940000023
v represents the preset vehicle speed, p represents the preset time length, dijRepresenting the actual distance from the ith free driver to the jth demand spill area; a isij1 when the ith idle driver is dispatched to the jth demand overflow area, and 0 otherwise;
and aiming at the ith idle driver, taking the corresponding jth demand overflow area when the H is the maximum value as the demand overflow area to which the ith idle driver needs to be adjusted.
In an embodiment of the present invention, the method further includes:
and aiming at each idle driver at the target starting time point, sending the corresponding information of the corresponding demand overflow area to be adjusted and a preset prompt signal to a preset terminal so as to prompt the current idle driver to move to the corresponding demand overflow area to be adjusted.
In an embodiment of the present invention, the step of sending, to a preset terminal, information of a demand overflow area to be adjusted and a preset prompt signal corresponding to each idle driver at the target starting time point further includes:
acquiring the order demands and the actual numerical values of idle drivers of all geographic areas at the target starting time point, and processing to obtain the difference value between the order demands and the actual numerical values of the idle drivers of each geographic area;
and according to the sequence of the difference of the actual numerical values from large to small, sequentially sending the information of the corresponding demand overflow area and a preset prompt signal to a preset terminal of an idle driver in the geographic area corresponding to the difference.
The invention also discloses a vehicle dispatching system, comprising:
the prediction module is used for inputting a target starting time point into a pre-trained prediction model corresponding to each geographic area to obtain order demands and prediction values of idle drivers in a time period corresponding to the target starting time point;
the acquisition module is used for acquiring a difference value between the order demand corresponding to each geographic area and the predicted value of the idle driver in a time period corresponding to the target starting time point, and taking the geographic area with the difference value reaching a preset difference value threshold as a demand overflow area;
and the processing module is used for acquiring the actual numerical values of the idle drivers in all the geographic areas at the target starting time point, and processing the actual numerical values to obtain a scheduling result according to the preset vehicle speed, the preset time length and the actual distance between the current idle driver and each demand overflow area.
The invention also discloses computer equipment which comprises a processor, wherein the processor is coupled with a memory, the memory stores program instructions, and the vehicle dispatching method is realized when the program instructions stored in the memory are executed by the processor.
The present invention also discloses a computer-readable storage medium containing a program which, when run on a computer, causes the computer to execute the above-described vehicle scheduling method.
In summary, the vehicle scheduling method, system, device and storage medium provided by the present invention can obtain the order demand and the predicted numerical value of the idle driver in each geographic area within a period of time after a time point is taken as a starting point through pre-training the prediction models corresponding to the plurality of geographic areas, and can obtain the demand overflow area to which each idle driver should be scheduled according to the actual distance from the idle driver in all the geographic areas to each demand overflow area at the time point, thereby not only considering the personal income and the overall experience of the vehicle driver, but also ensuring the benefit maximization of the operation platform; and the global idle drivers are scheduled, so that global optimal scheduling is realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart illustrating a vehicle dispatching method according to an embodiment of the invention.
Fig. 2 is a schematic structural diagram of a vehicle dispatching system according to an embodiment of the invention.
Fig. 3 is a schematic structural diagram of a computer device according to an embodiment of the invention.
Description of the element reference numerals
100. A vehicle dispatch system; 110. a prediction module; 120. an acquisition module; 130. and a processing module.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict. It is also to be understood that the terminology used in the examples is for the purpose of describing particular embodiments only, and is not intended to limit the scope of the present invention. Test methods in which specific conditions are not specified in the following examples are generally carried out under conventional conditions or under conditions recommended by the respective manufacturers.
Please refer to fig. 1 to 3. It should be understood that the structures, ratios, sizes, and the like shown in the drawings are only used for matching the disclosure of the present disclosure, and are not used for limiting the conditions of the present disclosure, so that the present disclosure is not limited to the technical essence, and any modifications of the structures, changes of the ratios, or adjustments of the sizes, can still fall within the scope of the present disclosure without affecting the function and the achievable purpose of the present disclosure. In addition, the terms "upper", "lower", "left", "right", "middle" and "one" used in the present specification are for clarity of description, and are not intended to limit the scope of the present invention, and the relative relationship between the terms and the terms is not to be construed as a scope of the present invention.
When numerical ranges are given in the examples, it is understood that both endpoints of each of the numerical ranges and any value therebetween can be selected unless the invention otherwise indicated. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs and the description of the present invention, and any methods, apparatuses, and materials similar or equivalent to those described in the examples of the present invention may be used to practice the present invention.
In practical application, the driver of net car of making an appointment runs on the road empty load, waits for the process that the passenger got off the order, is called empty car tour process, and this process probably accounts for more than 50% of net car of making an appointment driver operating time, very big influence net car of making an appointment driver's work income, reduced net car of making an appointment operation efficiency, this embodiment is used for reasonable effectual dispatch vehicle to improve driver individual work experience, improve operation platform's whole sales volume.
The network car booking operation platform can divide the area where the network car booking works and tours into a plurality of geographical areas according to a plurality of division methods, for example, in a city, if the network car booking operation platform is divided according to the administration range of each area, one geographical area corresponds to one area.
Referring to fig. 1, a schematic flow chart of a vehicle dispatching method in the embodiment is shown, where the vehicle dispatching method includes:
and S100, inputting the target starting time point into a pre-trained prediction model corresponding to each geographic area to obtain the order demand and the prediction value of an idle driver in a time period corresponding to the target starting time point.
In this embodiment, each networked car appointment is provided with a timer, the timer starts to time when the networked car appointment is in an idle state, the timer stops to time when the networked car appointment enters a passenger carrying state, and when the time counted by the timer exceeds a preset time threshold, the current driver of the networked car appointment is considered as an idle driver in this embodiment.
The pre-trained prediction model corresponding to each geographic area is obtained by training an xgboost model, if a time point is input into the prediction model corresponding to the current geographic area, the prediction model outputs order requirements and prediction values of idle drivers within a fixed time period from the time point as a starting point; for example, the fixed time period is 1 hour.
The prediction model can be obtained by training other models, the basic model adopted by the method is not limited, and only after a time point is input, the order requirement and the prediction value of an idle driver within a fixed time length from the time point as a starting point can be output.
In this embodiment, the method further includes a process of training a prediction model corresponding to each geographic area, including:
acquiring order demands and numerical values of idle drivers in a plurality of past time periods aiming at each geographic area, and dividing starting time points corresponding to the past time periods into a training set and a testing set according to a preset proportion; wherein the duration of each past time period conforms to the fixed duration; training a regression model by adopting a training set to obtain a trained regression model; inputting the test set into a trained regression model to obtain corresponding order demands and predicted values of idle drivers; and comparing the order demand and the idle driver value corresponding to each starting time point in the test set with the order demand and the idle driver prediction value obtained by the trained regression model, calculating the matching probability, and determining the current regression model as the prediction model when the probability reaches a preset probability threshold value.
At this time, a target starting time point is input into the prediction model, and the prediction model outputs the order demand and the predicted value of the idle driver within a fixed time period from the target starting time point, for example, the input target starting time point is 15: and 00, outputting the order requirement and the predicted value of the idle driver in the time period of 15: 00-16: 00 by the prediction model.
The above prediction model can be expressed as:
Figure BDA0003399735940000051
where t represents an input target start time point, Dt+pA predicted value representing the order demand of the time period corresponding to the target starting time point; f represents the regression relationship between the target starting time point and the corresponding prediction value of the order demand; o ist+pA predicted value of an idle driver representing a time period corresponding to the target start time point; g represents the regression relationship between the target starting time point and the predicted value of the corresponding idle driver.
And step S200, calculating a difference value between the order demand corresponding to each geographic area and the predicted value of the idle driver in a time period corresponding to the target starting time point, and taking the geographic area with the difference value reaching a preset difference value threshold as a demand overflow area.
Inputting the target starting time point into a prediction model corresponding to each geographic area to obtain an order demand and a predicted value of an idle driver corresponding to each geographic area, subtracting the predicted value of the idle driver from the predicted value of the order demand of each geographic area to obtain a difference value which can be used for representing a supply-demand relationship of the current geographic area, and when the difference value is less than 0, indicating that the geographic area is in a fixed time period from the target starting time point to the later, the travel demand of a user is low, the net appointment vehicle is in an empty vehicle tour state, and the net appointment vehicle in the geographic area can be dispatched to other areas; when the difference is greater than 0, it is indicated that the transportation capacity of the network appointment vehicle cannot meet the user requirement in a fixed time period after the target starting time point in the geographic area, the number of the network appointment vehicles is not enough, and the network appointment vehicle needs to be called from other geographic areas.
Step S300, acquiring actual values of idle drivers in all geographic areas at the target starting time point, and aiming at each idle driver: and processing to obtain the required overflow area to which the driver is to be dispatched according to the preset speed, the preset duration and the actual distance between the current idle driver and each required overflow area.
Step S300 specifically includes: according to the preset vehicle speed, the preset duration and the actual distance between the current idle driver and each required overflow area, the following formula is constructed:
Figure BDA0003399735940000061
wherein n represents the actual number of free drivers for all geographic areas at the target starting time point; m represents the total number of demand overflow areas;
Figure BDA0003399735940000062
v represents a preset vehicle speed, p represents a preset time period, dijRepresenting the actual distance from the ith free driver to the jth demand spill area; a isij1 when the ith idle driver is dispatched to the jth demand overflow area, and 0 otherwise; and aiming at the ith idle driver, taking the corresponding jth demand overflow area when the H is the maximum value as the demand overflow area to which the ith idle driver needs to be adjusted.
It should be noted that, the value of Q (i, j) here may also be obtained according to other factors, such as the real-time congestion degree of a path from the ith idle driver to the jth demand overflow area, and the like.
Dispatching the net car booking drivers according to the actual values of the idle drivers in the global range at the target starting time point, numbering all the idle drivers, and recording the number as d1,d2…di…dnAnd n is the actual value of the idle driver.
The demand overflow areas obtained in step S200 are further numbered as R1,R2…Rj…RmAnd m is the total number of demand overflow areas.
If the ith free driver diIs adjusted to the jth demand overflow area RjThe value brought is defined as Q (i, j), the ith free driver diOverflow region R from target start time point to jth demandjIs dijAnd implementing a preset duration p, a speed v, if dij<vp is then
Figure BDA0003399735940000063
If the dispatching distance is too far, the duration of the driving time p at the speed v still cannot reach, and the network car booking driver can be considered to have no lost oil fee for returning the cost if the dispatching is carried out.
Solving the maximum value of H according to the formula to obtain all idle drivers d1,d2…di…dnThe region is overflowed by the demand to be approached, and the benefit of the operation platform is maximized while the use experience of the network car booking driver is improved by the scheduling scheme at the moment.
In this embodiment, the method further includes:
and aiming at each idle driver at the target starting time point, sending the corresponding information of the corresponding demand overflow area to be adjusted and a preset prompt signal to a preset terminal so as to prompt the current idle driver to move to the corresponding demand overflow area to be adjusted.
And in this step, further comprising: acquiring order demands and actual numerical values of idle drivers of all geographic areas at a target starting time point, and processing to obtain a difference value between the order demands and the actual numerical values of the idle drivers of each geographic area; and according to the sequence of the difference of the actual values from large to small, sequentially sending the information of the corresponding demand overflow area and a preset prompt signal to a preset terminal of an idle driver in the geographic area corresponding to the difference.
The prompt signal may be, for example, a text prompt "the system suggests you to go to the following area", and it should be noted that, in this embodiment, the form and content of the prompt signal are not limited, and only the current idle driver needs to be prompted to go to the corresponding demand overflow area to be called.
And the information of the demand overflow area to be adjusted corresponding to each idle driver and a preset prompt signal are preferentially sent to the idle driver in the geographical area with the lowest trip demand of the user.
Referring to fig. 2, the present embodiment further includes a vehicle dispatching system 100, including:
the prediction module 110 is configured to input the target starting time point into a pre-trained prediction model corresponding to each geographic area, so as to obtain an order demand and a prediction value of an idle driver in a time period corresponding to the target starting time point;
the obtaining module 120 is configured to obtain a difference between an order demand corresponding to each geographic area and a predicted value of an idle driver in a time period corresponding to the target starting time point, and use the geographic area where the difference reaches a preset difference threshold as a demand overflow area;
and the processing module 130 is configured to obtain actual values of idle drivers in all geographic areas at the target starting time point, and process the actual values to obtain a scheduling result according to a preset vehicle speed, a preset duration and an actual distance between the current idle driver and each demand overflow area.
Referring to fig. 3, in the present embodiment, a computer device 200 is further included, which includes a processor 210, the processor 210 is coupled to a memory 220, the memory 220 stores program instructions, and when the program instructions stored in the memory 220 are executed by the processor 210, the vehicle dispatching method is implemented. The Processor 210 may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; or a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component; the Memory 220 may include a Random Access Memory (RAM), and may also include a Non-Volatile Memory (Non-Volatile Memory), such as at least one disk Memory. The Memory 220 may also be an internal Memory of Random Access Memory (RAM) type, and the processor 210 and the Memory 220 may be integrated into one or more independent circuits or hardware, such as: application Specific Integrated Circuit (ASIC). It should be noted that the computer program in the memory 220 can be implemented in the form of software functional units and stored in a computer readable storage medium when the computer program is sold or used as a stand-alone product. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, an electronic device, or a network device) to perform all or part of the steps of the method according to the embodiments of the present invention.
In the present embodiment, a computer-readable storage medium is also included, which includes a program that, when run on a computer, causes the computer to execute the vehicle scheduling method described above.
In summary, the vehicle scheduling method, system, device and storage medium provided by the present invention can obtain the order demand and the predicted numerical value of the idle driver in each geographic area within a period of time after a time point is taken as a starting point through pre-training the prediction models corresponding to the plurality of geographic areas, and can obtain the demand overflow area to which each idle driver should be scheduled according to the actual distance from the idle driver in all the geographic areas to each demand overflow area at the time point, thereby not only considering the personal income and the overall experience of the vehicle driver, but also ensuring the benefit maximization of the operation platform; and the global idle drivers are scheduled, so that global optimal scheduling is realized.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.

Claims (10)

1. A vehicle scheduling method, comprising:
inputting a target starting time point into a pre-trained prediction model corresponding to each geographic area to obtain order demands and prediction values of idle drivers in a time period corresponding to the target starting time point;
calculating the difference value between the order demand corresponding to each geographic area and the predicted value of the idle driver in the time period corresponding to the target starting time point, and taking the geographic area with the difference value reaching a preset difference value threshold value as a demand overflow area;
acquiring actual values of free drivers in all geographic areas at the target starting time point, and aiming at each free driver: and processing to obtain the required overflow area to which the driver is to be dispatched according to the preset speed, the preset duration and the actual distance between the current idle driver and each required overflow area.
2. The vehicle scheduling method according to claim 1, wherein: and taking the driver with the idle time exceeding a preset time threshold value as an idle driver.
3. The vehicle scheduling method according to claim 1, wherein: and training by adopting an xgboost model to obtain the prediction model.
4. The vehicle scheduling method according to claim 3, wherein: the prediction model is represented as:
Figure FDA0003399735930000011
wherein t represents the input target start time point, Dt+pA predicted numerical value representing the order demand of the time period corresponding to the target starting time point; f represents the regression relationship between the target starting time point and the prediction value of the corresponding order demand; o ist+pA predicted value representing an idle driver for a time period corresponding to the target starting time point; g represents a regression relationship of the target starting time point and the predicted value of the corresponding idle driver.
5. The vehicle scheduling method according to claim 1, wherein: the obtaining of the actual values of the idle drivers in all geographic areas at the target starting time point comprises, for each idle driver: processing to obtain a demand overflow area to which the driver is to be dispatched according to a preset speed, a preset duration and an actual distance between a current idle driver and each demand overflow area;
according to the preset vehicle speed, the preset duration and the actual distance between the current idle driver and each demand overflow area, the following formula is constructed:
Figure FDA0003399735930000012
wherein n represents the actual number of free drivers for all geographic areas at the target starting time point; m represents the total number of the demand overflow areas;
Figure FDA0003399735930000021
v represents the preset vehicle speed, p represents the preset time length, dijRepresenting the actual distance from the ith free driver to the jth demand spill area; a isij1 when the ith idle driver is dispatched to the jth demand overflow area, and 0 otherwise;
and aiming at the ith idle driver, taking the corresponding jth demand overflow area when the H is the maximum value as the demand overflow area to which the ith idle driver needs to be adjusted.
6. The vehicle scheduling method according to claim 1, wherein: further comprising:
and aiming at each idle driver at the target starting time point, sending the corresponding information of the corresponding demand overflow area to be adjusted and a preset prompt signal to a preset terminal so as to prompt the current idle driver to move to the corresponding demand overflow area to be adjusted.
7. The vehicle scheduling method according to claim 6, wherein: the step of sending the information of the corresponding demand overflow area to be adjusted and the preset prompt signal to the preset terminal for each idle driver at the target starting time point further comprises the following steps:
acquiring the order demands and the actual numerical values of idle drivers of all geographic areas at the target starting time point, and processing to obtain the difference value between the order demands and the actual numerical values of the idle drivers of each geographic area;
and according to the sequence of the difference of the actual numerical values from large to small, sequentially sending the information of the corresponding demand overflow area and a preset prompt signal to a preset terminal of an idle driver in the geographic area corresponding to the difference.
8. A vehicle dispatch system, comprising:
the prediction module is used for inputting a target starting time point into a pre-trained prediction model corresponding to each geographic area to obtain order demands and prediction values of idle drivers in a time period corresponding to the target starting time point;
the acquisition module is used for acquiring a difference value between the order demand corresponding to each geographic area and the predicted value of the idle driver in a time period corresponding to the target starting time point, and taking the geographic area with the difference value reaching a preset difference value threshold as a demand overflow area;
and the processing module is used for acquiring the actual numerical values of the idle drivers in all the geographic areas at the target starting time point, and processing the actual numerical values to obtain a scheduling result according to the preset vehicle speed, the preset time length and the actual distance between the current idle driver and each demand overflow area.
9. A computer device comprising a processor coupled to a memory, the memory storing program instructions that, when executed by the processor, implement the vehicle scheduling method of any of claims 1-7.
10. A computer-readable storage medium characterized by comprising a program which, when run on a computer, causes the computer to execute the vehicle scheduling method according to any one of claims 1 to 7.
CN202111512445.4A 2021-12-08 2021-12-08 Vehicle scheduling method, system, equipment and storage medium Pending CN114168701A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111512445.4A CN114168701A (en) 2021-12-08 2021-12-08 Vehicle scheduling method, system, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111512445.4A CN114168701A (en) 2021-12-08 2021-12-08 Vehicle scheduling method, system, equipment and storage medium

Publications (1)

Publication Number Publication Date
CN114168701A true CN114168701A (en) 2022-03-11

Family

ID=80485704

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111512445.4A Pending CN114168701A (en) 2021-12-08 2021-12-08 Vehicle scheduling method, system, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN114168701A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116129653A (en) * 2023-04-17 2023-05-16 创意信息技术股份有限公司 Bayonet vehicle detection method, device, equipment and storage medium
CN116343461A (en) * 2023-04-03 2023-06-27 北京白驹易行科技有限公司 Vehicle scheduling method, device and equipment

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116343461A (en) * 2023-04-03 2023-06-27 北京白驹易行科技有限公司 Vehicle scheduling method, device and equipment
CN116343461B (en) * 2023-04-03 2023-11-17 北京白驹易行科技有限公司 Vehicle scheduling method, device and equipment
CN116129653A (en) * 2023-04-17 2023-05-16 创意信息技术股份有限公司 Bayonet vehicle detection method, device, equipment and storage medium

Similar Documents

Publication Publication Date Title
CN107103383A (en) A kind of dynamic share-car dispatching method based on focus of calling a taxi
CN114168701A (en) Vehicle scheduling method, system, equipment and storage medium
US20130144831A1 (en) Predicting Taxi Utilization Information
CN108960431A (en) The prediction of index, the training method of model and device
CN111553530B (en) Inter-city network car booking and packing travel capacity prediction and travel recommendation method and system
CN110555990A (en) effective parking space-time resource prediction method based on LSTM neural network
CN110400015A (en) A kind of Time Estimation Method and its device, equipment
CN111080048A (en) Order dispatching method and device for reserving order of taxi taking, electronic equipment and storage medium
CN111507762A (en) Urban taxi demand prediction method based on multi-task co-prediction neural network
CN111753910A (en) Method and device for predicting drip order demand based on LSTM
CN110276557A (en) A kind of inter-network grid dispatching work order creation method
CN115830848A (en) Shared parking space intelligent distribution system and method based on LSTM model
CN113269364A (en) Scheduling method and device for shared vehicles
CN113962313A (en) Demand prediction method, system, storage medium and electronic equipment
CN111507542A (en) Goods quantity measuring method and device and electronic equipment
CN110543699B (en) Shared vehicle travel data simulation and shared vehicle scheduling method, device and equipment
CN111340984A (en) Taxi booking method and device based on digital key and electronic equipment
CN111383055A (en) Method, device and equipment for selecting products in center cabin of taxi and computer readable storage medium
CN110516872A (en) Information processing method and device, storage medium and electronic equipment
CN110910191A (en) Car pooling order generation method and equipment
CN116468339A (en) Method and device for scheduling capacity, electronic equipment and storage medium
CN112767030A (en) Network appointment pricing method and device and computer readable storage medium
CN109993328A (en) Network about vehicle order allocation method and device
CN112183791A (en) Network appointment scheduling method and device, electronic equipment and storage medium
CN111833595B (en) Shared automobile auxiliary vehicle configuration method, electronic device and 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