CN109087502B - Vehicle scheduling method, scheduling system and computer equipment based on order distribution - Google Patents
Vehicle scheduling method, scheduling system and computer equipment based on order distribution Download PDFInfo
- Publication number
- CN109087502B CN109087502B CN201710447357.8A CN201710447357A CN109087502B CN 109087502 B CN109087502 B CN 109087502B CN 201710447357 A CN201710447357 A CN 201710447357A CN 109087502 B CN109087502 B CN 109087502B
- Authority
- CN
- China
- Prior art keywords
- area
- order
- orders
- vehicle
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/20—Monitoring the location of vehicles belonging to a group, e.g. fleet of vehicles, countable or determined number of vehicles
- G08G1/202—Dispatching vehicles on the basis of a location, e.g. taxi dispatching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the disclosure provides a vehicle scheduling method, a scheduling system, computer equipment and a computer readable storage medium based on order distribution, which are applied to the technical field of vehicle scheduling, and the vehicle scheduling method based on order distribution comprises the following steps: determining the radius of the area and the amount of orders; dividing the area according to the area radius and the order number; judging whether the area is in a healthy state; when the area is not in a healthy state, starting a scheduling instruction; obtaining schedulable vehicles according to the region; and dispatching the dispatchable vehicle according to the dispatching instruction. The vehicle scheduling method and the vehicle scheduling system can schedule the vehicles in the area with sparse orders to the area with dense orders and insufficient driver and passenger supply and demand, guarantee timeliness and effectiveness of vehicle scheduling, improve order transaction rate and improve driver order listening experience.
Description
Technical Field
The embodiment of the disclosure relates to the technical field of vehicle scheduling, in particular to a vehicle scheduling method, a scheduling system, computer equipment and a computer-readable storage medium based on order distribution.
Background
The rapid development of the taxi industry greatly facilitates daily travel of people, but the situations that the capacity is insufficient in the peak period and the traffic rate is low and the riding ratio is low are also achieved, even if the area with insufficient capacity is known, efficient vehicle scheduling cannot be carried out, and finally the user cannot obtain taxi-taking service in time and the taxi driver's order-listening rate is low.
Therefore, how to reasonably define the area, how to judge the health degree of the area, how to select the dispatchable vehicle, and how to determine the address information of the dispatch area become problems to be solved urgently.
Disclosure of Invention
The disclosed embodiments are directed to solving at least one of the technical problems of the related art or the related art.
To this end, an object of the embodiments of the present disclosure is to provide a vehicle scheduling method based on order distribution.
Another object of the disclosed embodiments is to provide a vehicle dispatching system based on order distribution.
It is a further object of embodiments of the present disclosure to provide a computer apparatus.
It is yet another object of an embodiment of the present disclosure to provide a computer-readable storage medium.
In view of this, according to an object of the disclosed embodiment, a vehicle scheduling method based on order distribution is provided, including: determining the radius of the area and the amount of orders; dividing the area according to the area radius and the order number; judging whether the area is in a healthy state; when the area is not in a healthy state, starting a scheduling instruction; obtaining schedulable vehicles according to the region; and dispatching the dispatchable vehicle according to the dispatching instruction.
The vehicle scheduling method based on order distribution provided by the embodiment of the disclosure selects the area radius and the order number which can be divided into reasonable areas, and reasonably divides the areas according to the area radius and the order number, wherein the reasonably divided areas are more divided areas, more orders in the areas and more uniform area distribution, after the area division is completed, whether the area is an unhealthy area with low overall transaction rate and insufficient riding ratio or not is judged according to the transaction rate and the riding ratio of the area, and when the area is an unhealthy area, a scheduling instruction is started to obtain schedulable vehicles near the area, and the schedulable vehicles are scheduled to the area. The vehicle scheduling method and the vehicle scheduling system can schedule the vehicles in the area with sparse orders to the area with dense orders and insufficient driver and passenger supply and demand, guarantee timeliness and effectiveness of vehicle scheduling, improve order transaction rate and improve driver order listening experience.
The vehicle scheduling method based on order distribution according to the embodiment of the present disclosure may further have the following technical features:
in the foregoing technical solution, preferably, the step of determining the radius of the area and the amount of orders specifically includes: defining the maximum area radius and the minimum amount of orders; acquiring a plurality of first-class areas in an area smaller than the radius of the maximum area; in a plurality of first-type regionsTaking a plurality of second type areas with orders larger than the minimum orders; calculating the distribution entropy according to a preset formula according to the total orders of the plurality of second type areas; acquiring the total order number when the distribution entropy is maximum as an actual total order number; determining the radius of the area and the amount of orders according to the actual total amount of orders; preset formula as
Wherein E isr,mTo distribute entropy, PiThe order number of the ith second type area accounts for the total order number of the plurality of second type areas, and n is the number of the plurality of second type areas.
In the technical scheme, the maximum area radius and the minimum order number are defined, the order number is more in the peak time period, the maximum area radius needs to be properly adjusted to be smaller or the minimum order number needs to be properly increased in order to avoid that a plurality of areas are automatically combined, the order number is relatively less in the peak time period, so that the order number is more dispersed, and the maximum area radius needs to be properly adjusted to be larger or the minimum order number needs to be properly reduced in order to avoid being mistakenly considered as noise. After the maximum area radius and the minimum amount of orders are defined, a plurality of first type areas which are in the area smaller than the maximum area radius are obtained, the first type areas are the areas which are in the area smaller than the maximum area radius, a plurality of second type areas with the amount of orders larger than the minimum amount of orders are obtained in the first type areas, and the second type areas are the areas with the order number larger than the minimum amount of orders in the first type areas. The order quantity of each second type area is added to be used as the total order quantity of the plurality of second type areas, the area distribution entropy is obtained according to the total order quantity, the total order quantity of the plurality of second type areas is determined by the number of the plurality of second type areas and the order quantity of each second type area, therefore, the distribution entropy is positively correlated with the number of the second type areas according to a preset formula, namely the more clusters are clustered, the larger the distribution entropy is, the more the order quantity in the clusters is distributed uniformly, and the larger the distribution entropy is. And acquiring the total order number when the distribution entropy is maximum as an actual total order number, determining the area radius and the order number when the distribution entropy is maximum according to the actual total order number, ensuring that the number of the divided area orders is more and the area distribution is more uniform, and further improving the accuracy of vehicle scheduling.
In any of the above technical solutions, preferably, the step of determining whether the area is in a healthy state specifically includes: acquiring the current transaction rate of the area and the current riding ratio of the area; judging whether the current transaction rate is less than a preset transaction rate; when the current transaction rate is smaller than the preset transaction rate, setting the expected transaction rate of the region; obtaining an expected riding ratio according to the expected transaction rate; judging whether the current ride-through ratio is smaller than the expected ride-through ratio or not; and when the current driving-multiplying ratio is smaller than the expected driving-multiplying ratio, judging that the area is not in a healthy state.
In the technical scheme, the current transaction rate of the area and the current ride rate of the area are obtained, if the current transaction rate does not meet the preset transaction rate, that is, the transaction rate is low, the expected transaction rate of the area is set, and the expected ride rate is obtained according to the expected transaction rate, wherein the expected ride rate is a linear function of the expected transaction rate, for example, a function of Y ═ a × X + b, Y is the expected ride rate, X is the expected transaction rate, and a and b can be obtained through a linear regression method through the obtained samples. And judging whether the current riding ratio is smaller than the expected riding ratio, and when the current riding ratio is smaller than the expected riding ratio, determining that the area is in an unhealthy state, and further carrying out vehicle dispatching on the area, so that the vehicle-booking user vehicle-booking success rate of the area and the driver order-receiving success rate of the area are improved.
In any of the above technical solutions, preferably, the step of obtaining the schedulable vehicle according to the region specifically includes: calculating a rectangular boundary of the region; increasing the preset area around the rectangular boundary to form a new rectangular boundary; acquiring vehicles in the new rectangular boundary and the difference value area between the rectangular boundaries; taking the vehicles meeting the preset conditions in the vehicles in the difference region as schedulable vehicles; the vehicles meeting the preset conditions are vehicles which are smaller than the first preset amount of orders in a first preset range around and are not in an order dense area.
In the technical scheme, a rectangular boundary of the area is calculated, and the boundary calculation method calculates the maximum longitude and latitude (maxlng, maxlat) and the minimum longitude and latitude (minlg, minlat) of an order used in the area, and then uses a rectangle described by the following four points (maxlng, maxlat), (maxlng, minlat), (minng, maxlat), (minng, minlat) as the boundary of the area. Increasing the preset area around the rectangular boundary to form a new rectangular boundary, namely outwards extending preset values from four points describing the boundary, calculating four new points, and taking the rectangle described by the four new points as the new rectangular boundary. The method comprises the steps of obtaining a new rectangular boundary and a difference value area between the rectangular boundaries, namely a 'return' font area, and taking a vehicle which meets the condition that the number of orders in a first preset range around the vehicle in the 'return' font area is smaller than a first preset order number and is not in an order dense area as a schedulable vehicle, so that the vehicle which has fewer current surrounding orders and is closer to a target scheduling area can be scheduled, the effectiveness and rationality of vehicle scheduling are guaranteed, and a better driver and passenger supply and demand effect is guaranteed.
In any of the above technical solutions, preferably, the step of scheduling the dispatchable vehicle according to the scheduling instruction specifically includes: taking order points with the order number larger than a second preset order number in a second preset range around the area as core order points; acquiring address information of a core order point; and scheduling the dispatchable vehicles to the core order point according to the scheduling instruction and the address information of the core order point.
In the technical scheme, after a dispatchable vehicle is found, a core order point which is closest to the vehicle needs to be selected and adjusted for the vehicle due to the fact that the area of an order gathering area is large, the concept of the core order point is that the number of orders in a preset range around the order point is not less than the preset order number, address information of the core order point is obtained, the dispatchable vehicle is dispatched to the position of the core order point which is closest to the dispatchable vehicle in the area, the vehicle is guaranteed to be dispatched to the area with the dense order number quickly, and the order receiving rate of a driver is improved.
In any of the above technical solutions, preferably, the step of acquiring address information of the core order point specifically includes: acquiring the longitude and latitude of the core order point; analyzing the address information of the core order point according to the longitude and latitude of the core order point; the address information of the core order point comprises regions, streets and business circles.
According to the technical scheme, the address information of the core order point is determined through the longitude and latitude of the core order point and is specifically applied to the region, the street and the business district, so that the schedulable vehicle can quickly reach the core order point, the vehicle scheduling efficiency is improved, the vehicle reaching time is saved, and the user can be guaranteed to timely get the vehicle.
According to another object of the disclosed embodiment, a vehicle dispatching system based on order distribution is provided, which includes: a determining unit for determining the area radius and the amount of orders; the dividing unit is used for dividing the area according to the area radius and the order number; the judging unit is used for judging whether the area is in a healthy state or not; the starting unit is used for starting a scheduling instruction when the region is not in a healthy state; the vehicle obtaining unit is used for obtaining schedulable vehicles according to the areas; and the scheduling unit is used for scheduling the dispatchable vehicles according to the scheduling instruction.
The vehicle scheduling system based on order distribution provided by the embodiment of the disclosure selects the area radius and the order number which can be divided into reasonable areas through the determining unit, the areas are reasonably divided through the dividing unit according to the area radius and the order number, the reasonably divided areas are areas with more divided areas, more orders in the areas and more uniform area distribution, after the areas are divided, the judging unit judges whether the areas are unhealthy areas with low overall transaction rate and insufficient order ratio according to the transaction rate and the order ratio of the areas, when the areas are unhealthy areas, the starting unit starts a scheduling instruction, schedulable vehicles near the areas are obtained through the vehicle obtaining unit, and the schedulable vehicles are scheduled to the areas through the scheduling unit. The vehicle scheduling method and the vehicle scheduling system can schedule the vehicles in the area with sparse orders to the area with dense orders and insufficient driver and passenger supply and demand, guarantee timeliness and effectiveness of vehicle scheduling, improve order transaction rate and improve driver order listening experience.
The vehicle dispatching system based on order distribution according to the embodiment of the disclosure may further have the following technical features:
in the foregoing technical solution, preferably, the determining unit includes: definition ofA unit for defining a maximum area radius and a minimum amount of orders; the cluster determining unit is used for acquiring a plurality of first-class areas in the area smaller than the maximum area radius; and acquiring a plurality of second type areas with the amount of orders larger than the minimum amount of orders in the plurality of first type areas; the first calculating unit is used for calculating the distribution entropy according to a preset formula according to the total orders of the plurality of second type areas; acquiring the total order number when the distribution entropy is maximum as an actual total order number; the determining unit is specifically used for determining the area radius and the amount of orders according to the actual total amount of orders; preset formula as
Wherein E isr,mTo distribute entropy, PiThe order number of the ith second type area accounts for the total order number of the plurality of second type areas, and n is the number of the plurality of second type areas.
In the technical scheme, the definition unit defines the maximum area radius and the minimum order number, the order number is more in the peak time period, the maximum area radius needs to be properly adjusted to be smaller or the minimum order number needs to be properly increased in order to avoid that a plurality of areas are automatically combined, the order number is relatively less in the peak time period, so that the order number is more dispersed, and the maximum area radius needs to be properly adjusted to be larger or the minimum order number needs to be properly reduced in order to avoid being mistakenly considered as noise. After the maximum area radius and the minimum amount of orders are defined, the clustering determining unit acquires a plurality of first type areas within an area smaller than the maximum area radius, the first type areas being areas within an area smaller than the maximum area radius, acquires a plurality of second type areas with the amount of orders larger than the minimum amount of orders among the plurality of first type areas, and the second type areas being areas with the number of orders larger than the minimum amount of orders in the first type areas. The order quantity of each second type area is added to be used as the total order quantity of the plurality of second type areas, the first calculating unit obtains the area distribution entropy according to the total order quantity, and the total order quantity of the plurality of second type areas is determined by the number of the plurality of second type areas and the order quantity of each second type area, so that the distribution entropy is known to be positively correlated with the number of the second type areas according to a preset formula, namely the more clusters are clustered, the larger the distribution entropy is, the more the order quantity in the clusters is distributed uniformly, and the larger the distribution entropy is. The total order number when the distribution entropy is maximum is obtained and used as the actual total order number, the determining unit determines the area radius and the order number when the distribution entropy is maximum according to the actual total order number, the divided area orders are more, the area distribution is uniform, and the accuracy of vehicle scheduling is improved.
In any one of the above technical solutions, preferably, the judging unit includes: the acquisition unit is used for acquiring the current transaction rate of the area and the current riding ratio of the area; the judging unit is specifically used for judging whether the current transaction rate is smaller than a preset transaction rate; the setting unit is used for setting the expected transaction rate of the region when the current transaction rate is less than the preset transaction rate; the obtaining unit is also used for obtaining the expected riding ratio according to the expected transaction rate; the judging unit is also used for judging whether the riding ratio is smaller than the expected riding ratio or not; and when the current ride-through ratio is less than the desired ride-through ratio, determining that the region is not in a healthy state.
In the technical scheme, an obtaining unit obtains a current transaction rate of an area and a current ride rate of the area, if the current transaction rate does not meet a preset transaction rate, that is, the transaction rate is low, a setting unit sets an expected transaction rate of the area, and an obtaining unit obtains the expected ride rate according to the expected transaction rate, where the expected ride rate is a linear function of the expected transaction rate, for example, a function of Y ═ a × X + b, Y is the expected ride rate, X is the expected transaction rate, and a and b can be obtained through a linear regression method through obtained samples. The judging unit judges whether the current driving-riding ratio is smaller than the expected driving-riding ratio or not, and when the current driving-riding ratio is smaller than the expected driving-riding ratio, the area is determined to be in an unhealthy state, so that vehicle dispatching is carried out on the area, and the vehicle-booking success rate of vehicle-booking users in the area and the order-taking success rate of drivers in the area are improved.
In any one of the above technical solutions, preferably, the vehicle acquisition unit includes: a second calculation unit for calculating a rectangular boundary of the region; the vehicle acquisition unit is specifically used for increasing the preset area of the periphery of the rectangular boundary to form a new rectangular boundary; acquiring vehicles in the new rectangular boundary and the difference value area between the rectangular boundaries; taking the vehicles meeting the preset conditions in the vehicles in the difference region as schedulable vehicles; the vehicles meeting the preset conditions are vehicles which are smaller than the first preset amount of orders in a first preset range around and are not in an order dense area.
In the technical solution, the second calculating unit calculates the rectangular boundary of the area, and the boundary calculating method calculates the maximum longitude and latitude (maxlng, maxlat) and the minimum longitude and latitude (minlg, minlat) of the order used in the area, and then uses the rectangle described by the following four points (maxlng, maxlat), (maxlng, minlat), (minng, maxlat), (minlg, minlat) as the boundary of the area. Increasing the preset area around the rectangular boundary to form a new rectangular boundary, namely outwards extending preset values from four points describing the boundary, calculating four new points, and taking the rectangle described by the four new points as the new rectangular boundary. The vehicle obtaining unit obtains a new rectangular boundary and a difference value area between the rectangular boundaries, namely a 'return' font area, and vehicles which meet the requirement that the number of orders in a first preset range around the vehicles in the 'return' font area is smaller than a first preset order number and are not in an order dense area are taken as schedulable vehicles, so that the vehicles which are few in the number of orders around and are close to a target scheduling area can be determined to be scheduled, the effectiveness and the rationality of vehicle scheduling are guaranteed, and a better driver and passenger supply and demand effect is guaranteed.
In any of the above technical solutions, preferably, the scheduling unit includes: an order point determining unit, configured to use, as a core order point, an order point in a second preset range around the area, where the number of orders is greater than a second preset order number; an address acquisition unit, configured to acquire address information of a core order point; and the scheduling unit is specifically used for scheduling the schedulable vehicle to the core order point according to the scheduling instruction and the address information of the core order point.
In the technical scheme, after a dispatchable vehicle is found, because the area of an order aggregation area is large, a order point determining unit is required to select and dispatch a core order point which is closest to the vehicle, the concept of the core order point is that the number of orders in a preset range around the order point is not less than a preset order number, an address obtaining unit obtains address information of the core order point, and a dispatching unit dispatches the dispatchable vehicle to the position of the core order point which is closest to the dispatching unit in the area, so that the vehicle is guaranteed to be dispatched to the area with the dense order number quickly, and the order taking rate of a driver is improved.
In any of the foregoing technical solutions, preferably, the address obtaining unit is specifically configured to: acquiring the longitude and latitude of the core order point; analyzing the address information of the core order point according to the longitude and latitude of the core order point; the address information of the core order point comprises regions, streets and business circles.
In the technical scheme, the address acquisition unit determines the address information of the core order point through the longitude and latitude of the core order point and specifically reaches the region, the street and the business district, so that the schedulable vehicle can quickly reach the core order point, the vehicle scheduling efficiency is improved, the vehicle reaching time is saved, and the user can timely get the vehicle.
According to another object of an embodiment of the present disclosure, a computer device is provided, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor implements the following steps when executing the computer program: determining the radius of the area and the amount of orders; dividing the area according to the area radius and the order number; judging whether the area is in a healthy state; when the area is not in a healthy state, starting a scheduling instruction; obtaining schedulable vehicles according to the region; and dispatching the dispatchable vehicle according to the dispatching instruction.
According to the computer equipment provided by the embodiment of the disclosure, when a processor executes a computer program, the region radius and the order number which can be divided into reasonable regions are selected, the regions are reasonably divided according to the region radius and the order number, the reasonably divided regions are more divided regions, more order numbers of the regions are provided, the region distribution is uniform, after the region division is completed, whether the regions are unhealthy regions with low overall transaction rate and insufficient riding ratio or not is judged according to the transaction rate and the riding ratio of the regions, when the regions are unhealthy regions, a scheduling instruction is started, schedulable vehicles near the regions are obtained, and the schedulable vehicles are scheduled to the regions. The vehicle scheduling method and the vehicle scheduling system can schedule the vehicles in the area with sparse orders to the area with dense orders and insufficient driver and passenger supply and demand, guarantee timeliness and effectiveness of vehicle scheduling, improve order transaction rate and improve driver order listening experience.
According to a further object of an embodiment of the present disclosure, a computer-readable storage medium is proposed, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the order distribution based vehicle scheduling method according to any one of the preceding claims.
The computer-readable storage medium provided by the embodiment of the disclosure, when being executed by a processor, realizes selecting an area radius and an order number which can be divided into reasonable areas, and reasonably divides the areas according to the area radius and the order number, wherein the reasonably divided areas are areas with more divided areas, more orders in the areas and more uniform area distribution, after the areas are divided, whether the areas are unhealthy areas with low overall transaction rate and insufficient order rate is judged according to the transaction rate and the order rate of the areas, and when the areas are unhealthy areas, a scheduling instruction is started to obtain schedulable vehicles near the areas, and the schedulable vehicles are scheduled to the areas. The vehicle scheduling method and the vehicle scheduling system can schedule the vehicles in the area with sparse orders to the area with dense orders and insufficient driver and passenger supply and demand, guarantee timeliness and effectiveness of vehicle scheduling, improve order transaction rate and improve driver order listening experience.
Additional aspects and advantages of the disclosed embodiments will be set forth in part in the description which follows or may be learned by practice of the disclosed embodiments.
Drawings
The above and/or additional aspects and advantages of the embodiments of the present disclosure will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 illustrates a flow diagram of a vehicle dispatch method based on order distribution in one embodiment of the present disclosure;
FIG. 2 illustrates a flow diagram of a vehicle dispatch method based on order distribution in accordance with another embodiment of the present disclosure;
FIG. 3 illustrates a flow diagram of a vehicle dispatch method based on order distribution in accordance with yet another embodiment of the present disclosure;
FIG. 4 illustrates a flow diagram of a vehicle dispatch method based on order distribution in accordance with yet another embodiment of the disclosed embodiments;
FIG. 5 illustrates a flow diagram of a vehicle dispatch method based on order distribution in accordance with yet another embodiment of the disclosed embodiments;
FIG. 6 illustrates a flow diagram of a vehicle dispatch method based on order distribution in accordance with yet another embodiment of the disclosed embodiments;
FIG. 7 illustrates a schematic block diagram of an order distribution based vehicle dispatch system in accordance with one embodiment of the present disclosure;
FIG. 8 shows a schematic block diagram of an order distribution based vehicle dispatch system of another embodiment of the present disclosure;
FIG. 9 illustrates a schematic block diagram of an order distribution based vehicle dispatch system in accordance with yet another embodiment of the present disclosure;
FIG. 10 shows a schematic block diagram of an order distribution based vehicle dispatch system of yet another embodiment of the disclosed embodiments;
FIG. 11 shows a schematic block diagram of an order distribution based vehicle dispatch system of yet another embodiment of the disclosed embodiments;
FIG. 12 shows a schematic block diagram of a computer device of one embodiment of the disclosed embodiments;
FIG. 13a is a schematic diagram illustrating a cluster distribution in accordance with an embodiment of the present disclosure;
FIG. 13b is a schematic diagram illustrating a cluster distribution of another embodiment of the present disclosure;
FIG. 13c is a schematic diagram illustrating a cluster distribution of yet another embodiment of the present disclosure;
FIG. 13d is a schematic diagram illustrating a cluster distribution of yet another embodiment of the present disclosure;
FIG. 14 is a schematic diagram illustrating a relationship between a transaction rate and a driver-to-driver ratio according to an embodiment of the present disclosure;
FIG. 15 illustrates a driver dispatch diagram for one particular embodiment of an embodiment of the present disclosure.
Detailed Description
In order that the above objects, features and advantages of the embodiments of the present disclosure can be more clearly understood, embodiments of the present disclosure will be described in further detail below with reference to the accompanying drawings and detailed description. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the disclosure, however, the embodiments of the disclosure may be practiced in other ways than those described herein, and therefore the scope of the embodiments of the disclosure is not limited to the specific embodiments disclosed below.
In an embodiment of the first aspect of the embodiments of the present disclosure, a vehicle scheduling method based on order distribution is provided, and fig. 1 illustrates a flowchart of the vehicle scheduling method based on order distribution according to an embodiment of the present disclosure. Wherein, the method comprises the following steps:
and step 112, dispatching the dispatchable vehicle according to the dispatching instruction.
The vehicle scheduling method based on order distribution provided by the embodiment of the disclosure selects the area radius and the order number which can be divided into reasonable areas, and reasonably divides the areas according to the area radius and the order number, wherein the reasonably divided areas are more divided areas, more orders in the areas and more uniform area distribution, after the area division is completed, whether the area is an unhealthy area with low overall transaction rate and insufficient riding ratio or not is judged according to the transaction rate and the riding ratio of the area, and when the area is an unhealthy area, a scheduling instruction is started to obtain schedulable vehicles near the area, and the schedulable vehicles are scheduled to the area. The vehicle scheduling method and the vehicle scheduling system can schedule the vehicles in the area with sparse orders to the area with dense orders and insufficient driver and passenger supply and demand, guarantee timeliness and effectiveness of vehicle scheduling, improve order transaction rate and improve driver order listening experience.
Fig. 2 shows a flow chart of a vehicle scheduling method based on order distribution according to another embodiment of the present disclosure. Wherein, the method comprises the following steps:
and step 220, dispatching the dispatchable vehicle according to the dispatching instruction.
The vehicle scheduling method based on order distribution according to the embodiment of the present disclosure may further have the following technical features:
in the foregoing technical solution, preferably, the step of determining the radius of the area and the amount of orders specifically includes: defining the maximum area radius and the minimum orderA singular number; acquiring a plurality of first-class areas in an area smaller than the radius of the maximum area; acquiring a plurality of second type areas with the amount of orders larger than the minimum amount of orders in the plurality of first type areas; calculating the distribution entropy according to a preset formula according to the total orders of the plurality of second type areas; acquiring the total order number when the distribution entropy is maximum as an actual total order number; determining the radius of the area and the amount of orders according to the actual total amount of orders; preset formula as
Er,mTo distribute entropy, PiThe order number of the ith second type area accounts for the total order number of the plurality of second type areas, and n is the number of the plurality of second type areas.
In this embodiment, the maximum area radius and the minimum order number are defined, the order number is larger during the peak time, in order to avoid the multiple areas being automatically combined, the maximum area radius needs to be adjusted to be smaller or the minimum order number needs to be increased, while during the near peak time, the order number is relatively smaller and is therefore more distributed, and in order to avoid being mistaken for noise, the maximum area radius needs to be adjusted to be larger or the minimum order number needs to be decreased. After the maximum area radius and the minimum amount of orders are defined, a plurality of first type areas which are in the area smaller than the maximum area radius are obtained, the first type areas are the areas which are in the area smaller than the maximum area radius, a plurality of second type areas with the amount of orders larger than the minimum amount of orders are obtained in the first type areas, and the second type areas are the areas with the order number larger than the minimum amount of orders in the first type areas. The order quantity of each second type area is added to be used as the total order quantity of the plurality of second type areas, the area distribution entropy is obtained according to the total order quantity, the total order quantity of the plurality of second type areas is determined by the number of the plurality of second type areas and the order quantity of each second type area, therefore, the distribution entropy is positively correlated with the number of the second type areas according to a preset formula, namely the more clusters are clustered, the larger the distribution entropy is, the more the order quantity in the clusters is distributed uniformly, and the larger the distribution entropy is. And acquiring the total order number when the distribution entropy is maximum as an actual total order number, determining the area radius and the order number when the distribution entropy is maximum according to the actual total order number, ensuring that the number of the divided area orders is more and the area distribution is more uniform, and further improving the accuracy of vehicle scheduling.
Fig. 3 shows a flowchart of a vehicle scheduling method based on order distribution according to still another embodiment of the present disclosure. Wherein, the method comprises the following steps:
and step 320, dispatching the dispatchable vehicle according to the dispatching instruction.
In this embodiment, a current transaction rate of the area and a current ride-through ratio of the area are obtained, if the current transaction rate does not satisfy the preset transaction rate, that is, the transaction rate is low, an expected transaction rate of the area is set, and the expected ride-through ratio is obtained according to the expected transaction rate, where the expected ride-through ratio is a linear function of the expected transaction rate, for example, a function of Y ═ a × X + b, Y is the expected ride-through ratio, X is the expected transaction rate, and a and b can be obtained by a linear regression method through the obtained samples. And judging whether the current riding ratio is smaller than the expected riding ratio, and when the current riding ratio is smaller than the expected riding ratio, determining that the area is in an unhealthy state, and further carrying out vehicle dispatching on the area, so that the vehicle-booking user vehicle-booking success rate of the area and the driver order-receiving success rate of the area are improved.
Fig. 4 shows a flow chart of a vehicle scheduling method based on order distribution according to another embodiment of the present disclosure. Wherein, the method comprises the following steps:
and step 420, dispatching the dispatchable vehicle according to the dispatching instruction.
In this embodiment, the rectangular boundary of the area is calculated, and the boundary calculation method adopts the method of calculating the maximum longitude and latitude (maxlng, maxlat) and the minimum longitude and latitude (minlg, minlat) of the order used in the area, and then using the rectangle described by the following four points (maxlng, maxlat), (maxlng, minlat), (minng, maxlat), (minng, minlat) as the boundary of the area. Increasing the preset area around the rectangular boundary to form a new rectangular boundary, namely outwards extending preset values from four points describing the boundary, calculating four new points, and taking the rectangle described by the four new points as the new rectangular boundary. The method comprises the steps of obtaining a new rectangular boundary and a difference value area between the rectangular boundaries, namely a 'return' font area, and taking a vehicle which meets the condition that the number of orders in a first preset range around the vehicle in the 'return' font area is smaller than a first preset order number and is not in an order dense area as a schedulable vehicle, so that the vehicle which has fewer current surrounding orders and is closer to a target scheduling area can be scheduled, the effectiveness and rationality of vehicle scheduling are guaranteed, and a better driver and passenger supply and demand effect is guaranteed.
Fig. 5 shows a flow chart of a vehicle scheduling method based on order distribution according to another embodiment of the present disclosure. Wherein, the method comprises the following steps:
In the embodiment, after the dispatchable vehicle is found, because the area of the order aggregation area is large, a core order point closest to the dispatchable vehicle needs to be selected for the vehicle, the concept of the core order point is that the number of orders in a preset range around the order point is not less than the preset order number, the address information of the core order point is obtained, the dispatchable vehicle is dispatched to the position of the core order point closest to the dispatchable vehicle in the area, the vehicle is guaranteed to be dispatched to the area with dense order number quickly, and the order taking rate of a driver is improved.
Fig. 6 shows a flow chart of a vehicle scheduling method based on order distribution according to still another embodiment of the disclosed embodiments. Wherein, the method comprises the following steps:
The address information of the core order point comprises regions, streets and business circles.
In the embodiment, the address information of the core order point is determined through the longitude and latitude of the core order point and is specifically applied to the region, the street and the business district, so that the schedulable vehicle can quickly reach the core order point, the vehicle scheduling efficiency is improved, the vehicle reaching time is saved, and the user can be ensured to timely drive the vehicle.
In a second aspect of the embodiments of the present disclosure, a vehicle dispatching system based on order distribution is proposed, and fig. 7 shows a schematic block diagram of a vehicle dispatching system 700 based on order distribution according to an embodiment of the present disclosure. Wherein, this system includes:
a determining unit 702 for determining the area radius and the amount of orders;
a dividing unit 704, configured to divide the area according to the area radius and the order number;
a judging unit 706, configured to judge whether the area is in a healthy state;
a starting unit 708, configured to start a scheduling instruction when the area is not in a healthy state;
a vehicle acquisition unit 710 for acquiring schedulable vehicles according to regions;
and a scheduling unit 712, configured to schedule the dispatchable vehicle according to the scheduling instruction.
The vehicle dispatching system 700 based on order distribution provided by the embodiment of the disclosure selects the area radius and the order number capable of being divided into reasonable areas through the determining unit 702, the areas are reasonably divided through the dividing unit 704 according to the area radius and the order number, the reasonable divided areas are areas with more divided areas, more orders in the areas and more uniform area distribution, after the area division is completed, the judging unit 706 judges whether the area is an unhealthy area with low overall transaction rate and insufficient riding ratio according to the transaction rate and riding ratio of the area, when the area is the unhealthy area, the starting unit 708 starts a dispatching instruction, dispatchable vehicles near the area are obtained through the vehicle obtaining unit 710, and the dispatching unit 712 dispatches the dispatchable vehicles to the area. The vehicle scheduling method and the vehicle scheduling system can schedule the vehicles in the area with sparse orders to the area with dense orders and insufficient driver and passenger supply and demand, guarantee timeliness and effectiveness of vehicle scheduling, improve order transaction rate and improve driver order listening experience.
Fig. 8 shows a schematic block diagram of a vehicle dispatch system 800 based on order distribution according to another embodiment of the present disclosure. Wherein, this system includes:
a determining unit 802 for determining the area radius and the amount of orders;
a dividing unit 804, configured to divide an area according to the area radius and the order number;
a judging unit 806, configured to judge whether the area is in a healthy state;
a starting unit 808, configured to start a scheduling instruction when the area is not in a healthy state;
a vehicle obtaining unit 810 for obtaining schedulable vehicles according to regions;
a scheduling unit 812 for scheduling schedulable vehicles according to the scheduling instructions;
the determining unit 802 includes:
a defining unit 822 for defining a maximum area radius and a minimum amount of orders;
a cluster determining unit 824, configured to obtain a plurality of first type areas within an area smaller than the maximum area radius; and acquiring a plurality of second type areas with the amount of orders larger than the minimum amount of orders in the plurality of first type areas;
a first calculating unit 826, configured to calculate a distribution entropy according to a preset formula according to the total amount of orders of the plurality of second type regions; acquiring the total order number when the distribution entropy is maximum as an actual total order number;
a determining unit 802, specifically configured to determine the area radius and the amount of orders according to the actual total amount of orders;
wherein the preset formula is
Er,mTo distribute entropy, PiThe order number of the ith second type area accounts for the total order number of the plurality of second type areas, and n is the number of the plurality of second type areas.
In this embodiment, the defining unit 822 defines the maximum area radius and the minimum order number, the orders are more in the peak time, in order to avoid the multiple areas being automatically combined, the maximum area radius needs to be adjusted to be smaller or the minimum order number needs to be increased, and in the near-peak time, the orders are more dispersed because the order number is relatively less, and in order to avoid being mistakenly regarded as noise, the maximum area radius needs to be adjusted to be larger or the minimum order number needs to be decreased. After the maximum area radius and the minimum amount of orders are defined, the cluster determining unit 824 acquires a plurality of first type areas within an area smaller than the maximum area radius, and acquires a plurality of second type areas having orders larger than the minimum amount of orders among the plurality of first type areas. The order quantity of each second type area is added to be used as the total order quantity of the plurality of second type areas, the first calculating unit 826 obtains the area distribution entropy according to the total order quantity, and the total order quantity of the plurality of second type areas is determined by the number of the plurality of second type areas and the order quantity of each second type area, so that the distribution entropy is known to be positively correlated with the number of the second type areas according to a preset formula, namely the more clusters are clustered, the larger the distribution entropy is, the more the order quantity in the clusters is distributed uniformly, and the larger the distribution entropy is. The total order number when the distribution entropy is maximized is obtained as an actual total order number, and the determining unit 802 determines the area radius and the order number when the distribution entropy is maximized according to the actual total order number, so that the number of divided area orders is large, the area distribution is uniform, and the accuracy of vehicle scheduling is improved.
Fig. 9 shows a schematic block diagram of a vehicle dispatch system 900 based on order distribution according to yet another embodiment of the disclosed embodiments. Wherein, this system includes:
a determining unit 902 for determining the area radius and the amount of orders;
a dividing unit 904 for dividing the area according to the area radius and the order number;
a judging unit 906, configured to judge whether the area is in a healthy state;
a starting unit 908 for starting a scheduling instruction when the region is not in a healthy state;
a vehicle acquiring unit 910 configured to acquire schedulable vehicles according to regions;
a scheduling unit 912 for scheduling schedulable vehicles according to the scheduling command;
the determining unit 902 includes:
a defining unit 922 for defining the maximum area radius and the minimum amount of orders;
a cluster determining unit 924, configured to obtain a plurality of first type regions within a region smaller than the maximum region radius; and acquiring a plurality of second type areas with the amount of orders larger than the minimum amount of orders in the plurality of first type areas;
a first calculating unit 926, configured to calculate the distribution entropy according to a preset formula according to the total amount of orders of the plurality of second type regions; acquiring the total order number when the distribution entropy is maximum as an actual total order number;
a determining unit 902, specifically configured to determine the area radius and the amount of orders according to the actual total amount of orders;
the judging unit 906 includes:
an obtaining unit 962, configured to obtain a current transaction rate of the area and a current ride-through ratio of the area;
a judging unit 906, specifically configured to judge whether the current transaction rate is smaller than a preset transaction rate;
a setting unit 964, configured to set an expected transaction rate of the area when the current transaction rate is less than a preset transaction rate;
an obtaining unit 962, configured to obtain an expected riding ratio according to the expected trading rate;
a judging unit 906, further configured to judge whether the riding ratio is less than the desired riding ratio; and when the current ride-through ratio is less than the desired ride-through ratio, determining that the region is not in a healthy state.
In this embodiment, the obtaining unit 962 obtains the current transaction rate of the area and the current ride rate of the area, if the current transaction rate does not satisfy the preset transaction rate, that is, the transaction rate is lower, the setting unit 964 sets the expected transaction rate of the area, and the obtaining unit 962 obtains the expected ride rate according to the expected transaction rate, where the expected ride rate is a linear function of the expected transaction rate, for example, a function of Y ═ a × X + b, Y is the expected ride rate, X is the expected transaction rate, and a and b can be obtained by a linear regression method through the obtained samples. The judging unit 906 judges whether the current riding ratio is smaller than the expected riding ratio, and when the current riding ratio is smaller than the expected riding ratio, determines that the area is in an unhealthy state, and further performs vehicle scheduling on the area, so as to improve the vehicle-booking user vehicle-booking success rate of the area and the driver order-receiving success rate of the area.
Fig. 10 shows a schematic block diagram of a vehicle dispatch system 1000 based on order distribution of yet another embodiment of the disclosed embodiments. Wherein, this system includes:
a determining unit 1002 for determining the area radius and the amount of orders;
a dividing unit 1004 for dividing the area according to the area radius and the order number;
a judging unit 1006, configured to judge whether the area is in a healthy state;
a starting unit 1008, configured to start a scheduling instruction when the area is not in a healthy state;
a vehicle acquisition unit 1010 for acquiring schedulable vehicles according to the region;
a scheduling unit 1012 for scheduling schedulable vehicles according to the scheduling command;
the determining unit 1002 includes:
a defining unit 1022 for defining the maximum regional radius and the minimum amount of orders;
a cluster determining unit 1024, configured to obtain a plurality of first-class regions located in a region smaller than the maximum region radius; and acquiring a plurality of second type areas with the amount of orders larger than the minimum amount of orders in the plurality of first type areas;
a first calculating unit 1026, configured to calculate the distribution entropy according to a preset formula according to the total amount of orders of the plurality of second type regions; acquiring the total order number when the distribution entropy is maximum as an actual total order number;
a determining unit 1002, specifically configured to determine the area radius and the amount of orders according to the actual total amount of orders;
the judgment unit 1006 includes:
an obtaining unit 1062, configured to obtain a current transaction rate of the area and a current ride-through ratio of the area;
the determining unit 1006 is specifically configured to determine whether the current transaction rate is smaller than a preset transaction rate;
a setting unit 1064, configured to set an expected transaction rate of the area when the current transaction rate is less than a preset transaction rate;
the obtaining unit 1062 is further configured to obtain an expected ride ratio according to the expected transaction rate;
a judging unit 1006, further configured to judge whether the riding ratio is less than the desired riding ratio; when the current ride-through ratio is smaller than the expected ride-through ratio, judging that the area is not in a healthy state;
the vehicle acquisition unit 1010 includes:
a second calculation unit 10102 for calculating rectangular boundaries of the region;
the vehicle obtaining unit 1010 is specifically configured to increase the periphery of the rectangular boundary by a preset area to form a new rectangular boundary; acquiring vehicles in the new rectangular boundary and the difference value area between the rectangular boundaries; taking the vehicles meeting the preset conditions in the vehicles in the difference region as schedulable vehicles;
the vehicles meeting the preset conditions are vehicles which are smaller than the first preset amount of orders in a first preset range around and are not in an order dense area.
In this embodiment, the second calculation unit 10102 calculates the rectangular boundary of the area, and the boundary calculation method adopts a method of calculating the maximum longitude and latitude (maxlng, maxlat), the minimum longitude and latitude (minng, minlat) of the order used in the area, and then uses the rectangle described by the following four points (maxlng, maxlat), (maxlng, minlat), (minng, maxlat), (minng, minlat) as the boundary of the area. Increasing the preset area around the rectangular boundary to form a new rectangular boundary, namely outwards extending preset values from four points describing the boundary, calculating four new points, and taking the rectangle described by the four new points as the new rectangular boundary. The vehicle acquiring unit 1010 acquires a new rectangular boundary and a difference value area between the rectangular boundaries, namely a 'return' font area, and takes a vehicle which satisfies that the number of orders in a first preset range around the vehicle in the 'return' font area is smaller than a first preset order number and is not in an order dense area as an schedulable vehicle, so that the vehicle which has fewer orders around the vehicle and is closer to a target scheduling area can be determined to be scheduled, the effectiveness and rationality of vehicle scheduling are ensured, and a better driver and passenger supply and demand effect is ensured.
Fig. 11 shows a schematic block diagram of a vehicle dispatch system 1100 based on order distribution of yet another embodiment of the disclosed embodiments. Wherein, this system includes:
a determining unit 1102 for determining the area radius and the amount of orders;
a dividing unit 1104 for dividing the area according to the area radius and the order number;
a determining unit 1106, configured to determine whether the area is in a healthy state;
a starting unit 1108, configured to start a scheduling instruction when the area is not in a healthy state;
a vehicle acquisition unit 1110 for acquiring schedulable vehicles according to regions;
a scheduling unit 1112 for scheduling schedulable vehicles according to the scheduling instructions;
the determining unit 1102 includes:
a defining unit 1122 for defining the maximum area radius and the minimum amount of orders;
a cluster determining unit 1124 for acquiring a plurality of first type regions within a region smaller than the maximum region radius; and acquiring a plurality of second type areas with the amount of orders larger than the minimum amount of orders in the plurality of first type areas;
a first calculating unit 1126, configured to calculate the distribution entropy according to a preset formula according to the total amount of orders of the plurality of second-type regions; acquiring the total order number when the distribution entropy is maximum as an actual total order number;
a determining unit 1102, specifically configured to determine the area radius and the amount of orders according to the actual total amount of orders;
the determining unit 1106 includes:
an obtaining unit 1162, configured to obtain a current transaction rate of the area and a current riding ratio of the area;
the determining unit 1106 is specifically configured to determine whether the current transaction rate is smaller than a preset transaction rate;
a setting unit 1164, configured to set an expected transaction rate of the area when the current transaction rate is smaller than a preset transaction rate;
an obtaining unit 1162, configured to obtain the expected riding ratio according to the expected transaction rate;
a judging unit 1106, configured to judge whether the riding ratio is smaller than the desired riding ratio; when the current ride-through ratio is smaller than the expected ride-through ratio, judging that the area is not in a healthy state;
the vehicle acquisition unit 1110 includes:
a second calculation unit 11102 for calculating a rectangular boundary of the region;
the vehicle obtaining unit 1110 is specifically configured to increase the preset area around the rectangular boundary to form a new rectangular boundary; acquiring vehicles in the new rectangular boundary and the difference value area between the rectangular boundaries; taking the vehicles meeting the preset conditions in the vehicles in the difference region as schedulable vehicles;
the scheduling unit 1112 includes:
an order point determining unit 11122 configured to take, as a core order point, an order point in a second preset range around the area where the number of orders is greater than a second preset number of orders;
an address obtaining unit 11124, configured to obtain address information of the core order point;
the scheduling unit 1112 is specifically configured to schedule the dispatchable vehicle to the core order point according to the scheduling instruction and the address information of the core order point.
In this embodiment, after the dispatchable vehicle is found, because the area of the order aggregation area is large, the order point determining unit 11122 is required to select and dispatch the core order point closest to the vehicle to the certain vehicle, the concept of the core order point is that the number of orders in the preset range around the order point is not less than the preset number of orders, the address obtaining unit 11124 obtains the address information of the core order point, and the dispatching unit 1112 dispatches the dispatchable vehicle to the position of the core order point closest to the dispatching unit in the area, so as to ensure that the vehicle is dispatched to the area with dense order number quickly, and improve the order taking rate of the driver.
In any of the above technical solutions, preferably, the address obtaining unit 11124 is specifically configured to: acquiring the longitude and latitude of the core order point; analyzing the address information of the core order point according to the longitude and latitude of the core order point; the address information of the core order point comprises regions, streets and business circles.
In the embodiment, the address obtaining unit determines the address information of the core order point through the longitude and latitude of the core order point and specifies the address information to the region, the street and the business district, so that the schedulable vehicle can quickly reach the core order point, the vehicle scheduling efficiency is improved, the vehicle reaching time is saved, and the user can timely get the vehicle.
In an embodiment of the third aspect of the embodiments of the present disclosure, a computer device is provided, and fig. 12 shows a schematic block diagram of a computer device 1200 according to an embodiment of the present disclosure. Wherein the computer device 1200 comprises:
a memory 1202, a processor 1204, and a computer program stored on the memory 1202 and executable on the processor 1204, the processor 1204 implementing the following steps when executing the computer program: determining the radius of the area and the amount of orders; dividing the area according to the area radius and the order number; judging whether the area is in a healthy state; when the area is not in a healthy state, starting a scheduling instruction; obtaining schedulable vehicles according to the region; and dispatching the dispatchable vehicle according to the dispatching instruction.
In the computer apparatus 1200 provided in the present disclosure, when the processor 1204 executes a computer program, it is implemented to select a region radius and an order number that can be divided into reasonable regions, and reasonably divide the regions according to the region radius and the order number, where the reasonably divided regions are more divided regions, more order numbers of the regions, and more uniform region distribution, and after the region division is completed, it is determined whether the region is an unhealthy region with a low overall transaction rate and an insufficient riding ratio according to the transaction rate and the riding ratio of the region, and when the region is an unhealthy region, a scheduling instruction is started to obtain schedulable vehicles near the region, and the schedulable vehicles are scheduled to the region. The vehicle scheduling method and the vehicle scheduling system can schedule the vehicles in the area with sparse orders to the area with dense orders and insufficient driver and passenger supply and demand, guarantee timeliness and effectiveness of vehicle scheduling, improve order transaction rate and improve driver order listening experience.
An embodiment of the fourth aspect of the embodiments of the present disclosure proposes a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the following steps: determining the radius of the area and the amount of orders; dividing the area according to the area radius and the order number; judging whether the area is in a healthy state; when the area is not in a healthy state, starting a scheduling instruction; obtaining schedulable vehicles according to the region; and dispatching the dispatchable vehicle according to the dispatching instruction.
The computer-readable storage medium provided by the embodiment of the disclosure, when being executed by a processor, realizes selecting an area radius and an order number which can be divided into reasonable areas, and reasonably divides the areas according to the area radius and the order number, wherein the reasonably divided areas are areas with more divided areas, more orders in the areas and more uniform area distribution, after the area division is completed, whether the area is an unhealthy area with low overall transaction rate and insufficient order rate is judged according to the transaction rate and the order rate of the area, and when the area is the unhealthy area, a scheduling instruction is started to obtain schedulable vehicles near the area, and the schedulable vehicles are scheduled to the area. The vehicle scheduling method and the vehicle scheduling system can schedule the vehicles in the area with sparse orders to the area with dense orders and insufficient driver and passenger supply and demand, guarantee timeliness and effectiveness of vehicle scheduling, improve order transaction rate and improve driver order listening experience.
In a specific embodiment of the present disclosure, the vehicle scheduling method based on order distribution specifically includes:
firstly, selecting the granularity of the area and reasonably dividing the area
The Dbscan algorithm needs to set a minimum area radius r and a minimum order number m in advance, then perform clustering according to the two values, automatically merge adjacent areas, and automatically identify noise. Selecting different minimum area radiuses r, the minimum order number m and the order number in different time periods t to obtain a clustering result: fig. 13a shows the clustering results when r is 1500 m, m is 5, t is 08: 00-08: 10, fig. 13b shows the clustering results when r is 1000 m, m is 5, t is 08: 00-08: 10, fig. 13c shows the clustering results when r is 1000 m, m is 5, t is 06: 36-06: 46, fig. 13d shows the clustering results when r is 1800 m, m is 4, t is 06: 36-06: 46.
Comparing fig. 13a to fig. 13d, it is found that when the total volume of orders is 400 in the period of time t 08: 00-08: 10, the effect of fig. 13b is better than that of fig. 13a, fig. 13a sets the middle large area as a cluster as a whole, and fig. 13b has a few discarded points, but the granularity of area division is better than that of fig. 13a as a whole. When the total amount of orders is 167 at time t 06: 36-06: 46, the effect of fig. 13d is significantly better than that of fig. 13 c.
Analyzing the four cases in fig. 13a to 13d, during the peak time, since the order number is more to avoid the multiple areas being automatically merged, it is necessary to turn r down or increase m up appropriately; in the period of near flat peak, the orders are relatively small and thus are scattered, and in order to avoid being mistaken for noise, r needs to be adjusted to be larger or m needs to be smaller appropriately.
By combining with the service requirements, the order number and the regional distribution of each city have very large difference, and even for one city, the difference is still huge in different time periods, so that for different cities and different time periods of the same city, two parameters r and m of the Dbscan algorithm need to be treated differently. Therefore, although Dbscan is an unsupervised learning algorithm, how to select the appropriate r and m for different situations becomes a supervised learning process based on historical data.
The desired resulting cluster distribution should meet several objectives as follows:
target 3, the distribution of each cluster is as uniform as possible.
According to these three criteria, fig. 13b and 13d are relatively good and fig. 13a and 13c are relatively poor. The number of orders per cluster for target 1 is not too small, which may set a minimum value for m, assuming 5, then the minimum number per cluster must be greater than 5, otherwise it is identified as noise. Considering the order transmission distance, the maximum value of r should not exceed 2000 m.
For the metrics of object 2 and object 3, a concept of distribution entropy is introduced here. Defining: for a certain time period of a certain city, for given r and m, the distribution entropy of the pattern clustered by Dbscan is
Er,mTo distribute entropy, PiThe order number of the ith preset cluster accounts for the total order number of the plurality of preset clusters, n is the number of the plurality of preset clusters,
e can be obtained by the formular,m∈[0，logn]，Er,mAnd n is positively correlated, namely the distribution entropy is larger as more clusters are clustered, and the distribution entropy is larger as the order number distribution in the clusters is more uniform, so that the order number distribution in the clusters is exactly matched with the targets 2 and 3. Thus, the model becomes an optimization problem:
the target is as follows: max (E)r,m)
m≥5
r≤2000
m＝f(c)
r＝g(c)
r and m are linear or non-linear functions of c, e.g. may be
Is determined by sampling samples according to the target in a linear regression modea1, b1, a2, b2, and f (c) and g (c) are then fitted.
And (3) verifying the model: for the four cases in fig. 13a to 13d, table 1 shows the sample data in the case of fig. 13a, table 2 shows the sample data in the case of fig. 13b, table 3 shows the sample data in the case of fig. 13c, and table 4 shows the sample data in the case of fig. 13 d.
TABLE 1
| Cluster numbering | Amount of orders | Order number ratio (Pi) |
| 1 | 39 | 0.117117 |
| 2 | 257 | 0.771772 |
| 9 | 9 | 0.027027 |
| 16 | 8 | 0.024024 |
| 24 | 6 | 0.018018 |
| 36 | 8 | 0.024024 |
| 59 | 6 | 0.018018 |
TABLE 2
TABLE 3
| Cluster numbering | Amount of orders | Order number ratio (Pi) |
| 12 | 5 | 0.121951 |
| 23 | 8 | 0.195122 |
| 26 | 5 | 0.121951 |
| 31 | 13 | 0.317073 |
| 75 | 5 | 0.121951 |
| 91 | 5 | 0.121951 |
TABLE 4
Calculating the distribution entropy E of each clusterr,mValue, E in FIG. 13ar,m1-0.26988, E in fig. 13br,m2-1.14058, i.e. E r,m 2>E r,m1, the effect with figure 13b is better than expected with figure 13 a. E in FIG. 13cr,m0.74241, E in fig. 13dr,m4-0.97075, i.e. E r,m 4>Er,m3, the effect with figure 13d is better than expected with figure 13 c.
Further Er,m 2Er,m 4>Er,m 3>E r,m1, the distribution entropy is the largest because of the large number of orders, the large number of clusters, and the uniform clustering, and both fig. 13c and fig. 13d are uniform in distribution, and then fig. 13d recalls more points, so that the clusters are more. In fig. 13a, since a plurality of clusters are combined, the number of clusters is small, and the distribution is very uneven, so that the distribution entropy is the lowest.
Second, judge the standard of the regional health degree
The criterion for judging the health degree of the area is a transaction rate and a ride ratio, namely the transaction rate and the ride ratio meet a certain linear relation, an expected transaction rate is given to an area with a lower transaction rate, an expected ride ratio is calculated according to a calculation formula and then compared with the current ride ratio, and when the ride ratio is less than a certain degree, a scheduling order is started. As shown in fig. 14, the calculation formula may be a function of Y — a × X + b, Y is a desired squaring ratio, X is a desired intersection rate, and a and b may be determined by a linear regression method using the obtained samples. For example, setting the desired rate of transaction to 1, then the desired ride ratio should be 16.
By this relationship, the case in fig. 13b and the case in fig. 13d are compared. For the case of fig. 13b in which the time period (8: 00-8: 10) is in the early peak period, it can be seen that the crossing rate is overall low, and the ride-over ratio is also severely insufficient. In table 5, the areas with a large number of orders, a low deal rate and an insufficient riding ratio in table 2, that is, the three areas belong to serious unhealthy areas, and driver scheduling can be performed.
TABLE 5
| Cluster numbering | Amount of orders | Success number | Number of drivers | Rate of successful transaction | Ratio of driver to |
| 21 | 22 | 7 | 140 | 0.318182 | 6.363636 |
| 24 | 33 | 12 | 299 | 0.363636 | 9.060606 |
| 46 | 31 | 11 | 275 | 0.354839 | 8.870968 |
For the case of fig. 13d, the time interval (6: 36-6: 46) belongs to a relatively flat peak time interval, and the driver can still be dispatched for the area with more orders, extremely low transaction rate and insufficient riding ratio. Table 6 is the area in table 4 that the driver can be scheduled to enter. With cluster 5 in table 4, since the rate of the deal is still possible and the ride ratio is already high, the driver can not be increased any more.
TABLE 6
| Cluster numbering | Amount of orders | Success number | Number of drivers | Rate of successful transaction | Ratio of driver to |
| 1 | 17 | 7 | 67 | 0.411765 | 3.941176 |
| 2 | 25 | 15 | 134 | 0.6 | 5.36 |
| 9 | 12 | 5 | 72 | 0.416667 | 6 |
| 11 | 8 | 4 | 31 | 0.5 | 3.875 |
Combining the above case in fig. 13b and the case in fig. 13d, we conclude that the region into which the driver can be dispatched should satisfy the characteristics:
the characteristic 1 is that the order number of the area is large (if the order number is small, the driver can not hear the order in the timing scheduling);
and 3, the riding ratio in the region is insufficient (the dispatching can solve the problem, and if the riding ratio is sufficient, the readjustment driver does not help).
The three targets have different values for different cities and different time periods, and are required to be fitted according to historical data. For a certain area, the driver is considered to be called in if the number of orders is larger than n, the rate of bargain is lower than s and the riding ratio is lower than r. In the case of FIG. 13b, (n, s, r) is preferably (15, 0.6, 10), and in the case of FIG. 13d, (n, s, r) is preferably (8, 0.65, 8).
Third, how to select the driver capable of being allocated
This indicator is from the driver's perspective, and in what circumstances the driver would like to accept the dispatch, empirically, the following objectives are met as much as possible:
and 3, the driver is closer to the target dispatching area.
To achieve these three objectives, the following steps are performed:
step one, calculating the boundary of a certain unhealthy area, wherein the boundary calculation method adopts the steps of calculating the maximum longitude and latitude (maxlng, maxlat) and the minimum longitude and latitude (minng, minlat) of an order used in the area, and then using a rectangle described by the following four points (maxlng, maxlat), (maxlng, minlat), (minng, maxlat), (minng, minlat) as the boundary of the area;
step two, after the boundary of the area is calculated, four points describing the boundary are expanded outwards for 1000 meters, then four points are calculated, and the four points are used as a second boundary, so that drivers in the 'return' shaped area between the two boundaries can be matched with the drivers;
step three, for the driver in the 'Hui' shape, the following conditions are met to be a true configurable driver: the number of orders of the driver in 2000 meters is less than 3, and the driver is not in any order-dense area;
step four, after drivers capable of being dispatched are found, because the face price of the order aggregation area is large, a core order point which is closest to the drivers is selected and dispatched to the drivers, and the concept of the core order point is that the number of orders in the r distance range around the order is not less than m;
and step five, for each schedulable driver, finding the nearest core point in the scheduling area and sending a scheduling order.
The whole process is shown in fig. 15, the area a is a certain order gathering area, the "return" type area where the area B is located is a candidate dispatch driver area, D1 and D2 are dispatchable drivers, and O1 and O2 are core points closest to the two drivers, respectively.
Fourth, address information description of scheduling area
Having determined the dispatching driver and the core point to be dispatched, the key is the address description of the core point. The existing information is longitude and latitude of a core point, a Baidu map api is planned, address information is analyzed according to the longitude and latitude of the core point, and a combination of distributed + street + business is adopted as the address information.
In the description herein, reference to the term "one embodiment," "some embodiments," "a specific embodiment," or the like, means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the embodiments of the disclosure. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure, and various modifications and changes may be made to the present disclosure by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the disclosed embodiments should be included in the scope of protection of the disclosed embodiments.
Claims (14)
1. A vehicle scheduling method based on order distribution is characterized by comprising the following steps:
determining the radius of the area and the amount of orders;
dividing the area according to the area radius and the order number;
judging whether the area is in a healthy state;
when the area is not in a healthy state, starting a scheduling instruction;
obtaining schedulable vehicles according to the area;
dispatching the dispatchable vehicle according to the dispatching instruction;
the step of determining the radius of the area and the amount of orders specifically includes:
defining the maximum area radius and the minimum amount of orders;
acquiring a plurality of first-class areas in an area smaller than the maximum area radius;
acquiring a plurality of second type areas with the amount of orders larger than the minimum amount of orders in the plurality of first type areas;
calculating the distribution entropy according to a preset formula according to the total orders of the plurality of second-type areas;
acquiring the total order number when the distribution entropy is maximum as an actual total order number;
and determining the radius of the area and the amount of orders according to the actual total amount of orders.
2. The order distribution based vehicle dispatching method of claim 1,
the preset formula is
Wherein E isr,mFor said distribution entropy, PiThe order number of the ith second type area accounts for the total order number of the plurality of second type areas, and n is the number of the plurality of second type areas.
3. The order distribution-based vehicle dispatching method according to claim 1, wherein the step of determining whether the area is in a healthy state specifically comprises:
acquiring the current transaction rate of the area and the current riding ratio of the area;
judging whether the current transaction rate is smaller than a preset transaction rate or not;
when the current transaction rate is smaller than the preset transaction rate, setting the expected transaction rate of the area;
obtaining an expected riding ratio according to the expected transaction rate;
judging whether the current ride-through ratio is smaller than an expected ride-through ratio or not;
and when the current driving-multiplying ratio is smaller than the expected driving-multiplying ratio, judging that the area is not in a healthy state.
4. The order distribution-based vehicle dispatching method according to claim 1, wherein the step of obtaining the dispatchable vehicle according to the region specifically comprises:
calculating a rectangular boundary of the region;
increasing the preset area around the rectangular boundary to form a new rectangular boundary;
acquiring vehicles in the new rectangular boundary and the difference value area between the rectangular boundaries;
taking the vehicles meeting preset conditions in the vehicles in the difference region as the schedulable vehicle;
the vehicles meeting the preset conditions are vehicles which are smaller than a first preset order number in a first preset range around and are not located in an order dense area.
5. The order distribution-based vehicle scheduling method according to any one of claims 1 to 4, wherein the step of scheduling the schedulable vehicle according to the scheduling instruction specifically comprises:
taking order points with the order number larger than a second preset order number in a second preset range around the area as core order points;
acquiring address information of the core order point;
and scheduling the schedulable vehicle to the core order point according to the scheduling instruction and the address information of the core order point.
6. The order distribution-based vehicle scheduling method according to claim 5, wherein the step of obtaining address information of the core order point specifically includes:
acquiring the longitude and latitude of the core order point;
analyzing the address information of the core order point according to the longitude and latitude of the core order point;
the address information of the core order point comprises regions, streets and business circles.
7. A vehicle dispatch system based on order distribution, comprising:
a determining unit for determining the area radius and the amount of orders;
the dividing unit is used for dividing the area according to the area radius and the order number;
the judging unit is used for judging whether the area is in a healthy state or not;
the starting unit is used for starting a scheduling instruction when the area is not in a healthy state;
the vehicle obtaining unit is used for obtaining schedulable vehicles according to the areas;
the scheduling unit is used for scheduling the schedulable vehicle according to the scheduling instruction;
the defining unit is used for defining the maximum area radius and the minimum amount of orders;
a cluster determining unit, configured to acquire a plurality of first-class regions within a region smaller than the maximum region radius; and a plurality of second type areas having orders larger than the minimum order number are obtained from the plurality of first type areas;
the first calculating unit is used for calculating the distribution entropy according to a preset formula according to the total orders of the plurality of second type areas; acquiring the total order number when the distribution entropy is maximum as an actual total order number;
the determining unit is specifically configured to determine the area radius and the amount of orders according to the actual total amount of orders.
8. The order distribution based vehicle dispatch system of claim 7,
the preset formula is
Wherein E isr,mFor said distribution entropy, PiThe order number of the ith second type area accounts for the total order number of the plurality of second type areas, and n is the number of the plurality of second type areas.
9. The order distribution based vehicle dispatching system of claim 7, wherein the determining unit comprises:
the acquisition unit is used for acquiring the current transaction rate of the area and the current riding ratio of the area;
the judging unit is specifically configured to judge whether the current transaction rate is smaller than a preset transaction rate;
the setting unit is used for setting the expected transaction rate of the area when the current transaction rate is smaller than the preset transaction rate;
the obtaining unit is further used for obtaining an expected riding ratio according to the expected transaction rate;
the judging unit is also used for judging whether the current riding ratio is smaller than an expected riding ratio; and when the current ride-through ratio is less than the desired ride-through ratio, determining that the area is not in a healthy state.
10. The order distribution based vehicle dispatching system of claim 7, wherein the vehicle acquisition unit comprises:
a second calculation unit for calculating a rectangular boundary of the region;
the vehicle acquisition unit is specifically configured to increase the preset area around the rectangular boundary to form a new rectangular boundary;
acquiring vehicles in the new rectangular boundary and the difference value area between the rectangular boundaries;
taking the vehicles meeting preset conditions in the vehicles in the difference region as the schedulable vehicle;
the vehicles meeting the preset conditions are vehicles which are smaller than a first preset order number in a first preset range around and are not located in an order dense area.
11. The order distribution based vehicle dispatching system of any of claims 7-10, wherein the dispatching unit comprises:
an order point determining unit, configured to use, as a core order point, an order point in a second preset range around the area, where the order number is greater than a second preset order number;
an address acquisition unit, configured to acquire address information of the core order point;
the scheduling unit is specifically configured to schedule the schedulable vehicle to the core order point according to the scheduling instruction and the address information of the core order point.
12. The order distribution-based vehicle dispatching system of claim 11, wherein the address obtaining unit is specifically configured to:
acquiring the longitude and latitude of the core order point;
analyzing the address information of the core order point according to the longitude and latitude of the core order point;
the address information of the core order point comprises regions, streets and business circles.
13. Computer arrangement comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor when executing the computer program realizes the steps of the order distribution based vehicle scheduling method according to any of claims 1 to 6.
14. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the order distribution based vehicle scheduling method according to any one of claims 1 to 6.
Priority Applications (5)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710447357.8A CN109087502B (en) | 2017-06-14 | 2017-06-14 | Vehicle scheduling method, scheduling system and computer equipment based on order distribution |
| PCT/CN2018/086724 WO2018228110A1 (en) | 2017-06-14 | 2018-05-14 | Systems and methods for transport capacity scheduling |
| CN201880037805.XA CN110741402B (en) | 2017-06-14 | 2018-05-14 | System and method for capacity scheduling |
| AU2018284492A AU2018284492A1 (en) | 2017-06-14 | 2018-05-14 | Systems and methods for transport capacity scheduling |
| US16/713,047 US11621921B2 (en) | 2017-06-14 | 2019-12-13 | Systems and methods for transport capacity scheduling |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710447357.8A CN109087502B (en) | 2017-06-14 | 2017-06-14 | Vehicle scheduling method, scheduling system and computer equipment based on order distribution |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109087502A CN109087502A (en) | 2018-12-25 |
| CN109087502B true CN109087502B (en) | 2020-12-08 |
Family
ID=64839390
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710447357.8A Active CN109087502B (en) | 2017-06-14 | 2017-06-14 | Vehicle scheduling method, scheduling system and computer equipment based on order distribution |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109087502B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109685515B (en) * | 2018-12-26 | 2021-02-05 | 巽腾(广东)科技有限公司 | Identity recognition method and device based on dynamic rasterization management and server |
| CN110310472A (en) * | 2019-06-13 | 2019-10-08 | 杭州圆点科技有限公司 | A kind of vehicle intelligent scheduling system and method |
| CN112949967B (en) * | 2019-11-26 | 2023-08-18 | Jvc建伍株式会社 | Vehicle scheduling processing device, vehicle scheduling method, and vehicle scheduling program |
| CN114009067B (en) * | 2020-02-18 | 2023-04-04 | 格步计程车控股私人有限公司 | System and method for partitioning a geographic area into logical areas for dynamic pricing |
| CN111402573A (en) * | 2020-03-24 | 2020-07-10 | 深圳市元征科技股份有限公司 | Shared vehicle scheduling method, system, equipment and computer storage medium |
| CN113807608B (en) * | 2021-10-09 | 2022-07-01 | 哈尔滨学院 | Cold chain supply management system based on logistics optimization, storage medium and equipment |
| CN114091932A (en) * | 2021-11-25 | 2022-02-25 | 南京领行科技股份有限公司 | Resource scheduling method, device, medium and electronic equipment |
| CN114093191A (en) * | 2021-11-25 | 2022-02-25 | 济南亚跃信息技术有限公司 | Unmanned intelligent scheduling system and automatic driving method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007249918A (en) * | 2006-03-20 | 2007-09-27 | Hitachi Software Eng Co Ltd | Taxi dispatch system using portable terminal |
| SG191453A1 (en) * | 2011-12-30 | 2013-07-31 | Singapore Technologies Dynamics Pte Ltd | System and method for flexible and efficient public transportation |
| CN103985247A (en) * | 2014-04-24 | 2014-08-13 | 北京嘀嘀无限科技发展有限公司 | Taxi transport capacity scheduling system based on city taxi calling demand distribution density |
| CN104657933A (en) * | 2015-03-04 | 2015-05-27 | 北京嘀嘀无限科技发展有限公司 | Method and equipment for informing order supply and demand density |
| CN104867065A (en) * | 2015-06-05 | 2015-08-26 | 北京嘀嘀无限科技发展有限公司 | Method and equipment for processing orders |
| CN105608886A (en) * | 2016-01-21 | 2016-05-25 | 滴滴出行科技有限公司 | Method and device for scheduling traffic tools |
| CN105825310A (en) * | 2016-04-11 | 2016-08-03 | 湖南科技大学 | Taxi passenger-searching path recommendation method based on information entropy |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1932921A (en) * | 2006-09-28 | 2007-03-21 | 江苏天泽信息产业有限公司 | Method for fast positioning nearby emptying vehicle in taxi dispatching |
| CN106373387A (en) * | 2016-10-25 | 2017-02-01 | 先锋智道（北京）科技有限公司 | Vehicle scheduling, apparatus and system |
-
2017
- 2017-06-14 CN CN201710447357.8A patent/CN109087502B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007249918A (en) * | 2006-03-20 | 2007-09-27 | Hitachi Software Eng Co Ltd | Taxi dispatch system using portable terminal |
| SG191453A1 (en) * | 2011-12-30 | 2013-07-31 | Singapore Technologies Dynamics Pte Ltd | System and method for flexible and efficient public transportation |
| CN103985247A (en) * | 2014-04-24 | 2014-08-13 | 北京嘀嘀无限科技发展有限公司 | Taxi transport capacity scheduling system based on city taxi calling demand distribution density |
| CN104657933A (en) * | 2015-03-04 | 2015-05-27 | 北京嘀嘀无限科技发展有限公司 | Method and equipment for informing order supply and demand density |
| CN104867065A (en) * | 2015-06-05 | 2015-08-26 | 北京嘀嘀无限科技发展有限公司 | Method and equipment for processing orders |
| CN105608886A (en) * | 2016-01-21 | 2016-05-25 | 滴滴出行科技有限公司 | Method and device for scheduling traffic tools |
| CN105825310A (en) * | 2016-04-11 | 2016-08-03 | 湖南科技大学 | Taxi passenger-searching path recommendation method based on information entropy |
Non-Patent Citations (2)
| Title |
|---|
| 出租车供求匹配模型及其应用;李烁 等;《中国科技信息》;20161231(第17期);第57-60页 * |
| 出租车空驶及对策研究;连谢长 等;《城市交通发展模式转型与创新——中国城市交通规划2011年年会论文集》;20111231;第909-914页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109087502A (en) | 2018-12-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109087502B (en) | Vehicle scheduling method, scheduling system and computer equipment based on order distribution | |
| CN109191896B (en) | Personalized parking space recommendation method and system | |
| US10528062B2 (en) | Computerized vehicle control system for fleet routing | |
| CN107103383B (en) | Dynamic taxi sharing scheduling method based on taxi-taking hotspot | |
| US10692028B2 (en) | Optimal demand-based allocation | |
| CN107292798A (en) | A kind of shared bicycle parks determination method and device a little | |
| WO2016023435A1 (en) | Taxi operating area familiarity-based dispatching system and method in online taxi hiring | |
| CN109673165A (en) | System and method for dispatching buses | |
| CN106651027B (en) | Internet regular bus route optimization method based on social network | |
| CN110741402A (en) | System and method for capacity scheduling | |
| CN111144676A (en) | Vehicle order distribution method, device, server and computer readable storage medium | |
| WO2013188843A2 (en) | Vehicle fleet routing system | |
| CN111428137B (en) | Recommendation method and recommendation device for electric vehicle charging facilities | |
| CN111191899B (en) | Vehicle scheduling method based on region division parallel genetic algorithm | |
| CN111861078A (en) | Work order distribution method and device, electronic equipment and storage medium | |
| CN110728421B (en) | Road network charging optimization method based on charging demand big data | |
| CN112257936B (en) | Recommendation method and device for order receiving area, electronic equipment and storage medium | |
| CN116611678B (en) | Data processing method, device, computer equipment and storage medium | |
| CN111429166B (en) | Electric vehicle charging demand spatial distribution prediction method based on maximum contour clustering | |
| CN111079008B (en) | Scheme recommendation method and system for taxi driver to leave in storage pool | |
| CN110992686B (en) | Traffic travel big data analysis method | |
| CN114091932A (en) | Resource scheduling method, device, medium and electronic equipment | |
| CN112308339B (en) | Processing method and device of charging data | |
| CN116757459B (en) | Intelligent scheduling scheme for automatic driving taxies and comprehensive evaluation method and system | |
| CN113869550A (en) | Taxi scheduling method based on grid division and graph analysis |
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 |