WO2021189363A1 - 停车场服务区域的确定方法、装置、设备以及存储介质 - Google Patents

停车场服务区域的确定方法、装置、设备以及存储介质 Download PDF

Info

Publication number
WO2021189363A1
WO2021189363A1 PCT/CN2020/081441 CN2020081441W WO2021189363A1 WO 2021189363 A1 WO2021189363 A1 WO 2021189363A1 CN 2020081441 W CN2020081441 W CN 2020081441W WO 2021189363 A1 WO2021189363 A1 WO 2021189363A1
Authority
WO
WIPO (PCT)
Prior art keywords
parking lot
parking
lots
target
area
Prior art date
Application number
PCT/CN2020/081441
Other languages
English (en)
French (fr)
Inventor
彭磊
张康帅
李慧云
Original Assignee
深圳先进技术研究院
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳先进技术研究院 filed Critical 深圳先进技术研究院
Priority to AU2020438755A priority Critical patent/AU2020438755A1/en
Priority to US17/619,112 priority patent/US20220222592A1/en
Priority to GB2118130.0A priority patent/GB2599549A/en
Priority to PCT/CN2020/081441 priority patent/WO2021189363A1/zh
Publication of WO2021189363A1 publication Critical patent/WO2021189363A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40—Business processes related to the transportation industry
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07B—TICKET-ISSUING APPARATUS; FARE-REGISTERING APPARATUS; FRANKING APPARATUS
    • G07B15/00—Arrangements or apparatus for collecting fares, tolls or entrance fees at one or more control points
    • G07B15/02—Arrangements or apparatus for collecting fares, tolls or entrance fees at one or more control points taking into account a variable factor such as distance or time, e.g. for passenger transport, parking systems or car rental systems
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
    • G08G1/141—Traffic control systems for road vehicles indicating individual free spaces in parking areas with means giving the indication of available parking spaces
    • G08G1/142—Traffic control systems for road vehicles indicating individual free spaces in parking areas with means giving the indication of available parking spaces external to the vehicles
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
    • G08G1/145—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas
    • G08G1/148—Management of a network of parking areas

Definitions

  • This application relates to the field of computer technology, and in particular to a method, device, equipment and storage medium for determining the service area of a parking lot.
  • the prior art generally maps the quantified parking lot service capacity to the geographic space through the Voronoi diagram, forming mutually exclusive areas of different sizes. Because the coverage result contains the geographic information relationship between parking lots, the service area of each parking lot can be visually presented.
  • the embodiment of the present application provides a method, device, equipment, and storage medium for determining the service area of a parking lot, which can improve the efficiency and accuracy of determining the service area of a parking lot, and has high applicability.
  • an embodiment of the present application provides a method for determining the service area of a parking lot, and the method includes:
  • the transition probability matrix corresponding to each second parking lot in each second parking lot set is determined according to the above initial weight and the above initial location information.
  • a transition probability in a transition probability matrix is used to illustrate that the parking user parks in a second parking lot. Probability of transferring to another second parking lot in the same second parking lot collection when there is no empty parking space;
  • the service area of each second parking lot is determined according to the initial location information and the service capability value.
  • an embodiment of the present application provides a device for determining a service area of a parking lot, and the device includes:
  • the clustering module is used to cluster all the first parking lots to obtain at least one second parking lot set according to the initial weight and initial position information of each first parking lot in the first parking lot set;
  • the first determining module is used to determine the transition probability matrix corresponding to each second parking lot in each second parking lot set according to the above initial weight and the above initial location information, and one transition probability in one transition probability matrix is used for illustration, The probability that a parking user transfers to another second parking lot in the same second parking lot set when there is no empty parking space in a second parking lot;
  • the second determining module is configured to determine the service capability value of each second parking lot according to the initial weight and the transition probability matrix
  • the third determining module is configured to determine the service area of each second parking lot according to the initial location information and the service capability value.
  • an embodiment of the present application provides a device.
  • the device includes a processor and a memory, and the processor and the memory are connected to each other.
  • the memory is used to store a computer program that supports the terminal device to execute the method provided in the first aspect and/or any one of the possible implementations of the first aspect, the computer program includes program instructions, and the processor is configured to call the foregoing The program instructions execute the methods provided in the embodiments of this application.
  • an embodiment of the present application provides a computer-readable storage medium that stores a computer program, and the computer program is executed by a processor to implement the method provided in the embodiment of the present application.
  • At least one second parking lot set is obtained by clustering the first parking lot set, and then the service area of each second parking lot in each second parking lot set is determined at the same time, which can improve the determination.
  • the efficiency of the service area On the other hand, through the initial weight and initial location information of each second parking lot, the probability of each second parking lot in the same second parking lot set being transferred to another second parking lot can be determined, and then each second parking lot can be determined.
  • the transition probability matrix of the field set under the influence of initial weight and initial position information to reflect the interaction relationship between the second parking lot.
  • the service capacity value of each second parking lot can be accurately determined through the initial weight and the transition probability matrix, thereby constraining the service area boundary of each second parking lot, and improving the connectivity between the service areas of each second parking lot. , High applicability.
  • FIG. 1 is a schematic flowchart of a method for determining a parking lot service area provided by an embodiment of the present application
  • FIG. 2 is a schematic diagram of a clustering scenario for all first parking lots provided by an embodiment of the present application
  • FIG. 3 is a schematic flowchart of a method for determining a service area of a second parking lot provided by an embodiment of the present application
  • FIG. 4 is a schematic diagram of a scene for determining a triangular area provided by an embodiment of the present application
  • FIG. 5 is a schematic diagram of a scene for determining a circular area provided by an embodiment of the present application.
  • Fig. 6 is a schematic diagram of a scenario for determining a service area provided by an embodiment of the present application.
  • Fig. 7 is a schematic structural diagram of a device for determining a parking lot service area provided by an embodiment of the present application.
  • Fig. 8 is a schematic structural diagram of a device provided by an embodiment of the present application.
  • FIG. 1 is a schematic flowchart of a method for determining a parking lot service area provided by an embodiment of the present application.
  • the method for determining the service area of the parking lot shown in FIG. 1 may include the following steps S101 to S104.
  • S101 According to the initial weight and initial position information of each first parking lot in the first parking lot set, cluster all the first parking lots to obtain at least one second parking lot set.
  • the first parking lot set is a set of parking lots formed by all parking lots within a certain area of the service area of all parking lots, such as a set of parking lots formed by all parking lots in an administrative area of a city.
  • the initial weight of each parking lot in the first parking lot set (for convenience of description, hereinafter referred to as each first parking lot) is used to represent the initial service capacity value of each first parking lot.
  • the initial service capacity value of each first parking lot is when the parking spaces of each first parking lot are empty, and when the distance relationship with other parking lots, the charging relationship, and the road reason are not considered, the first parking lot
  • the initial weight of each first parking lot can be determined from its parking user range, the number of parking spaces, and parking fee information.
  • the aforementioned parking user range is used to indicate the degree of openness of the first parking lot.
  • the first parking lot in the park it is open to all users, so the first parking lot in the park has a higher degree of openness.
  • the first parking lot in a government building it is mainly for government employees, so the opening degree of the first parking lot in the government building is relatively low.
  • the degree of openness of each first parking lot can range from 0 to 1, where 1 means the highest degree of openness, and 0 means the lowest degree of openness.
  • the degree of openness of each first parking lot can be determined based on actual application scenarios. limit.
  • the above-mentioned number of parking spaces represents the number of all parking spaces including empty parking spaces and in-use parking spaces in each first parking lot, that is, the number of all parking spaces set up in each first parking lot.
  • the above parking fee information can be the fee charged by the parking user for each first parking lot for the first hour of parking, or it can be the fee charged by the parking user for each first parking lot for one day, which is specifically determined according to actual application scenarios. No restrictions.
  • the quantification method of the initial weight of each first parking lot is: That is, for any first parking lot, the more total parking spaces, the higher the degree of openness, and the lower the charge, the greater the initial weight of the first parking lot.
  • u i i parking to the parking range of the user v i is the number of parking spaces in the parking lot i
  • w i is the parking fee parking lot information i
  • P 1 is a first set of parking. in, Is the total number of parking spaces in all parking lots in the first parking lot set, Is the total parking fee information of all the first parking lots in the first parking lot set.
  • w i is the fee charged by the parking lot i for the first hour of parking by the parking user
  • the location information of each first parking lot can be determined to compare All the first parking lots in the first parking lot set are clustered, so that all the first parking lots in the first parking lot set are divided into at least one sub-parking lot set in the position dimension (for convenience of description, hereinafter referred to as second parking lot) Parking lot collection).
  • the location information of each first parking lot may be the latitude and longitude of each first parking lot to accurately mark the specific location of each first parking lot.
  • MeanShift clustering is achieved by iteratively moving each first parking lot to a high-density location. In iterative movement, the initial weight of each first parking lot is used as the weight, so that the first parking lot with a higher initial weight moves less, and the first parking lot with a higher initial weight will become the center of each cluster.
  • the initial weight is For the initial position information [L 1 ,...,L n ], the initial weight is For the n first parking lots, the clustering of the n first parking lots can be described by the following formula:
  • L f represents the moving position of each first parking lot
  • f represents the number of moves.
  • the Shift function defines the movement mode of all the first parking lots:
  • N n is the adjacent parking lot of parking lot n
  • N n ⁇ L n
  • d[L i ,L j ] ⁇ d 1 ,j 1,...,n,j ⁇ i ⁇
  • d 1 is the first Distance threshold.
  • all the first parking lots in the first parking lot set can be moved, and all the first parking lots can be moved at the same time each time.
  • a first parking lot in the first parking lot set as an example, when moving the first parking lot, you can first determine the distance (European distance) between the first parking lot and other first parking lots, and determine The first parking lot whose distance from the first parking lot is less than the first distance threshold is regarded as the neighboring parking lot of the first parking lot.
  • the above-mentioned first distance threshold may be determined according to the initial location information of each first parking lot in the first parking lot set, or may be determined according to the number of first parking lots in the first parking lot set, and may be determined according to actual application scenarios. , There is no restriction here.
  • the sum of the initial weights (initial service capacity values) of all adjacent parking lots of the first parking lot can be determined, and the first parking lot can be determined according to the position information of the first parking lot before each movement. Position information after each move.
  • the position information of all the first parking lots after each movement can be determined every time all the first parking lots are moved.
  • the neighboring parking lot of the first parking lot each time it moves is the first parking lot whose distance from the first parking lot (Euclidean distance) is less than the first distance threshold each time the first parking lot moves. . That is, every time all the first parking lots are moved, the neighboring parking lots of each first parking lot need to be determined again according to the location information of all the first parking lots during the movement.
  • the moving distance Euclidean distance
  • the clustering of all the first parking lots in the first parking lot set is completed.
  • at least one cluster area can be obtained in the first parking lot set, that is, the first parking lot with a lower initial weight moves to the first parking lot with a higher initial weight adjacent to it, and multiple first parking lots in the same cluster
  • the parking lot is a clustered parking lot set (for convenience of description, hereinafter referred to as the second parking lot set).
  • each point represents a first parking lot
  • the size of the point represents the initial weight of the first parking lot. The larger the point, the greater the initial weight, and the smaller the point, the smaller the initial weight.
  • the point with the smaller initial weight gradually approaches the adjacent point with the larger initial weight, and finally three clustering regions are formed.
  • all points (the first parking lot) in a cluster area belong to the same second parking lot set. After the first parking lot in each cluster is remapped to its real location, the first parking lot can be easily obtained.
  • the parking lot set includes three second parking lot sets.
  • the above-mentioned improved MeanShift algorithm is used to continue to move the current moving distance. Clustering is performed on all the first parking lots after the first parking lot until the longest moving distance is less than the first distance threshold among the moving distances of each first parking lot in a certain time. Go into details again.
  • S102 Determine a transition probability matrix corresponding to each second parking lot in each second parking lot set according to the initial weight and the initial location information.
  • the transition probability matrix corresponding to each second parking lot can be determined according to the initial weight and initial position information of each second parking lot in each second parking lot set. Specifically, because the distance between the two second parking lots is small, the parking lot users may transfer from one second parking lot to another second parking lot. Therefore, each second parking lot in each second parking set can be determined. The distance between the parking lot and other second parking lots in the same second parking set. Further, the first target distance less than or equal to the second distance threshold is determined, and the parking user is determined to park at each second parking lot according to the initial weight of the second parking lot corresponding to the first target distance and the vacancy rate of each parking lot The first probability of transferring to the second parking lot corresponding to each first target distance when there is no empty parking space. Determine the second target distance greater than the second distance threshold, and determine the second probability that the parking user will transfer to the second parking lot corresponding to each second target distance when there is no empty parking space in each second parking lot.
  • connection weight is which is:
  • the vacant parking rate of the second parking lot i may be the vacant parking rate of the second parking lot j, q it , v i represents the total parking digits of the second parking lot i, v it represents the available parking digits of the second parking lot i at time t, or represents the available parking digits of the second parking lot in the time period t.
  • the probability of the parking user going to the second parking lot i is If the Euclidean distance d ji between the second parking lot j and the second parking lot i is less than the second distance threshold d 2 , when the parking user finds that the parking space of the second parking lot j is full, the parking user goes to the second parking The probability of field i is zero. Further, according to the probability that the parking user goes to the second parking lot i
  • the transition probability matrix S t corresponding to the second parking lot set (including m second parking lots) where the second parking lot j is located can be determined:
  • any element in the transition probability matrix St represents the probability of a parking user transferring to another second parking lot in the same second parking lot set when there is no vacant parking space in one second parking lot.
  • S103 Determine the service capability value of each second parking lot according to the initial weight and the transition probability matrix.
  • the initial weights of all second parking lots in each second parking lot set can be constructed as the corresponding to each second parking lot set.
  • Initial vector Also taking a second parking lot set as an example, the initial weights of all second parking lots in the second parking lot set can be constructed as a column vector PR t (that is, the initial vector of the second parking lot). Among them, an element in the column vector PR t represents the initial weight of a second parking lot.
  • r represents the number of iterations, when the number of iterations is 0, Is the above-mentioned column vector PR t . It is not difficult to obtain, multiply the column vector PR t with the transition probability matrix S t corresponding to the same second parking lot set to obtain an iteration value Further iterative value Multiply the transition probability matrix S t corresponding to the same second parking lot set to get an iteration value And so on until Among them, ⁇ is the preset convergence threshold, that is, when The iteration ends when convergence is reached. Assuming that the final iteration value is but An element in represents the service capacity value of a second parking lot.
  • the final iteration value corresponding to each second parking lot set can be determined separately, so as to determine each second parking lot in each second parking lot set according to the final iteration value corresponding to each second parking lot set.
  • the service capacity value of the farm wherein, when the transition probability matrix S t per second is based on the parking lot of empty spaces is determined at time t, i.e., the transition probability matrix any element of S t represents the user in the parking space without a parking lot at a second time t When the parking space is transferred to another second parking lot in the same second parking lot set, An element in represents the service capacity value of a second parking lot at time t, and the service capacity value of a second parking lot changes with time.
  • the transition probability matrix S on a per-second rate of empty spaces in the parking time period t is determined, i.e., the transition probability matrix any element of S t represents parking user within a second time period t no parking lot
  • the probability of transferring to another second parking lot in the same second parking set An element in represents a service capacity value in a second parking lot time period t.
  • S104 Determine the service area of each second parking lot according to the initial location information and the service capability value.
  • the service area of each second parking lot is determined by a triangular area (Delaunay triangle) and a circular area (Apolloniu circle) corresponding to each second parking lot.
  • Fig. 3 is a schematic flowchart of a method for determining a service area of a second parking lot provided by an embodiment of the present application.
  • the method for determining the service area of the second parking lot shown in FIG. 3 may include the following steps S1041 to S1043.
  • the triangular area corresponding to each second parking lot is composed of each second parking lot and two second parking lots in the same second parking lot set (for convenience of description, hereinafter referred to as two targets)
  • the initial location information of the second parking lot) is determined.
  • the circumscribed circle area of the triangular area (Delaunay triangle) corresponding to each second parking lot does not include parking lots other than the three second parking lots constituting the triangular area.
  • the initial position information of three second parking lots in the second parking lot set can be arbitrarily selected to form a candidate triangle area, and the circumscribed circle corresponding to the candidate triangle area is determined area.
  • each second parking lot in the second parking lot set corresponds to at least one triangular area, that is, each second parking lot is a fixed point of at least one triangular area.
  • FIG. 4 is a schematic diagram of a scene for determining a triangular area provided by an embodiment of the present application.
  • Figure 4 Choose from three second parking lots q 1 (q 1x , q 1y ), q 2 (q 2x , q 2y ), and q 3 (q 3x , q 3y ), the circumcircle area that constitutes the candidate triangle area is :
  • the second parking lot q 4 (q 4x , q 4y ) can be located in the circumscribed circle area C 123 (x, y) as shown in Figure 4, that is At this time, the second parking lot q 1 (q 1x , q 1y ), q 2 (q 2x , q 2y ), and q 3 (q 3x , q 3y ) constitute the candidate triangle area, that is, the candidate triangle area is not the second parking lot q 1 (q 1x , q 1y ), q 2 (q 2x , q 2y ), and q 3 (q 3x , q 3y ) are the triangle regions corresponding to any second parking lot.
  • the circular area corresponding to each second parking lot is determined by the initial location information of each second parking lot and one of the two target second parking lots and the service capacity value at time t,
  • the above-mentioned two target second parking lots are the other two second parking lots that form a triangular area with each second parking lot.
  • the radius and center of the circular area are determined according to the initial position information of each second parking lot and one of the two target second parking lots and the service capacity value at time t.
  • the circular area is determined according to the radius and the center of the circle to determine all the circular areas corresponding to each second parking lot.
  • the distance between any position on the boundary of a circular area and each second parking lot is the same as the distance
  • the ratio of the distance of a target second parking lot is constant, and each second parking lot is located in a circular area.
  • the determined second parking q 1 (q 1x, q 1y ) service area may determine a second parking q (q 1x, q 1y) corresponding to a circular area.
  • the second parking lot q 1 (q 1x , q 1y ) and the second parking lot q 2 (q 2x , q 2y ) form a circular area AC(q 1 , q 2 ), and the second parking lot q 3 (q 3x , q 3y ) constitutes a circular area AC(q 1 , q 3 ).
  • the center of the circular area AC(p 1 ,p 2) is Radius is d 12 is the Euclidean distance from the second parking lot q 1 (q 1x , q 1y ) to the second parking lot q 2 (q 2x , q 2y ).
  • w 1 PR 1 /PR 2
  • PR 1 is the service capacity value of the second parking lot q 1 (q 1x ,q 1y ) at time t
  • PR 2 is the second parking lot q 2 (q 2x ,q 2y ) Service capability value.
  • FIG. 5 is a schematic diagram of a scene for determining a circular area provided by an embodiment of the present application.
  • the second parking lot q 2 (q 2x ,q 2y ) in q 1 ,q 2 ,q 3 )) is determined to be the circular area of the second parking lot q 1 (q 1x ,q 1y )
  • the second parking lot can be determined
  • the two candidate circular areas corresponding to the parking lot q 1 (q 1x , q 1y ) because when determining the service area of the second parking lot q 1 (q 1x , q 1y ), the second parking lot q 1 (q 1x ,q 1y ) needs to be located in the circular area.
  • the candidate circular area on the side containing the second parking lot q 1 (q 1x ,q 1y ) can be determined as the second parking lot q 1 (q 1x ,q 1y ) Is the circular area AC(q 1 ,q 2 ).
  • the center of the circular area AC(p 1 ,p 3) is Radius is d 13 is the Euclidean distance from the second parking lot q 1 (q 1x , q 1y ) to the second parking lot q 3 (q 3x , q 3y ).
  • w 2 PR 1 /PR 3
  • PR 1 is the service capacity value of the second parking lot q 1 (q 1x ,q 1y ) at time t
  • PR 3 is the second parking lot q 3 (q 3x ,q 3y ) Service capability value.
  • the ratio of the Euclidean distance from any position on the boundary of the circular area AC(q 1 , q 3 ) to the second parking lot q 1 (q 1x , q 1y ) and the second parking lot q 3 (q 3x , q 3y) Is a constant.
  • the two circular areas corresponding to the second parking lot q 1 (q 1x , q 1y ) can be determined, because when determining the service area of the second parking lot q 1 (q 1x , q 1y ), the first The second parking lot q 1 (q 1x ,q 1y ) needs to be located in a circular area, so the center area containing the second parking lot q 1 (q 1x ,q 1y ) can be determined as the second parking lot q 1 (q 1x ,q 1y ) of the circular area AC(q 1 ,q 3 ).
  • S1043 Determine the intersection area of the circular area and the triangular area corresponding to each second parking lot as the service area of each second parking lot.
  • each second parking lot may correspond to at least one triangular area and at least two circular areas. Therefore, for each second parking lot, each The service area corresponding to the second parking lot is an intersection area of the above-mentioned at least one triangular area and at least two circular areas. Wherein, the service area of each second parking lot represents the coverage area of the parking lot in terms of parking function and geographic location.
  • FIG. 6 is a schematic diagram of a scenario for determining a service area provided by an embodiment of the present application.
  • the circular area of 1x ,q 1y ) has only AC(q 1 ,q 3 ) and AC(q 1 ,q 2 ). At this time, it is not difficult to obtain the service area of the second parking lot q 1 (q 1x , q 1y) as:
  • Poly(q 1 ) ⁇ (x,y)
  • the triangular area and circular area of each second parking lot are the triangular and circular areas of each second parking lot at time t area. That is to say, the service area of each second parking lot determined at this time is its service area at time t, and it changes continuously over time, so that the service area of each second parking lot at different times can be determined in real time. .
  • the triangular area and the circular area of each second parking lot are the triangles of each second parking lot in the time period t Area and circular area. That is to say, the service area of each second parking lot determined at this time is its service area within the time period t, and the service area of each second parking lot can be measured within a certain period of time.
  • At least one second parking lot set is obtained by clustering the first parking lot set, and then the service area of each second parking lot in each second parking lot set is determined at the same time, which can improve the determination.
  • the efficiency of the service area On the other hand, the service capacity value of each second parking lot can be accurately determined through the initial weight and the transition probability matrix, thereby constraining the service area boundary of each second parking lot, and improving the connectivity between the service areas of each second parking lot. sex.
  • the service area of each second parking lot at different times can be determined to determine the changing trend of the service area of each second parking lot, so that parking users can choose a suitable (larger service area) parking at different times.
  • users can formulate different parking lot management strategies at different times.
  • it can also determine the service area of each second parking lot in a certain period of time, and measure the service area of all parking lots in a certain area from a macro perspective, so that all parking lots in the area can be rationally planned. High sex.
  • FIG. 7 is a schematic structural diagram of an apparatus for determining a parking lot service area provided by an embodiment of the present application.
  • the device 1 provided in the embodiment of the present application includes:
  • the clustering module 11 is configured to cluster all the first parking lots to obtain at least one second parking lot set according to the initial weight and initial position information of each first parking lot in the first parking lot set;
  • the first determining module 12 is configured to determine the transition probability matrix corresponding to each second parking lot in each second parking lot set according to the above initial weight and the above initial location information, and one transition probability in one transition probability matrix is used for illustration , The probability that a parking user transfers to another second parking lot in the same second parking lot set when there is no empty parking space in a second parking lot;
  • the second determining module 13 is configured to determine the service capability value of each second parking lot according to the initial weight and the transition probability matrix
  • the third determining module 14 is configured to determine the service area of each second parking lot according to the initial location information and the service capability value.
  • the foregoing apparatus 1 further includes a fourth determining module 15, and the foregoing fourth determining module 15 is further configured to:
  • the initial weight of each parking lot in the first parking lot set is determined.
  • the aforementioned clustering module 11 is used to:
  • the target moving distance is less than the first distance threshold, all the first parking lots stop moving, and at least one second parking lot set is determined according to the location information when each first parking lot stops moving, and the target moving distance It is the longest distance among the movement distances of the position information after each movement of each first parking lot and the position information after the previous movement.
  • the above-mentioned first determining module 12 is used to:
  • the transition probability matrix corresponding to each second parking lot set is determined according to the first probability and the second probability, and the transition probability matrix corresponding to a second parking lot set includes all the second parking lots in the second parking lot set. Probability of transferring to another second parking lot.
  • the above-mentioned second determining module 13 is used to:
  • the service capacity value of each second parking lot is determined according to the target iteration value.
  • the above-mentioned third determining module 14 is used to:
  • a triangular area is determined by the initial position information of the two target second parking lots in each second parking lot and the same second parking lot set.
  • the circumcircle area of the area does not include other second parking lots;
  • a circular area consists of the initial position information and service capabilities of each of the above-mentioned second parking lots and one of the above-mentioned two target second parking lots. Value is determined;
  • intersection area of the circular area and the triangular area corresponding to each second parking lot is determined as the service area of each second parking lot.
  • the above-mentioned third determining module 14 is used to:
  • the circular area is determined according to the radius and the center of the circle to determine all circular areas corresponding to each second parking lot, wherein any position on the boundary of the one circular area is away from each second parking lot.
  • the ratio of the distance to the second parking lot from the one target is a constant, and each second parking lot is located in the circular area.
  • the above-mentioned device 1 can execute the implementation manners provided in each step in FIG. 1 and/or FIG. 3 through its built-in functional modules.
  • At least one second parking lot set is obtained by clustering the first parking lot set, and then the service area of each second parking lot in each second parking lot set is determined at the same time, which can improve the determination.
  • the efficiency of the service area On the other hand, the service capacity value of each second parking lot can be accurately determined through the initial weight and the transition probability matrix, thereby constraining the service area boundary of each second parking lot, and improving the connectivity between the service areas of each second parking lot. sex.
  • the service area of each second parking lot at different times can be determined to determine the changing trend of the service area of each second parking lot, so that parking users can choose a suitable (larger service area) parking at different times.
  • users can formulate different parking lot management strategies at different times.
  • it can also determine the service area of each second parking lot in a certain period of time, and measure the service area of all parking lots in a certain area from a macro perspective, so that all parking lots in the area can be rationally planned. High sex.
  • the device 1000 in this embodiment may include: a processor 1001, a network interface 1004, and a memory 1005.
  • the above device 1000 may also include a user interface 1003, and at least one communication bus 1002.
  • the communication bus 1002 is used to implement connection and communication between these components.
  • the user interface 1003 may include a display screen (Display) and a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface.
  • the network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).
  • the memory 1004 may be a high-speed RAM memory, or a non-volatile memory (non-volatile memory), such as at least one disk memory.
  • the memory 1005 may also be at least one storage device located far away from the foregoing processor 1001.
  • the memory 1005, which is a computer-readable storage medium may include an operating system, a network communication module, a user interface module, and a device control application program.
  • the network interface 1004 can provide network communication functions; the user interface 1003 is mainly used to provide an input interface for the user; and the processor 1001 can be used to call the device control application stored in the memory 1005 To achieve:
  • the transition probability matrix corresponding to each second parking lot in each second parking lot set is determined according to the above initial weight and the above initial location information.
  • a transition probability in a transition probability matrix is used to illustrate that the parking user parks in a second parking lot. Probability of transferring to another second parking lot in the same second parking lot collection when there is no empty parking space;
  • the service area of each second parking lot is determined according to the initial location information and the service capability value.
  • the foregoing processor 1001 is further configured to:
  • the initial weight of each parking lot in the first parking lot set is determined.
  • the above-mentioned processor 1001 is configured to:
  • the target moving distance is less than the first distance threshold, all the first parking lots stop moving, and at least one second parking lot set is determined according to the location information when each first parking lot stops moving, and the target moving distance It is the longest distance among the movement distances of the position information after each movement of each first parking lot and the position information after the previous movement.
  • the above-mentioned processor 1001 is configured to:
  • the transition probability matrix corresponding to each second parking lot set is determined according to the first probability and the second probability, and the transition probability matrix corresponding to a second parking lot set includes all the second parking lots in the second parking lot set. Probability of transferring to another second parking lot.
  • the above-mentioned processor 1001 is configured to:
  • the service capacity value of each second parking lot is determined according to the target iteration value.
  • the above-mentioned processor 1001 is configured to:
  • a triangular area is determined by the initial position information of the two target second parking lots in each second parking lot and the same second parking lot set.
  • the circumcircle area of the area does not include other second parking lots;
  • a circular area consists of the initial position information and service capabilities of each of the above-mentioned second parking lots and one of the above-mentioned two target second parking lots. Value is determined;
  • intersection area of the circular area and the triangular area corresponding to each second parking lot is determined as the service area of each second parking lot.
  • the above-mentioned processor 1001 is configured to:
  • the circular area is determined according to the radius and the center of the circle to determine all circular areas corresponding to each second parking lot, wherein any position on the boundary of the one circular area is away from each second parking lot.
  • the ratio of the distance to the second parking lot from the one target is a constant, and each second parking lot is located in the circular area.
  • the aforementioned processor 1001 may be a central processing unit (CPU), and the processor may also be other general-purpose processors or digital signal processors (DSP). , Application specific integrated circuit (ASIC), ready-made programmable gate array (field-programmable gate array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc.
  • the general-purpose processor may be a microprocessor or the processor may also be any conventional processor or the like.
  • the memory may include a read-only memory and a random access memory, and provides instructions and data to the processor. A part of the memory may also include a non-volatile random access memory. For example, the memory can also store device type information.
  • the above-mentioned device 1000 can execute the implementation manners provided in each step in FIG. 1 and/or FIG. 3 through its built-in functional modules.
  • At least one second parking lot set is obtained by clustering the first parking lot set, and then the service area of each second parking lot in each second parking lot set is determined at the same time, which can improve the determination.
  • the efficiency of the service area On the other hand, the service capacity value of each second parking lot can be accurately determined through the initial weight and the transition probability matrix, thereby constraining the service area boundary of each second parking lot, and improving the connectivity between the service areas of each second parking lot. sex.
  • the service area of each second parking lot at different times can be determined to determine the changing trend of the service area of each second parking lot, so that parking users can choose a suitable (larger service area) parking at different times
  • users can formulate different parking lot management strategies at different times.
  • it can also determine the service area of each second parking lot within a certain period of time, and measure the service area of all parking lots in a certain area from a macro perspective, so that all parking lots in the area can be rationally planned and applicable High sex.
  • the embodiments of the present application also provide a computer-readable storage medium that stores a computer program and is executed by a processor to implement the method provided in each step in FIG. 1 and/or FIG. 3.
  • a processor to implement the method provided in each step in FIG. 1 and/or FIG. 3.
  • the foregoing computer-readable storage medium may be an internal storage unit of the task processing apparatus provided in any of the foregoing embodiments, such as a hard disk or memory of an electronic device.
  • the computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart media card (SMC), or a secure digital (SD) card equipped on the electronic device. Flash card, etc.
  • the aforementioned computer-readable storage medium may also include magnetic disks, optical disks, read-only memory (ROM) or random access memory (RAM), etc.
  • the computer-readable storage medium may also include both an internal storage unit of the electronic device and an external storage device.
  • the computer-readable storage medium is used to store the computer program and other programs and data required by the electronic device.
  • the computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Tourism & Hospitality (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Data Mining & Analysis (AREA)
  • Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • General Health & Medical Sciences (AREA)
  • Finance (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Traffic Control Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本申请实施例公开了一种停车场服务区域的确定方法、装置、设备以及存储介质，该方法包括：根据第一停车场集合中每个第一停车场的初始权重和初始位置信息，对所有第一停车场进行聚类得到至少一个第二停车场集合；根据初始权重和初始位置信息确定每个第二停车场集合中每个第二停车场对应的转移概率矩阵，一个转移概率矩阵中的一个转移概率用于说明，停车用户在一个第二停车场无空车位时转移至同一第二停车场集合中的另一第二停车场的概率；根据初始权重和转移概率矩阵确定每个第二停车场的服务能力值；根据初始位置信息和服务能力值确定每个第二停车场的服务区域。采用本申请实施例，可提升确定停车场服务区域的效率和准确性，适用性高。

Description

停车场服务区域的确定方法、装置、设备以及存储介质 技术领域
本申请涉及计算机技术领域，尤其涉及一种停车场服务区域的确定方法、装置、设备以及存储介质。
背景技术
随着小型载客汽车和私家车保有量的快速上升，现有的停车设施愈发难以满足日益增长的停车需求。在大城市中心区域，停车用户通常需要徘徊搜寻空车位，这在增加交通流量的同时也容易导致交通拥堵，甚至引发交通事故。为减少停车用户花搜寻停车场的时间，现有技术一般通过Voronoi图将量化的停车场服务能力映射到地理空间上，形成的大小不一的互斥区域。因为覆盖结果包含了停车场之间的地理信息关系，所以可以直观地呈现各个停车场的服务区域。
但是现有的Voronoi图确定出的服务区域的确定过程较为复杂，并且在没有边界限制的情况下，一些服务能力较强的停车场的，可以任意扩大服务区域并最终包围其他停车场，导致停车场服务区域并不准确，适用性差。因此如何提升确定停车场服务区域的效率和准确性成为亟需解决的问题。
发明内容
本申请实施例提供一种停车场服务区域的确定方法、装置、设备以及存储介质，可提升确定停车场服务区域的效率和准确性，适用性高。
第一方面，本申请实施例提供一种停车场服务区域的确定方法，该方法包括：
根据第一停车场集合中每个第一停车场的初始权重和初始位置信息，对所有第一停车场进行聚类得到至少一个第二停车场集合；
根据上述初始权重和上述初始位置信息确定每个第二停车场集合中每个第二停车场对应的转移概率矩阵，一个转移概率矩阵中的一个转移概率用于说 明，停车用户在一个第二停车场无空车位时转移至同一第二停车场集合中的另一第二停车场的概率；
根据上述初始权重和上述转移概率矩阵确定上述每个第二停车场的服务能力值；
根据上述初始位置信息和上述服务能力值确定上述每个第二停车场的服务区域。
第二方面，本申请实施例提供了一种停车场服务区域的确定装置，该装置包括：
聚类模块，用于根据第一停车场集合中每个第一停车场的初始权重和初始位置信息，对所有第一停车场进行聚类得到至少一个第二停车场集合；
第一确定模块，用于根据上述初始权重和上述初始位置信息确定每个第二停车场集合中每个第二停车场对应的转移概率矩阵，一个转移概率矩阵中的一个转移概率用于说明，停车用户在一个第二停车场无空车位时转移至同一第二停车场集合中的另一第二停车场的概率；
第二确定模块，用于根据上述初始权重和上述转移概率矩阵确定上述每个第二停车场的服务能力值；
第三确定模块，用于根据上述初始位置信息和上述服务能力值确定上述每个第二停车场的服务区域。
第三方面，本申请实施例提供了一种设备，该设备包括处理器和存储器，该处理器和存储器相互连接。该存储器用于存储支持该终端设备执行上述第一方面和/或第一方面任一种可能的实现方式提供的方法的计算机程序，该计算机程序包括程序指令，该处理器被配置用于调用上述程序指令，执行本申请实施例所提供的方法。
第四方面，本申请实施例提供了一种计算机可读存储介质，该计算机可读存储介质存储有计算机程序，该计算机程序被处理器执行以实现本申请实施例所提供的方法。
在本申请实施例中，通过对第一停车场集合进行聚类得到至少一个第二停车场集合，进而同时确定每个第二停车场集合中每个第二停车场的服务区域，可提高确定服务区域的效率。另一方面，通过每个第二停车场的初始权重和初 始位置信息可确定同一第二停车场集合中每个第二停车场转移至其他第二停车场的概率，进而确定每个第二停车场集合在初始权重和初始位置信息影响下的转移概率矩阵，以体现第二停车场之间的相互作用关系。进一步地，通过初始权重和转移概率矩阵可准确确定每个第二停车场的服务能力值，进而约束每个第二停车场的服务区域边界，提升各个第二停车场服务区域之间的连通性，适用性高。
附图说明
为了更清楚地说明本申请实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1是本申请实施例提供的停车场服务区域的确定方法的流程示意图；
图2是本申请实施例提供的对所有第一停车场进行聚类的场景示意图；
图3是本申请实施例提供的确定第二停车场的服务区域方法的流程示意图；
图4是本申请实施例提供的确定三角形区域的场景示意图；
图5是本申请实施例提供的确定圆形区域的场景示意图；
图6是本申请实施例提供的确定服务区域的场景示意图；
图7是本申请实施例提供的停车场服务区域的确定装置的结构示意图；
图8是本申请实施例提供的设备的结构示意图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
请参见图1，图1是本申请实施例提供的停车场服务区域的确定方法的流程示意图。图1所示的停车场服务区域的确定方法可包括如下步骤S101至S104。
S101、根据第一停车场集合中每个第一停车场的初始权重和初始位置信息，对所有第一停车场进行聚类得到至少一个第二停车场集合。
在一些可行的实施方式中，第一停车场集合为需要确定所有停车场服务区域的某一区域范围内所有停车场构成的停车场集合，如一个城市行政区内的所有停车场构成的停车场集合，某商业区方圆一定范围(如5km)内所有停车场构成的停车场集合，具体可根据实际应用场景确定，在此不做限制。第一停车场集合中的每个停车场(为方便描述，以下简称每个第一停车场)的初始权重用于表示每个第一停车场的初始服务能力值。其中，每个第一停车场的初始服务能力值为每个第一停车场车位均为空，且不考虑与其他停车场因为距离关系、收费关系以及道路原因等因素影响时，该第一停车场对于停车用户的初始服务能力值。具体地，每个第一停车场的初始权重可从其停车用户范围、停车位数量以及停车费信息等方面进行确定。
其中，上述停车用户范围用于表示第一停车场的开放程度，如对于公园内的第一停车场来说，其面向于所有用户，因此公园内的第一停车场的开放程度较高。再例如，对于政府大楼内的第一停车场来说，其主要面向于政府职员，因此政府大楼内的第一停车场的开放程度较低。其中，每个第一停车场的开放程度可取值0至1，1表示开放程度最高，0表示开放程度最低，每个第一停车场的开放程度可基于实际应用场景确定，在此不做限制。
其中，上述停车位数量表示每个第一停车场包括空车位和在用停车位在内的所有停车位数量，即每个第一停车场所设立的所有停车位数量。
其中，上述停车费信息可以为停车用户停车首小时每个第一停车场收取的费用，也可以为停车用户停车一天每个第一停车场收取的费用，具体的根据实际应用场景确定，在此不做限制。
具体地，每个第一停车场的初始权重的量化方式为：
Figure PCTCN2020081441-appb-000001
即对于任一第一停车场来说，总停车位越多、开放程度越高、收费越低则表示该第一停车场的初始权重越大。其中，u i为停车场i的停车用户范围，v i为停车场i的停车位数量，w i为停车场i的停车费信息，P 1为第一停车场集合。其中，
Figure PCTCN2020081441-appb-000002
为第一停车场集合中所有停车场的总停车位数量，
Figure PCTCN2020081441-appb-000003
为第一停车场集合中所有第一停车场的总停车费信息，例如，当w i为停车用户停车首小时停车场i收取的费用，
Figure PCTCN2020081441-appb-000004
为第一停车场集合中所有第一停车场对停车用户停车首小时所收取的费用之和。
在一些可行的实施方式中，为了提升每个第一停车场的服务区域的确定效率，可在确定每个第一停车场的初始权重时，确定每个第一停车场的位置信息，以对第一停车场集合中的所有第一停车场进行聚类，从而在位置维度将第一停车场集合中的所有第一停车场划分为至少一个子停车场集合(为方便描述，以下简称第二停车场集合)。其中，每个第一停车场的位置信息可以为每个第一停车场的经纬度，以精确标记每个第一停车场的具体位置。
具体地，在对第一停车场集合中所有第一停车场进行聚类时，可采用改进的MeanShift算法实现。MeanShift聚类是通过将每个第一停车场迭代移动到高密度位置实现的。在迭代移动时以每个第一停车场的初始权重作为加权，使得初始权重较高的第一停车场移动距离少，并且初始权重高的第一停车场将成为每个聚类的中心。对于初始位置信息为[L 1,…,L n]，初始权重为
Figure PCTCN2020081441-appb-000005
的n个第一停车场来说，对n个第一停车场进行聚类可由下述公式进行描述：
Figure PCTCN2020081441-appb-000006
其中，L f表示每个第一停车场的移动位置，f表示移动次数。Shift函数定义了所有第一停车场的移动方式：
Figure PCTCN2020081441-appb-000007
其中，N n是停车场n的邻近停车场，N n＝{L n|d[L i,L j]≤d 1,j＝1,…,n,j≠i}，d 1为第一距离阈值。当每次移动的最大距离(欧式距离)足够小时，上述迭代过程停止，完成对所有第一停车场的聚类，即
Figure PCTCN2020081441-appb-000008
ε为第一距离阈值。
具体地，可对第一停车场集合中的所有第一停车场进行移动，并且每次同时移动所有的第一停车场。以第一停车场集合中的一个第一停车场为例，在对该第一停车场进行移动时，可先确定该第一停车场与其他第一停车场的距离(欧式距离)，并确定出与该第一停车场的距离小于第一距离阈值的第一停车场作为该第一停车场的邻近停车场。其中，上述第一距离阈值可根据第一停车场集合中各个第一停车场的初始位置信息确定，也可根据第一停车场集合中第一停车场的数量确定，具体可根据实际应用场景确定，在此不做限制。
进一步地，可确定该第一停车场所有邻近停车场的初始权重(初始服务能力值)之和，并根据该第一停车场在每次移动前的位置信息一并确定出该第一停车场在每次移动后的位置信息。基于上述实现方式，可在每次对所有第一停车场进行移动时确定出所有第一停车场在每次移动后的位置信息。其中，该第一停车场在每次移动时的邻近停车场为该第一停车场在每次移动时，距离该第一停车场的距离(欧式距离)小于第一距离阈值的第一停车场。即在每次移动所有第一停车场时，需重新根据该次移动时所有第一停车场的位置信息确定出每个第一停车场的邻近停车场。
进一步地，在每次移动所有第一停车场之后，可确定每个第一停车场每次移动后的位置信息距离上一次移动后的位置信息的移动距离(欧式距离)，当每次移动所有第一停车场中每个第一停车场的移动距离中，距离最长的移动距离小于第一距离阈值时，完成对第一停车场集合中所有第一停车场的聚类。此时第一停车场集合中可得到至少一个聚类区域，即初始权重较低的第一停车场移动至与其邻近的初始权重较高的第一停车场，在同一聚类的多个第一停车场即为一个聚类停车场集合(为方便描述，以下简称第二停车场集合)。也就是说，通过对第一停车场中所有第一停车场进行聚类可将所有第一停车场进行区域性划分，一个区域为一个第二停车场集合。参见图2，图2是本申请实施例提供的对所有第一停车场进行聚类的场景示意图。在图2中，每个点表示一个第一停车场，点的大小表示第一停车场的初始权重大小，点越大初始权重越大，点越小初始权重越小。通过上述改进的MeanShift算法对所有点进行聚类后，初始权重较小的点逐渐靠近与其邻近的初始权重较大的点，并最终形成三个聚类区域。其中，一个聚类局域中的所有点(第一停车场)属于同一第二停车场 集合，在将每一聚类中的第一停车场重新映射到其真实位置之后，可容易得到第一停车场集合包括三个第二停车场集合。
可选地，当某次移动所有第一停车场中每个第一停车场的移动距离中，距离最长的移动距离仍大于第一距离阈值时，则继续采用上述改进的MeanShift算法对当前移动后的所有第一停车场进行聚类，直至当某次移动所有第一停车场中每个第一停车场的移动距离中，距离最长的移动距离小于第一距离阈值时停止，在此不再赘述。
S102、根据初始权重和初始位置信息确定每个第二停车场集合中每个第二停车场对应的转移概率矩阵。
在一些可行的实施方式中，根据每个第二停车场集合中每个第二停车场的初始权重和初始位置信息可确定出每个第二停车场对应的转移概率矩阵。具体地，由于两个第二停车场距离较小时，停车场用户才可能从一个第二停车场转移至另一第二停车场，因此可确定出每个第二停车场集合中每个第二停车场与同一第二停车场集合中其他第二停车场的距离。进一步地，确定小于或者等于第二距离阈值的第一目标距离，根据第一目标距离对应的第二停车场的初始权重和每个停车场的空车位率，确定停车用户在每个第二停车场无空车位时，转移至每个第一目标距离对应的第二停车场的第一概率。确定大于第二距离阈值的第二目标距离，确定停车用户在每个第二停车场无空车位时，转移至每个第二目标距离对应的第二停车场的第二概率。
以一个第二停车场集合中的第二停车场j为例，如果第二停车场j到第二停车场i之间的欧式距离d ji小于或者等于第二距离阈值d 2时，则在第二停车场i和第二停车场j之间建立连接，并且连接权重为
Figure PCTCN2020081441-appb-000009
即：
Figure PCTCN2020081441-appb-000010
进一步地，第二停车场i的空车位率可以是第二停车场j的空车位率为q it，
Figure PCTCN2020081441-appb-000011
v i表示第二停车场i的总停车位数，v it表示第二停车场i在t时刻的可用停车位数，或者表示第二停车场在时间段t内的可用停车位数。
当停车用户发现第二停车场j的停车位已满时，停车用户前往第二停车场i的概率为
Figure PCTCN2020081441-appb-000012
若第二停车场j到第二停车场i之间的欧式距离d ji小于第二距离阈值d 2时，当停车用户发现第二停车场j的停车位已满时，停车用户前往第二停车场i的概率为0。进一步地，根据停车用户前往第二停车场i的概率
Figure PCTCN2020081441-appb-000013
可确定出第二停车场j所在的第二停车场集合(包含m个第二停车场)对应的转移概率矩阵S t：
Figure PCTCN2020081441-appb-000014
其中，转移概率矩阵S t中的任一元素表示停车用户在一个第二停车场无空车位时转移至同一第二停车场集合中另一第二停车场的概率。
S103、根据初始权重和转移概率矩阵确定每个第二停车场的服务能力值。
在一些可行的实施方式中，在确定每个第二停车场的服务能力值时，可将每个第二停车场集合所有第二停车场的初始权重构建为每个第二停车场集合对应的初始向量。同样以一个第二停车场集合为例，可将该第二停车场集合中所有第二停车场的初始权重构建为一个列向量PR t(即该第二停车场的初始向量)。其中，列向量PR t中的一个元素表示一个第二停车场的初始权重。
进一步地，将列向量PR t与同一第二停车场集合对应的转移概率矩阵S t进行迭代，即
Figure PCTCN2020081441-appb-000015
其中，r表示迭代次数，当迭代次数为0时，
Figure PCTCN2020081441-appb-000016
为上述列向量PR t。不难得到，将列向量PR t与同一第二停车场集合对应的转移概率矩阵S t相乘得到一次迭代值
Figure PCTCN2020081441-appb-000017
进一步将一次迭代值
Figure PCTCN2020081441-appb-000018
与同一第二停车场集合对应的转移概率矩阵S t相乘得到一次迭代值
Figure PCTCN2020081441-appb-000019
以此类推，直至
Figure PCTCN2020081441-appb-000020
其中，θ为预设收敛阈值，即当
Figure PCTCN2020081441-appb-000021
达到收敛时迭代结束。假 设得到的最终迭代值为
Figure PCTCN2020081441-appb-000022
则
Figure PCTCN2020081441-appb-000023
中的一个元素表示一个第二停车场的服务能力值。
基于相同的实现方式，可分别确定每个第二停车场集合对应的最终迭代值，以根据每个第二停车场集合对应的最终迭代值确定出每个第二停车场集合中每个第停车场的服务能力值。其中，当转移概率矩阵S t是基于每个第二停车场在t时刻的空车位率确定，即转移概率矩阵S t中的任一元素表示停车用户在一个第二停车场在t时刻无空车位时转移至同一第二停车场集合中另一第二停车场的概率时，
Figure PCTCN2020081441-appb-000024
中的一个元素表示一个第二停车场在t时刻的服务能力值，一个第二停车场的服务能力值随时间变化。当转移概率矩阵S t是基于每个第二停车场在时间段t内的空车位率确定，即转移概率矩阵S t中的任一元素表示停车用户在一个第二停车场时间段t内无空车位时转移至同一第二停车场集合中另一第二停车场的概率时，
Figure PCTCN2020081441-appb-000025
中的一个元素表示一个第二停车场时间段t内的服务能力值。
S104、根据初始位置信息和服务能力值确定每个第二停车场的服务区域。
在一些可行的实施方式中，每个第二停车场的服务区域由每个第二停车场对应的三角形区域(Delaunay三角形)和圆形区域(Apolloniu圆)确定，具体可参见图3。图3是本申请实施例提供的确定第二停车场的服务区域方法的流程示意图。图3所示的确定第二停车场的服务区域的方法可包括如下步骤S1041至S1043。
S1041、确定每个第二停车场对应的三角形区域。
在一些可行的实施方式中，每个第二停车场对应的三角形区域由每个第二停车场和同一第二停车场集合中的两个第二停车场(为方便描述，以下简称两个目标第二停车场)的初始位置信息确定。其中，每个第二停车场对应的三角形区域(Delaunay三角形)的外接圆区域中不包含除构成该三角形区域的三个第二停车场的其他停车场。具体地，以一个第二停车场集合为例，可任意选取该第二停车场集合中的三个第二停车场的初始位置信息构成一个候选三角形区域，并确定该候选三角形区域对应的外接圆区域。进一步地，依次确定上述三个第二停车场外的其他停车场是否在上述外接圆区域内，如果上述三个第二停车场外的其他停车场不在上述外接圆区域内，则说明上述候选三角形区域为 该第二停车场集合中的一个三角形区域。以此类推，直至遍历完该第二停车场集合中所有第二停车场所有的候选三角形区域，以确定出该第二停车场集合中所有的三角形区域。并且，该第二停车场集合中每个第二停车场均对应至少一个三角形区域，即每个第二停车场为至少一个三角形区域的定点。
举例来说，存在第二停车场集合Q＝{(q ix,q iy)|i＝1...6}，其包含6个第二停车场，此时第二停车场集合Q中存在10个候选三角形区域，其中(q ix,q iy)表示第二停车场的初始位置信息。参见图4，图4是本申请实施例提供的确定三角形区域的场景示意图。图4任选三个第二停车场q 1(q 1x,q 1y)、q 2(q 2x,q 2y)以及q 3(q 3x,q 3y)，其构成候选三角形区域的外接圆区域为：
Figure PCTCN2020081441-appb-000026
其中，
Figure PCTCN2020081441-appb-000027
Figure PCTCN2020081441-appb-000028
对于除第二停车场q 1(q 1x,q 1y)、q 2(q 2x,q 2y)以及q 3(q 3x,q 3y)外的第二停车场q 4(q 4x,q 4y)，可将第二停车场q 4(q 4x,q 4y)的初始位置信息代入上述外接圆区域C 123(x,y)中，即令x＝p 4x，y＝p 4y。当C 123(q 4x,q 4y)小于0时，可如图4中所示第二停车场q 4(q 4x,q 4y)位于外接圆区域C 123(x,y)内，也就是说此时第二停车场q 1(q 1x,q 1y)、q 2(q 2x,q 2y)以及q 3(q 3x,q 3y)构成的候选三角形区域，即候选三角形区域不是第二停车场q 1(q 1x,q 1y)、q 2(q 2x,q 2y)以及q 3(q 3x,q 3y)任一第二停车场对应的三角形区域。假设C 123(q 4x,q 4y)大于0时，可基于上述实现方式逐一验证第二停车场q 5(q 5x,q 5y)和第二停车场q 6(q 6x,q 6y)是否位于内，并且当第二停车场q 1(q 1x,q 1y)、q 5(q 5x,q 5y)以及q 6(q 6x,q 6y)均位于外接圆区域C 123(x,y)外时，可确定候选三角形区域为第二停车场q 1(q 1x,q 1y)、q 2(q 2x,q 2y)以及q 3(q 3x,q 3y)对应的三角形区域DT＝{q 1,q 2,q 3)}。
S1042、确定每个第二停车场对应的圆形区域。
在一些可行的实施方式中，除确定每个第二停车场对应的三角形区域之外， 还需要确定每个第二停车场对应的圆形区域(Apolloniu圆)。其中，每个第二停车场对应的圆形区域由每个第二停车场和上述两个目标第二停车场中的一个目标第二停车场的初始位置信息和t时刻的服务能力值确定，上述两个目标第二停车场为与每个第二停车场构成一个三角形区域的其他两个第二停车场。进一步地，根据每个第二停车场和两个目标第二停车场中的一个目标第二停车场的初始位置信息和t时刻的服务能力值确定出圆形区域的半径和圆心。进而根据半径和圆心确定出圆形区域以确定每个第二停车场对应的所有圆形区域，其中，一个圆形区域的边界上的任一位置距离每个第二停车场的距离，与距离一个目标第二停车场的距离之比为常数，并且每个第二停车场位于一个圆形区域内。
假设步骤S1042中的第二停车场q 1(q 1x,q 1y)、q 2(q 2x,q 2y)以及q 3(q 3x,q 3y)构成一个三角形区域DT＝{q 1,q 2,q 3)}。当需要确定第二停车场q 1(q 1x,q 1y)的服务区域时，可确定第二停车场q 1(q 1x,q 1y)对应的圆形区域。其中，第二停车场q 1(q 1x,q 1y)与第二停车场q 2(q 2x,q 2y)构成一个圆形区域AC(q 1,q 2)，与第二停车场q 3(q 3x,q 3y)构成一个圆形区域AC(q 1,q 3)。
其中，圆形区域AC(p 1,p 2)的圆心为
Figure PCTCN2020081441-appb-000029
半径为
Figure PCTCN2020081441-appb-000030
d 12为第二停车场q 1(q 1x,q 1y)至第二停车场q 2(q 2x,q 2y)的欧式距离。其中，w 1＝PR 1/PR 2，PR 1为第二停车场q 1(q 1x,q 1y)的t时刻的服务能力值，PR 2为第二停车场q 2(q 2x,q 2y)的服务能力值。即圆形区域AC(q 1,q 2)边界上任意一位置到第二停车场q 1(q 1x,q 1y)和第二停车场q 2(q 2x,q 2y)的欧式距离之比为常数。如图5所示，图5是本申请实施例提供的确定圆形区域的场景示意图。在图5中的三角形区域由第二停车场q 1(q 1x,q 1y)、q 2(q 2x,q 2y)以及q 3(q 3x,q 3y)，在基于该三角形区域DT＝{q 1,q 2,q 3)}中的第二停车场q 2(q 2x,q 2y)确定第二停车场q 1(q 1x,q 1y)的圆形区域时，可确定出第二停车场q 1(q 1x,q 1y)对应的两个候选圆形区域，由于在确定第二停车场q 1(q 1x,q 1y)的服务区域时，第二停车场q 1(q 1x,q 1y)需位于圆形区域内，此时可将包含第二停车场q 1(q 1x,q 1y)一侧的候选圆形区域确定为第二停车场q 1(q 1x,q 1y)的圆形区域AC(q 1,q 2)。
同理，圆形区域AC(p 1,p 3)的圆心为
Figure PCTCN2020081441-appb-000031
半径为
Figure PCTCN2020081441-appb-000032
d 13为第二停车场q 1(q 1x,q 1y)至第二停车场q 3(q 3x,q 3y)的欧式距离。其中，w 2＝PR 1/PR 3，PR 1为第二停车场q 1(q 1x,q 1y)的t时刻的服务能力值，PR 3为第二停车场q 3(q 3x,q 3y)的服务能力值。即圆形区域AC(q 1,q 3)边界上任意一位置到第二停车场q 1(q 1x,q 1y)和第二停车场q 3(q 3x,q 3y)的欧式距离之比为常数。基于上述实现方式可确定出第二停车场q 1(q 1x,q 1y)对应的两个圆形区域，由于在确定第二停车场q 1(q 1x,q 1y)的服务区域时，第二停车场q 1(q 1x,q 1y)需位于圆形区域内，因此可将包含第二停车场q 1(q 1x,q 1y)的圆心区域确定为第二停车场q 1(q 1x,q 1y)的圆形区域AC(q 1,q 3)。
S1043、将每个第二停车场对应的圆形区域和三角形区域的交集区域确定为每个第二停车场的服务区域。
在一些可行的实施方式中，在一个第二停车场集合中，每个第二停车场可对应有至少一个三角形区域和至少两个圆形区域，因此对应每个第二停车场而言，每个第二停车场对应的服务区域为上述至少一个三角形区域和至少两个圆形区域的交集区域。其中，每个第二停车场的服务区域表示该停车场在停车功能和地理位置方面的覆盖区域。参见图6，图6是本申请实施例提供的确定服务区域的场景示意图。图6中所示的三角形区域为第二停车场q 1(q 1x,q 1y)、q 2(q 2x,q 2y)以及q 3(q 3x,q 3y)构成的三角形区域DT＝{q 1,q 2,q 3)}，且第二停车场q 1(q 1x,q 1y)仅对应三角形区域DT＝{q 1,q 2,q 3)}，第二停车场q 1(q 1x,q 1y)的圆形区域只有AC(q 1,q 3)和AC(q 1,q 2)。此时不难得到第二停车场q 1(q 1x,q 1y)的服务区域为：
Poly(q 1)＝{(x,y)|(x,y)∈AC(q 1,q 2)∩AC(q 1,q 3)∩DT(q 1,q 2,q 3)}。
基于上述方式不难得到每个第二停车场集合中每个第二停车场的服务区域。当每个第二停车场的服务能力值为t时刻的服务能力值时，每个第二停车场的三角形区域以及圆形区域均为每个第二停车场在t时刻的三角形区域和圆形区域。也就是说此时确定出的每个第二停车场的服务区域为其在t时刻的服务区域，并且随着时间不断进行变化，进而可实时确定每个第二停车场在不同时刻的服务区域。当每个第二停车场的服务能力值为时间段t内的服务能力值时，每个第二停车场的三角形区域以及圆形区域均为每个第二停车场在时间段 t内的三角形区域和圆形区域。也就是说此时确定出的每个第二停车场的服务区域为其在时间段t内的服务区域，进而可在一定时间内衡量每个第二停车场的服务区域。
在本申请实施例中，通过对第一停车场集合进行聚类得到至少一个第二停车场集合，进而同时确定每个第二停车场集合中每个第二停车场的服务区域，可提高确定服务区域的效率。另一方面，通过初始权重和转移概率矩阵可准确确定每个第二停车场的服务能力值，进而约束每个第二停车场的服务区域边界，提升各个第二停车场服务区域之间的连通性。进一步地，可确定每个第二停车场在不同时刻的服务区域，以确定每个第二停车场服务区域的变化趋势，从而对于停车用户可在不同时间选择合适(服务区域较大)的停车场，对于停车场管理用户可在不同时间制定不同的停车场管理策略。同时，还可确定每个第二停车场在一定时间段内的服务区域，以从宏观角度衡量某一区域内所有停车场的服务区域，从而可对该区域内所有停车场进行合理规划，适用性高。
参见图7，图7是本申请实施例提供的停车场服务区域的确定装置的结构示意图。本申请实施例提供的装置1包括：
聚类模块11，用于根据第一停车场集合中每个第一停车场的初始权重和初始位置信息，对所有第一停车场进行聚类得到至少一个第二停车场集合；
第一确定模块12，用于根据上述初始权重和上述初始位置信息确定每个第二停车场集合中每个第二停车场对应的转移概率矩阵，一个转移概率矩阵中的一个转移概率用于说明，停车用户在一个第二停车场无空车位时转移至同一第二停车场集合中的另一第二停车场的概率；
第二确定模块13，用于根据上述初始权重和上述转移概率矩阵确定上述每个第二停车场的服务能力值；
第三确定模块14，用于根据上述初始位置信息和上述服务能力值确定上述每个第二停车场的服务区域。
在一些可行的实施方式中，上述装置1还包括第四确定模块15，上述第四确定模块15还用于：
获取第一停车场集合中每个第一停车场的停车用户范围、停车位数量以及停车费信息；
确定所有第一停车场的总停车位数量和总停车费信息；
根据上述停车用户范围、上述停车位数量、上述停车费信息、上述总停车位数量以及上述总停车费信息，确定上述第一停车场集合中每个停车场的初始权重。
在一些可行的实施方式中，上述聚类模块11用于：
确定所有第一停车场每次移动后的位置信息，其中，上述每个第一停车场进行移动时，其他第一停车场同时进行移动，上述每个第一停车场每次移动后的位置信息由上述每个第一停车场在每次移动前，上述每个第一停车场的位置信息和所有邻近停车场的初始权重确定，上述邻近停车场为上述每个第一停车场在每次移动前，距离上述每个第一停车场的距离小于第一距离阈值的第一停车场，
根据上述所有第一停车场每次移动后的位置信息，确定上述每个第一停车场每次移动后的位置信息距离上一次移动后的位置信息的移动距离；
当目标移动距离小于上述第一距离阈值时，上述所有第一停车场停止移动，并根据上述每个第一停车场停止移动时的位置信息确定出至少一个第二停车场集合，上述目标移动距离为上述每个第一停车场每次移动后的位置信息距离上一次移动后的位置信息的移动距离中的最长距离。
在一些可行的实施方式中，上述第一确定模块12用于：
根据上述初始位置信息，确定每个第二停车场集合中每个第二停车场与同一第二停车场集合中其他第二停车场的距离；
确定小于或者等于第二距离阈值的第一目标距离，根据上述第一目标距离对应的第二停车场的初始权重和上述每个停车场的空车位率，确定停车用户在上述每个第二停车场无空车位时，转移至上述每个第一目标距离对应的第二停车场的第一概率；
确定大于上述第二距离阈值的第二目标距离，确定上述停车用户在上述每个第二停车场无空车位时，转移至上述每个第二目标距离对应的第二停车场的第二概率；
根据上述第一概率和上述第二概率确定上述每个第二停车场集合对应的转移概率矩阵，一个第二停车场集合对应的转移概率矩阵包含上述一个第二停车场集合中所有第二停车场转移至其他第二停车场的概率。
在一些可行的实施方式中，上述第二确定模块13用于：
确定上述每个第二停车场集合对应的初始向量，上述服务能力向量包含上述每个第二停车场集合中所有第二停车场的初始权重；
将上述每个第二停车场集合对应的服务能力向量和相对应的转移概率矩阵相乘，得到上述每个第二停车场集合对应的一次迭代值；
将上述一次迭代值与上述相对应的转移概率矩阵相乘得到上述每个第二停车场集合对应的二次迭代值，直至得到目标迭代值，其中，上述目标迭代值的上一次迭代值与上述目标迭代值之差小于预设收敛阈值时；
根据上述目标迭代值确定出上述每个第二停车场的服务能力值。
在一些可行的实施方式中，上述第三确定模块14用于：
确定上述每个第二停车场对应的三角形区域，一个三角形区域由上述每个第二停车场和上述同一第二停车场集合中的两个目标第二停车场的初始位置信息确定，上述一个三角形区域的外接圆区域中不包含其他第二停车场；
确定上述每个第二停车场对应的圆形区域，一个圆形区域由上述每个第二停车场和上述两个目标第二停车场中的一个目标第二停车场的初始位置信息和服务能力值确定；
将上述每个第二停车场对应的圆形区域和三角形区域的交集区域确定为上述每个第二停车场的服务区域。
在一些可行的实施方式中，上述第三确定模块14用于：
根据上述每个第二停车场和上述两个目标第二停车场中的一个目标第二停车场的初始位置信息和服务能力值确定出圆形区域的半径和圆心，
根据上述半径和上述圆心确定出上述圆形区域以确定上述每个第二停车场对应的所有圆形区域，其中，上述一个圆形区域的边界上的任一位置距离上述每个第二停车场的距离，与距离上述一个目标第二停车场的距离之比为常数，并且上述每个第二停车场位于上述圆形区域内。
具体实现中，上述装置1可通过其内置的各个功能模块执行如上述图1 和/或图3中各个步骤所提供的实现方式，具体可参见上述各个步骤所提供的实现方式，在此不再赘述。
在本申请实施例中，通过对第一停车场集合进行聚类得到至少一个第二停车场集合，进而同时确定每个第二停车场集合中每个第二停车场的服务区域，可提高确定服务区域的效率。另一方面，通过初始权重和转移概率矩阵可准确确定每个第二停车场的服务能力值，进而约束每个第二停车场的服务区域边界，提升各个第二停车场服务区域之间的连通性。进一步地，可确定每个第二停车场在不同时刻的服务区域，以确定每个第二停车场服务区域的变化趋势，从而对于停车用户可在不同时间选择合适(服务区域较大)的停车场，对于停车场管理用户可在不同时间制定不同的停车场管理策略。同时，还可确定每个第二停车场在一定时间段内的服务区域，以从宏观角度衡量某一区域内所有停车场的服务区域，从而可对该区域内所有停车场进行合理规划，适用性高。
参见图8，图8是本申请实施例提供的设备的结构示意图。如图8所示，本实施例中的设备1000可以包括：处理器1001，网络接口1004和存储器1005，此外，上述设备1000还可以包括：用户接口1003，和至少一个通信总线1002。其中，通信总线1002用于实现这些组件之间的连接通信。其中，用户接口1003可以包括显示屏(Display)、键盘(Keyboard)，可选用户接口1003还可以包括标准的有线接口、无线接口。网络接口1004可选的可以包括标准的有线接口、无线接口(如WI-FI接口)。存储器1004可以是高速RAM存储器，也可以是非不稳定的存储器(non-volatile memory)，例如至少一个磁盘存储器。存储器1005可选的还可以是至少一个位于远离前述处理器1001的存储装置。如图8所示，作为一种计算机可读存储介质的存储器1005中可以包括操作系统、网络通信模块、用户接口模块以及设备控制应用程序。
在图8所示的设备1000中，网络接口1004可提供网络通讯功能；而用户接口1003主要用于为用户提供输入的接口；而处理器1001可以用于调用存储器1005中存储的设备控制应用程序，以实现：
根据第一停车场集合中每个第一停车场的初始权重和初始位置信息，对所有第一停车场进行聚类得到至少一个第二停车场集合；
根据上述初始权重和上述初始位置信息确定每个第二停车场集合中每个第二停车场对应的转移概率矩阵，一个转移概率矩阵中的一个转移概率用于说明，停车用户在一个第二停车场无空车位时转移至同一第二停车场集合中的另一第二停车场的概率；
根据上述初始权重和上述转移概率矩阵确定上述每个第二停车场的服务能力值；
根据上述初始位置信息和上述服务能力值确定上述每个第二停车场的服务区域。
在一些可行的实施方式中，上述处理器1001还用于：
获取第一停车场集合中每个第一停车场的停车用户范围、停车位数量以及停车费信息；
确定所有第一停车场的总停车位数量和总停车费信息；
根据上述停车用户范围、上述停车位数量、上述停车费信息、上述总停车位数量以及上述总停车费信息，确定上述第一停车场集合中每个停车场的初始权重。
在一些可行的实施方式中，上述处理器1001用于：
确定所有第一停车场每次移动后的位置信息，其中，上述每个第一停车场进行移动时，其他第一停车场同时进行移动，上述每个第一停车场每次移动后的位置信息由上述每个第一停车场在每次移动前，上述每个第一停车场的位置信息和所有邻近停车场的初始权重确定，上述邻近停车场为上述每个第一停车场在每次移动前，距离上述每个第一停车场的距离小于第一距离阈值的第一停车场，
根据上述所有第一停车场每次移动后的位置信息，确定上述每个第一停车场每次移动后的位置信息距离上一次移动后的位置信息的移动距离；
当目标移动距离小于上述第一距离阈值时，上述所有第一停车场停止移动，并根据上述每个第一停车场停止移动时的位置信息确定出至少一个第二停车场集合，上述目标移动距离为上述每个第一停车场每次移动后的位置信息距离上一次移动后的位置信息的移动距离中的最长距离。
在一些可行的实施方式中，上述处理器1001用于：
根据上述初始位置信息，确定每个第二停车场集合中每个第二停车场与同一第二停车场集合中其他第二停车场的距离；
确定小于或者等于第二距离阈值的第一目标距离，根据上述第一目标距离对应的第二停车场的初始权重和上述每个停车场的空车位率，确定停车用户在上述每个第二停车场无空车位时，转移至上述每个第一目标距离对应的第二停车场的第一概率；
确定大于上述第二距离阈值的第二目标距离，确定上述停车用户在上述每个第二停车场无空车位时，转移至上述每个第二目标距离对应的第二停车场的第二概率；
根据上述第一概率和上述第二概率确定上述每个第二停车场集合对应的转移概率矩阵，一个第二停车场集合对应的转移概率矩阵包含上述一个第二停车场集合中所有第二停车场转移至其他第二停车场的概率。
在一些可行的实施方式中，上述处理器1001用于：
确定上述每个第二停车场集合对应的初始向量，上述服务能力向量包含上述每个第二停车场集合中所有第二停车场的初始权重；
将上述每个第二停车场集合对应的服务能力向量和相对应的转移概率矩阵相乘，得到上述每个第二停车场集合对应的一次迭代值；
将上述一次迭代值与上述相对应的转移概率矩阵相乘得到上述每个第二停车场集合对应的二次迭代值，直至得到目标迭代值，其中，上述目标迭代值的上一次迭代值与上述目标迭代值之差小于预设收敛阈值时；
根据上述目标迭代值确定出上述每个第二停车场的服务能力值。
在一些可行的实施方式中，上述处理器1001用于：
确定上述每个第二停车场对应的三角形区域，一个三角形区域由上述每个第二停车场和上述同一第二停车场集合中的两个目标第二停车场的初始位置信息确定，上述一个三角形区域的外接圆区域中不包含其他第二停车场；
确定上述每个第二停车场对应的圆形区域，一个圆形区域由上述每个第二停车场和上述两个目标第二停车场中的一个目标第二停车场的初始位置信息和服务能力值确定；
将上述每个第二停车场对应的圆形区域和三角形区域的交集区域确定为 上述每个第二停车场的服务区域。
在一些可行的实施方式中，上述处理器1001用于：
根据上述每个第二停车场和上述两个目标第二停车场中的一个目标第二停车场的初始位置信息和服务能力值确定出圆形区域的半径和圆心，
根据上述半径和上述圆心确定出上述圆形区域以确定上述每个第二停车场对应的所有圆形区域，其中，上述一个圆形区域的边界上的任一位置距离上述每个第二停车场的距离，与距离上述一个目标第二停车场的距离之比为常数，并且上述每个第二停车场位于上述圆形区域内。
应当理解，在一些可行的实施方式中，上述处理器1001可以是中央处理单元(central processing unit，CPU)，该处理器还可以是其他通用处理器、数字信号处理器(digital signal processor，DSP)、专用集成电路(application specific integrated circuit，ASIC)、现成可编程门阵列(field-programmable gate array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。该存储器可以包括只读存储器和随机存取存储器，并向处理器提供指令和数据。存储器的一部分还可以包括非易失性随机存取存储器。例如，存储器还可以存储设备类型的信息。
具体实现中，上述设备1000可通过其内置的各个功能模块执行如上述图1和/或图3中各个步骤所提供的实现方式，具体可参见上述各个步骤所提供的实现方式，在此不再赘述。
在本申请实施例中，通过对第一停车场集合进行聚类得到至少一个第二停车场集合，进而同时确定每个第二停车场集合中每个第二停车场的服务区域，可提高确定服务区域的效率。另一方面，通过初始权重和转移概率矩阵可准确确定每个第二停车场的服务能力值，进而约束每个第二停车场的服务区域边界，提升各个第二停车场服务区域之间的连通性。进一步地，可确定每个第二停车场在不同时刻的服务区域，以确定每个第二停车场服务区域的变化趋势，从而对于停车用户可在不同时间选择合适(服务区域较大)的停车场，对于停车场管理用户可在不同时间制定不同的停车场管理策略。同时，还可确定每个第二停车场在一定时间段内的服务区域，以从宏观角度衡量某一区域内所有停车场 的服务区域，从而可对该区域内所有停车场进行合理规划，适用性高。
本申请实施例还提供一种计算机可读存储介质，该计算机可读存储介质存储有计算机程序，被处理器执行以实现图1和/或图3中各个步骤所提供的方法，具体可参见上述各个步骤所提供的实现方式，在此不再赘述。
上述计算机可读存储介质可以是前述任一实施例提供的任务处理装置的内部存储单元，例如电子设备的硬盘或内存。该计算机可读存储介质也可以是该电子设备的外部存储设备，例如该电子设备上配备的插接式硬盘，智能存储卡(smart media card,SMC)，安全数字(secure digital,SD)卡，闪存卡(flash card)等。上述计算机可读存储介质还可以包括磁碟、光盘、只读存储记忆体(read-only memory，ROM)或随机存储记忆体(randomaccess memory，RAM)等。进一步地，该计算机可读存储介质还可以既包括该电子设备的内部存储单元也包括外部存储设备。该计算机可读存储介质用于存储该计算机程序以及该电子设备所需的其他程序和数据。该计算机可读存储介质还可以用于暂时地存储已经输出或者将要输出的数据。
本申请的权利要求书和说明书及附图中的术语“第一”、“第二”等是用于区别不同对象，而不是用于描述特定顺序。此外，术语“包括”和“具有”以及它们任何变形，意图在于覆盖不排他的包含。例如包含了一系列步骤或单元的过程、方法、系统、产品或设备没有限定于已列出的步骤或单元，而是可选地还包括没有列出的步骤或单元，或可选地还包括对于这些过程、方法、产品或设备固有的其它步骤或单元。在本文中提及“实施例”意味着，结合实施例描述的特定特征、结构或特性可以包含在本申请的至少一个实施例中。在说明书中的各个位置展示该短语并不一定均是指相同的实施例，也不是与其它实施例互斥的独立的或备选的实施例。本领域技术人员显式地和隐式地理解的是，本文所描述的实施例可以与其它实施例相结合。在本申请说明书和所附权利要求书中使用的术语“和/或”是指相关联列出的项中的一个或多个的任何组合以及所有可能组合，并且包括这些组合。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、计算机软件或者二者的结合来实现，为了清楚地说明硬件和软件的可互换性，在上述说明中已经按照功能一般性地 描述了各示例的组成及步骤。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
以上所揭露的仅为本申请较佳实施例而已，当然不能以此来限定本申请之权利范围，因此依本申请权利要求所作的等同变化，仍属本申请所涵盖的范围。

Claims (16)

  1. 一种停车场服务区域的确定方法，其特征在于，所述方法包括：
    根据第一停车场集合中每个第一停车场的初始权重和初始位置信息，对所有第一停车场进行聚类得到至少一个第二停车场集合；
    根据所述初始权重和所述初始位置信息确定每个第二停车场集合中每个第二停车场对应的转移概率矩阵，一个转移概率矩阵中的一个转移概率用于说明，停车用户在一个第二停车场无空车位时转移至同一第二停车场集合中的另一第二停车场的概率；
    根据所述初始权重和所述转移概率矩阵确定所述每个第二停车场的服务能力值；
    根据所述初始位置信息和所述服务能力值确定所述每个第二停车场的服务区域。
  2. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    获取第一停车场集合中每个第一停车场的停车用户范围、停车位数量以及停车费信息；
    确定所有第一停车场的总停车位数量和总停车费信息；
    根据所述停车用户范围、所述停车位数量、所述停车费信息、所述总停车位数量以及所述总停车费信息，确定所述第一停车场集合中每个停车场的初始权重。
  3. 根据权利要求1所述的方法，其特征在于，所述对所有第一停车场进行聚类得到至少一个第二停车场集合包括：
    确定所有第一停车场每次移动后的位置信息，其中，所述每个第一停车场进行移动时，其他第一停车场同时进行移动，所述每个第一停车场每次移动后的位置信息由所述每个第一停车场在每次移动前，所述每个第一停车场的位置信息和所有邻近停车场的初始权重确定，所述邻近停车场为所述每个第一停车 场在每次移动前，距离所述每个第一停车场的距离小于第一距离阈值的第一停车场，
    根据所述所有第一停车场每次移动后的位置信息，确定所述每个第一停车场每次移动后的位置信息距离上一次移动后的位置信息的移动距离；
    当目标移动距离小于所述第一距离阈值时，所述所有第一停车场停止移动，并根据所述每个第一停车场停止移动时的位置信息确定出至少一个第二停车场集合，所述目标移动距离为所述每个第一停车场每次移动后的位置信息距离上一次移动后的位置信息的移动距离中的最长距离。
  4. 根据权利要求1所述的方法，其特征在于，所述根据所述初始权重和所述初始位置信息确定每个第二停车场集合中每个第二停车场对应的转移概率矩阵包括：
    根据所述初始位置信息，确定每个第二停车场集合中每个第二停车场与同一第二停车场集合中其他第二停车场的距离；
    确定小于或者等于第二距离阈值的第一目标距离，根据所述第一目标距离对应的第二停车场的初始权重和所述每个停车场的空车位率，确定停车用户在所述每个第二停车场无空车位时，转移至所述每个第一目标距离对应的第二停车场的第一概率；
    确定大于所述第二距离阈值的第二目标距离，确定所述停车用户在所述每个第二停车场无空车位时，转移至所述每个第二目标距离对应的第二停车场的第二概率；
    根据所述第一概率和所述第二概率确定所述每个第二停车场集合对应的转移概率矩阵，一个第二停车场集合对应的转移概率矩阵包含所述一个第二停车场集合中所有第二停车场转移至其他第二停车场的概率。
  5. 根据权利要求1所述方法，其特征在于，所述根据所述转移概率矩阵确定所述每个第二停车场的服务能力值包括：
    确定所述每个第二停车场集合对应的初始向量，所述服务能力向量包含所述每个第二停车场集合中所有第二停车场的初始权重；
    将所述每个第二停车场集合对应的服务能力向量和相对应的转移概率矩阵相乘，得到所述每个第二停车场集合对应的一次迭代值；
    将所述一次迭代值与所述相对应的转移概率矩阵相乘得到所述每个第二停车场集合对应的二次迭代值，直至得到目标迭代值，其中，所述目标迭代值的上一次迭代值与所述目标迭代值之差小于预设收敛阈值时；
    根据所述目标迭代值确定出所述每个第二停车场的服务能力值。
  6. 根据权利要求1所述的方法，其特征在于，所述根据所述初始位置信息和所述服务能力值确定所述每个第二停车场的服务区域包括：
    确定所述每个第二停车场对应的三角形区域，一个三角形区域由所述每个第二停车场和所述同一第二停车场集合中的两个目标第二停车场的初始位置信息确定，所述一个三角形区域的外接圆区域中不包含其他第二停车场；
    确定所述每个第二停车场对应的圆形区域，一个圆形区域由所述每个第二停车场和所述两个目标第二停车场中的一个目标第二停车场的初始位置信息和服务能力值确定；
    将所述每个第二停车场对应的圆形区域和三角形区域的交集区域确定为所述每个第二停车场的服务区域。
  7. 根据权利要求6所述的方法，其特征在于，所述确定所述每个第二停车场对应的圆形区域包括：
    根据所述每个第二停车场和所述两个目标第二停车场中的一个目标第二停车场的初始位置信息和服务能力值确定出圆形区域的半径和圆心，
    根据所述半径和所述圆心确定出所述圆形区域以确定所述每个第二停车场对应的所有圆形区域，其中，所述一个圆形区域的边界上的任一位置距离所述每个第二停车场的距离，与距离所述一个目标第二停车场的距离之比为常数，并且所述每个第二停车场位于所述圆形区域内。
  8. 一种停车场服务区域的确定装置，其特征在于，所述装置包括：
    聚类模块，用于根据第一停车场集合中每个第一停车场的初始权重和初始位置信息，对所有第一停车场进行聚类得到至少一个第二停车场集合；
    第一确定模块，用于根据所述初始权重和所述初始位置信息确定每个第二停车场集合中每个第二停车场对应的转移概率矩阵，一个转移概率矩阵中的一个转移概率用于说明，停车用户在一个第二停车场无空车位时转移至同一第二停车场集合中的另一第二停车场的概率；
    第二确定模块，用于根据所述初始权重和所述转移概率矩阵确定所述每个第二停车场的服务能力值；
    第三确定模块，用于根据所述初始位置信息和所述服务能力值确定所述每个第二停车场的服务区域。
  9. 根据权利要求8所述的方法，其特征在于，所述装置还包括第四确定模块，所述第四确定模块还用于：
    获取第一停车场集合中每个第一停车场的停车用户范围、停车位数量以及停车费信息；
    确定所有第一停车场的总停车位数量和总停车费信息；
    根据所述停车用户范围、所述停车位数量、所述停车费信息、所述总停车位数量以及所述总停车费信息，确定所述第一停车场集合中每个停车场的初始权重。
  10. 根据权利要求8所述的方法，其特征在于，所述聚类模块用于：
    确定所有第一停车场每次移动后的位置信息，其中，所述每个第一停车场进行移动时，其他第一停车场同时进行移动，所述每个第一停车场每次移动后的位置信息由所述每个第一停车场在每次移动前，所述每个第一停车场的位置信息和所有邻近停车场的初始权重确定，所述邻近停车场为所述每个第一停车场在每次移动前，距离所述每个第一停车场的距离小于第一距离阈值的第一停车场，
    根据所述所有第一停车场每次移动后的位置信息，确定所述每个第一停车场每次移动后的位置信息距离上一次移动后的位置信息的移动距离；
    当目标移动距离小于所述第一距离阈值时，所述所有第一停车场停止移动，并根据所述每个第一停车场停止移动时的位置信息确定出至少一个第二停车场集合，所述目标移动距离为所述每个第一停车场每次移动后的位置信息距离上一次移动后的位置信息的移动距离中的最长距离。
  11. 根据权利要求8所述的方法，其特征在于，所述第一确定模块用于：
    根据所述初始位置信息，确定每个第二停车场集合中每个第二停车场与同一第二停车场集合中其他第二停车场的距离；
    确定小于或者等于第二距离阈值的第一目标距离，根据所述第一目标距离对应的第二停车场的初始权重和所述每个停车场的空车位率，确定停车用户在所述每个第二停车场无空车位时，转移至所述每个第一目标距离对应的第二停车场的第一概率；
    确定大于所述第二距离阈值的第二目标距离，确定所述停车用户在所述每个第二停车场无空车位时，转移至所述每个第二目标距离对应的第二停车场的第二概率；
    根据所述第一概率和所述第二概率确定所述每个第二停车场集合对应的转移概率矩阵，一个第二停车场集合对应的转移概率矩阵包含所述一个第二停车场集合中所有第二停车场转移至其他第二停车场的概率。
  12. 根据权利要求8所述的方法，其特征在于，所述第二确定模块用于：
    确定所述每个第二停车场集合对应的初始向量，所述服务能力向量包含所述每个第二停车场集合中所有第二停车场的初始权重；
    将所述每个第二停车场集合对应的服务能力向量和相对应的转移概率矩阵相乘，得到所述每个第二停车场集合对应的一次迭代值；
    将所述一次迭代值与所述相对应的转移概率矩阵相乘得到所述每个第二停车场集合对应的二次迭代值，直至得到目标迭代值，其中，所述目标迭代值的上一次迭代值与所述目标迭代值之差小于预设收敛阈值时；
    根据所述目标迭代值确定出所述每个第二停车场的服务能力值。
  13. 根据权利要求8所述的方法，其特征在于，所述第三确定模块用于：
    确定所述每个第二停车场对应的三角形区域，一个三角形区域由所述每个第二停车场和所述同一第二停车场集合中的两个目标第二停车场的初始位置信息确定，所述一个三角形区域的外接圆区域中不包含其他第二停车场；
    确定所述每个第二停车场对应的圆形区域，一个圆形区域由所述每个第二停车场和所述两个目标第二停车场中的一个目标第二停车场的初始位置信息和服务能力值确定；
    将所述每个第二停车场对应的圆形区域和三角形区域的交集区域确定为所述每个第二停车场的服务区域。
  14. 根据权利要求13所述的方法，其特征在于，所述第三确定模块用于：
    根据所述每个第二停车场和所述两个目标第二停车场中的一个目标第二停车场的初始位置信息和服务能力值确定出圆形区域的半径和圆心，
    根据所述半径和所述圆心确定出所述圆形区域以确定所述每个第二停车场对应的所有圆形区域，其中，所述一个圆形区域的边界上的任一位置距离所述每个第二停车场的距离，与距离所述一个目标第二停车场的距离之比为常数，并且所述每个第二停车场位于所述圆形区域内。
  15. 一种设备，其特征在于，包括处理器和存储器，所述处理器和存储器相互连接；
    所述存储器用于存储计算机程序，所述计算机程序包括程序指令，所述处理器被配置用于调用所述程序指令，执行如权利要求1至7任一项所述的方法。
  16. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质存储有计算机程序，所述计算机程序被处理器执行以实现权利要求1至7任一项所述的方法。
PCT/CN2020/081441 2020-03-26 2020-03-26 停车场服务区域的确定方法、装置、设备以及存储介质 WO2021189363A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
AU2020438755A AU2020438755A1 (en) 2020-03-26 2020-03-26 Method and apparatus for determining service area of parking lot, device, and storage medium
US17/619,112 US20220222592A1 (en) 2020-03-26 2020-03-26 Method and apparatus for determining service area of parking lot, device, and storage medium
GB2118130.0A GB2599549A (en) 2020-03-26 2020-03-26 Method and apparatus for determining service area of parking lot, device, and storage medium
PCT/CN2020/081441 WO2021189363A1 (zh) 2020-03-26 2020-03-26 停车场服务区域的确定方法、装置、设备以及存储介质

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/081441 WO2021189363A1 (zh) 2020-03-26 2020-03-26 停车场服务区域的确定方法、装置、设备以及存储介质

Publications (1)

Publication Number Publication Date
WO2021189363A1 true WO2021189363A1 (zh) 2021-09-30

Family

ID=77890908

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/081441 WO2021189363A1 (zh) 2020-03-26 2020-03-26 停车场服务区域的确定方法、装置、设备以及存储介质

Country Status (4)

Country Link
US (1) US20220222592A1 (zh)
AU (1) AU2020438755A1 (zh)
GB (1) GB2599549A (zh)
WO (1) WO2021189363A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116543310A (zh) * 2023-06-30 2023-08-04 眉山环天智慧科技有限公司 一种基于Voronoi图和核密度的道路线提取方法

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004046416A (ja) * 2002-07-10 2004-02-12 Matsushita Electric Ind Co Ltd 車両位置検出システム、車載装置、通信装置および車両位置検出方法
CN107230381A (zh) * 2017-05-03 2017-10-03 四川九洲电器集团有限责任公司 一种停车位推荐方法、服务器以及客户端

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004046416A (ja) * 2002-07-10 2004-02-12 Matsushita Electric Ind Co Ltd 車両位置検出システム、車載装置、通信装置および車両位置検出方法
CN107230381A (zh) * 2017-05-03 2017-10-03 四川九洲电器集团有限责任公司 一种停车位推荐方法、服务器以及客户端

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
LU QINGHAO; TANG ZHILING; NIE YAN; PENG LEI: "ParkingRank-D: A Spatial-temporal Ranking Model of Urban Parking Lots in City-wide Parking Guidance System", 2019 IEEE INTELLIGENT TRANSPORTATION SYSTEMS CONFERENCE (ITSC), IEEE, 27 October 2019 (2019-10-27), pages 388 - 393, XP033668810, DOI: 10.1109/ITSC.2019.8917481 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116543310A (zh) * 2023-06-30 2023-08-04 眉山环天智慧科技有限公司 一种基于Voronoi图和核密度的道路线提取方法
CN116543310B (zh) * 2023-06-30 2023-10-31 眉山环天智慧科技有限公司 一种基于Voronoi图和核密度的道路线提取方法

Also Published As

Publication number Publication date
GB202118130D0 (en) 2022-01-26
AU2020438755A1 (en) 2022-01-27
GB2599549A (en) 2022-04-06
US20220222592A1 (en) 2022-07-14

Similar Documents

Publication Publication Date Title
JP6081616B2 (ja) モバイルデバイスの測位
CN108346282B (zh) 共享单车的停车监控方法、计算设备及存储介质
WO2020078015A1 (zh) 基于道路匹配的定位方法、芯片子系统及电子设备
WO2019037683A1 (zh) 一种基站的部署方法及装置
CN110111599B (zh) 一种基于大数据的停车诱导方法、终端设备及存储介质
CN110213714B (zh) 终端定位的方法及装置
WO2020232999A1 (zh) 基于信息安全的定位数据监控方法及相关设备
WO2021147431A1 (zh) 无线热点与兴趣点的映射方法、装置、计算机可读存储介质和计算机设备
CN111445075B (zh) 停车场服务区域的确定方法、装置、设备以及存储介质
WO2021189363A1 (zh) 停车场服务区域的确定方法、装置、设备以及存储介质
WO2016023190A1 (zh) 一种定位ap的方法和装置
CN115588008B (zh) 基于视觉的单车规范摆放的判定方法及其应用
CN114422955B (zh) 5g室内弱覆盖区域的定位方法及装置、设备、存储介质
CN114885369A (zh) 网络覆盖质量检测处理方法、装置、电子设备和存储介质
CN110675206A (zh) 群租发现方法、装置、设备及计算机可读介质
WO2018041150A1 (zh) Ap放置
CN105844572B (zh) 拥挤风险监控方法及拥挤风险监控装置
CN111429742B (zh) 一种路侧设备分配方法及装置
CN115988509B (zh) 一种通信网络规划方法、系统、终端及存储介质
CN115272025A (zh) 确定人口分布热力数据的方法、装置和存储介质
WO2023160479A1 (zh) 仓库确定方法、装置及设备
WO2020024206A1 (zh) 基于dcgan的停车数据修补方法、装置、设备及存储介质
AU2020104496A4 (en) Method and apparatus for determining service area of parking lot, device, and storage medium
CN114187524B (zh) 家用空调识别方法、装置、设备、存储介质及产品
CN112347357B (zh) 停车场包月方案推荐方法和系统

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20927156

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 202118130

Country of ref document: GB

Kind code of ref document: A

Free format text: PCT FILING DATE = 20200326

ENP Entry into the national phase

Ref document number: 2020438755

Country of ref document: AU

Date of ref document: 20200326

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20927156

Country of ref document: EP

Kind code of ref document: A1