Parking lot scheduling method and system based on big data

Abstract

The invention provides a parking lot scheduling method and system based on big data, and relates to the technical field of parking scheduling, and the method comprises the steps: determining a plurality of first permanent parking portraits and first temporary parking portraits according to the historical parking record of a first parking lot, dividing the first parking lot into a plurality of first parking regions according to the parking portraits, and carrying out the parking of the first parking lot; and when a vehicle is driven into the first parking lot, parking indication information is generated according to whether the vehicle is a permanent vehicle, and in the process of generating the parking indication information, the first real-time parking information of the first parking lot and the corresponding parking portrait are integrated. According to the technical scheme of the invention, big data analysis can be performed on the historical parking records of the parking lot, so that parking guidance information with a relatively high adaptation degree can be provided for permanent parking and temporary parking, and congestion caused by piling parking can be reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of parking scheduling, and in particular relates to a parking lot scheduling method and system based on big data. Background Art

[0002] The existing technology has made it possible to reserve parking spaces, thereby enabling orderly scheduling of parking lots to a certain extent. However, when the real-time traffic volume is large, traffic jams may occur because too many vehicles wish to park in the same area of ​​the parking lot. Summary of the invention

[0003] The purpose of the present invention is to provide a parking lot scheduling method and system based on big data to solve the technical problem of vehicle congestion caused by clustered parking in the prior art.

[0004] The present application proposes a parking lot scheduling method based on big data, characterized in that the method includes:

[0005] S1: Determine a plurality of first permanent parking portraits and first temporary parking portraits according to historical parking records of a first parking lot;

[0006] S2: determining a plurality of first parking areas according to the first location distribution information of the first parking lot, a plurality of the first parking portraits of permanent vehicles, and the first temporary parking portraits;

[0007] S3: Determine whether the first vehicle entering is a parked vehicle, if so, proceed to S4, otherwise proceed to S5;

[0008] S4: generating first parking instruction information for each first parked vehicle according to the parking portrait of each first parked vehicle and the first real-time parking information;

[0009] S5: Generate second parking instruction information for each first temporary parking according to the first temporary parking portrait and the first real-time parking information.

[0010] Preferably, S1 comprises the following sub-steps:

[0011] S11: extracting historical parking records of the first parking lot within a preset time period, and determining a plurality of first parking records;

[0012] S12: clustering the plurality of first parking records according to the first vehicle identifier to obtain a plurality of first parking record sets, and determining the first parking record sets that meet a preset condition as a first resident vehicle parking record set;

[0013] S13: determining a plurality of first parked vehicle parking portraits according to a plurality of first parked vehicle parking record sets;

[0014] S14: determining a plurality of first temporary parking records according to the plurality of first parking record sets and the plurality of first permanent vehicle parking record sets, and generating a first temporary parking portrait according to the plurality of first temporary parking records.

[0015] Preferably, the S13 includes the following sub-steps:

[0016] S131: calculating a first average entry time and a first average exit time for each of the first parking record sets of permanent vehicles;

[0017] S132: acquiring a first parking area for each of the first parking record sets of permanent vehicles;

[0018] S133: Generate a plurality of the first parked vehicle parking portraits according to the plurality of the first average entry times, the first average exit times and the first parking areas.

[0019] Preferably, the S14 includes the following sub-steps:

[0020] S141: removing a plurality of first parking record sets for permanent vehicles from a plurality of first parking record sets to obtain a plurality of first temporary parking records;

[0021] S142: Analyze the plurality of first temporary parking records to obtain the first temporary parking portrait.

[0022] Preferably, S2 comprises the following sub-steps:

[0023] S21: determining a plurality of first parking coordinate points according to a plurality of the first permanent parking portraits and the first temporary parking portraits;

[0024] S22: Determine a plurality of first parking areas according to a plurality of the first parking coordinate points and a first parking area threshold.

[0025] Preferably, the S4 comprises the following sub-steps:

[0026] S41: determining a first parking priority according to a matching degree between the first parking portrait of the permanent vehicle and the current time;

[0027] S42: determining a first number of vacant parking spaces according to the first real-time parking information, and if the first number of vacant parking spaces is lower than a preset value, proceeding to S43, otherwise proceeding to S44; the first number of vacant parking spaces refers to the number of vacant parking spaces in the parking area preferred by the first entering vehicle;

[0028] S43: Providing first parking indication information for the first entering vehicle according to the first parking priority and the plurality of first parking areas.

[0029] Preferably, S5 comprises the following sub-steps:

[0030] S51: determining first position information to be guided according to a matching degree between the first incoming vehicle and the first temporary parking portrait;

[0031] S52: Determine second parking instruction information according to the first real-time parking information, the plurality of the first parking areas, and the first position information to be guided.

[0032] The present application also proposes a parking lot scheduling system based on big data, which is used to implement the above-mentioned parking lot scheduling method based on big data.

[0033] The present application proposes a parking lot scheduling method and system based on big data, which relates to the technical field of parking scheduling. First, according to the historical parking records of the first parking lot, multiple first resident vehicle parking portraits and first temporary parking portraits are determined, and the first parking lot is divided into multiple first parking areas according to the above parking portraits. Then, when a vehicle enters the first parking lot, parking instruction information is generated respectively according to whether the vehicle is a resident vehicle. In the process of generating the parking instruction information, the first real-time parking information and the corresponding parking portrait of the first parking lot are integrated. Through the technical solution of the present application, the historical parking records of the parking lot can be analyzed by big data, so as to provide parking guidance information with high adaptability for resident vehicles and temporary parking, thereby reducing the congestion caused by clustered parking. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the implementation methods or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.

[0035] Figure 1 It is an execution flow chart of a parking lot scheduling method based on big data of the present invention.

[0036] Figure 2 It is an execution flow chart of determining a plurality of first permanent parking portraits and first temporary parking portraits of the present invention. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments, wherein the illustrative embodiments and descriptions are only used to explain the present invention but are not intended to limit the present invention.

[0039] A parking lot scheduling method and system based on big data of the present invention are described in detail below.

[0040] This embodiment proposes a parking lot scheduling method based on big data. The method flow is as follows: Figure 1 As shown, the specific steps include:

[0041] S1: Determine a plurality of first parking portraits of permanent vehicles and first temporary parking portraits according to historical parking records of a first parking lot.

[0042] In order to adapt to the characteristics of the first parking lot itself and provide customized parking guidance information for the first permanent vehicle and the first temporary parking, in this step, it is necessary to determine multiple first permanent vehicle parking portraits and first temporary parking portraits respectively according to the historical parking records of the first parking lot.

[0043] The S1 specifically includes the following sub-steps:

[0044] S11: extracting historical parking records of the first parking lot within a preset time period, and determining a plurality of first parking records.

[0045] During the operation period of the first parking lot, parking records will be generated for all vehicles entering and exiting. In this step, the historical parking records within the preset time period need to be extracted from the database one by one.

[0046] Preferably, in order to ensure that the portrayal of the parking portrait has a certain statistical significance, the preset time period is preferably one week or longer.

[0047] S12: clustering the plurality of first parking records according to the first vehicle identification to obtain a plurality of first parking record sets, and determining the first parking record sets that meet a preset condition as a first parked vehicle parking record set.

[0048] Since the multiple first parking records include parking records for permanent vehicles and temporary parking, in order to divide the multiple first parking records into parking records for permanent vehicles and parking records for temporary parking, it is necessary to first cluster the vehicles according to vehicle identifications such as license plate numbers to obtain multiple first parking record sets, where each first parking record set corresponds to a vehicle.

[0049] Next, the plurality of first parking record sets may be screened according to a preset condition, thereby screening out a plurality of first parking record sets for permanent vehicles, wherein the preset condition may be the first parking record sets for parking more than a specified number of times within the preset time period.

[0050] S13: Determine a plurality of first parked vehicle parking portraits according to a plurality of first parked vehicle parking record sets.

[0051] Since each of the first parked vehicle parking record sets corresponds to one vehicle, multiple first parked vehicles can be determined based on multiple first parked vehicle parking record sets. Further, multiple first parked vehicle parking portraits corresponding to multiple first parked vehicles can be determined based on the first parked vehicle parking record sets.

[0052] The S13 may include the following sub-steps:

[0053] S131: For each of the first parking record sets of permanently parked vehicles, calculate a first average entry time and a first average exit time.

[0054] In this step, multiple parking records can be extracted from the first permanent vehicle parking record set, and multiple entry time information and multiple exit time information can be extracted from the multiple parking records, so as to calculate the first average entry time and the average exit time using a specific algorithm.

[0055] S132: For each of the first parking record sets of permanently parked vehicles, obtain a first parking area.

[0056] In this step, multiple parking positions of the first parked vehicle can be acquired through historical image information, so as to determine the first parking area based on the multiple parking positions. The first parking area can be an area of ​​a preset range where the first parked vehicle prefers to park.

[0057] S133: Generate a plurality of the first parked vehicle parking portraits according to the plurality of the first average entry times, the first average exit times and the first parking areas.

[0058] In this step, the first average entry time, the first average exit time and the first parking area may be used as labels to form a plurality of parking portraits of the first permanently parked vehicles.

[0059] S14: determining a plurality of first temporary parking records according to the plurality of first parking record sets and the plurality of first permanent vehicle parking record sets, and generating a first temporary parking portrait according to the plurality of first temporary parking records.

[0060] The plurality of first parking record sets include parking records of permanent vehicles and parking records of temporary parking. Therefore, in this step, the plurality of first parking record sets of permanent vehicles are removed from the plurality of first parking record sets to obtain a plurality of first temporary parking records.

[0061] The S14 comprises the following sub-steps:

[0062] S141: removing a plurality of first parking record sets for permanent vehicles from a plurality of first parking record sets to obtain a plurality of first temporary parking records.

[0063] The plurality of first parking record sets are a complete set, and after removing the plurality of first parking record sets for permanent vehicles, a plurality of first temporary parking records can be obtained.

[0064] S142: Analyze the plurality of first temporary parking records to obtain the first temporary parking portrait.

[0065] In the process of analyzing the first temporary parking records, the change patterns of the parking quantity, entry time, exit time and parking position of the first temporary parking records over time are mainly obtained. After determining the labels for the above factors respectively, the first temporary parking portrait can be obtained.

[0066] S2: Determine a plurality of first parking areas according to the first location distribution information of the first parking lot, a plurality of the first permanent parking portraits, and the first temporary parking portraits.

[0067] In this step, the first parking lot is divided into multiple first parking areas, so as to facilitate the subsequent provision of parking guidance information for vehicles to be parked.

[0068] The S2 comprises the following sub-steps:

[0069] S21: Determine a plurality of first parking coordinate points according to a plurality of the first permanent parking portraits and the first temporary parking portraits.

[0070] The first plurality of permanent parking portraits and the first temporary parking portraits all contain tags related to parking positions, so in this step, the position information in the corresponding tags can be statistically analyzed to obtain the first plurality of parking coordinate points.

[0071] Preferably, the first parking coordinate points may be acquired by taking the geometric center of the parking position information in the multiple tags.

[0072] S22: Determine a plurality of first parking areas according to a plurality of the first parking coordinate points and a first parking area threshold.

[0073] Usually, the area where the car owner is accustomed to parking will not exceed a certain area threshold. Therefore, in this step, multiple first parking areas can be determined based on the multiple first parking coordinate points determined in S21 and the preset first parking area threshold.

[0074] Preferably, the multiple first parking areas can be determined by taking the multiple first parking coordinate points as the center and the first parking area threshold as the range. In addition, in the process of determining the multiple first parking areas, it should be ensured as much as possible that different first parking areas do not overlap or the overlapping areas are as small as possible.

[0075] S3: Determine whether the first vehicle entering is a parked vehicle. If so, proceed to S4; otherwise, proceed to S5.

[0076] In this step, it can be determined whether the vehicle identification information of the first input vehicle matches the vehicle identification information in the first permanent vehicle parking record set. If so, it indicates that the first input vehicle is a permanent vehicle, and then proceeds to S4. Otherwise, it indicates that the first input vehicle is a temporary parking vehicle, and then proceeds to S5.

[0077] S4: Generate first parking instruction information for each first parked vehicle according to the parking portrait of each first parked vehicle and the first real-time parking information.

[0078] In this step, it is necessary to refer to the parking portrait of the first parked vehicle and the first real-time parking information of the first parking lot to generate the first parking indication information for each of the first parked vehicles.

[0079] The S4 comprises the following sub-steps:

[0080] S41: Determine a first parking priority according to a matching degree between the first parking portrait of the permanent vehicle and the current time.

[0081] In this step, the first parking priority is determined according to the matching degree between the entry time and the exit time in the parking portrait of the first permanent vehicle and the current time.

[0082] The first parking priority is used to represent the extent to which the first incoming vehicle can be preferentially guided to the position indicated in the first parking portrait of the parked vehicle in the first parking instruction information.

[0083] S42: Determine the first number of vacant parking spaces according to the first real-time parking information. If the first number of vacant parking spaces is lower than a preset value, proceed to S43; otherwise, proceed to S44.

[0084] The first number of vacant parking spaces refers to the number of vacant parking spaces in the parking area preferred by the first entering vehicle.

[0085] S43: Providing first parking indication information for the first entering vehicle according to the first parking priority and the plurality of first parking areas.

[0086] When there are fewer vacant parking spaces in the preferred parking area, vehicles with higher first parking priorities need to be guided to the preferred parking area first. If the first parking priority does not meet the requirement, the first vehicle needs to be guided to other first parking areas adjacent to the signal parking area.

[0087] S5: Generate second parking instruction information for each first temporary parking according to the first temporary parking portrait and the first real-time parking information.

[0088] In this step, it is necessary to refer to the first temporary parking portrait and the first real-time parking information of the first parking lot to generate the first parking indication information for each of the first temporary parking lots.

[0089] The S5 comprises the following sub-steps:

[0090] S51: Determine first position information to be guided according to a matching degree between the first entering vehicle and the first temporary parking portrait.

[0091] When the entry time of the first entering vehicle has a high matching degree with the first temporary parking portrait, the first entering vehicle is preferentially guided to the parking position indicated by the first temporary parking portrait, that is, the first position information to be guided.

[0092] S52: Determine second parking instruction information according to the first real-time parking information, the plurality of the first parking areas, and the first position information to be guided.

[0093] When the available parking space of the first position information to be guided is lower than a preset value, the first incoming vehicle needs to be guided to other first parking areas close to the first position information to be guided.

[0094] The first and second parking instruction information may be displayed on a billboard in the first parking lot, or sent to and displayed on a mobile terminal of a corresponding car owner.

[0095] The present application also proposes a parking lot scheduling system based on big data, which is used to execute the above-mentioned parking lot scheduling method based on big data.

[0096] The present application proposes a parking lot scheduling method and system based on big data, which relates to the technical field of parking scheduling. First, according to the historical parking records of the first parking lot, multiple first resident vehicle parking portraits and first temporary parking portraits are determined, and the first parking lot is divided into multiple first parking areas according to the above parking portraits. Then, when a vehicle enters the first parking lot, parking instruction information is generated respectively according to whether the vehicle is a resident vehicle. In the process of generating the parking instruction information, the first real-time parking information and the corresponding parking portrait of the first parking lot are integrated. Through the technical solution of the present application, the historical parking records of the parking lot can be analyzed by big data, so as to provide parking guidance information with high adaptability for resident vehicles and temporary parking, thereby reducing the congestion caused by clustered parking.

[0097] The above description is only a preferred embodiment of the present invention, so all equivalent changes or modifications made according to the structure, characteristics and principles described in the scope of the patent application of the present invention are included in the scope of the patent application of the present invention.

Claims

1. A parking lot scheduling method based on big data, characterized in that: The method includes: S1: Determine a plurality of first permanent parking portraits and first temporary parking portraits according to historical parking records of a first parking lot; S2: determining a plurality of first parking areas according to the first location distribution information of the first parking lot, a plurality of the first parking portraits of permanent vehicles, and the first temporary parking portraits; S3: Determine whether the first vehicle entering is a parked vehicle, if so, proceed to S4, otherwise proceed to S5; S4: generating first parking instruction information for each first parked vehicle according to the parking portrait of each first parked vehicle and the first real-time parking information; S5: Generate second parking instruction information for each first temporary parking according to the first temporary parking portrait and the first real-time parking information.

2. A parking lot scheduling method based on big data according to claim 1, characterized in that: The S1 comprises the following sub-steps: S11: extracting historical parking records of the first parking lot within a preset time period, and determining a plurality of first parking records; S12: clustering the plurality of first parking records according to the first vehicle identifier to obtain a plurality of first parking record sets, and determining the first parking record sets that meet a preset condition as a first resident vehicle parking record set; S13: determining a plurality of first parked vehicle parking portraits according to a plurality of first parked vehicle parking record sets; S14: determining a plurality of first temporary parking records according to the plurality of first parking record sets and the plurality of first permanent vehicle parking record sets, and generating a first temporary parking portrait according to the plurality of first temporary parking records.

3. A parking lot scheduling method based on big data according to claim 2, characterized in that: The S13 comprises the following sub-steps: S131: calculating a first average entry time and a first average exit time for each of the first parking record sets of permanent vehicles; S132: acquiring a first parking area for each of the first parking record sets of permanent vehicles; S133: Generate a plurality of the first parked vehicle parking portraits according to the plurality of the first average entry times, the first average exit times and the first parking areas.

4. A parking lot scheduling method based on big data according to claim 3, characterized in that: The S14 comprises the following sub-steps: S141: removing a plurality of first parking record sets for permanent vehicles from a plurality of first parking record sets to obtain a plurality of first temporary parking records; S142: Analyze the plurality of first temporary parking records to obtain the first temporary parking portrait.

5. A parking lot scheduling method based on big data according to claim 4, characterized in that: The S2 comprises the following sub-steps: S21: determining a plurality of first parking coordinate points according to a plurality of the first permanent parking portraits and the first temporary parking portraits; S22: Determine a plurality of first parking areas according to a plurality of the first parking coordinate points and a first parking area threshold.

6. A parking lot scheduling method based on big data according to claim 5, characterized in that: The S4 comprises the following sub-steps: S41: determining a first parking priority according to a matching degree between the first parking portrait of the permanent vehicle and the current time; S42: determining a first number of vacant parking spaces according to the first real-time parking information, and if the first number of vacant parking spaces is lower than a preset value, proceeding to S43, otherwise proceeding to S44; the first number of vacant parking spaces refers to the number of vacant parking spaces in the parking area preferred by the first entering vehicle; S43: Providing first parking indication information for the first entering vehicle according to the first parking priority and the plurality of first parking areas.

7. A parking lot scheduling method based on big data according to claim 6, characterized in that: The S5 comprises the following sub-steps: S51: determining first position information to be guided according to a matching degree between the first incoming vehicle and the first temporary parking portrait; S52: Determine second parking instruction information according to the first real-time parking information, the plurality of the first parking areas, and the first position information to be guided.

8. A parking lot scheduling system based on big data, used to implement a parking lot scheduling method based on big data in claims 1-7 above.

Images