Intelligent scheduling system and method for dynamic parking resources based on smart city

Abstract

The application relates to the technical field of parking resource scheduling, in particular to a dynamic parking resource intelligent scheduling system and method based on a smart city. In the system, a parking space vacancy state analysis module predicts parking space idle evaluation values of each candidate parking lot in a future time interval based on current states of all vehicles in each candidate parking lot and the predicted parking duration, and the future time interval matches the predicted arrival time of the target vehicle. The application provides a high-probability parking lot with a parking space when the target vehicle arrives, completely avoids the trouble of the target vehicle blindly searching for a parking space, and to a certain extent, reduces the number of vehicles searching for a parking space in the surrounding area of the navigation destination of the target vehicle, thereby relieving the traffic congestion in the surrounding area of the navigation destination from the source, and improving the overall urban traffic operation efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of parking resource scheduling, in particular to a dynamic parking resource intelligent scheduling system and method based on a smart city. BACKGROUND

[0002] With the acceleration of urbanization and the continuous growth of the number of motor vehicles, "parking difficulty" has become one of the primary problems that plague city managers and citizens. Existing smart parking solutions focus on the static provision of information, such as displaying the location and current number of empty parking spaces through an App or electronic sign. However, existing technologies can only provide the instantaneous state of the parking lot and cannot predict future parking availability. Drivers often arrive at the destination parking lot to find that the parking space has been occupied, exacerbating traffic congestion and parking time around the destination; at the same time, the user's parking duration is closely related to the place they go to (such as a restaurant, shopping mall, or office), and the service state of the destination (such as the restaurant queue) is often ignored in existing technologies. The parking lot management system is also relatively isolated and cannot be linked with the surrounding places. For example, for parking lots around a shopping mall, it is not possible to conduct forward-looking parking resource scheduling based on the upcoming demand (such as a batch of vehicles that will soon end their meal) and supply (such as a batch of vehicles that will soon arrive) for parking spaces, thereby failing to plan the most suitable parking lot for the user in advance. Therefore, there are significant defects in existing technologies. SUMMARY

[0003] The present application aims to provide a dynamic parking resource intelligent scheduling system and method based on a smart city to solve the problems raised in the background.

[0004] To solve the above technical problems, the present application provides the following technical solution: a dynamic parking resource intelligent scheduling method based on a smart city, the method comprising:

[0005] S1, obtaining navigation destination information of a target vehicle, and based on the navigation destination information, determining one or more candidate parking lots around the navigation destination;

[0006] S2, obtaining real-time consumption data of surrounding shops associated with each candidate parking lot, and combining historical travel time data of users of parked vehicles in the candidate parking lot, dynamically predicting the estimated parking duration of each parked vehicle in the candidate parking lot;

[0007] S3, based on the current state of all vehicles in each candidate parking lot and the estimated parking duration, predicting the parking space idle evaluation value of each candidate parking lot in a future time interval, the future time interval matching the estimated arrival time of the target vehicle;

[0008] S4, generating a parking scheduling suggestion based on the obtained parking space idle evaluation value, and sending the scheduling suggestion to the target vehicle or a parking lot manager to complete vehicle guiding and pre-allocation of parking resources.

[0009] Further, in the process of determining the candidate parking lot around the navigation destination in S1, the distance from the obtained candidate parking lot to the navigation destination is less than or equal to a preset distance.

[0010] In the present application, the navigation destination of the target vehicle is obtained, so as to establish the core target of the parking service, provide data support for subsequent analysis of the candidate parking lot and generation of the parking scheduling suggestion, and make the parking scheduling service have a clear direction.

[0011] In the process of obtaining the real-time consumption data of the surrounding shops associated with each candidate parking lot in S2, under the authorization state of the vehicle owner of the vehicle parked in the candidate parking lot, the real-time consumption data of the corresponding vehicle owner in the shops within a preset radius around the corresponding parking lot during the parking of the vehicle is obtained, and the real-time consumption data at least includes the shop type, the current queue number of the shop, the current queue time, the expected waiting time consumption and the historical average service time consumption.

[0012] For the vehicle whose owner is not authorized in the vehicle parked in the candidate parking lot, only the vehicle parking time interval of the corresponding license plate in the corresponding parking lot each time is counted.

[0013] Further, in the process of dynamically predicting the expected parking duration of each parked vehicle in the candidate parking lot in S2, for the vehicle whose owner is authorized in the vehicle parked in the candidate parking lot, the real-time consumption data of the corresponding vehicle owner in the shops within a preset radius around the corresponding parking lot during the parking of the vehicle is obtained, and the consumption expected time of the corresponding vehicle owner based on the current time is calculated, which is recorded as T1, and the T1 is equal to the sum of the expected waiting time consumption corresponding to the current queue of the shop in the real-time consumption data corresponding to the current time and the historical average service time consumption; the user historical travel time data of the corresponding vehicle owner in the candidate parking lot is called, the average additional time consumption of the corresponding vehicle owner for completing the same type of shop consumption behavior is recorded as T2, and the additional time consumption includes walking time and shopping time; the maximum value of the parking duration of the corresponding vehicle owner in the historical data each time is recorded as T3; the expected parking duration interval of the corresponding vehicle based on the current time in the candidate parking lot is obtained, which is recorded as [Tmin, Tmax]; the Tmin is min{T1+T2, T3}, and the Tmax is max{T1+T2, T3}, the min{} represents a minimum value function, and the max{} represents a maximum value function.

[0014] For the candidate parking lot in the parking vehicle, the value of Tmin is the average value of the parking duration corresponding to each trip of the corresponding vehicle owner in the historical data, and Tmax=T3.

[0015] The application takes the real-time consumption data of the vehicle owner in the store as a key input for predicting the parking duration, so that the prediction result changes from "fuzzy guess" based on historical statistics to "accurate calculation" based on real-time reality, greatly improving the prediction accuracy. At the same time, the application combines historical data of the user, analyzes from the perspective of personal habits of the user (such as speed of doing things, dining speed), and to some extent, can calibrate the parking duration predicted based on real-time consumption data, ensuring the accuracy of the predicted parking duration.

[0016] Further, the method for predicting the parking space idle evaluation value of each candidate parking lot in the future time interval in S3 comprises the following steps:

[0017] S31, obtain the interval duration of the navigation information of the target vehicle to the ith candidate parking lot from the current time, denoted as THi; construct the parking interval duration requirement interval of the target vehicle to the ith candidate parking lot, denoted as [THi·(1-Q), THi·(1+Q)], Q represents the average value of the deviation of the actual duration in the navigation information to the destination in the historical data based on the navigation prediction duration, the navigation prediction duration is obtained by navigation software, and the deviation based on the actual duration based on the navigation prediction duration is equal to the absolute value of the difference between the actual duration and the navigation prediction duration divided by the quotient of the prediction duration;

[0018] S32, construct the future time interval based on the ith candidate parking lot, the future time interval based on the ith candidate parking lot is the time interval corresponding to the sum of each element in [THi·(1-Q), THi·(1+Q)] and the current time;

[0019] S33, obtain the parking space idle evaluation value of the jth parked vehicle in the ith candidate parking lot in the future time interval, denoted as P ij ,

[0020]

[0021] Wherein, Wij represents the predicted parking duration interval of the jth parked vehicle in the ith candidate parking lot based on the current time; Wij∩[THi·(1-Q), THi·(1+Q)] represents the intersection interval of Wij and the future time interval; N Wij represents the trip frequency of the owner of the jth parked vehicle in the ith candidate parking lot in the historical data corresponding to the parking duration belonging to Wij; N Wij∩[THi·（1-Q），THi·（1+Q）]represent the travel frequency of the owner of the jth parked vehicle in the ith candidate parking lot in the historical data corresponding to the parking duration belonging to Wij intersect [THi·(1-Q), THi·(1+Q)]; if Wij intersect [THi·(1-Q), THi·(1+Q)] is empty, then determine N Wij∩[THi·（1-Q），THi·（1+Q）] =0;

[0022] S34, obtain the parking space occupancy rate corresponding to each time point in the ith candidate parking lot within the preset time interval based on the current time, construct the parking space occupancy rate change curve of the ith candidate parking lot within the preset time interval based on the current time, and record it as Ri; obtain the parking space occupancy rate change curve corresponding to each day within the preset time interval based on the current time in the historical data of the ith candidate parking lot, and call the average value of the parking space occupancy rate corresponding to each time point belonging to the future time interval in the date in which the similarity between the parking space occupancy rate change curve of the ith candidate parking lot based on the preset time interval based on the current time in the historical data and Ri is greater than or equal to a preset threshold, and record it as Di;

[0023] S35, calculate the parking space comprehensive idle evaluation value of the parked vehicle in the ith candidate parking lot within the future time interval, and record it as PZi, wherein the PZi is equal to the sum of the parking space idle evaluation values of each parked vehicle in the ith candidate parking lot within the future time interval;

[0024] S36, predict the parking space idle evaluation value of each candidate parking lot within the future time interval, and record it as PCi,

[0025] If 1-Di is greater than or equal to Fi, then determine PCi=max{ (1-Di) ·Mi, PZi}, wherein the Mi represents the total number of parking spaces in the ith candidate parking lot; and the Fi represents the maximum value of the quotient of the number of parked vehicles leaving the ith candidate parking lot in the historical data within any unit time and Mi; if 1-Di is less than Fi, then determine PCi=PZi.

[0026] The application analyzes the intersection relationship between the parking duration of a single parked vehicle in the candidate parking lot and the future time interval based on the ith candidate parking lot, and further predicts the evaluation of the corresponding parked vehicle leaving and making the parking space idle when the target vehicle arrives at the ith candidate parking lot. Meanwhile, the change trend of the parking space occupancy rate in the candidate parking lot with time on different dates is combined to further analyze the parking space idle evaluation value of each candidate parking lot within the future time interval, which provides data support for generating parking scheduling suggestions for the target vehicle subsequently.

[0027] Further, in the process of constructing the i th candidate parking lot in S34 based on the parking occupancy rate change curve Ri in the previous preset time interval based on the current time, in the coordinate system of the relationship between the parking occupancy rate and time, the coordinate points corresponding to the parking occupancy rates of adjacent time points in the i th candidate parking lot in the previous preset time interval based on the current time are sequentially connected.

[0028] When calculating the similarity between the parking occupancy rate change curve of the i th candidate parking lot in the historical data and Ri in the previous preset time interval based on the current time, the similarity between the parking occupancy rate change curve of the i th candidate parking lot in the historical data on the k th day and Ri in the previous preset time interval based on the current time is denoted as G k，i ;

[0029]

[0030] , wherein TW1 represents the starting time point in the previous preset time interval based on the current time in a day; TW2 represents the ending time point in the previous preset time interval based on the current time in a day; DY t，i，k represents the parking occupancy rate corresponding to the time point t in the previous preset time interval based on the current time in a day in the parking occupancy rate change curve of the i th candidate parking lot in the historical data on the k th day in the previous preset time interval based on the current time; DY t，i represents the parking occupancy rate corresponding to the time point t in the previous preset time interval based on the current time in a day in Ri;

[0031] When |DY t，i，k -DY t，i is less than or equal to the preset parking occupancy rate deviation, it is determined that the value of G is 1; otherwise, it is determined that the value of G is 0.

[0032] Further, in the process of generating the parking scheduling suggestion in S4, the parking space idle evaluation values of the candidate parking lots in the future time interval are sequentially obtained, and a segment formed by the first n elements in the sequence of the candidate parking lots in the descending order of the corresponding parking space idle evaluation values in the future time interval is taken as the parking calling suggestion.

[0033] After the parking scheduling suggestion generated in the application is fed back to the owner of the target vehicle, the owner of the target vehicle selects a unique candidate parking lot according to the own demand, and takes it as a new navigation destination to update the driving route.

[0034] The dynamic parking resource intelligent scheduling system based on a smart city comprises:

[0035] A candidate parking lot locking module, which acquires navigation destination information of a target vehicle, determines one or more candidate parking lots around a navigation destination based on the navigation destination information;

[0036] A parking duration analysis module, which acquires real-time consumption data of surrounding shops associated with each candidate parking lot, and dynamically predicts the expected parking duration of each parked vehicle in the candidate parking lot in combination with user historical travel time consumption data of the parked vehicles in the candidate parking lot;

[0037] A parking space vacancy state analysis module, which predicts a parking space vacancy evaluation value of each candidate parking lot in a future time interval based on the current state of all vehicles in each candidate parking lot and the expected parking duration, the future time interval matching the expected arrival time of the target vehicle;

[0038] A parking dispatch management module, which generates a parking dispatch suggestion based on the obtained parking space vacancy evaluation value, and sends the dispatch suggestion to the target vehicle or parking lot management personnel to complete vehicle guidance and pre-allocation of parking resources.

[0039] Further, the parking duration analysis module comprises a consumption data correlation analysis unit and a parking duration dynamic prediction unit,

[0040] The consumption data correlation analysis unit acquires real-time consumption data of surrounding shops associated with each candidate parking lot;

[0041] The parking duration dynamic prediction unit dynamically predicts the expected parking duration of each parked vehicle in the candidate parking lot in combination with user historical travel time consumption data of the parked vehicles in the candidate parking lot.

[0042] Compared with the prior art, the present application has the following beneficial effects:

[0043] (1) The present application realizes the leap from the instantaneous state of idle parking spaces to the dynamic resource pre-dispatching of parking lots through multi-dimensional data fusion and intelligent prediction; in combination with each candidate parking lot around the target vehicle, real-time consumption data of surrounding shops associated with each candidate parking lot, and user historical travel time consumption data of parked vehicles in the candidate parking lot, the expected parking duration of each parked vehicle in the candidate parking lot is dynamically predicted, and then the parking space vacancy evaluation value of each candidate parking lot in a future time interval is accurately predicted, thereby providing data support for accurately generating a parking dispatch suggestion for the target vehicle.

[0044] (2) The present application provides a high-probability parking lot for users, that is, a parking lot with a high probability of having a parking space when the target vehicle arrives, which completely avoids the problem of the target vehicle blindly searching for a parking space, and to a certain extent, reduces the number of vehicles searching for a parking space in the surrounding area of the target vehicle's navigation destination, thereby relieving the traffic congestion around the navigation destination from the source, and improving the overall urban traffic operation efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0045] The accompanying drawings are included to provide a further understanding of the present application, and constitute a part of the specification, illustrate the present application together with the embodiments thereof, and explain the present application, but do not constitute a limitation of the present application. In the drawings:

[0046] Fig. 1 is a structural schematic diagram of the dynamic parking resource intelligent scheduling system based on the smart city of the present application;

[0047] Fig. 2 is a flowchart of the dynamic parking resource intelligent scheduling method based on the smart city of the present application. DETAILED DESCRIPTION

[0048] The technical solutions in the embodiments of the present application will be described in detail below with reference to the accompanying drawings of the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0049] Please refer to Figs. 1-2 , the present application provides a technical solution: as Fig. 1 shown, the present embodiment provides a dynamic parking resource intelligent scheduling system based on the smart city, which comprises:

[0050] A candidate parking lot locking module, the candidate parking lot locking module acquires navigation destination information of a target vehicle, and determines one or more candidate parking lots around the navigation destination based on the navigation destination information;

[0051] A parking duration analysis module, the parking duration analysis module comprises a consumption data correlation analysis unit and a parking duration dynamic prediction unit,

[0052] The consumption data correlation analysis unit acquires real-time consumption data of surrounding shops associated with each candidate parking lot;

[0053] The parking duration dynamic prediction unit dynamically predicts the predicted parking duration of each parked vehicle in the candidate parking lot in combination with the historical travel time consumption data of the users of the parked vehicles in the candidate parking lot;

[0054] a parking space vacancy state analysis module configured to predict a parking space vacancy evaluation value of each candidate parking lot in a future time interval based on current states of all vehicles in each candidate parking lot and the predicted parking duration, the future time interval matching a predicted arrival time of the target vehicle;

[0055] a parking dispatch management module configured to generate a parking dispatch suggestion based on the obtained parking space vacancy evaluation value, and send the dispatch suggestion to the target vehicle or a parking lot manager to complete vehicle guidance and pre-allocation of parking resources.

[0056] As shown in Fig. 2 the embodiment, a dynamic parking resource intelligent dispatch method based on a smart city is provided, and the method includes:

[0057] S1, obtaining navigation destination information of a target vehicle, and determining one or more candidate parking lots around a navigation destination based on the navigation destination information;

[0058] In the process of determining the candidate parking lots around the navigation destination in S1, the obtained candidate parking lots are within a preset distance from the navigation destination;

[0059] S2, obtaining real-time consumption data of surrounding shops associated with each candidate parking lot, and dynamically predicting a predicted parking duration of each parked vehicle in the candidate parking lot in combination with historical travel time consumption data of users of the parked vehicles in the candidate parking lot;

[0060] In the process of obtaining the real-time consumption data of the surrounding shops associated with each candidate parking lot in S2, under an authorized state of a vehicle owner of a parked vehicle in the candidate parking lot, real-time consumption data of the corresponding vehicle owner at a shop within a preset radius around the corresponding parking lot during vehicle parking is obtained, and the real-time consumption data at least includes a shop type, a current queue number of the shop, a current queue time, a predicted waiting time consumption, and a historical average service time consumption;

[0061] For a vehicle whose owner is not authorized among the parked vehicles in the candidate parking lot, only the vehicle parking time interval of the corresponding license plate in the corresponding parking lot is counted.

[0062] In this embodiment, the consumption intention of the owner of the target vehicle and the type of target store can also be directly identified according to the destination navigated by the target vehicle. For example, if the target vehicle is navigating to a restaurant in a shopping mall, the candidate parking lot is located in the periphery of the corresponding shopping mall. Since the navigation destination of the owner of the target vehicle is a restaurant, it can be known that the consumption intention of the owner of the target vehicle is to eat, or more specifically, to eat a certain type of food (such as hot pot, barbecue, or self-service). Therefore, the target store type is not only the specific restaurant navigated, but also the same type of restaurant in the periphery.

[0063] In the process of dynamically predicting the expected parking duration of each parked vehicle in the candidate parking lot in S2, for the vehicle authorized by the owner among the parked vehicles in the candidate parking lot, real-time consumption data of the corresponding store within a preset radius around the corresponding parking lot during the parking of the vehicle is obtained, and the expected consumption time of the corresponding owner based on the current time is calculated, denoted as T1, which is equal to the sum of the expected waiting time corresponding to the current queue of the store in the real-time consumption data corresponding to the current time and the historical average service time; the user historical travel time data of the corresponding owner in the candidate parking lot is called, and the average additional time of the corresponding owner to complete the same type of store consumption behavior is denoted as T2, which includes walking time and shopping time; the maximum value of the parking duration corresponding to each trip of the corresponding owner in the historical data in the candidate parking lot is denoted as T3; the expected parking duration interval of the corresponding vehicle in the candidate parking lot based on the current time is obtained, denoted as [Tmin, Tmax]; Tmin=min{T1+T2, T3}, Tmax=max{T1+T2, T3}, min{} represents the minimum value function, and max{} represents the maximum value function;

[0064] For the vehicle not authorized by the owner among the parked vehicles in the candidate parking lot, the value of Tmin is the average value of the parking duration corresponding to each trip of the corresponding owner in the historical data in the candidate parking lot, and Tmax=T3.

[0065] S3, based on the current state of all vehicles in each candidate parking lot and the expected parking duration, predicting the parking space idle evaluation value of each candidate parking lot in a future time interval, the future time interval matches the expected arrival time of the target vehicle;

[0066] The method for predicting the parking space idle evaluation value of each candidate parking lot in a future time interval in S3 includes the following steps:

[0067] S31, obtain the interval length of the time distance between the current time and the time when the target vehicle reaches the i-th candidate parking lot in the navigation information, denoted as THi; construct the parking interval length requirement interval of the target vehicle reaching the i-th candidate parking lot, denoted as [THi·(1-Q), THi·(1+Q)], Q represents the average value of the deviation ratio of the actual time length based on the navigation prediction time length in the historical data to the navigation prediction time length, the navigation prediction time length is obtained by the navigation software, and the deviation ratio of the actual time length based on the navigation prediction time length is equal to the quotient of the absolute value of the difference between the actual time length and the navigation prediction time length divided by the prediction time length;

[0068] S32, construct the future time interval based on the i-th candidate parking lot, which is the time interval corresponding to each element in [THi·(1-Q), THi·(1+Q)] added to the current time;

[0069] S33, obtain the parking space idle evaluation value of the j-th parked vehicle in the i-th candidate parking lot in the future time interval, denoted as P ij ,

[0070]

[0071] Wherein, Wij represents the predicted parking time length interval of the j-th parked vehicle in the i-th candidate parking lot based on the current time; Wij∩[THi·(1-Q), THi·(1+Q)] represents the intersection interval of Wij and the future time interval; N Wij represents the travel frequency of the owner of the j-th parked vehicle in the i-th candidate parking lot in the historical data corresponding to the parking time length belonging to Wij; N Wij∩[THi·（1-Q），THi·（1+Q）] represents the travel frequency of the owner of the j-th parked vehicle in the i-th candidate parking lot in the historical data corresponding to the parking time length belonging to Wij∩[THi·(1-Q), THi·(1+Q)]; if Wij∩[THi·(1-Q), THi·(1+Q)] is empty, then N Wij∩[THi·（1-Q），THi·（1+Q）] =0;

[0072] S34, obtain the parking space occupancy rate corresponding to each time point in the i-th candidate parking lot within the preset time interval based on the current time, construct the parking space occupancy rate change curve of the i-th candidate parking lot within the preset time interval based on the current time, denoted as Ri; obtain the parking space occupancy rate change curve corresponding to each time point in the i-th candidate parking lot within the preset time interval based on the current time in the historical data, and call the average value of the parking space occupancy rate corresponding to each time point belonging to the future time interval in the date in which the similarity between the parking space occupancy rate change curve of the i-th candidate parking lot within the preset time interval based on the current time in the historical data and Ri is greater than or equal to a preset threshold, denoted as Di;

[0073] In the process of constructing the i-th candidate parking lot based on the parking space occupancy rate change curve Ri in the preset time interval before the current time, in the coordinate system of the relationship between the parking space occupancy rate and time (in this embodiment, the coordinate system is a rectangular coordinate system with time as the horizontal coordinate axis, o as the origin, and parking space occupancy rate as the vertical axis), the coordinate points of the parking space occupancy rates corresponding to the adjacent time points in the i-th candidate parking lot in the preset time interval before the current time are sequentially connected.

[0074] When calculating the similarity between the parking space occupancy rate change curve corresponding to the i-th candidate parking lot in the preset time interval before the current time on the k-th day in the historical data and Ri, the similarity between the parking space occupancy rate change curve corresponding to the i-th candidate parking lot in the preset time interval before the current time on the k-th day in the historical data and Ri is denoted as G k，i ;

[0075]

[0076] TW1 represents the starting time point in the preset time interval before the current time in a day; TW2 represents the ending time point in the preset time interval before the current time in a day; DY t，i，k represents the parking space occupancy rate corresponding to the time point t in the preset time interval before the current time in a day in the parking space occupancy rate change curve corresponding to the i-th candidate parking lot in the preset time interval before the current time on the k-th day in the historical data; DY t，i represents the parking space occupancy rate corresponding to the time point t in the preset time interval before the current time in a day in Ri;

[0077] When |DY t，i，k -DY t，i is less than or equal to the preset parking space occupancy rate deviation, it is determined that the value of G is 1; otherwise, it is determined that the value of G is 0.

[0078] S35, calculating the parking space comprehensive idle evaluation value of the vehicle parked in the i-th candidate parking lot in the future time interval, denoted as PZi, which is equal to the sum of the parking space idle evaluation values of each parked vehicle in the i-th candidate parking lot in the future time interval.

[0079] S36, predicting the parking space idle evaluation value of each candidate parking lot in the future time interval, denoted as PCi,

[0080] If 1-Di≥Fi, PCi is determined as max{ (1-Di) ·Mi, PZi}, where Mi represents the total number of parking spaces in the ith candidate parking lot; and Fi represents the maximum value of the quotient of the number of vehicles parked in the ith candidate parking lot in any unit time and Mi in historical data. If 1-Di<Fi, PCi is determined as PZi.

[0081] S4, based on the obtained parking space vacancy evaluation value, generating a parking scheduling suggestion, and sending the scheduling suggestion to the target vehicle or parking lot manager to complete vehicle guidance and pre-allocation of parking resources.

[0082] In the process of generating the parking scheduling suggestion in S4, the parking space vacancy evaluation values of the candidate parking lots in the future time interval are obtained in sequence, and a segment formed by the first n elements in a candidate parking lot sequence in descending order of the corresponding parking space vacancy evaluation values in the future time interval is used as the parking scheduling suggestion.

[0083] It should be noted that, in this document, relational terms such as first and second and the like can merely be used to distinguish one entity or action from another, without necessarily requiring or implying any such actual relationship or order between or among the entities or actions. Moreover, the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0084] Finally, it should be noted that the above descriptions are only preferred embodiments of the present application, and are not intended to limit the present application. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art will still be able to modify the technical solutions described in the foregoing embodiments or make equivalent replacements to some technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A dynamic parking resource intelligent scheduling method based on a smart city, characterized in that, The method comprises: S1, obtaining navigation destination information of a target vehicle, and determining one or more candidate parking lots around a navigation destination based on the navigation destination information; S2, obtaining real-time consumption data of surrounding shops associated with each candidate parking lot, and dynamically predicting the expected parking duration of each parked vehicle in the candidate parking lot in combination with historical travel time consumption data of users of the parked vehicles in the candidate parking lot; S3, predicting a parking space idle evaluation value of each candidate parking lot in a future time interval based on the current state of all vehicles in each candidate parking lot and the expected parking duration, the future time interval matching the expected arrival time of the target vehicle; The method for predicting the parking space idle evaluation value of each candidate parking lot in the future time interval in S3 comprises the following steps: S31, obtaining the interval length of the time when the target vehicle reaches the ith candidate parking lot from the current time, denoted as THi; constructing a parking interval length requirement interval of the target vehicle reaching the ith candidate parking lot, denoted as [THi·(1-Q), THi·(1+Q)], Q representing the average value of the deviation of the actual time length in the navigation information to the navigation expected time length, the navigation expected time length being obtained by navigation software, the deviation of the actual time length to the navigation expected time length being equal to the absolute value of the difference between the actual time length and the navigation expected time length divided by the quotient of the expected time length; S32, constructing a future time interval based on the ith candidate parking lot, the future time interval based on the ith candidate parking lot being the time interval corresponding to each element in [THi·(1-Q), THi·(1+Q)] added to the current time; S33, obtaining a parking space vacancy evaluation value of the jth parked vehicle in the ith candidate parking lot in a future time interval, denoted as P ij , ； wherein Wij represents the estimated parking duration interval of the jth parked vehicle in the ith candidate parking lot based on the current time; Wij∩[THi·(1-Q), THi·(1+Q)] represents the intersection interval of Wij and the future time interval; N Wij represents the travel frequency of the owner of the jth parked vehicle in the ith candidate parking lot in the historical data corresponding to the parking duration belonging to Wij; N Wij∩[THi·（1-Q），THi·（1+Q）] represents the travel frequency of the owner of the jth parked vehicle in the ith candidate parking lot in the historical data corresponding to the parking duration belonging to Wij∩[THi·(1-Q), THi·(1+Q)]; if Wij∩[THi·(1-Q), THi·(1+Q)] is an empty set, then N Wij∩[THi·（1-Q），THi·（1+Q）] = 0. S34, obtaining the parking space occupancy rate corresponding to each time point in the ith candidate parking lot in a preset time interval based on the current time, constructing a parking space occupancy rate change curve of the ith candidate parking lot in the preset time interval based on the current time, denoted as Ri; obtaining the parking space occupancy rate change curve of the ith candidate parking lot in the historical data based on the current time in the preset time interval, and calling the average value of the parking space occupancy rate corresponding to each time point in the future time interval in the dates in which the similarity between the parking space occupancy rate change curve of the ith candidate parking lot in the historical data based on the current time in the preset time interval and Ri is greater than or equal to a preset threshold, denoted as Di; S35, calculating a comprehensive parking space idle evaluation value of the parked vehicles in the ith candidate parking lot in the future time interval, denoted as PZi, the PZi being equal to the sum of the parking space idle evaluation values of each parked vehicle in the ith candidate parking lot in the future time interval; S36, predicting the parking space idle evaluation value of each candidate parking lot in the future time interval, denoted as PCi, If 1-Di≥Fi, PCi is determined as max{ (1-Di) ·Mi, PZi}, where Mi represents the total number of parking spaces in the ith candidate parking lot, and Fi represents the maximum value of the quotient of the number of parked vehicles leaving the ith candidate parking lot in any unit time and Mi in historical data; if 1-Di<Fi, PCi is determined as PZi; S4. Based on the obtained parking space vacancy evaluation value, a parking scheduling suggestion is generated, and the scheduling suggestion is sent to the target vehicle or parking lot manager to complete vehicle guidance and pre-allocation of parking resources. 2.The smart city-based dynamic parking resource intelligent scheduling method according to claim 1, characterized in that: In the process of determining the candidate parking lot around the navigation destination in S1, the distance from the obtained candidate parking lot to the navigation destination is less than or equal to a preset distance; In the process of obtaining the real-time consumption data of the surrounding shops associated with each candidate parking lot in S2, under the authorization state of the vehicle owner of the parked vehicle in the candidate parking lot, the real-time consumption data of the corresponding vehicle owner in the shops within a preset radius around the corresponding parking lot during the parking period of the vehicle is obtained, and the real-time consumption data at least includes the shop type, the current queue number of the shop, the current queue time, the estimated waiting time consumption and the historical average service time consumption. For the vehicle whose owner is not authorized among the parked vehicles in the candidate parking lot, only the vehicle parking time interval of the corresponding license plate in the corresponding parking lot each time is counted. 3.The smart city-based dynamic parking resource intelligent scheduling method according to claim 1, characterized in that: In the process of dynamically predicting the estimated parking duration of each parked vehicle in the candidate parking lot in S2, for the vehicle whose owner is authorized among the parked vehicles in the candidate parking lot, the real-time consumption data of the corresponding vehicle owner in the shops within a preset radius around the corresponding parking lot during the parking period of the vehicle is obtained, and the consumption estimated time of the corresponding vehicle owner based on the current time is calculated and recorded as T1, which is equal to the sum of the estimated waiting time and the historical average service time corresponding to the current queue of the shop in the real-time consumption data corresponding to the current time; the user historical travel time data of the corresponding vehicle owner in the candidate parking lot is called, and the average additional time of the corresponding vehicle owner to complete the same type of shop consumption behavior is recorded as T2, the additional time including walking time and shopping time; the maximum value of the parking duration corresponding to each trip of the corresponding vehicle owner in the historical data is recorded as T3; The estimated parking duration interval of the corresponding vehicle in the candidate parking lot based on the current time is obtained and recorded as [Tmin, Tmax]; Tmin=min{T1+T2, T3} and Tmax=max{T1+T2, T3}, where min{} represents a minimum function and max{} represents a maximum function; For the vehicle whose owner is not authorized among the parked vehicles in the candidate parking lot, the value of Tmin is the average value of the parking duration corresponding to each trip of the corresponding vehicle owner in the historical data, and Tmax=T3. 4.The smart city based dynamic parking resource intelligent scheduling method of claim 1, wherein: In the process of constructing the i-th candidate parking lot in the S34 based on the parking occupancy rate change curve Ri in the preset time interval before the current time, in the coordinate system of the relationship between the parking occupancy rate and time, the coordinate points corresponding to the parking occupancy rates of the i-th candidate parking lot at adjacent time points in the preset time interval before the current time are sequentially connected. When the similarity between the parking space occupancy rate change curve corresponding to the i th candidate parking lot in the historical data within the preset time interval before the current time on the k th day and Ri is calculated, the similarity between the parking space occupancy rate change curve corresponding to the i th candidate parking lot in the historical data within the preset time interval before the current time on the k th day and Ri is denoted as G k，i ; ； TW1 represents a starting time point in a preset time interval before the current time in a day; TW2 represents an ending time point in the preset time interval before the current time in a day; DY t，i，k represents a parking space occupancy rate corresponding to a time point t in a preset time interval before the current time in a day in the historical data in the kth day in the i th candidate parking lot in the corresponding parking space occupancy rate change curve in the preset time interval before the current time in a day; DY t，i represents a parking space occupancy rate corresponding to a time point t in a preset time interval before the current time in a day in Ri. When |DY t，i，k -DY t，i If the value of |DY is less than or equal to a preset parking space occupancy deviation, it is determined that the value of 1; otherwise, it is determined that the value of 0. 5.The smart city based dynamic parking resource intelligent scheduling method of claim 1, wherein: In the process of generating the parking scheduling suggestion in the S4, the parking space idle evaluation values of each candidate parking lot in the future time interval are sequentially obtained, and a segment corresponding to the first n elements in the candidate parking lot sequence in descending order of the corresponding parking space idle evaluation values in the future time interval is formed as the parking scheduling suggestion.

6. The dynamic parking resource intelligent scheduling system based on smart city, applying the dynamic parking resource intelligent scheduling method based on smart city in any one of claims 1-5, characterized in that, The system comprises: a candidate parking lot locking module, which obtains navigation destination information of a target vehicle, and determines one or more candidate parking lots around the navigation destination based on the navigation destination information; a parking duration analysis module, which comprises a consumption data correlation analysis unit and a parking duration dynamic prediction unit, the consumption data correlation analysis unit obtains real-time consumption data of surrounding shops associated with each candidate parking lot; the parking duration dynamic prediction unit dynamically predicts the predicted parking duration of each parked vehicle in the candidate parking lot in combination with historical travel time consumption data of users of the parked vehicles in the candidate parking lot; a parking space vacancy state analysis module, which predicts parking space idle evaluation values of each candidate parking lot in a future time interval based on the current state of all vehicles in each candidate parking lot and the predicted parking duration, the future time interval matching a predicted arrival time of the target vehicle; a parking scheduling management module, which generates a parking scheduling suggestion based on the obtained parking space idle evaluation values, and sends the scheduling suggestion to the target vehicle or a parking lot manager to complete vehicle guidance and pre-allocation of parking resources.

Images