A Smart City Parking Guidance System and Method Based on the Internet of Things

Abstract

This application provides a smart city parking guidance system and method based on the Internet of Things (IoT). It constructs road network association information between various parking zones, and determines the availability index of each parking zone by combining all road network association information with the occupancy characteristics of parking spaces during peak hours in the target parking lot. It plans a reliable driving route for the user vehicle based on the current location of the user vehicle, the changing trends of short-term parking space occupancy characteristics in each parking zone, and the availability index of each parking zone. When the user vehicle arrives at the target parking zone marked by the reliable driving route, the system determines the target available parking space for the user vehicle based on the spatial distribution characteristics of each available parking space in the target parking zone and the attribute differences between each available parking space. The IoT control center sends the target available parking space information to the user vehicle's in-vehicle navigation system. This solution achieves reliable guidance for user vehicles, thereby improving the accuracy of parking guidance.

Description

Technical Field

[0001] This application relates to the field of intelligent transportation Internet of Things (IoT) technology, and more specifically, to an IoT-based smart city parking guidance system and method. Background Technology

[0002] With the acceleration of urbanization, the development of Internet of Things (IoT) technology has provided new possibilities for intelligent transportation systems. By connecting various transportation infrastructures and vehicles, real-time data collection and exchange can be achieved, thereby improving traffic efficiency and safety. On this basis, intelligent transportation IoT application services have emerged. These services not only provide real-time vehicle information but also predict traffic trends through data analysis, offering users personalized travel suggestions and optimized routes to reduce congestion and improve the overall intelligence level of urban transportation. In smart city parking guidance applications, smart city parking guidance systems effectively realize an intelligent and convenient parking experience by relying on a variety of cutting-edge technologies.

[0003] In existing smart city parking guidance applications, parking planning is typically based on IoT technology. First, sensors are deployed in parking lots to monitor parking space occupancy and transmit this data to a central server. Then, the central server creates a real-time updated parking database based on the uploaded data, displaying the availability of parking spaces in each parking lot. Finally, the smart city parking guidance system recommends the best parking option based on the availability of parking spaces. However, existing smart city parking guidance systems often rely on current parking data for zoned guidance, but they struggle to dynamically adapt to changes in the road network capacity (i.e., the maximum number of vehicles the road network in which the parking zone is located can accommodate), parking space distribution, and vehicle location. This results in a lack of confidence in guiding users' vehicles, thus reducing the accuracy of parking guidance. Therefore, how to achieve confidence in guiding users' vehicles and improve the accuracy of parking guidance has become a challenge for the industry. Summary of the Invention

[0004] This application provides a smart city parking guidance system and method based on the Internet of Things, which can realize confidence guidance for user vehicles, thereby improving the accuracy of parking guidance.

[0005] Firstly, this application provides a smart city parking guidance method based on the Internet of Things, comprising the following steps:

[0006] Obtain road network data for each parking zone in the target parking lot;

[0007] The road network data of each parking zone is uploaded to the Internet of Things (IoT) control center. The IoT control center constructs road network association information between each parking zone based on all the road network data, and determines the availability index of each parking zone by combining all the road network association information with the occupancy characteristics of parking spaces during peak hours in the target parking lot.

[0008] The short-term change characteristics of parking space occupancy in each parking zone when a user vehicle enters the target parking lot entrance are determined. Based on the current location of the user vehicle, the changing trends between the short-term change characteristics, and the availability index of each parking zone, a confident driving route for the user vehicle is planned.

[0009] When the user vehicle arrives at the target parking zone marked by the trusted driving route, the parking space attributes of each available parking space in the target parking zone are obtained from the Internet of Things control center. Based on the spatial distribution characteristics of each available parking space in the target parking zone and the attributes of each parking space, the target available parking space for the user vehicle is determined.

[0010] The IoT control center sends the target available parking space information to the user's vehicle's in-vehicle navigation system, guiding the user's vehicle to the target available parking space.

[0011] In some embodiments, the IoT control center constructs road network association information between various parking zones based on all road network data, specifically including:

[0012] Obtain road network data for each parking zone within the target parking lot from the IoT control center;

[0013] A road network connection map for each parking zone is constructed based on the road network data for each parking zone.

[0014] Based on the historical traffic flow data and current traffic flow value of each road segment in each road network connection map, the toll cost of each road network connection map is calculated.

[0015] The road network association information between each parking zone is determined based on each road network connection map and its corresponding toll cost.

[0016] In some embodiments, determining the availability index of each parking zone by combining all road network association information with the occupancy characteristics of parking spaces during peak hours in the target parking lot specifically includes:

[0017] Extract the occupancy characteristics of parking spaces during peak hours from the historical parking data of the target parking lot. The occupancy characteristics include the occupancy characteristics of each parking zone.

[0018] Aggregate analysis of the occupancy characteristics of each parking zone to generate dynamic usage values ​​of parking spaces in each parking zone during peak parking hours in the target parking lot;

[0019] Based on all road network association information and the dynamic usage values ​​of parking spaces in each parking zone, the availability index of each parking zone is calculated.

[0020] In some embodiments, planning a reliable driving route for the user vehicle based on its current location, the changing trends between various short-term change characteristics, and the availability index of each parking zone specifically includes:

[0021] Obtain the current location of the user's vehicle;

[0022] Determine the changing trends among various short-term change characteristics, and extract multiple candidate parking zones from all parking zones based on all changing trends;

[0023] For each candidate parking zone, the driving effectiveness of the user vehicle to the candidate parking zone is determined based on the availability index and short-term change characteristics of the candidate parking zone, thereby obtaining the driving effectiveness of the user vehicle to each candidate parking zone.

[0024] The target parking zone is extracted from all candidate parking zones based on the driving effectiveness of each candidate parking zone.

[0025] Based on the spatial location of the target parking zone and the current location of the user's vehicle, a reliable driving route for the user's vehicle is planned.

[0026] In some embodiments, determining the target available parking space for the user's vehicle based on the spatial distribution characteristics of each available parking space within the target parking zone and the attributes of each parking space specifically includes:

[0027] Obtain the spatial distribution characteristics of each available parking space within the target parking zone;

[0028] The parking space attributes of each vacant parking space are quantized to obtain the quantized attribute value of each vacant parking space.

[0029] The attribute difference values ​​between each available parking space within the target parking zone are determined based on the quantitative attribute values ​​of each available parking space.

[0030] Extract the available parking space corresponding to the largest attribute difference value from all attribute difference values ​​as candidate available parking spaces, and then obtain multiple candidate available parking spaces.

[0031] For each candidate available parking space, the spatial distribution characteristics and parking space attributes corresponding to the candidate available parking space are evaluated by multiple factors to obtain the availability score of each candidate available parking space.

[0032] Extract the candidate available parking space with the highest availability score from all candidate available parking spaces and use it as the target available parking space for the user's vehicle.

[0033] In some embodiments, the method further includes dividing the target parking lot into multiple parking zones using a directional zoning method.

[0034] In some embodiments, road network data for each parking zone is uploaded to the IoT control center via a message queue telemetry transmission protocol.

[0035] Secondly, this application provides a smart city parking guidance system based on the Internet of Things, comprising:

[0036] The acquisition module is used to acquire road network data for each parking zone in the target parking lot;

[0037] The processing module is used to upload the road network data of each parking zone to the Internet of Things control center. The Internet of Things control center constructs the road network association information between each parking zone based on all the road network data, and determines the availability index of each parking zone by combining all the road network association information with the occupancy characteristics of parking spaces during peak hours of the target parking lot.

[0038] The processing module is also used to determine the short-term change characteristics of parking space occupancy in each parking zone when the user vehicle enters the target parking lot entrance, and to plan the user vehicle’s confidence driving route based on the user vehicle’s current location, the change trend between the short-term change characteristics, and the availability index of each parking zone.

[0039] The processing module is also used to obtain the parking space attributes of each available parking space in the target parking zone from the Internet of Things control center when the user vehicle arrives at the target parking zone marked by the confidence driving route, and determine the target available parking space of the user vehicle based on the spatial distribution characteristics of each available parking space in the target parking zone and each parking space attribute.

[0040] The execution module is used by the IoT control center to send the target available parking space information to the user vehicle's in-vehicle navigation system and guide the user vehicle to the target available parking space.

[0041] Thirdly, this application provides a computer device including a memory and a processor, the memory storing code, and the processor being configured to acquire the code and execute the above-described IoT-based smart city parking guidance method.

[0042] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described smart city parking guidance method based on the Internet of Things.

[0043] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects:

[0044] The IoT-based smart city parking guidance system and method provided in this application first acquires road network data for each parking zone in the target parking lot; secondly, the road network data for each parking zone is uploaded to the IoT control center, which constructs road network association information between each parking zone based on all the road network data, and determines the availability index of each parking zone by combining all the road network association information with the occupancy characteristics of parking spaces during peak hours in the target parking lot; furthermore, the short-term change characteristics of parking space occupancy in each parking zone are determined when a user vehicle enters the target parking lot entrance, based on the current location of the user vehicle. The system plans a reliable driving route for the user vehicle based on the changing trends between various short-term change characteristics and the availability index of each parking zone. Then, when the user vehicle arrives at the target parking zone marked by the reliable driving route, it obtains the parking space attributes of each available parking space in the target parking zone from the IoT control center. Based on the spatial distribution characteristics of each available parking space in the target parking zone and the attributes of each parking space, it determines the target available parking space for the user vehicle. Finally, the IoT control center sends the target available parking space information to the user vehicle's in-vehicle navigation system to guide the user vehicle to the target available parking space.

[0045] Therefore, this application can achieve confidence-based guidance for user vehicles, thereby improving the accuracy of parking guidance. First, it constructs road network association information between parking zones based on road network data for each zone, demonstrating the traffic relationships between them, thus dynamically adjusting vehicle flow, optimizing parking resource allocation, and preventing overcrowding in certain zones. Second, it determines the availability index of each parking zone by combining all road network association information with the occupancy characteristics of parking spaces during peak hours in the target parking lot, providing information on the impact of road network capacity, parking space distribution, and vehicle position changes in each parking zone, thereby optimizing parking resource utilization, improving traffic management efficiency, and reducing the impact of dynamic changes in road network capacity, parking space distribution, and vehicle position. Furthermore, it uses the current location of the user vehicle, the changing trends between various short-term change characteristics, and each... The availability index of each parking zone is used to plan a confident driving route for the user's vehicle, ensuring that the user's vehicle quickly reaches the target parking zone, thereby greatly reducing the vehicle's driving time in the parking lot and avoiding traffic congestion and road bottlenecks. Then, based on the spatial distribution characteristics of each available parking space in the target parking zone and the attributes of each parking space, the target available parking space for the user's vehicle is determined. The driver can quickly find the target available parking space, thereby reducing the time spent queuing and searching for parking spaces and obtaining a parking space that better matches the driver's parking preferences, thus providing confident guidance for the user's vehicle. Finally, the IoT control center sends the target available parking space information to the user's vehicle's in-vehicle navigation system, guiding the user's vehicle to the target available parking space. In summary, the technical solution provided in this application can achieve confident guidance for user vehicles, thereby improving the accuracy of parking guidance. Attached Figure Description

[0046] Figure 1 This is an exemplary flowchart of an IoT-based smart city parking guidance method according to some embodiments of this application;

[0047] Figure 2 This is an exemplary flowchart illustrating the determination of road network association information according to some embodiments of this application;

[0048] Figure 3 This is an exemplary flowchart illustrating the determination of a confidence driving route according to some embodiments of this application;

[0049] Figure 4 This is a schematic diagram of the structure of an IoT-based smart city parking guidance system according to some embodiments of this application;

[0050] Figure 5 This is a schematic diagram of the structure of a computer device that implements an IoT-based smart city parking guidance method according to some embodiments of this application. Detailed Implementation

[0051] To better understand the technical solution of this application, the technical solution of this application will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0052] refer to Figure 1 The figure is an exemplary flowchart of an IoT-based smart city parking guidance method 100 according to some embodiments of this application. The IoT-based smart city parking guidance method 100 mainly includes the following steps:

[0053] In step 101, road network data for each parking zone in the target parking lot is obtained.

[0054] It should be noted that in this application, the target parking lot is divided into multiple parking zones using the orientation zoning method, for example, four parking zones: east, west, south, and north. The parking zones represent parking areas in different spaces within the target parking lot.

[0055] In practice, the road network data of each parking zone in the target parking lot can be obtained through the parking lot management database. The road network data includes the road segment information, intersection node information and traffic weight of each road segment of the parking zone. In this embodiment, the road network data represents the collection of various information related to the road network in the parking zone. By obtaining the road network data of the parking zone, the parking characteristics of different parking zones can be effectively managed, and conditions can be provided for the accurate parking of subsequent car owners.

[0056] In step 102, the road network data of each parking zone is uploaded to the Internet of Things (IoT) control center. The IoT control center constructs road network association information between each parking zone based on all the road network data, and determines the availability index of each parking zone by combining all the road network association information with the occupancy characteristics of parking spaces during peak hours in the target parking lot.

[0057] In specific implementation, the road network data of each parking zone can be uploaded to the IoT control center through the message queue telemetry transmission protocol. In addition, in other embodiments, other methods can also be used to upload the road network data of each parking zone to the IoT control center, such as Wi-Fi and Bluetooth. This is not limited here. The IoT control center refers to the control center responsible for collecting and processing data from various IoT devices (such as sensors, smart meters, cameras, smart home appliances, etc.).

[0058] In some embodiments, reference Figure 2 As shown, this figure is an exemplary flowchart illustrating the determination of road network association information according to some embodiments of this application. In this embodiment, the IoT control center constructs the road network association information between various parking zones based on all road network data, which can be achieved through the following steps:

[0059] First, in step 1021, road network data of each parking zone in the target parking lot is obtained from the Internet of Things control center;

[0060] Secondly, in step 1022, a road network connection map for each parking zone is established based on the road network data of each parking zone;

[0061] Then, in step 1023, the toll cost of each road network connection map is calculated based on the historical traffic flow data and current traffic flow value of each road segment in each road network connection map.

[0062] Finally, in step 1024, the road network association information between each parking zone is determined based on each road network connection map and its corresponding toll cost.

[0063] In specific implementation, firstly, road network data for each parking zone within the target parking lot is obtained from the IoT control center; secondly, a road network connection diagram for each parking zone is established based on the road network data of each parking zone, that is, the road network data of each parking zone is imported into the Microscopic Open System for Traffic Simulation (SUMO) in the traffic simulation tool, and the SUMO outputs the road network connection diagram for each parking zone. Alternatively, other traffic simulation tools can be used for processing, such as MATSim, which is not limited here. In the road network connection diagram, nodes represent intersections or parking entrances, and edges represent road segments; furthermore, based on the historical traffic flow data and current traffic flow values ​​of each road segment in each road network connection diagram, the passage cost of each road network connection diagram is calculated, that is, the historical data of each road segment in the target parking lot is retrieved from the historical database of each road network connection diagram. For each road network connection map, the historical traffic flow data and current traffic flow value of each road segment are used. The average traffic flow value of all historical traffic flow data of all road segments in the road network connection map is calculated, and the ratio of the current traffic flow value to the average traffic flow value is used as the passage cost of the road network connection map, thereby obtaining the passage cost of each road network connection map. Finally, based on each road network connection map and its corresponding passage cost, the road network association information between each parking zone is determined. That is, for every two road network connection maps, the absolute difference of the corresponding passage costs is calculated to obtain the road network association value, and the road network association value is used to represent the road network association information between the two road network connection maps, thereby obtaining the road network association information between each parking zone. In addition, in other embodiments, other calculation methods can be used to calculate the road network association information between each parking zone, which is not limited here.

[0064] It should be noted that, in this embodiment, the road network connection diagram represents a topology model established based on the road structure within the parking zone; the traffic flow value represents a quantitative indicator of vehicle traffic conditions on each road segment within the parking zone; the passage cost represents the cost of vehicle passage within the parking zone. By determining the passage cost, the passage efficiency of different road segments within the parking lot can be accurately reflected, providing intelligent decision support for the parking guidance system; the road network association information in this application represents the association information of road network characteristics between different parking zones. The road network association information is characterized by the road network association value, which represents the degree of association of road network characteristics between different parking zones. By determining the road network association information, the traffic relationship between parking zones is effectively displayed. Through the road network association information, the vehicle flow direction can be effectively dynamically adjusted, the allocation of parking resources can be optimized, and overcrowding in certain zones can be avoided.

[0065] In some embodiments, determining the availability index of each parking zone by combining all road network association information with the occupancy characteristics of parking spaces during peak hours in the target parking lot can be achieved through the following steps:

[0066] Extract the occupancy characteristics of parking spaces during peak hours from the historical parking data of the target parking lot. The occupancy characteristics include the occupancy characteristics of each parking zone.

[0067] Aggregate analysis of the occupancy characteristics of each parking zone to generate dynamic usage values ​​of parking spaces in each parking zone during peak parking hours in the target parking lot;

[0068] Based on all road network association information and the dynamic usage values ​​of parking spaces in each parking zone, the availability index of each parking zone is calculated.

[0069] In specific implementation, firstly, the occupancy characteristics of parking spaces during peak hours in the target parking lot are extracted from historical parking data of the target parking lot through a data acquisition system. These occupancy characteristics include the average occupancy rate, the trend of parking space occupancy changes, and the frequency of parking space use. Secondly, the occupancy characteristics of each parking zone are aggregated using a weighted average statistical analysis method to obtain the dynamic usage value of parking spaces in each parking zone during peak hours. Alternatively, regression analysis can be used to calculate the dynamic usage value, which is not limited here. Finally, based on all road network association information and the dynamic usage values ​​of parking spaces in each parking zone, the availability index of each parking zone is calculated. Specifically, the road network association value corresponding to each road network association information is extracted, the standard deviation of all road network association values ​​is calculated, and the standard deviation result is used as a road network constraint factor. For each parking zone, the road network constraint factor is multiplied by the availability index of the parking zone, and the product result is used as the availability index of the parking zone, thus obtaining the availability index of each parking zone.

[0070] It should be noted that, in this application, the occupancy feature represents the usage status characteristics of parking spaces in a parking zone. The occupancy feature mainly describes the average occupancy rate of parking spaces, the trend of parking space occupancy changes, and the frequency of parking space use. Through these features, the availability of parking zones or parking spaces can be accurately assessed, and the parking lot can be used for resource scheduling and optimized parking planning. In this embodiment, the dynamic usage value represents the dynamic change index of parking space use within a parking zone. That is, the larger the dynamic usage value, the greater the dynamic change in parking space use within the parking zone, and vice versa. In this embodiment, the road network constraint factor represents the traffic impact value brought about by the road network structure in the parking lot. In this application, the availability index represents the quantitative parameter of the availability of vacant parking spaces in a parking zone. That is, the larger the availability index, the greater the availability of vacant parking spaces in the parking zone, and vice versa. The availability index reflects the current parking space utilization rate, vacancy level, and accessibility of parking spaces in a parking zone within a certain period of time. By determining the availability index, more accurate parking guidance services can be provided to car owners, the utilization rate of parking resources can be optimized, and traffic management efficiency can be effectively improved.

[0071] In step 103, the short-term change characteristics of parking space occupancy in each parking zone when the user vehicle enters the target parking lot entrance are determined. Based on the current position of the user vehicle, the changing trends between the various short-term change characteristics, and the availability index of each parking zone, a confident driving route for the user vehicle is planned.

[0072] In some embodiments, determining the short-term change characteristics of parking space occupancy in each parking zone when a user's vehicle enters the target parking lot entrance can be achieved by the following steps:

[0073] Determine the vehicle diversion coefficient for each parking zone when a user's vehicle enters the target parking lot entrance;

[0074] Based on the dynamic monitoring module of the IoT control center, vehicle entry and exit events in each parking zone are continuously collected to generate a time series of vehicle entry and exit rates in each parking zone.

[0075] Select a parking zone as the selected parking zone, and perform short-term trend analysis on the time series corresponding to the selected parking zone to obtain the initial short-term change characteristics of user vehicles parking in the selected parking zone when entering the target parking lot entrance;

[0076] The initial short-term change characteristics are corrected based on the vehicle diversion coefficient of the selected parking zone, thereby obtaining the short-term change characteristics of the user vehicle's parking space occupancy in the selected parking zone when entering the target parking lot entrance.

[0077] The short-term change characteristics of the remaining parking spaces in the target parking lot entrance are further determined, thereby obtaining the short-term change characteristics of the parking spaces in each parking zone when the user vehicle enters the target parking lot entrance.

[0078] In specific implementation, firstly, the vehicle diversion coefficients of each parking zone are determined when user vehicles enter the target parking lot entrance. That is, for each parking zone, the ratio of the number of vehicles entering the parking zone to the number of vehicles leaving the parking zone when user vehicles enter the target parking lot entrance is used as the vehicle diversion coefficient of the parking zone, thus obtaining the vehicle diversion coefficients of each parking zone when user vehicles enter the target parking lot entrance. Secondly, the dynamic monitoring module of the IoT control center continuously collects vehicle entry and exit events in each parking zone to generate a time series of vehicle entry and exit rates in each parking zone. Further, a parking zone is selected as the selected parking zone, and the time series corresponding to the selected parking zone is subjected to short-term trend analysis using exponential smoothing in time series analysis methods to obtain the initial short-term change characteristics of parking space occupancy in the selected parking zone when user vehicles enter the target parking lot entrance. In addition, in In other embodiments, a moving average method in time series analysis can be used to perform short-term trend analysis on the time series corresponding to the selected parking zone, which is not limited here; then, the initial short-term change characteristics are corrected based on the vehicle diversion coefficient of the selected parking zone to obtain the short-term change characteristics of the user vehicle's parking space occupancy in the selected parking zone when entering the target parking lot entrance, that is, the corrected expression is: short-term change characteristics = initial short-term change characteristics + (1 + vehicle diversion coefficient); finally, the short-term change characteristics of the remaining parking spaces at the target parking lot entrance are further determined by the method of "correcting the initial short-term change characteristics based on the vehicle diversion coefficient of the selected parking zone to obtain the short-term change characteristics of the user vehicle's parking space occupancy in the selected parking zone when entering the target parking lot entrance", thereby obtaining the short-term change characteristics of the user vehicle's parking space occupancy in each parking zone when entering the target parking lot entrance.

[0079] It should be noted that, in this embodiment, the vehicle diversion coefficient represents the degree to which the parking zone is affected by the diversion of vehicle traffic flow; in this embodiment, the time series represents an ordered dataset of changes in the vehicle entry and exit rates within the parking zone, recorded in chronological order; in this embodiment, the initial short-term change feature represents the short-term trend information of the initial dynamic changes in parking zone occupancy; in this application, the short-term change feature represents the short-term trend information of the dynamic changes in parking zone occupancy, and the short-term change feature can reflect the dynamics of parking occupancy in parking zones in real time. By analyzing the short-term change feature, car owners can know the occupancy trend of certain parking zones in advance, quickly select a suitable parking zone, reduce the time spent searching for parking spaces, and thus improve overall parking efficiency.

[0080] In some embodiments, reference Figure 3 As shown in the figure, this is an exemplary flowchart of determining a confident driving route according to some embodiments of this application. In this embodiment, the confident driving route of the user vehicle is planned by means of the following steps based on the current location of the user vehicle, the changing trend between various short-term change characteristics, and the availability index of each parking zone:

[0081] First, in step 1031, the current location of the user's vehicle is obtained;

[0082] Secondly, in step 1032, the changing trends between various short-term change features are determined, and multiple candidate parking zones are extracted from all parking zones based on all the changing trends;

[0083] Furthermore, in step 1033, for each candidate parking zone, the driving effectiveness of the user vehicle to the candidate parking zone is determined based on the availability index and short-term change characteristics of the candidate parking zone, thereby obtaining the driving effectiveness of the user vehicle to each candidate parking zone.

[0084] Then, in step 1034, the target parking zone is extracted from all candidate parking zones based on the driving effectiveness of each candidate parking zone;

[0085] Finally, in step 1035, a confidence driving route for the user vehicle is planned based on the spatial location of the target parking zone and the current location of the user vehicle.

[0086] In specific implementation, firstly, the current location of the user's vehicle is obtained via GPS; secondly, the changing trends between various short-term change features are determined, and multiple candidate parking zones are extracted from all parking zones based on all changing trends. That is, for every two short-term change features, the absolute difference between the two short-term change features is calculated to obtain the changing trend between the two short-term change features, and then the changing trends between each short-term change feature are obtained. The parking zone corresponding to the largest changing trend is extracted from all parking zones as a candidate parking zone, resulting in multiple candidate parking zones. That is, one changing trend corresponds to two short-term change features, one short-term change feature corresponds to one parking zone, and so on. Furthermore, for each candidate parking zone, the driving effectiveness of the user's vehicle in driving to the candidate parking zone is determined based on the availability index and short-term change features of the candidate parking zone. That is, for each candidate parking zone, the availability index of the candidate parking zone is calculated by weighted summation. The driving efficiency of the user vehicle to the candidate parking zone is calculated by using performance indicators and short-term change characteristics. In other embodiments, other calculation methods can also be used to calculate the driving efficiency of the user vehicle to the candidate parking zone, which is not limited here. Then, based on the driving efficiency of each candidate parking zone, the target parking zone is extracted from all candidate parking zones, that is, the candidate parking zone with the highest driving efficiency is extracted as the target parking zone. Finally, based on the spatial location of the target parking zone and the current location of the user vehicle, the single-source shortest path algorithm (Dijkstra) in the path search algorithm is used to plan the confidence driving route of the user vehicle. That is, starting from the current location of the user vehicle and ending at the spatial location of the target parking zone, the shortest driving route is searched by Dijkstra's algorithm, and the shortest driving route is taken as the confidence driving route of the user vehicle.

[0087] It should be noted that, in this application, the changing trend represents the dynamic differences in the short-term parking occupancy characteristics between different parking zones; in this embodiment, the candidate parking zone represents a pre-selected parking zone; in this embodiment, the driving efficiency represents the suitability index of the user vehicle driving to the candidate parking zone, and the driving efficiency reflects the superiority of selecting the candidate parking zone as the target parking zone; in this application, the confidence driving route represents the best driving path of the user vehicle from the current location to the target parking zone. The planning of the confidence driving route can ensure that the user vehicle can quickly reach the target parking zone, thereby greatly reducing the driving time of the vehicle in the parking lot, thus avoiding traffic congestion and road bottlenecks, and reducing the ineffective driving of the driver when looking for a parking space.

[0088] In step 104, when the user vehicle arrives at the target parking zone marked by the trusted driving route, the parking space attributes of each available parking space in the target parking zone are obtained from the Internet of Things control center, and the target available parking space for the user vehicle is determined based on the spatial distribution characteristics of each available parking space in the target parking zone and the attributes of each parking space.

[0089] In specific implementation, when the user vehicle arrives at the target parking zone marked by the trusted driving route, the parking space attributes of each available parking space in the target parking zone are obtained from the IoT control center. The parking space attributes include distance attributes (distance from the available parking space to the elevator entrance), parking space size attributes, and parking space fee attributes. In this application, the parking space attributes represent a combination of various feature information of the parking space. The parking space attributes are used to describe the characteristics of each parking space and provide relevant parking guidance and decision-making basis for the vehicle.

[0090] In some embodiments, determining the target available parking space for the user's vehicle based on the spatial distribution characteristics of each available parking space within the target parking zone and the attributes of each parking space can be achieved through the following steps:

[0091] Obtain the spatial distribution characteristics of each available parking space within the target parking zone;

[0092] The parking space attributes of each vacant parking space are quantized to obtain the quantized attribute value of each vacant parking space.

[0093] The attribute difference values ​​between each available parking space within the target parking zone are determined based on the quantitative attribute values ​​of each available parking space.

[0094] Extract the available parking space corresponding to the largest attribute difference value from all attribute difference values ​​as candidate available parking spaces, and then obtain multiple candidate available parking spaces.

[0095] For each candidate available parking space, the spatial distribution characteristics and parking space attributes corresponding to the candidate available parking space are evaluated by multiple factors to obtain the availability score of each candidate available parking space.

[0096] Extract the candidate available parking space with the highest availability score from all candidate available parking spaces and use it as the target available parking space for the user's vehicle.

[0097] In specific implementation, firstly, the spatial distribution characteristics of all vacant parking spaces within the target parking zone are acquired through sensors; secondly, the parking space attributes of each vacant parking space are quantified to obtain the quantified attribute value of each vacant parking space, that is: for each vacant parking space, the distance attribute, parking space size attribute, and parking space cost attribute are extracted from the parking space attributes of the vacant parking space, and the distance attribute, the parking space size attribute, and the parking space cost attribute are weighted and summed according to the parking preferences of vehicle users to obtain the quantified attribute value of the vacant parking space, thereby obtaining the quantified attribute value of each vacant parking space. The weight of each attribute can be set between 0 and 1 according to the parking preferences of vehicle users, which will not be elaborated here; furthermore, the attribute difference value between each vacant parking space within the target parking zone is determined based on the quantified attribute value of each vacant parking space, that is: for every two vacant parking spaces, the absolute difference of the quantified attribute values ​​corresponding to the two vacant parking spaces is calculated to obtain the attribute difference value between the two vacant parking spaces. The attribute difference values ​​between available parking spaces are obtained, and then the attribute difference values ​​between each available parking space in the target parking zone are obtained. Further, the available parking space corresponding to the largest attribute difference value is extracted from all attribute difference values ​​as a candidate available parking space, thus obtaining multiple candidate available parking spaces. Then, for each candidate available parking space, the spatial distribution characteristics and parking space attributes corresponding to the candidate available parking space are evaluated using multiple factors to obtain the availability score of each candidate available parking space. That is, for each candidate available parking space, the spatial distribution characteristics and parking space attributes corresponding to the candidate available parking space are usually evaluated using the analytic hierarchy process (AHP) to obtain the availability score of each candidate parking space. Alternatively, a weighted summation method can also be used to evaluate the spatial distribution characteristics and parking space attributes corresponding to the candidate available parking spaces, which is not limited here. Finally, the candidate available parking space corresponding to the largest availability score is extracted from all candidate available parking spaces as the target available parking space for the user's vehicle.

[0098] It should be noted that, in this application, spatial distribution characteristics represent the spatial location information of vacant parking spaces; in this embodiment, quantitative attribute values ​​represent values ​​that quantitatively describe multiple parking space attributes, and by determining the quantitative attribute values, the parking preference of vehicle users can be analyzed to the greatest extent; in this embodiment, attribute difference relationships represent the attribute deviation relationships between different vacant parking spaces, which can be specifically characterized by attribute deviation values, where the attribute deviation value represents the amount of attribute deviation between different vacant parking spaces; in this embodiment, candidate vacant parking spaces represent pre-selected vacant parking spaces; in this application, availability score represents a numerical indicator of the availability of vacant parking spaces, i.e. The higher the availability score, the greater the availability of the vacant parking space, and vice versa. The availability score helps the system prioritize multiple candidate parking spaces and recommend the most suitable parking space to the user. In this application, the target vacant parking space refers to the user's vehicle's target parking space, that is, the optimal parking space recommended to the car owner by the intelligent parking guidance system. By determining the target vacant parking space, the car owner can avoid unnecessary time waste and safety hazards. Especially in busy parking lots, the car owner can quickly find an empty parking space, thereby reducing the time spent queuing and searching for parking spaces and obtaining a parking space that better matches the car owner's parking preferences.

[0099] In step 105, the IoT control center sends the target available parking space information to the user vehicle's in-vehicle navigation system and guides the user vehicle to the target available parking space.

[0100] In some embodiments, the IoT control center sends the target available parking space information to the user vehicle's in-vehicle navigation system, and guides the user vehicle to the target available parking space. This can be achieved through the following steps:

[0101] Once a user's vehicle obtains the target available parking space, the IoT control center sends the target available parking space information to the user's vehicle's in-vehicle navigation system.

[0102] The car owner drives the vehicle to the target available parking space according to the information displayed by the in-vehicle navigation system.

[0103] In practice, once a user's vehicle finds a target available parking space, the IoT control center obtains the target available parking space information through the integrated intelligent parking management system and sends the information to the user's vehicle's in-vehicle navigation system. Upon receiving the information, the in-vehicle navigation system displays the exact location of the target available parking space, including the space's coordinates, direction guidance, and distance. The driver then drives the vehicle to the target available parking space according to the information displayed by the in-vehicle navigation system, thus efficiently completing the parking process.

[0104] Furthermore, in another aspect of this application, in some embodiments, this application provides an Internet of Things-based smart city parking guidance system, with reference to... Figure 4 The figure is a schematic diagram of the structure of an IoT-based smart city parking guidance system according to some embodiments of this application. The IoT-based smart city parking guidance system 200 includes: an acquisition module 201, a processing module 202, and an execution module 203, which are described below:

[0105] The acquisition module 201 in this application is mainly used to acquire road network data of each parking zone in the target parking lot;

[0106] Processing module 202, in this application, is mainly used to upload the road network data of each parking zone to the Internet of Things control center. The Internet of Things control center constructs the road network association information between each parking zone based on all the road network data, and determines the availability index of each parking zone by combining all the road network association information with the occupancy characteristics of parking spaces during peak hours of the target parking lot.

[0107] The processing module 202 is also used to determine the short-term change characteristics of parking space occupancy in each parking zone when the user vehicle enters the target parking lot entrance, and to plan the confidence driving route of the user vehicle based on the current position of the user vehicle, the change trend between each short-term change characteristic and the availability index of each parking zone.

[0108] In addition, the processing module 202 is also used to obtain the parking space attributes of each available parking space in the target parking zone from the Internet of Things control center when the user vehicle arrives at the target parking zone marked by the confidence driving route, and determine the target available parking space of the user vehicle based on the spatial distribution characteristics of each available parking space in the target parking zone and each parking space attribute.

[0109] The execution module 203 in this application is mainly used by the Internet of Things control center to send the target vacant parking space information to the user vehicle's in-vehicle navigation system and guide the user vehicle to the target vacant parking space.

[0110] In addition, this application also provides a computer device, the computer device including a memory and a processor, the memory storing code, and the processor being configured to acquire the code and execute the above-described IoT-based smart city parking guidance method.

[0111] In some embodiments, reference Figure 5 The figure is a schematic diagram of the structure of a computer device implementing an IoT-based smart city parking guidance method according to some embodiments of this application. The IoT-based smart city parking guidance method in the above embodiments can... Figure 5 The computer device shown is used to implement this, and the computer device 300 includes at least one processor 301, a communication bus 302, a memory 303, and at least one communication interface 304.

[0112] The processor 301 can be a general-purpose central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more devices used to control the execution of the IoT-based smart city parking guidance method described in this application.

[0113] The communication bus 302 can be used to transmit information between the aforementioned components.

[0114] The memory 303 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital versatile optical discs, Blu-ray discs, etc.), magnetic disks or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory 303 may exist independently and be connected to the processor 301 via the communication bus 302. The memory 303 may also be integrated with the processor 301.

[0115] The memory 303 stores program code for executing the solution of this application, and its execution is controlled by the processor 301. The processor 301 executes the program code stored in the memory 303. The program code may include one or more software modules. In the above embodiments, the determination of the IoT-based smart city parking guidance method can be implemented by the processor 301 and one or more software modules in the program code in the memory 303.

[0116] Communication interface 304 uses any transceiver-like device to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0117] In a specific implementation, as one example, a computer device may include multiple processors, each of which may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. Here, a processor may refer to one or more devices, circuits, and / or processing cores used to process data (e.g., computer program instructions).

[0118] The aforementioned computer device can be a general-purpose computer device or a special-purpose computer device. In specific implementations, the computer device can be a desktop computer, a portable computer, a network server, a handheld digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. This application does not limit the type of computer device.

[0119] In addition, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described smart city parking guidance method based on the Internet of Things.

[0120] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0121] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A smart city parking guidance method based on the Internet of Things, characterized in that, The method includes the following steps: Obtain road network data for each parking zone in the target parking lot; The road network data of each parking zone is uploaded to the Internet of Things (IoT) control center. The IoT control center constructs road network association information between each parking zone based on all the road network data, and determines the availability index of each parking zone by combining all the road network association information with the occupancy characteristics of parking spaces during peak hours in the target parking lot. The short-term change characteristics of parking space occupancy in each parking zone when a user vehicle enters the target parking lot entrance are determined. The short-term change characteristics represent the short-term trend information of dynamic changes in parking space occupancy. Based on the current location of the user vehicle, the change trend between each short-term change characteristic, and the availability index of each parking zone, a confident driving route for the user vehicle is planned. When the user vehicle arrives at the target parking zone marked by the trusted driving route, the parking space attributes of each available parking space in the target parking zone are obtained from the Internet of Things control center. Based on the spatial distribution characteristics of each available parking space in the target parking zone and the attributes of each parking space, the target available parking space for the user vehicle is determined. The IoT control center sends the target available parking space information to the user vehicle's in-vehicle navigation system, guiding the user vehicle to the target available parking space. The determination of the short-term changes in parking space occupancy in each parking zone when a user's vehicle enters the target parking lot entrance is achieved through the following steps: Determine the vehicle diversion coefficient for each parking zone when a user's vehicle enters the target parking lot entrance; Based on the dynamic monitoring module of the IoT control center, vehicle entry and exit events in each parking zone are continuously collected to generate a time series of vehicle entry and exit rates in each parking zone. Select a parking zone as the selected parking zone, and perform short-term trend analysis on the time series corresponding to the selected parking zone to obtain the initial short-term change characteristics of user vehicles parking in the selected parking zone when entering the target parking lot entrance; The initial short-term change characteristics are corrected based on the vehicle diversion coefficient of the selected parking zone, thereby obtaining the short-term change characteristics of the user vehicle's parking space occupancy in the selected parking zone when entering the target parking lot entrance. The short-term change characteristics of the remaining parking spaces in the target parking lot entrance are further determined, thereby obtaining the short-term change characteristics of the parking spaces in each parking zone when the user vehicle enters the target parking lot entrance.

2. The method as described in claim 1, characterized in that, The IoT control center constructs road network association information between various parking zones based on all road network data, specifically including: Obtain road network data for each parking zone within the target parking lot from the IoT control center; A road network connection map for each parking zone is constructed based on the road network data for each parking zone. Based on the historical traffic flow data and current traffic flow value of each road segment in each road network connection map, the toll cost of each road network connection map is calculated. The road network association information between each parking zone is determined based on each road network connection map and its corresponding toll cost.

3. The method as described in claim 1, characterized in that, The availability indicators for each parking zone are determined by combining all road network information with the occupancy characteristics of parking spaces during peak hours in the target parking lot. Specifically, these indicators include: Extract the occupancy characteristics of parking spaces during peak hours from the historical parking data of the target parking lot. The occupancy characteristics include the occupancy characteristics of each parking zone. Aggregate analysis of the occupancy characteristics of each parking zone to generate dynamic usage values ​​of parking spaces in each parking zone during peak parking hours in the target parking lot; Based on all road network association information and the dynamic usage values ​​of parking spaces in each parking zone, the availability index of each parking zone is calculated.

4. The method as described in claim 1, characterized in that, The plan for a reliable driving route for the user vehicle, based on its current location, the trends in various short-term change characteristics, and the availability indicators of each parking zone, specifically includes: Obtain the current location of the user's vehicle; Determine the changing trends among various short-term change characteristics, and extract multiple candidate parking zones from all parking zones based on all changing trends; For each candidate parking zone, the driving effectiveness of the user vehicle to the candidate parking zone is determined based on the availability index and short-term change characteristics of the candidate parking zone, thereby obtaining the driving effectiveness of the user vehicle to each candidate parking zone. The target parking zone is extracted from all candidate parking zones based on the driving effectiveness of each candidate parking zone. Based on the spatial location of the target parking zone and the current location of the user's vehicle, a reliable driving route for the user's vehicle is planned.

5. The method as described in claim 1, characterized in that, Determining the target available parking space for the user's vehicle based on the spatial distribution characteristics of each available parking space within the target parking zone and the attributes of each parking space specifically includes: Obtain the spatial distribution characteristics of each available parking space within the target parking zone; The parking space attributes of each vacant parking space are quantized to obtain the quantized attribute value of each vacant parking space. The attribute difference values ​​between each available parking space within the target parking zone are determined based on the quantitative attribute values ​​of each available parking space. Extract the available parking space corresponding to the largest attribute difference value from all attribute difference values ​​as candidate available parking spaces, and then obtain multiple candidate available parking spaces. For each candidate available parking space, the spatial distribution characteristics and parking space attributes corresponding to the candidate available parking space are evaluated by multiple factors to obtain the availability score of each candidate available parking space. Extract the candidate available parking space with the highest availability score from all candidate available parking spaces and use it as the target available parking space for the user's vehicle.

6. The method as described in claim 1, characterized in that, Also includes: The target parking lot is divided into multiple parking zones using the orientation zoning method.

7. The method as described in claim 1, characterized in that, The road network data of each parking zone is uploaded to the IoT control center through the message queue telemetry transmission protocol.

8. A smart city parking guidance system based on the Internet of Things, which uses the method described in any one of claims 1 to 7 for parking guidance, characterized in that, The system includes: The acquisition module is used to acquire road network data for each parking zone in the target parking lot; The processing module is used to upload the road network data of each parking zone to the Internet of Things control center. The Internet of Things control center constructs the road network association information between each parking zone based on all the road network data, and determines the availability index of each parking zone by combining all the road network association information with the occupancy characteristics of parking spaces during peak hours of the target parking lot. The processing module is also used to determine the short-term change characteristics of parking space occupancy in each parking zone when the user vehicle enters the target parking lot entrance, and to plan the user vehicle’s confidence driving route based on the user vehicle’s current location, the change trend between the short-term change characteristics, and the availability index of each parking zone. The processing module is also used to obtain the parking space attributes of each available parking space in the target parking zone from the Internet of Things control center when the user vehicle arrives at the target parking zone marked by the confidence driving route, and determine the target available parking space of the user vehicle based on the spatial distribution characteristics of each available parking space in the target parking zone and each parking space attribute. The execution module is used by the IoT control center to send the target available parking space information to the user vehicle's in-vehicle navigation system and guide the user vehicle to the target available parking space.

9. A computer device, characterized in that, The computer device includes a memory and a processor, the memory storing code, and the processor being configured to retrieve the code and execute the IoT-based smart city parking guidance method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the IoT-based smart city parking guidance method as described in any one of claims 1 to 7.

Images