Intelligent parking space management method, device and equipment and storage medium

Abstract

The invention relates to an intelligent parking space management method, device and equipment and a storage medium, and the method comprises the steps: obtaining basic space layout data and parking space management information of a parking lot, and carrying out the region division processing, and obtaining the corresponding region parking space information; acquiring real-time sensing data acquired by the parking lot, and performing association processing on the real-time sensing data and the regional parking space information to obtain a corresponding real-time parking space state group; obtaining vehicle behavior data collected by the parking lot, and performing use prediction on the regional parking space information to obtain a corresponding parking space occupation trend; vehicle feature recognition is carried out on the vehicle behavior data to obtain corresponding special vehicle information, and parking demand prediction is carried out on the special vehicle information based on the parking space occupation trend to obtain a corresponding special vehicle priority parking space; and comprehensively analyzing the initial parking space distribution scheme and the priority parking space of the special vehicle to obtain a corresponding global scheduling strategy. The parking stall use state of each area can be mastered in real time.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent parking space management, and in particular to an intelligent parking space management method, device, equipment and storage medium. Background Art

[0002] With the continuous acceleration of urbanization and the continuous growth of the number of motor vehicles, the problem of parking difficulties has become increasingly prominent, and intelligent parking lot management has become an important issue in the development of modern cities. Traditional parking lot management methods mainly rely on manual monitoring and fixed parking space allocation strategies, which is difficult to adapt to the increasingly complex parking needs. Existing parking lot management systems often only focus on the monitoring of the idle status of a single parking space, while ignoring the dynamic allocation of parking space resources and the differentiated needs of different vehicles, which leads to low efficiency in the utilization of parking resources and cannot meet the emergency parking needs of special vehicles. At the same time, due to the lack of in-depth analysis of vehicle behavior characteristics and parking needs, it is difficult for the existing system to achieve intelligent parking space prediction and allocation, resulting in unreasonable parking lot resource scheduling and poor user experience. This simplified management method can no longer meet the operational needs of modern smart parking lots, and a more intelligent and refined parking space management method is urgently needed. Summary of the invention

[0003] The main purpose of the present invention is to provide an intelligent parking space management method, device, equipment and storage medium, which can grasp the parking space usage status of each area in real time.

[0004] To achieve the above object, the present invention provides an intelligent parking space management method, comprising: Obtain the basic spatial layout data and parking space management information of the parking lot, and perform regional division processing to obtain the corresponding regional parking space information; Acquire the real-time sensor data collected by the parking lot, and associate it with the regional parking space information to obtain a corresponding real-time parking space status group; Acquire vehicle behavior data collected by the parking lot, and make usage predictions for the parking space information in the area to obtain corresponding parking space occupancy trends; Performing resource planning analysis on the real-time parking space status group and the parking space occupancy trend to obtain a corresponding initial parking space allocation plan; Performing vehicle feature recognition on the vehicle behavior data to obtain corresponding special vehicle information, performing parking demand prediction on the special vehicle information based on the parking space occupancy trend to obtain corresponding special vehicle priority parking spaces; The initial parking space allocation plan and the priority parking spaces for special vehicles are comprehensively analyzed to obtain a corresponding global scheduling strategy.

[0005] Furthermore, the basic spatial layout data and parking space management information of the parking lot are obtained, and the area division processing is performed to obtain the corresponding area parking space information, including: Performing grid division processing on the basic spatial layout data to obtain a corresponding basic grid unit group; Extracting the outline of the basic grid unit group according to the parking space management information to obtain corresponding obstacle boundary data; Performing regional connectivity analysis on the obstacle boundary data to obtain a corresponding available space area set; Matching basic parking space information according to the available space area set to obtain a corresponding initial parking space layout diagram; Performing regional spatial clustering on the initial parking space layout diagram to obtain corresponding regional spatial groupings; Mapping parking space management rules according to the regional spatial grouping, and performing parking space number allocation processing to obtain a corresponding regional parking space index; Collect parking space environment parameters according to the regional parking space index to obtain a corresponding parking space environment feature set; Multi-dimensional data fusion is performed on the parking space environment feature set to obtain the regional parking space information.

[0006] Furthermore, the real-time sensor data collected by the parking lot is acquired, and the real-time sensor data is associated with the regional parking space information to obtain a corresponding real-time parking space status group, including: Separating the real-time sensing data to obtain corresponding real-time parking space occupancy data and parking space image data; Performing regional feature positioning on the parking space image data according to the real-time parking space occupancy data to obtain corresponding parking space image feature data; Performing parking space occupancy analysis on the parking space image feature data to obtain corresponding parking space occupancy data; Performing data fusion processing on the real-time parking space occupancy data and the parking space occupancy feature vector to obtain a corresponding parking space state feature set; According to the parking space status feature set, the parking space information of the area is mapped and associated with numbers to obtain a corresponding parking space status mapping table; Performing time series clustering on the parking space status mapping table to obtain corresponding parking space status grouping data; The parking space status grouping data is classified and labeled according to a preset status standard to obtain a corresponding real-time parking space status group.

[0007] Furthermore, the acquiring of the vehicle behavior data collected by the parking lot and the prediction of the use of the regional parking space information to obtain the corresponding parking space occupancy trend include: Performing data fusion on the vehicle entry and exit time data, vehicle path data and parking space selection data collected from the parking lot to obtain corresponding vehicle behavior data; Perform parking feature analysis based on the vehicle behavior data to obtain corresponding parking space selection feature data and parking duration feature data; Performing cluster analysis on the parking space selection feature data and the parking duration feature data to obtain a corresponding parking behavior pattern library; Performing correlation analysis on regional parking space history records based on the parking behavior pattern library to obtain corresponding regional parking space usage rules; Performing time series decomposition on the parking space usage pattern in the area to obtain corresponding fixed-time usage characteristics and fluctuating-time usage characteristics; Probabilistic statistics are performed based on the fixed time period usage characteristics and the fluctuating time period usage characteristics to obtain a corresponding regional parking space occupancy probability distribution; A sequence prediction process is performed on the parking space occupancy probability distribution in the area to obtain a corresponding parking space occupancy trend.

[0008] Furthermore, performing resource planning analysis on the real-time parking space status group and the parking space occupancy trend to obtain a corresponding initial parking space allocation plan includes: Performing a parking space state time series analysis on the real-time parking space state group to obtain a corresponding parking space state change pattern; Performing regional clustering on the parking space occupancy trend according to the parking space state change pattern to obtain a corresponding regional occupancy density distribution; Calculate the saturation threshold of the occupancy density distribution of the area to obtain corresponding parking space saturation level data; Quantify the parking space resource partitions according to the parking space saturation level data to obtain a corresponding allocatable parking space set; Performing spatial distance calculation on the set of allocatable parking spaces to obtain a corresponding parking space proximity relationship graph; Performing a network topology analysis on the allocatable parking space set according to the parking space proximity relationship graph to obtain a corresponding parking space connected subgraph group; Constructing a minimum spanning tree for the connected subgraph group of parking spaces to obtain a corresponding optimized allocation path; A resource configuration analysis is performed on the set of allocatable parking spaces according to the optimized allocation path to obtain a corresponding initial parking space allocation plan.

[0009] Further, the performing vehicle feature recognition on the vehicle behavior data to obtain corresponding special vehicle information, performing parking demand prediction on the special vehicle information based on the parking space occupancy trend to obtain corresponding special vehicle priority parking spaces, includes: Extracting features from the vehicle behavior data to obtain a corresponding vehicle behavior feature data set; Performing classification and identification processing according to the vehicle behavior feature data set to obtain a corresponding vehicle type identification; Performing special vehicle screening processing on the vehicle type identifier to obtain a corresponding special vehicle list; Performing historical parking matching analysis on the special vehicle list to obtain corresponding special vehicle parking patterns; Performing time prediction analysis on the special vehicle parking mode to obtain a corresponding vehicle arrival time prediction result; The parking space occupancy trend is divided into windows according to the vehicle arrival time prediction result to obtain a corresponding parking space availability schedule; Prioritizing the parking space availability schedule to obtain a corresponding priority parking space candidate set; The special vehicle list is matched and optimized according to the priority parking space candidate set to obtain a corresponding special vehicle priority parking space allocation plan.

[0010] Furthermore, the initial parking space allocation scheme and the priority parking spaces for special vehicles are comprehensively analyzed to obtain a corresponding global scheduling strategy, including: Performing resource allocation analysis on the initial parking space allocation plan and the priority parking spaces for special vehicles to obtain a parking space resource allocation matrix; Performing dynamic parking scheduling according to the parking space resource allocation matrix to obtain a dynamic parking scheduling sequence; Prioritizing the parking space dynamic scheduling sequence to obtain a parking space scheduling priority table; Performing resource reservation analysis on the priority parking spaces for special vehicles according to the parking space scheduling priority table to obtain a reserved parking space group; Performing spatial distribution calculation on the reserved parking space group to obtain a parking space spatial distribution map; Dynamically updating the initial parking space allocation plan according to the parking space spatial distribution map to obtain an updated parking space allocation plan; Performing conflict detection on the updated parking space allocation scheme to obtain parking space conflict area information; Optimizing and adjusting the updated parking space allocation plan according to the parking space conflict area information to obtain an optimized parking space allocation strategy; Performing spatiotemporal consistency verification on the optimized parking space allocation strategy to obtain a verified scheduling plan; The verification scheduling scheme is globally scheduled for resources to obtain the global scheduling strategy.

[0011] The present invention further provides an intelligent parking space management device, which is applied to any one of the intelligent parking space management methods described above, comprising: A collection module, which is used to obtain basic spatial layout data and parking space management information of the parking lot, and perform regional division processing to obtain corresponding regional parking space information; An analysis module, the analysis module is used to obtain the real-time sensor data collected by the parking lot, and associate it with the regional parking space information to obtain a corresponding real-time parking space status group; An association module, the association module is used to obtain the vehicle behavior data collected by the parking lot, and to make a usage prediction for the parking space information in the area to obtain a corresponding parking space occupancy trend; A processing module, the processing module is used to perform resource planning analysis on the real-time parking space status group and the parking space occupancy trend to obtain a corresponding initial parking space allocation plan; A control module, the control module is used to perform vehicle feature recognition on the vehicle behavior data to obtain corresponding special vehicle information, perform parking demand prediction on the special vehicle information based on the parking space occupancy trend to obtain corresponding special vehicle priority parking spaces; An execution module is used to comprehensively analyze the initial parking space allocation plan and the priority parking spaces for special vehicles to obtain a corresponding global scheduling strategy.

[0012] The present invention also provides an intelligent parking space management device, comprising: Memory, used to store programs; The processor is used to execute the program to implement each step of the intelligent parking space management method as described in any one of claims 1 to 7.

[0013] The present invention also provides a storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute any of the above methods.

[0014] The present invention provides an intelligent parking space management method, device, equipment and storage medium, which have the following beneficial effects: By dividing the basic spatial layout data and parking space management information of the parking lot into regions, the refined management of parking resources is realized and the accuracy of parking resource allocation is improved. By associating the real-time sensor data with the regional parking space information, the parking space usage status of each region can be grasped in real time, which effectively solves the problem of untimely resource monitoring in traditional parking lot management. Based on the vehicle behavior data, the use prediction of regional parking space information can accurately grasp the parking space occupancy law, predict the parking demand in advance, and avoid the unreasonable resource allocation under the traditional management method. By conducting resource planning and analysis on the real-time parking space status and occupancy trend, a scientific parking space allocation plan is formulated, which significantly improves the operation efficiency of the parking lot. At the same time, through vehicle feature recognition and parking demand prediction of special vehicles, priority parking spaces are reserved for special vehicles, which solves the problem that differentiated parking needs cannot be met under the traditional management method. Finally, by comprehensively analyzing the initial parking space allocation plan and the priority parking spaces for special vehicles, a global scheduling strategy is formulated, which realizes the intelligent scheduling and optimal configuration of parking resources, greatly improving the user's parking experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a flow chart of an intelligent parking space management method provided by the present invention; Figure 2 This is a structural diagram of an intelligent parking space management device provided by the present invention; Figure 3 This is a structural diagram of an intelligent parking space management device provided by the present invention.

[0016] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0018] The present invention is further described below in conjunction with the accompanying drawings and specific implementation methods.

[0019] Reference Figure 1 As shown, the present invention provides an intelligent parking space management method, which is characterized by comprising: Step S1: Obtain the basic spatial layout data and parking space management information of the parking lot, and perform regional division processing to obtain corresponding regional parking space information; Step S2: acquiring real-time sensor data collected by the parking lot, and correlating the data with the regional parking space information to obtain a corresponding real-time parking space status group; Step S3: Obtain vehicle behavior data collected in the parking lot, and make usage predictions for regional parking space information to obtain corresponding parking space occupancy trends; Step S4: Perform resource planning analysis on the real-time parking space status group and parking space occupancy trend to obtain a corresponding initial parking space allocation plan; Step S5: Perform vehicle feature recognition on the vehicle behavior data to obtain corresponding special vehicle information, perform parking demand prediction on the special vehicle information based on the parking space occupancy trend, and obtain corresponding special vehicle priority parking spaces; Step S6: Comprehensively analyze the initial parking space allocation plan and the priority parking spaces for special vehicles to obtain the corresponding global scheduling strategy.

[0020] Based on the above steps, the detailed process is as follows: Step S1: Obtain the basic spatial layout data and parking space management information of the parking lot, and perform regional division processing, including obtaining spatial data such as the floor plan and parking space distribution map of the parking lot. Specifically, record the basic information such as the specific location coordinates, parking space size, and parking space number of each parking space. At the same time, it is also necessary to collect management information such as parking space type (such as ordinary parking space, charging pile parking space, barrier-free parking space, etc.), charging standards, and use restrictions. After obtaining these basic data, intelligent regional division is performed according to the actual situation of the parking lot. The parking lot can be divided into multiple management areas based on factors such as location proximity and functional similarity. For example, it can be divided into A, B, and C areas according to the distance from the entrance and exit, or divided into temporary parking areas, long-term parking areas, etc. according to the purpose. The system also needs to assign corresponding management attributes to each area, such as different areas may have different charging standards or use restrictions. The results of this regional division will directly affect the subsequent parking space allocation and management strategies.

[0021] Step S2: Acquire the real-time sensor data of the parking lot and associate it for processing. On the basis of establishing the basic data model, deploy various sensors to monitor the status of parking spaces in real time. These sensors usually include geomagnetic sensors, video surveillance cameras, ultrasonic sensors, etc. Geomagnetic sensors can accurately detect whether a parking space is occupied, video surveillance can identify the specific parking location and license plate information of the vehicle, and ultrasonic sensors can measure the distance between the vehicle and adjacent objects. The system associates these real-time collected sensor data with the regional parking space information divided in step S1 to establish a real-time parking space status database. This database not only records the occupancy status of each parking space (free, occupied, reserved, etc.), but also includes environmental information around the parking space (such as temperature, light, etc.), as well as timestamp information of vehicle entry and exit. The association processing of these data provides an important basis for subsequent parking space management decisions.

[0022] Step S3: Obtain vehicle behavior data and use prediction The system predicts parking space usage trends by analyzing historical parking data and real-time traffic data. First, collect vehicle entry and exit records, parking duration, visit frequency and other behavioral data. These data can come from license plate recognition systems, parking payment records, visitor reservation systems, etc. By statistically analyzing these data, the system can identify patterns such as parking patterns on weekdays and weekends, changes in parking demand during peak hours in the morning and evening, and traffic fluctuations on special holidays. At the same time, the system will also use machine learning algorithms to predict parking space occupancy in the future in combination with external factors such as weather conditions and surrounding activity arrangements. This prediction can help parking lot managers adjust parking space allocation strategies in advance and optimize resource utilization efficiency.

[0023] Step S4: Perform resource planning analysis on the real-time parking space status group and parking space occupancy trend. Based on the real-time parking space status information and predicted parking space occupancy trend obtained in the previous step, start intelligent resource planning analysis. Comprehensively evaluate each parking space based on multiple factors, including the geographical location advantage of the parking space, the current occupancy status, the expected vacancy time, the perfection of surrounding facilities, etc. At the same time, combined with dynamic factors such as parking space turnover rate and regional congestion level in different time periods, a real-time availability index is calculated for each parking space. On this basis, an optimization algorithm, such as a genetic algorithm or a heuristic algorithm, is used to generate an initial parking space allocation plan. This plan will take into account the overall utilization efficiency of the parking lot and try to avoid overcrowding in some areas while other areas are idle. The initial allocation plan will also include some alternative plans to deal with emergencies and special needs.

[0024] Step S5: Vehicle feature identification and priority parking allocation for special vehicles This step focuses on the identification and priority of special vehicles. The characteristics of vehicles entering the parking lot are identified through license plate recognition, RFID tags or other identity recognition technologies. Special vehicles may include emergency vehicles, vehicles for the disabled, vehicles for VIP users, electric vehicles, etc. A special demand forecasting model is established based on the historical parking data of different types of special vehicles and the real-time parking space occupancy trend. This model will consider factors such as the frequency of use, parking duration, and priority level of special vehicles, and reserve an appropriate number of priority parking spaces for these vehicles. The number and location of reserved parking spaces will be adjusted dynamically over time to ensure that the parking needs of special vehicles are met while avoiding waste of resources. The system will also establish an emergency response mechanism to quickly adjust the parking space allocation strategy under special circumstances.

[0025] Step S6: Integrate the previous initial parking space allocation plan with the priority parking space requirements for special vehicles to form the final global scheduling strategy. This process must first resolve possible resource conflicts. For example, when the ordinary parking space allocation plan overlaps with the reserved parking spaces for special vehicles, adjustments are made according to the pre-set priority rules. The global scheduling strategy also needs to consider the impact of external factors such as real-time traffic flow, weather conditions, and special events. Establish a dynamic feedback mechanism to continuously monitor the execution effect of the scheduling strategy, including indicators such as parking space utilization, user satisfaction, and traffic efficiency. When these indicators are abnormal or reach the preset threshold, the strategy optimization process is automatically triggered to adjust the parking space allocation plan in a timely manner. The final scheduling strategy must be able to balance efficiency and fairness, ensuring the optimal use of parking resources while taking into account the reasonable needs of different user groups.

[0026] The present invention provides an intelligent parking space management method, which realizes the refined management of parking resources and improves the accuracy of parking lot resource allocation by regional division processing of parking lot basic space layout data and parking space management information. By associating real-time sensor data with regional parking space information, the parking space usage status of each area can be grasped in real time, effectively solving the problem of untimely resource monitoring in traditional parking lot management. Based on vehicle behavior data, the use prediction of regional parking space information can accurately grasp the parking space occupancy law, predict parking demand in advance, and avoid the unreasonable resource allocation under the traditional management method. By performing resource planning and analysis on the real-time parking space status and occupancy trend, a scientific parking space allocation plan is formulated, which significantly improves the operation efficiency of the parking lot. At the same time, by vehicle feature recognition and parking demand prediction of special vehicles, priority parking spaces are reserved for special vehicles, solving the problem that differentiated parking needs cannot be met under the traditional management method. Finally, by comprehensively analyzing the initial parking space allocation plan and the priority parking spaces for special vehicles, a global scheduling strategy is formulated, which realizes the intelligent scheduling and optimal configuration of parking resources, greatly improving the user's parking experience.

[0027] In one embodiment, basic spatial layout data and parking space management information of a parking lot are obtained, and area division processing is performed to obtain corresponding area parking space information, including: By obtaining the floor plan of the parking lot as the basic spatial layout data and combining it with parking space management information such as parking space size and aisle width measured on site, the parking lot space is accurately divided into areas to obtain detailed regional parking space information.

[0028] The plane layout drawing is evenly divided into grids of 0.5m x 0.5m in size to form a basic grid unit group. Each grid unit contains attribute information such as location coordinates and occupancy status. Based on the parking space management information of fixed facilities such as load-bearing columns and walls inside the parking lot, edge detection and contour extraction operations are performed on the basic grid unit group to generate a data set representing the obstacle boundary.

[0029] The obstacle boundary data is analyzed for connected domains through the region growing algorithm to identify all the independent areas in the parking lot that are not connected to each other, forming a set of available space areas. Each area in the set has the basic conditions for parking vehicles. For each available space area, it is matched with the standard parking space size (such as 2.5 meters × 5 meters) to determine the maximum number of parking spaces that can be accommodated in the area and the arrangement method, thereby generating an initial parking space layout diagram.

[0030] The density clustering algorithm is used to perform spatial clustering analysis on the parking spaces in the initial parking space layout diagram, and the parking spaces in adjacent areas are divided into the same group to obtain the regional spatial grouping results. Based on the functional positioning of different areas, the corresponding parking space management rules are matched for each group, such as visitor area, fixed parking space area, etc., and a unique number is assigned to each parking space in the form of "area number-row number-space number" to form a regional parking space index.

[0031] After completing the parking space layout planning, the sensor equipment deployed in various areas of the parking lot collects environmental parameters such as light intensity, air quality, temperature and humidity around the parking spaces to build a parking space environmental feature set. Finally, the multi-dimensional data such as the parking space location information, size data, management attributes and environmental characteristics are fused and processed to form complete regional parking space information.

[0032] This embodiment adopts a gridded space division method and combines multi-dimensional data fusion processing to achieve accurate planning and efficient use of parking space resources. The uniform grid division strategy based on 0.5 meters × 0.5 meters ensures the accuracy and standardization of parking space layout. The connected domain analysis is performed through the regional growing algorithm to effectively identify all available spaces inside the parking lot, avoiding waste of resources. The application of the density clustering algorithm enables adjacent parking spaces to be reasonably grouped, improving the systematic nature of parking space management. The numbering system of "area code-row number-space number" establishes a clear parking space index structure for rapid positioning and management. The collection and fusion processing of environmental sensor data provides all-round information support for parking space management and enhances the intelligent level of parking lot operations. This method establishes a complete parking space resource management system, which significantly improves the space utilization and management efficiency of parking lots.

[0033] In one embodiment, real-time sensor data collected by the parking lot is obtained, and is associated with regional parking space information to obtain a corresponding real-time parking space status group, including: Real-time sensor data is obtained through the sensor network deployed in the parking area. The sensor data includes occupancy status information collected by the parking space occupancy sensor and image data collected by the parking space monitoring camera. The system performs data separation processing on the acquired sensor data and stores the parking space occupancy sensor data and image data in the corresponding data cache area respectively.

[0034] The target area to be analyzed is determined based on the parking space occupancy sensor data, and the regional features are located in the image data. The positioning process uses an edge detection algorithm to extract the contour features of the parking space area, and combines the pre-calibrated parking space coordinate information to obtain the image feature data corresponding to each parking space. The image feature data contains the grayscale, texture, contour and other visual features of the parking space area.

[0035] Perform occupancy status analysis on the extracted parking space image feature data. The analysis process uses a deep learning model to identify and classify the feature data and output the probability value of the parking space being occupied. The deep learning model is trained with a large amount of labeled data and has a high recognition accuracy.

[0036] The parking space occupancy data collected by the sensor and the occupancy probability obtained by image analysis are fused. The fusion adopts the Bayesian probability model, comprehensively considers the reliability weights of the two types of data, and generates the final parking space status feature vector. The feature vector contains key information such as parking space occupancy status and confidence.

[0037] According to the preset parking space numbering rules, a mapping relationship is established between the fused state features and the regional parking space information. The mapping table records the number, location coordinates, current state and other attribute information of each parking space. The system performs cluster analysis on the parking space state mapping table according to the time series and groups parking spaces with similar state change rules.

[0038] The grouped data is labeled according to the predefined status standards. The status standards include categories such as idle, occupied, reserved, and maintained, and each category has a corresponding judgment threshold. The labeling results form a real-time parking space status group, which serves as an important basis for parking space management decisions. The status group data is updated regularly to ensure that the management system has accurate parking space resource status.

[0039] This embodiment collects real-time data from the parking lot sensor network and combines it with regional parking space information for correlation processing. The intelligent parking space management method realizes accurate perception and analysis of parking space status. The system integrates multi-source data analysis technology to fuse the occupancy data collected by the sensor with the image feature data, effectively eliminating the misjudgment problem caused by a single data source and improving the accuracy of parking space status recognition. By analyzing the parking space image features with the help of a deep learning model and combining the Bayesian probability model for data fusion, the system can adaptively adjust the reliability weights of different data sources and enhance the robustness of status judgment. By establishing a mapping relationship between parking space numbers and status features and performing time series clustering analysis, the dynamic change law of parking space resources is mastered, providing a reliable basis for parking lot management decisions.

[0040] In one embodiment, vehicle behavior data collected in a parking lot is obtained, and usage prediction of regional parking space information is performed to obtain corresponding parking space occupancy trends, including: The system collects vehicle entry and exit time data, vehicle path data, and parking space selection data in real time through cameras, geomagnetic sensors, and other collection devices in the parking lot. These heterogeneous data are integrated and processed through data fusion algorithms to form a standardized vehicle behavior data set. During the data fusion process, the system performs time alignment and spatial matching on the data to eliminate the time difference error and spatial error between the collection devices to ensure the consistency and accuracy of the data.

[0041] Based on the fused vehicle behavior data, the parking space selection features and parking time features are extracted through the parking feature analysis module. Parking space selection features include static features such as parking space geographical location, surrounding facilities distribution, sunshade and rain shelter conditions, as well as dynamic features such as parking space turnover rate and usage frequency. Parking time features include time dimension features such as average parking time in different time periods and parking time distribution patterns.

[0042] The extracted feature data are clustered by cluster analysis algorithm to establish a parking behavior pattern library. During the cluster analysis process, the system divides vehicle behaviors into different categories according to the similarity of feature data, such as temporary parking, short-term parking, long-term parking, etc. Each mode has a unique feature combination.

[0043] Based on the parking behavior pattern library, the historical usage records of regional parking spaces are analyzed to explore the usage patterns of regional parking spaces. The association analysis calculates the correlation between different features to identify key factors affecting the use of parking spaces, such as the difference in usage between weekdays and holidays, and the impact of weather factors.

[0044] The identified regional parking space usage patterns are decomposed in time series, and the parking space usage characteristics are divided into fixed-time usage characteristics and fluctuating-time usage characteristics. Fixed-time usage characteristics reflect the periodic regularity of parking space usage, such as the usage pattern during the morning and evening peak hours on weekdays; fluctuating-time usage characteristics reflect temporary and sudden usage changes, such as the usage peak during large-scale events.

[0045] Based on the decomposed time series characteristics, the system calculates the occupancy probability distribution of regional parking spaces in different time periods. In the probability statistics process, the system comprehensively considers factors such as usage frequency, duration, and periodicity in historical data to construct a probability density function, thereby quantifying the possibility of parking spaces being occupied.

[0046] The time series prediction model is used to predict and analyze the probability distribution of parking space occupancy and generate the parking space occupancy trend in the future period. The prediction model combines the periodic laws and volatility changes in historical data, and predicts the changing trend of parking space occupancy status through time series analysis methods, providing a decision-making basis for parking lot management.

[0047] This embodiment achieves standardized integration of vehicle behavior data by fusing multi-source heterogeneous data collected from parking lots, effectively eliminates spatiotemporal errors between different collection devices, and ensures the accuracy and reliability of data analysis. The parking behavior pattern library established based on cluster analysis can accurately characterize the parking characteristics of different types of vehicles, providing a reliable data basis for parking space usage prediction. The parking space usage characteristics are divided into fixed time periods and fluctuating time periods by the time series decomposition method, accurately identifying periodic laws and temporary changes, and improving the prediction model's ability to analyze the parking space occupancy status in different periods. The probabilistic statistical model established on this basis comprehensively considers multi-dimensional influencing factors, realizes accurate quantification of parking space occupancy probability, and provides a scientific basis for parking lot management decisions. This method overcomes the problems of data fragmentation and low prediction accuracy in traditional parking space management methods, and significantly improves the efficiency and accuracy of intelligent parking space management.

[0048] In one embodiment, a resource planning analysis is performed on the real-time parking space status group and the parking space occupancy trend to obtain a corresponding initial parking space allocation plan, including: The intelligent parking space management method performs resource planning analysis on the real-time parking space status group and parking space occupancy trend to obtain the initial parking space allocation plan. The optimal allocation of parking space resources is achieved through technical means such as parking space status time series analysis, regional clustering, saturation analysis, resource partitioning, spatial distance calculation, network topology analysis and minimum spanning tree.

[0049] In the parking space status time series analysis phase, the status data of each parking space is continuously sampled at a sampling interval of 5 minutes to record the occupied and idle status of the parking space. By analyzing the status data for 24 consecutive hours, the changing rules of the parking space status are extracted, including characteristic parameters such as occupied time, idle time, and alternating frequency. Based on these characteristic parameters, the parking space status change pattern is established to reflect the usage characteristics of each parking space.

[0050] In the regional clustering stage, the density clustering algorithm is used to divide the parking lot area based on the parking space status change pattern. The clustering radius is set to 20 meters, and the minimum number of sample points is set to 3. By calculating the status similarity and spatial distance between parking spaces, parking spaces with similar occupancy characteristics and close spatial locations are grouped together to form a regional occupancy density distribution map.

[0051] In the saturation analysis stage, a saturation threshold is set for each cluster area. When the parking space occupancy rate in the area exceeds 85%, it is judged as high saturation, when the occupancy rate is between 50% and 85%, it is judged as medium saturation, and when the occupancy rate is less than 50%, it is judged as low saturation. Based on real-time monitoring data, the parking space saturation level of each area is calculated.

[0052] In the resource partition quantification stage, the available parking spaces in each area are classified and marked according to the parking space saturation level data. For the vacant parking spaces in the low saturation area, they are preferentially included in the allocatable parking space set; for the vacant parking spaces in the medium saturation area, they are selectively included according to the time period characteristics; for the vacant parking spaces in the high saturation area, they are not included in the allocatable set for the time being.

[0053] In the spatial distance calculation phase, the distance between each parking space in the allocable parking space set is calculated. The distance calculation uses the actual driving path length rather than the straight-line distance. The system stores the calculation results in the form of an adjacency matrix and constructs a parking space proximity relationship graph.

[0054] In the network topology analysis phase, the system uses a depth-first search algorithm to identify connected components based on the parking space proximity relationship graph. Parking space nodes with a distance of less than 50 meters are considered connected, and multiple parking space connected subgraphs are obtained through traversal search, each of which represents a relatively independent allocable parking space area.

[0055] In the minimum spanning tree construction phase, the system applies the Kruskal algorithm to each parking space connected subgraph to construct a minimum spanning tree. The minimum spanning tree is used to determine the optimal path for parking space allocation and optimize the spatial efficiency of the allocation scheme.

[0056] In the resource allocation analysis phase, the system considers factors such as parking space saturation, spatial distance, and connectivity, and prioritizes the set of allocatable parking spaces. Based on the sorting results, the system generates an initial parking space allocation plan to allocate the most suitable parking space resources for parking needs. The allocation plan includes specific parking space numbers, location information, navigation paths, and other content.

[0057] This embodiment implements resource planning and analysis of real-time parking space status groups and parking space occupancy trends, and the intelligent parking space management method realizes efficient allocation of parking space resources. Based on the parking space status time series analysis and regional clustering technology, the system accurately grasps the usage characteristics of each area of ​​the parking lot, accurately identifies the parking space status change mode, and effectively improves the accuracy of parking space resource allocation. The saturation analysis mechanism is introduced to dynamically monitor the parking space occupancy in each area, realize the reasonable partitioning of parking space resources, and avoid the problem of excessive concentration or idle parking space resources in local areas. By constructing a parking space proximity relationship graph and performing network topology analysis, the system establishes a complete parking space spatial association network, providing a scientific spatial basis for parking space allocation. The minimum spanning tree algorithm is used to optimize the allocation path, which significantly reduces the time cost of users looking for parking spaces while ensuring the rationality of parking space allocation. This method breaks through the limitations of traditional parking space management methods, establishes an intelligent and systematic parking space resource allocation system, and greatly improves the parking lot management efficiency and user parking experience.

[0058] In one embodiment, vehicle characteristics are identified on vehicle behavior data to obtain corresponding special vehicle information, parking demand is predicted for the special vehicle information based on parking space occupancy trends, and corresponding special vehicle priority parking spaces are obtained, including: The intelligent parking space management method extracts features from vehicle behavior data, obtains behavioral features such as vehicle entry and exit time, parking duration, and parking frequency, and constructs a vehicle behavior feature dataset. This dataset covers multi-dimensional information such as vehicle entry and exit time distribution, parking duration, and visit cycle.

[0059] Based on the constructed data set, vehicles are classified into emergency vehicles, vehicles for the disabled, VIP vehicles and other types by identifying the types of vehicles, and the corresponding vehicle type identification is generated. The classification algorithm uses the random forest model to perform cluster analysis based on the similarity of vehicle behavior characteristics.

[0060] After obtaining the vehicle type identification, the vehicle is screened according to the preset special vehicle screening rules, and emergency vehicles, vehicles for disabled persons, etc. are included in the special vehicle list. The screening rules include multiple dimensions such as vehicle usage nature, vehicle authority level, special identification, etc.

[0061] The historical parking records of the vehicles in the special vehicle list are analyzed to extract the parking rules of each vehicle, including common parking time periods, average parking duration, parking location preferences, etc., to form a parking pattern for special vehicles. This pattern reflects the parking habits of the vehicles and the characteristics of the site usage.

[0062] Based on parking pattern data, the system uses a time series prediction model to predict the arrival time of special vehicles. The prediction model comprehensively considers historical patterns, periodic factors, weather effects and other variables to generate a prediction result of vehicle arrival time in the future.

[0063] According to the predicted arrival time, the parking lot occupancy is divided into time windows, based on factors such as the parking space turnover rate during peak and off-peak periods, and the priority level of special vehicles. The result of the time window division forms a parking space availability schedule.

[0064] The parking spaces in the parking space availability schedule are prioritized and scored based on the location, accessibility, site facilities, etc. The scoring results constitute the priority parking space candidate set, which provides the basis for subsequent allocation.

[0065] The priority parking space candidate set is matched and optimized with the special vehicle list, and the heuristic algorithm is used to find the optimal allocation plan. The optimization objectives include minimizing the time for special vehicles to find a parking space, maximizing the utilization rate of parking spaces, and finally generating a special vehicle priority parking space allocation plan.

[0066] This embodiment achieves accurate identification and classification management of different types of vehicles by extracting features and classifying vehicle behavior data, thereby improving the intelligent level of parking lot management. A parking model is constructed based on historical vehicle parking data, and arrival time prediction is performed in combination with a time series prediction model, making parking resource allocation more forward-looking and scientific. A complete parking space availability evaluation system is established by adopting a time window division and priority scoring mechanism, which improves the parking efficiency of special vehicles. The matching and optimization of special vehicles and priority parking spaces are performed through a heuristic algorithm, achieving the optimal configuration of parking space resources while ensuring the parking needs of special vehicles.

[0067] In one embodiment, the initial parking space allocation scheme and the priority parking spaces for special vehicles are comprehensively analyzed to obtain the corresponding global scheduling strategy, including: The initial parking space allocation plan and the priority parking spaces for special vehicles are analyzed for resource allocation, and an M×N dimensional parking space resource allocation matrix is ​​constructed, where M represents the number of parking spaces and N represents the time period division. Each element in the matrix has a value of 0 or 1, where 0 means that the parking space is free during the time period and 1 means that it is occupied. Based on the matrix, the system performs dynamic parking space scheduling and generates a scheduling sequence containing parking space numbers, time periods, and vehicle information. The scheduling sequence is prioritized according to multiple dimensions such as time priority, vehicle type, and distance to form a scheduling priority table.

[0068] According to the scheduling priority table, the resource reservation requirements for priority parking spaces for special vehicles are calculated and divided into reserved parking space groups. Reserved parking space groups include special-purpose parking spaces such as parking spaces for the disabled and pregnant women. Through spatial distribution calculation, the system generates a parking space distribution map, which includes the geographical location information, proximity relationship, and traffic path of the parking space. Based on the distribution map information, the system updates the initial allocation plan in real time to ensure the reasonable allocation of parking space resources.

[0069] A conflict detection algorithm is used to identify the time and space conflict areas in the updated parking allocation plan. Conflict areas include duplicate allocation, channel blockage, insufficient turning radius, etc. For the conflicts found, the system implements optimization and adjustment strategies, including parking space reallocation, traffic path optimization, time staggering and other measures. The optimized allocation strategy is verified for time and space consistency to ensure that physical constraints and scheduling rules are met.

[0070] After completing local verification, global resource scheduling is carried out, taking into account multiple goals such as overall parking lot operation efficiency, user satisfaction, and special parking space guarantee. The global scheduling strategy is solved through a mathematical programming model to obtain the optimal parking space allocation plan. This plan ensures the efficient use of parking space resources, meets the parking needs of different types of users, and realizes intelligent parking space management.

[0071] This embodiment realizes the dynamic optimization allocation of parking resources by establishing a parking space resource allocation matrix for global scheduling, and significantly improves the operational efficiency of the parking lot. Through a multi-dimensional priority sorting mechanism, the parking needs of special vehicles are reasonably guaranteed, reflecting the humanized characteristics of parking lot management. The system adopts spatial distribution calculation and conflict detection algorithms to effectively avoid problems such as repeated allocation of parking spaces and channel blockage, and improves the space utilization rate of the parking lot. The optimization and adjustment strategy based on spatiotemporal consistency verification ensures the feasibility of the parking space allocation plan and reduces the need for manual intervention. This method combines special parking space reservation with global resource scheduling, which not only guarantees the parking rights and interests of special groups, but also improves the overall operational efficiency of the parking lot, and has strong practical value.

[0072] Reference Figure 2As shown, the present invention further provides an intelligent parking space management device, which is applied to any one of the above intelligent parking space management methods, comprising: The acquisition module is used to obtain the basic spatial layout data and parking space management information of the parking lot, and perform regional division processing to obtain the corresponding regional parking space information; An analysis module is used to obtain real-time sensor data collected by the parking lot, and associate it with the regional parking space information to obtain a corresponding real-time parking space status group; The association module is used to obtain the vehicle behavior data collected by the parking lot, and to predict the use of regional parking space information to obtain the corresponding parking space occupancy trend; A processing module, which is used to perform resource planning analysis on the real-time parking space status group and parking space occupancy trend to obtain a corresponding initial parking space allocation plan; A control module, which is used to identify vehicle characteristics based on vehicle behavior data to obtain corresponding special vehicle information, predict parking demand for the special vehicle information based on parking space occupancy trends, and obtain corresponding special vehicle priority parking spaces; The execution module is used to comprehensively analyze the initial parking space allocation plan and the priority parking spaces for special vehicles to obtain the corresponding global scheduling strategy.

[0073] The present invention provides an intelligent parking space management device, which realizes the refined management of parking resources and improves the accuracy of parking lot resource allocation by regional division processing of parking lot basic space layout data and parking space management information. By associating real-time sensor data with regional parking space information, the parking space usage status of each area can be grasped in real time, effectively solving the problem of untimely resource monitoring in traditional parking lot management. Based on vehicle behavior data, the use prediction of regional parking space information can accurately grasp the parking space occupancy law, predict parking demand in advance, and avoid the unreasonable resource allocation under the traditional management method. By performing resource planning and analysis on the real-time parking space status and occupancy trend, a scientific parking space allocation plan is formulated, which significantly improves the operation efficiency of the parking lot. At the same time, by vehicle feature recognition and parking demand prediction of special vehicles, priority parking spaces are reserved for special vehicles, solving the problem that differentiated parking needs cannot be met under the traditional management method. Finally, by comprehensively analyzing the initial parking space allocation plan and the priority parking spaces for special vehicles, a global scheduling strategy is formulated, which realizes the intelligent scheduling and optimal configuration of parking resources, greatly improving the user's parking experience.

[0074] Reference Figure 3 As shown, the present invention also provides an intelligent parking space management device, including: Memory, used to store programs; The processor is used to execute the program to implement each step of any one of the above-mentioned intelligent parking space management methods.

[0075] In this embodiment, the processor and the memory may be connected via a bus or other means. The memory may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a read-only memory, a flash memory, a hard disk, or a solid-state drive. The processor may be a general-purpose processor, such as a central processing unit, a digital signal processor, an application-specific integrated circuit, or one or more integrated circuits configured to implement the embodiments of the present invention.

[0076] The present invention also provides a storage medium, characterized in that computer instructions are stored therein, and the computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 7.

[0077] It should be noted that technicians in the relevant technical field can clearly understand that for the convenience and conciseness of description, the specific working process of the system and each module described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0078] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. An intelligent parking space management method, characterized in that: include: Obtain the basic spatial layout data and parking space management information of the parking lot, and perform regional division processing to obtain the corresponding regional parking space information; Acquire the real-time sensor data collected by the parking lot, and associate it with the regional parking space information to obtain a corresponding real-time parking space status group; Acquire vehicle behavior data collected by the parking lot, and make usage predictions for the parking space information in the area to obtain corresponding parking space occupancy trends; Performing resource planning analysis on the real-time parking space status group and the parking space occupancy trend to obtain a corresponding initial parking space allocation plan; Performing vehicle feature recognition on the vehicle behavior data to obtain corresponding special vehicle information, performing parking demand prediction on the special vehicle information based on the parking space occupancy trend to obtain corresponding special vehicle priority parking spaces; The initial parking space allocation plan and the priority parking spaces for special vehicles are comprehensively analyzed to obtain a corresponding global scheduling strategy.

2. The intelligent parking space management method according to claim 1, characterized in that: The basic spatial layout data and parking space management information of the parking lot are obtained, and the area division process is performed to obtain the corresponding area parking space information, including: Performing grid division processing on the basic spatial layout data to obtain a corresponding basic grid unit group; Extracting the outline of the basic grid unit group according to the parking space management information to obtain corresponding obstacle boundary data; Performing regional connectivity analysis on the obstacle boundary data to obtain a corresponding available space area set; Matching basic parking space information according to the available space area set to obtain a corresponding initial parking space layout diagram; Performing regional spatial clustering on the initial parking space layout diagram to obtain corresponding regional spatial groupings; Mapping parking space management rules according to the regional spatial grouping, and performing parking space number allocation processing to obtain a corresponding regional parking space index; Collect parking space environment parameters according to the regional parking space index to obtain a corresponding parking space environment feature set; Multi-dimensional data fusion is performed on the parking space environment feature set to obtain the regional parking space information.

3. The intelligent parking space management method according to claim 1, characterized in that: The real-time sensor data collected by the parking lot is acquired, and the real-time sensor data is associated with the regional parking space information to obtain a corresponding real-time parking space status group, including: Separating the real-time sensing data to obtain corresponding real-time parking space occupancy data and parking space image data; Performing regional feature positioning on the parking space image data according to the real-time parking space occupancy data to obtain corresponding parking space image feature data; Performing parking space occupancy analysis on the parking space image feature data to obtain corresponding parking space occupancy data; Performing data fusion processing on the real-time parking space occupancy data and the parking space occupancy feature vector to obtain a corresponding parking space state feature set; According to the parking space status feature set, the parking space information of the area is mapped and associated with numbers to obtain a corresponding parking space status mapping table; Performing time series clustering on the parking space status mapping table to obtain corresponding parking space status grouping data; The parking space status grouping data is classified and labeled according to a preset status standard to obtain a corresponding real-time parking space status group.

4. The intelligent parking space management method according to claim 1, characterized in that: The acquiring of the vehicle behavior data collected by the parking lot and the use prediction of the parking space information in the area to obtain the corresponding parking space occupancy trend include: Performing data fusion on the vehicle entry and exit time data, vehicle path data and parking space selection data collected from the parking lot to obtain corresponding vehicle behavior data; Perform parking feature analysis based on the vehicle behavior data to obtain corresponding parking space selection feature data and parking duration feature data; Performing cluster analysis on the parking space selection feature data and the parking duration feature data to obtain a corresponding parking behavior pattern library; Performing correlation analysis on regional parking space history records based on the parking behavior pattern library to obtain corresponding regional parking space usage rules; Performing time series decomposition on the parking space usage pattern in the area to obtain corresponding fixed-time usage characteristics and fluctuating-time usage characteristics; Probabilistic statistics are performed based on the fixed time period usage characteristics and the fluctuating time period usage characteristics to obtain a corresponding regional parking space occupancy probability distribution; A sequence prediction process is performed on the parking space occupancy probability distribution in the area to obtain a corresponding parking space occupancy trend.

5. The intelligent parking space management method according to claim 1, characterized in that: The performing resource planning analysis on the real-time parking space status group and the parking space occupancy trend to obtain a corresponding initial parking space allocation plan includes: Performing a parking space state time series analysis on the real-time parking space state group to obtain a corresponding parking space state change pattern; Performing regional clustering on the parking space occupancy trend according to the parking space state change pattern to obtain a corresponding regional occupancy density distribution; Calculate the saturation threshold of the occupancy density distribution of the area to obtain corresponding parking space saturation level data; Quantify the parking space resource partitions according to the parking space saturation level data to obtain a corresponding allocatable parking space set; Performing spatial distance calculation on the set of allocatable parking spaces to obtain a corresponding parking space proximity relationship graph; Performing a network topology analysis on the allocatable parking space set according to the parking space proximity relationship graph to obtain a corresponding parking space connected subgraph group; Constructing a minimum spanning tree for the connected subgraph group of parking spaces to obtain a corresponding optimized allocation path; A resource configuration analysis is performed on the set of allocatable parking spaces according to the optimized allocation path to obtain a corresponding initial parking space allocation plan.

6. The intelligent parking space management method according to claim 1, characterized in that: The performing vehicle feature recognition on the vehicle behavior data to obtain corresponding special vehicle information, performing parking demand prediction on the special vehicle information based on the parking space occupancy trend to obtain corresponding special vehicle priority parking spaces, includes: Extracting features from the vehicle behavior data to obtain a corresponding vehicle behavior feature data set; Performing classification and identification processing according to the vehicle behavior feature data set to obtain a corresponding vehicle type identification; Performing special vehicle screening processing on the vehicle type identifier to obtain a corresponding special vehicle list; Performing historical parking matching analysis on the special vehicle list to obtain corresponding special vehicle parking patterns; Performing time prediction analysis on the special vehicle parking mode to obtain a corresponding vehicle arrival time prediction result; The parking space occupancy trend is divided into windows according to the vehicle arrival time prediction result to obtain a corresponding parking space availability schedule; Prioritizing the parking space availability schedule to obtain a corresponding priority parking space candidate set; The special vehicle list is matched and optimized according to the priority parking space candidate set to obtain a corresponding special vehicle priority parking space allocation plan.

7. The intelligent parking space management method according to claim 1, characterized in that: The initial parking space allocation scheme and the priority parking spaces for special vehicles are comprehensively analyzed to obtain a corresponding global scheduling strategy, including: Performing resource allocation analysis on the initial parking space allocation plan and the priority parking spaces for special vehicles to obtain a parking space resource allocation matrix; Performing dynamic parking scheduling according to the parking space resource allocation matrix to obtain a dynamic parking scheduling sequence; Prioritizing the parking space dynamic scheduling sequence to obtain a parking space scheduling priority table; Performing resource reservation analysis on the priority parking spaces for special vehicles according to the parking space scheduling priority table to obtain a reserved parking space group; Performing spatial distribution calculation on the reserved parking space group to obtain a parking space spatial distribution map; Dynamically updating the initial parking space allocation plan according to the parking space spatial distribution map to obtain an updated parking space allocation plan; Performing conflict detection on the updated parking space allocation scheme to obtain parking space conflict area information; Optimizing and adjusting the updated parking space allocation plan according to the parking space conflict area information to obtain an optimized parking space allocation strategy; Performing spatiotemporal consistency verification on the optimized parking space allocation strategy to obtain a verified scheduling plan; The verification scheduling scheme is globally scheduled for resources to obtain the global scheduling strategy.

8. An intelligent parking space management device, characterized in that: The intelligent parking space management method applied to any one of claims 1 to 6 above comprises: A collection module, which is used to obtain basic spatial layout data and parking space management information of the parking lot, and perform regional division processing to obtain corresponding regional parking space information; An analysis module, the analysis module is used to obtain the real-time sensor data collected by the parking lot, and associate it with the regional parking space information to obtain a corresponding real-time parking space status group; An association module, the association module is used to obtain the vehicle behavior data collected by the parking lot, and to make a usage prediction for the parking space information in the area to obtain a corresponding parking space occupancy trend; A processing module, the processing module is used to perform resource planning analysis on the real-time parking space status group and the parking space occupancy trend to obtain a corresponding initial parking space allocation plan; A control module, the control module is used to perform vehicle feature recognition on the vehicle behavior data to obtain corresponding special vehicle information, perform parking demand prediction on the special vehicle information based on the parking space occupancy trend to obtain corresponding special vehicle priority parking spaces; An execution module is used to comprehensively analyze the initial parking space allocation plan and the priority parking spaces for special vehicles to obtain a corresponding global scheduling strategy.

9. An intelligent parking space management device, characterized in that: include: Memory, used to store programs; The processor is used to execute the program to implement each step of the intelligent parking space management method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: Computer instructions are stored, and the computer instructions are used to make a computer execute the method according to any one of claims 1 to 7.

Images