Parking management method and system based on data analysis

Abstract

The invention relates to the field of parking lot management, in particular to a parking management method and system based on data analysis. The method comprises the following steps: acquiring real-time state information of a parking lot and a historical parking monitoring log of the parking lot; analyzing the dynamic characteristics of the vehicle in the fixed parking space according to the real-time state information of the parking lot, and predicting the available time so as to generate the predicted available time of the fixed parking space; acquiring traffic flow data of a target parking lot area; performing multi-section traffic flow analysis on the traffic flow data of the target parking lot area, and performing traffic flow time sequence trend evolution to generate real-time road state characteristics of the target area; and performing time sequence parking demand analysis on the historical parking monitoring log of the parking lot, and performing dynamic parking demand prediction of the target parking lot according to the real-time road state characteristics of the target area so as to generate a dynamic parking demand prediction value. According to the invention, parking lot management with high efficiency and high utilization rate is realized.

Description

Technical Field

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

[0002] With the continuous advancement of urbanization, the number of vehicles continues to increase, and the parking problem is becoming increasingly serious. Traditional parking lot management methods usually rely on manual scheduling and manual records, and there are problems such as low management efficiency, serious waste of parking resources, and vehicles taking too long to find parking spaces. This not only brings inconvenience to car owners, but also makes the resources of parking lots fail to be effectively utilized, resulting in low parking lot operation efficiency. Especially in large commercial areas, around office buildings and residential areas, the rapid growth of parking demand has exacerbated the problem of difficulty in parking.

[0003] Traditional parking lot management usually adopts fixed rules and manual monitoring, and it is impossible to understand the parking lot usage and vehicle flow data in real time. This makes it impossible for managers to make scientific decisions in a timely manner, and the grasp of information such as the distribution of vacant parking spaces and vehicle parking times is not accurate enough. Therefore, the reasonable allocation of parking resources, the effective use of parking spaces, and the parking experience of car owners all face great challenges.

[0004] With the rapid development of information technology and data analysis technology, parking lot management systems based on big data and intelligent algorithms are gradually emerging. By real-time monitoring of parking space usage, traffic flow, parking behavior of car owners and other data in the parking lot, combined with data analysis technology, it can realize intelligent scheduling, real-time navigation and dynamic optimization of parking lots. This intelligent parking management method based on data analysis can not only improve the utilization efficiency of parking lots and optimize parking space allocation, but also provide car owners with more convenient parking services and significantly improve the parking experience.

[0005] However, although the existing intelligent parking management methods have made certain progress, most systems still have problems such as incomplete data acquisition, insufficient algorithm optimization, and system response delays. Especially during peak parking demand periods, parking lots may experience uneven parking space allocation and vehicle congestion due to untimely real-time data processing. Therefore, it is particularly urgent to develop a more efficient, intelligent and responsive parking lot management method, a parking lot intelligent management system based on precise data analysis. Summary of the invention

[0006] In order to solve the above technical problems, the present invention proposes a parking management method and system based on data analysis to solve at least one of the above technical problems.

[0007] To achieve the above object, the present invention provides a parking management method based on data analysis, comprising the following steps: Step S1: obtaining the real-time status information of the parking lot and the historical parking monitoring log of the parking lot; analyzing the dynamic characteristics of vehicles in fixed parking spaces in the real-time status information of the parking lot, and predicting the available occupancy time, thereby generating the predicted available occupancy time of the fixed parking spaces; Step S2: Obtaining traffic flow data of the target parking area; performing multi-section traffic flow analysis on the traffic flow data of the target parking area, and performing time series trend evolution of the traffic flow to generate real-time road status characteristics of the target area; Step S3: Performing a time-series parking demand analysis on the parking lot's historical parking monitoring logs, and performing a dynamic parking demand forecast for the target parking lot based on the real-time road status characteristics of the target area, thereby generating a dynamic parking demand forecast value; Step S4: performing parking load peak prediction and parking lot capacity satisfaction rate evaluation based on the dynamic parking demand prediction value, thereby obtaining a parking lot capacity evaluation result; Step S5: Based on the parking lot capacity assessment result and the predicted occupancy time of the fixed parking spaces, a parking guidance decision for the vacant parking spaces is made, and an occupancy scheduling decision is made to obtain a parking guidance strategy for the vacant parking spaces and an occupancy scheduling strategy for the fixed parking spaces; Step S6: Perform intelligent parking collaborative management on the parking guidance strategy for the vacant parking spaces and the optimization scheduling strategy for the occupied time period, and build an intelligent parking collaborative management model.

[0008] By analyzing the dynamic characteristics of vehicles in fixed parking spaces and predicting the available occupancy time, the present invention can enable the system to better understand the usage of fixed parking spaces, predict the available occupancy time in advance, and improve the utilization rate of parking spaces. The generation of predicted available occupancy time for fixed parking spaces helps to optimize parking space allocation and improve the parking lot's vehicle capacity efficiency. By analyzing multi-section traffic flow and the time-series trend evolution of traffic flow, the system can generate real-time road status characteristics in the target area to help optimize the parking lot's traffic flow management and road traffic efficiency. The generation of real-time road status characteristics helps the system to more accurately evaluate the traffic conditions around the parking lot and provide more accurate data support for parking demand prediction. The time-series parking demand analysis combined with the real-time road status characteristics in the target area can more accurately predict the dynamic parking demand of the parking lot, help optimize parking resource management and parking lot planning, and the generation of dynamic parking demand prediction values ​​helps the system to make parking resource scheduling and management decisions in advance, thereby improving the efficiency and service level of the parking lot. The parking load peak prediction and parking lot capacity satisfaction rate assessment system can better understand the parking lot load and capacity utilization, and provide an important reference for parking resource management. The parking lot capacity assessment results help the system optimize the parking resource allocation and respond to parking peaks in advance, thereby improving the parking lot's operational efficiency and service quality. The formulation of idle parking guidance strategies and fixed parking space occupancy scheduling strategies can help optimize parking space allocation and improve parking lot parking efficiency, reduce confusion and congestion. By guiding vehicles to park in idle parking spaces, the system can improve parking lot utilization, reduce waiting time, and improve the overall efficiency and user experience of the parking lot. The establishment of an intelligent parking collaborative management model can help the system realize the intelligent allocation and coordination of parking resources, and improve the overall management efficiency and service level of the parking lot. Through intelligent parking collaborative management, the system can achieve the optimal configuration of parking resources, improve the efficiency of parking scheduling in the parking lot, and improve the parking utilization rate of vacant parking spaces.

[0009] Preferably, step S1 comprises the following steps: Step S11: Acquire the real-time status information of the parking lot and the historical parking monitoring log of the parking lot; Step S12: Analyze the parking space status of the real-time parking lot status information to obtain free parking space data and fixed parking space data; Step S13: analyzing the dynamic characteristics of vehicles in fixed parking spaces based on the historical parking monitoring logs of the parking lot, thereby obtaining a behavior profile of the owners of the fixed parking spaces; Step S14: predicting the available occupancy time of the fixed parking space data according to the behavior profile of the owner of the fixed parking space, thereby generating the predicted available occupancy time of the fixed parking space.

[0010] By acquiring real-time status and historical data, the system of the present invention can fully understand the operation of the parking lot and provide basic data for subsequent analysis and decision-making. The combination of real-time status information and historical monitoring logs can help the system more accurately evaluate the usage and demand changes of the parking lot. Through parking space status analysis, the system can accurately obtain data on vacant parking spaces and fixed parking spaces in the parking lot, providing a basis for subsequent analysis and decision-making. Obtaining vacant parking space data and fixed parking space data helps the system to monitor the parking space utilization of the parking lot in real time and provide support for the optimal allocation of parking resources. Through dynamic feature analysis of fixed parking space vehicles, the system can deeply understand the parking behavior and preferences of fixed parking space owners and form a fixed parking space owner behavior portrait. The establishment of a fixed parking space owner behavior portrait helps the system better predict the available occupation time of fixed parking spaces and improve the parking space utilization and service efficiency of the parking lot. Through the analysis of the fixed parking space owner behavior portrait, the system can accurately predict the available occupation time of fixed parking spaces, help optimize parking space allocation and improve parking efficiency of the parking lot. Generating the predicted available occupation time of fixed parking spaces helps the system to more effectively manage parking resources and improve the overall operational efficiency and user experience of the parking lot.

[0011] Preferably, the specific steps of step S13 are: Based on the parking lot's historical parking monitoring logs, the fixed parking space data is analyzed for multiple entry and exit time points, and multiple entry and exit time nodes are extracted; Calculate the vehicle dwell time for each of the multiple entry and exit time nodes and generate the dwell time for each time; Perform parking time fluctuation analysis on each stop time to obtain parking time fluctuation data; Perform time series variation fitting on the parking time fluctuation data and construct a parking time time series variation curve; Calculate the average length of stay for each stay to obtain the average length of stay; The parking demand time of fixed parking spaces is quantified based on the average stay time, thereby generating the parking demand time of vehicles in fixed parking spaces; The dynamic behavior characteristics of the parking time series change curve and the parking demand time of vehicles in fixed parking spaces are analyzed to obtain the dynamic behavior habit characteristics of vehicles in fixed parking spaces; The dynamic behavior habit characteristics of vehicles in fixed parking spaces are used to evolve the personalized characteristics of the owners and construct a behavioral profile of the owners of fixed parking spaces.

[0012] The present invention uses multi-point entry and exit time analysis and stay time calculation, so that the system can accurately capture the vehicle's stay pattern and parking time. Extracting multiple entry and exit time nodes and calculating the stay time is helpful to understand the regularity and changes of vehicle stays, and provide basic data for subsequent behavior feature analysis. Through parking time fluctuation analysis and time series change fitting, the system can reveal the volatility and regularity of parking time. Constructing a parking time time series change curve is helpful for the system to more accurately predict the changing trend of parking time, and provide a reference basis for the management and optimization of parking demand. By calculating the average stay time and quantifying the parking demand time of fixed parking spaces, the system can more accurately evaluate the utilization of parking resources. Based on the calculation of the average stay time, the system can reasonably plan the use of fixed parking spaces and improve the turnover rate and utilization efficiency of parking spaces. Through dynamic behavior feature analysis and personalized feature evolution, the system can deeply understand the parking behavior and habits of fixed parking space owners. Constructing a fixed parking space owner behavior portrait is helpful for system personalized service and management, and improves the operation efficiency and user experience of parking lots.

[0013] Preferably, step S2 specifically comprises the following steps: Step S21: Acquire traffic flow data of the target parking lot area based on regional road sensors; Step S22: performing a multi-section traffic flow analysis on the target parking lot area traffic flow data, thereby obtaining traffic flow characteristics of multiple sections; Step S23: performing spatial distribution analysis on the traffic flow characteristics of multiple road sections to generate traffic flow spatial distribution data; Step S24: performing time series trend evolution of vehicle flow on the spatial distribution data of vehicle flow, thereby generating time series distribution trend characteristics of vehicle flow; Step S25: Perform real-time road status mining on the time series distribution trend characteristics of the traffic flow to generate real-time road status characteristics of the target area. By acquiring regional road sensor data, the present invention can monitor the traffic flow situation around the target parking lot in real time, provide real-time traffic information for parking lot management, and acquire traffic flow data in the target parking lot area to help the system better understand the traffic conditions of surrounding roads, and provide a data basis for subsequent analysis and decision-making. Through multi-section traffic flow analysis, the system can deeply understand the traffic conditions and characteristics of different sections, reveal the distribution law of traffic flow, and obtain the traffic flow characteristics of multiple sections to help the system more comprehensively evaluate the traffic conditions of roads around the target parking lot, and provide detailed data support for subsequent analysis. Through spatial distribution analysis, the system can generate spatial distribution data of traffic flow in the target parking lot area, which helps to understand the traffic flow in different areas. The generation of spatial distribution data of vehicle flow helps the system better grasp the traffic flow distribution of roads around the target parking lot and provide a spatial perspective for subsequent analysis. Through the evolution of the time series trend of vehicle flow, the system can analyze the evolution trend of vehicle flow over time and reveal the time series characteristics of traffic flow. Generating the time series distribution trend characteristics of vehicle flow helps the system to more accurately predict the changing trend of future traffic flow and provide a basis for real-time road status mining. Through real-time road status mining, the system can generate real-time road status characteristics of the target area according to the time series distribution trend characteristics of vehicle flow. Generating real-time road status characteristics helps the system to monitor road traffic conditions in real time, provide real-time traffic information for parking lot users, and help them choose routes and avoid congestion more effectively.

[0014] Preferably, step S3 specifically comprises the following steps: Step S31: Performing a quantitative evaluation of historical parking vehicles on the parking lot historical parking monitoring log to generate the number of historical parking vehicles; Step S32: performing a time-series parking demand analysis on the number of historical parked vehicles to generate parking lot time-series parking demand data; Step S33: identifying periodic difference changes in the parking lot time series parking demand data to generate parking demand periodic difference change data; Step S34: Perform dynamic parking demand prediction for the target parking lot based on the parking demand cycle difference change data and the real-time road status characteristics of the target area, thereby generating a dynamic parking demand prediction value.

[0015] The present invention uses quantitative evaluation of historical parked vehicles. The system can quantitatively analyze the past parking conditions of the parking lot and understand the changing trend of the number of historical parked vehicles. Generating the number of historical parked vehicles helps the system establish a basic understanding of the past parking demand of the parking lot and provide historical data support for subsequent analysis. Through time-series parking demand analysis, the system can analyze the time-series characteristics of the number of historical parked vehicles and reveal the changing law of parking demand in the parking lot. Generating time-series parking demand data of the parking lot helps the system better understand the time-series changes of parking demand and provide a basis for subsequent analysis and prediction. Through periodic difference change identification, the system can find the changing characteristics of parking demand in the parking lot in different time periods, such as Sunday changes, holiday changes, etc. Generating parking demand periodic difference change data helps the system capture the periodic change law of parking demand more accurately and provide more dimensional references for dynamic prediction of parking demand. Through dynamic parking demand prediction, the system can combine parking demand periodic difference change data and real-time road status characteristics to predict the parking demand situation of the future parking lot. Generating dynamic parking demand prediction values ​​helps the system adjust parking resource allocation in real time and improve the resource utilization efficiency and service quality of the parking lot.

[0016] Preferably, the specific steps of step S4 are: Step S41: performing real-time situation change analysis on the idle parking space data to generate real-time situation change data of the idle parking spaces; Step S42: quantifying the parking lot load based on the real-time status change data of the vacant parking spaces to obtain the parking load data of the target parking lot; Step S43: predicting the parking load peak value of the target parking lot parking load data, thereby obtaining a predicted parking load peak value; Step S44: evaluating the parking lot capacity satisfaction rate of the predicted parking load peak based on the dynamic parking demand prediction value, thereby obtaining a parking lot capacity evaluation result.

[0017] The present invention can help the system monitor the changes of free parking spaces in the parking lot in real time and understand the real-time parking resource situation of the parking lot through real-time situation change analysis. Generating real-time situation change data of free parking spaces can help the system to adjust the allocation of parking resources in time and improve the resource utilization efficiency of the parking lot. Through the quantification of the parking lot load, the system can convert the free parking space data into the parking load situation of the parking lot to help evaluate the usage of the parking lot. Obtaining the parking load data of the target parking lot can help the system to understand the load situation of the parking lot more accurately and provide data support for subsequent analysis and decision-making. Through the parking load peak prediction, the system can predict the peak situation of the parking load of the parking lot to help respond to the high load situation of the parking lot in advance. Predicting the parking load peak can help the system to reasonably plan parking resources, optimize the operation strategy of the parking lot, and improve the service level of the parking lot. Through the parking lot capacity satisfaction rate evaluation, the system can combine the dynamic parking demand prediction value to evaluate whether the parking capacity of the parking lot is sufficient to meet future needs. Obtaining the parking lot capacity evaluation result can help the system to adjust the parking strategy in time, ensure that the parking lot can effectively meet the parking needs of users, and improve the overall operation efficiency of the parking lot.

[0018] Preferably, the specific steps of step S5 are: Step S51: when the parking lot capacity assessment result is that the capacity meets the demand prediction value, a parking guidance decision for an idle parking space is made and an idle parking space parking guidance strategy is constructed; Step S52: when the parking lot capacity assessment result is that the capacity does not meet the demand prediction value, a parking time prediction is performed on the dynamic parking demand prediction value, thereby obtaining parking time prediction data; Step S53: dynamically matching the predicted available occupancy time of fixed parking spaces with the available occupancy time of fixed parking spaces based on the parking duration prediction data, thereby obtaining the optimal occupancy matching parking space; Step S54: Make an occupancy scheduling decision for the optimal occupancy matching parking space and construct a fixed parking space occupancy scheduling strategy.

[0019] The present invention uses the idle parking space parking guidance decision-making system to construct a guidance strategy for the idle parking space according to the parking lot capacity assessment result, thereby improving the utilization rate of the parking lot. Constructing the idle parking space parking guidance strategy helps to improve the parking space utilization efficiency of the parking lot, reduce the time users spend looking for parking spaces, and improve user experience. Through the parking time prediction, the system can predict the parking time according to the dynamic parking demand prediction value, help optimize the allocation and utilization of parking resources, and obtain the parking time prediction data to help the system better understand the time characteristics of parking demand and provide a basis for the reasonable allocation of parking resources. Through the dynamic fixed parking space occupancy matching, the system can match the occupancy time of the fixed parking space according to the parking time prediction data to achieve more effective parking space utilization. Obtaining the optimal occupied matching parking space helps the system improve the utilization rate of the fixed parking space, reduce the vacant time of the parking space, and improve the resource utilization efficiency of the parking lot. Through the occupancy scheduling decision, the system can formulate the occupancy scheduling strategy of the fixed parking space according to the optimal occupied matching parking space, optimize the allocation of parking resources, and construct the fixed parking space occupancy scheduling strategy to help the system achieve flexible management of the fixed parking space and improve the parking efficiency and service level of the parking lot.

[0020] Preferably, the specific steps of step S6 are: Step S61: Real-time entry monitoring of vehicles in fixed parking spaces to generate vehicle entry data; Step S62: Performing a fixed parking space occupancy and expulsion warning based on the vehicle entry data to generate an occupancy and expulsion warning signal; Step S63: optimizing the occupancy time period of the fixed parking space occupancy scheduling strategy based on the occupancy and expulsion warning signal, and constructing an occupancy time period optimization scheduling strategy; Step S64: Perform intelligent parking collaborative management on the parking guidance strategy for the vacant parking spaces and the optimization scheduling strategy for the occupied time period, and construct an intelligent parking collaborative management model.

[0021] Through real-time entry monitoring, the present invention can accurately record the entry of vehicles into fixed parking spaces and provide real-time data support for subsequent parking management. The generation of vehicle entry data helps the system understand the real-time situation of vehicles in the parking lot and provides a basis for the allocation and scheduling of parking resources. Through occupation and expulsion warning, the system can warn of the occupancy of fixed parking spaces based on vehicle entry data and prepare for vehicle expulsion in advance. The generation of occupation and expulsion warning signals helps the system to release occupied parking spaces in a timely manner, improve the turnover rate of parking spaces, and reduce user waiting time. Through occupation and expulsion warning signals, the system can optimize the occupancy time period of fixed parking spaces and improve the utilization efficiency of fixed parking spaces. The construction of an optimized scheduling strategy for occupied time periods helps the system to more reasonably arrange the use time of fixed parking spaces and improve the utilization rate of parking resources. Through the intelligent parking collaborative management model, the system can comprehensively consider the parking guidance strategy for idle parking spaces and the optimized scheduling strategy for occupied time periods to achieve intelligent management of parking resources. The construction of an intelligent parking collaborative management model helps the system to optimize the allocation and scheduling of parking resources and improve the overall efficiency of the parking lot and user experience.

[0022] In this specification, a parking management system based on data analysis is provided, which is used to execute the parking management method based on data analysis as described above, including: The vehicle dynamic feature module is used to obtain the real-time status information of the parking lot and the historical parking monitoring log of the parking lot; analyze the dynamic features of vehicles in fixed parking spaces based on the real-time status information of the parking lot, and make an occupancy time prediction, thereby generating the predicted occupancy time of fixed parking spaces; The road state feature module is used to obtain the traffic flow data of the target parking area; perform multi-section traffic flow analysis on the traffic flow data of the target parking area, and perform the time series trend evolution of the traffic flow to generate real-time road state features of the target area; The parking demand prediction module is used to perform time-series parking demand analysis on the parking lot's historical parking monitoring logs, and to perform dynamic parking demand prediction on the target parking lot based on the real-time road status characteristics of the target area, thereby generating a dynamic parking demand prediction value; The load peak prediction module is used to predict the parking load peak and evaluate the parking lot capacity satisfaction rate based on the dynamic parking demand prediction value, so as to obtain the parking lot capacity evaluation result; The scheduling decision module is used to make parking guidance decisions for free parking spaces based on the parking lot capacity assessment results and the predicted occupancy time of fixed parking spaces, and make occupancy scheduling decisions to obtain parking guidance strategies for free parking spaces and occupancy scheduling strategies for fixed parking spaces; The collaborative management module is used to perform intelligent parking collaborative management on the parking guidance strategy for vacant parking spaces and the optimization scheduling strategy for occupied time periods, and to build an intelligent parking collaborative management model.

[0023] The present invention helps the system understand the dynamic characteristics and parking conditions of vehicles in the parking lot by acquiring real-time parking lot status information and historical parking monitoring logs. By analyzing the dynamic characteristics of vehicles in fixed parking spaces and predicting the available occupancy time, the system can accurately predict the available occupancy time of fixed parking spaces and optimize the utilization rate of fixed parking spaces. Acquiring traffic flow data in the target parking lot area helps the system understand the traffic conditions of surrounding roads and provide a reference basis for parking demand prediction. By analyzing the traffic flow and time series trend evolution, the system can generate real-time road status characteristics in the target area to help more accurately predict parking demand and optimize parking resource allocation. Parking demand prediction based on historical parking monitoring logs and road status characteristics helps the system more accurately predict the dynamic parking demand of the parking lot. Through the dynamic parking demand prediction value, the system can adjust the parking resource allocation according to the real-time road status characteristics, improve the resource utilization efficiency of the parking lot, and optimize the parking demand. Calculating the predicted value for parking load peak prediction and capacity satisfaction rate assessment can help the system to timely adjust the allocation of parking resources and optimize parking lot management. Obtaining the parking lot capacity assessment results can help the system to reasonably arrange parking resources, avoid parking congestion and improve the operating efficiency of the parking lot. Making idle parking guidance decisions and available scheduling decisions based on capacity assessment results and the predicted available time of fixed parking spaces can help the system to realize intelligent scheduling of parking resources. Constructing idle parking space parking guidance strategies and fixed parking space occupancy scheduling strategies can improve the utilization rate and service quality of parking lots and optimize parking processes. Intelligent parking collaborative management of idle parking space parking guidance strategies and occupied time period optimization scheduling strategies can help integrate information from various modules and realize comprehensive management and optimization of parking lot resources. Constructing an intelligent parking collaborative management model can improve the overall efficiency of parking lots, optimize the allocation of parking resources, and enhance user parking experience and management efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A schematic diagram of the steps of a parking management method based on data analysis of the present invention; Figure 2 Detailed implementation flow chart of step S1; Figure 3 Detailed implementation flow chart of step S2; Figure 4 Detailed implementation flow chart of step S3. DETAILED DESCRIPTION

[0025] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0026] The present application example provides a parking management method and system based on data analysis. The execution subject of the parking management method and system based on data analysis includes but is not limited to: mechanical equipment, data processing platform, cloud server node, network upload device, etc. equipped with the system can be regarded as the general computing node of the present application, and the data processing platform includes but is not limited to: at least one of an audio and image management system, an information management system, and a cloud data management system.

[0027] See also Figures 1 to 4 The present invention provides a parking management method based on data analysis, and the parking management method based on data analysis comprises the following steps: Step S1: obtaining the real-time status information of the parking lot and the historical parking monitoring log of the parking lot; analyzing the dynamic characteristics of vehicles in fixed parking spaces in the real-time status information of the parking lot, and predicting the available occupancy time, thereby generating the predicted available occupancy time of the fixed parking spaces; Step S2: Obtaining traffic flow data of the target parking area; performing multi-section traffic flow analysis on the traffic flow data of the target parking area, and performing time series trend evolution of the traffic flow to generate real-time road status characteristics of the target area; Step S3: Performing a time-series parking demand analysis on the parking lot's historical parking monitoring logs, and performing a dynamic parking demand forecast for the target parking lot based on the real-time road status characteristics of the target area, thereby generating a dynamic parking demand forecast value; Step S4: performing parking load peak prediction and parking lot capacity satisfaction rate evaluation based on the dynamic parking demand prediction value, thereby obtaining a parking lot capacity evaluation result; Step S5: Based on the parking lot capacity assessment result and the predicted occupancy time of the fixed parking spaces, a parking guidance decision for the vacant parking spaces is made, and an occupancy scheduling decision is made to obtain a parking guidance strategy for the vacant parking spaces and an occupancy scheduling strategy for the fixed parking spaces; Step S6: Perform intelligent parking collaborative management on the parking guidance strategy for the vacant parking spaces and the optimization scheduling strategy for the occupied time period, and build an intelligent parking collaborative management model.

[0028] By analyzing the dynamic characteristics of vehicles in fixed parking spaces and predicting the available occupancy time, the present invention can enable the system to better understand the usage of fixed parking spaces, predict the available occupancy time in advance, and improve the utilization rate of parking spaces. The generation of predicted available occupancy time for fixed parking spaces helps to optimize parking space allocation and improve the parking lot's vehicle capacity efficiency. By analyzing multi-section traffic flow and the time-series trend evolution of traffic flow, the system can generate real-time road status characteristics in the target area to help optimize the parking lot's traffic flow management and road traffic efficiency. The generation of real-time road status characteristics helps the system to more accurately evaluate the traffic conditions around the parking lot and provide more accurate data support for parking demand prediction. The time-series parking demand analysis combined with the real-time road status characteristics in the target area can more accurately predict the dynamic parking demand of the parking lot, help optimize parking resource management and parking lot planning, and the generation of dynamic parking demand prediction values ​​helps the system to make parking resource scheduling and management decisions in advance, thereby improving the efficiency and service level of the parking lot. The parking load peak prediction and parking lot capacity satisfaction rate assessment system can better understand the parking lot load and capacity utilization, and provide an important reference for parking resource management. The parking lot capacity assessment results help the system optimize the parking resource allocation and respond to parking peaks in advance, thereby improving the parking lot's operational efficiency and service quality. The formulation of idle parking guidance strategies and fixed parking space occupancy scheduling strategies can help optimize parking space allocation and improve parking lot parking efficiency, reduce confusion and congestion. By guiding vehicles to park in idle parking spaces, the system can improve parking lot utilization, reduce waiting time, and improve the overall efficiency and user experience of the parking lot. The establishment of an intelligent parking collaborative management model can help the system realize the intelligent allocation and coordination of parking resources, and improve the overall management efficiency and service level of the parking lot. Through intelligent parking collaborative management, the system can achieve the optimal configuration of parking resources, improve the efficiency of parking scheduling in the parking lot, and improve the parking utilization rate of vacant parking spaces.

[0029] In the embodiment of the present invention, refer to Figure 1 , is a schematic flow chart of the steps of a parking management method based on data analysis of the present invention. In this example, the steps of the parking management method based on data analysis include: Step S1: obtaining the real-time status information of the parking lot and the historical parking monitoring log of the parking lot; analyzing the dynamic characteristics of vehicles in fixed parking spaces in the real-time status information of the parking lot, and predicting the available occupancy time, thereby generating the predicted available occupancy time of the fixed parking spaces; In this embodiment, a parking lot management system or a sensor network is used to collect parking lot status information in real time, including: the current number of free parking spaces, the occupancy status of each parking space (free or occupied), and the vehicle entry and exit time. It is ensured that real-time data is stored through an API or a database interface for subsequent processing. Historical parking monitoring logs are extracted from the database to ensure that the data includes: timestamp, parking space number, vehicle entry and exit time, vehicle type and other relevant information. Data cleaning is performed to remove invalid or duplicate records to ensure data quality. The real-time status information and historical parking monitoring logs are integrated into a comprehensive data set. The structured data format (such as DataFrame) is convenient for subsequent analysis. It is ensured that each record contains key information such as time, parking space number, and occupancy status. Variables related to the dynamic characteristics of vehicles in fixed parking spaces are extracted from the integrated data set, including: the average length of vehicle stay, the frequency of vehicle entry and exit, and the parking space occupancy patterns in different time periods (peak hours, off-peak hours). Data processing tools such as Pandas or NumPy are used for data analysis, and statistical methods are applied to analyze the data. Analyze the dynamic characteristics of vehicles, for example: calculate the average stay time and occupancy rate in different time periods, use standard deviation or coefficient of variation to measure the volatility of parking time, use time series analysis methods (such as ARIMA, seasonal decomposition) to identify the trend and cyclical changes in parking demand, generate visual charts (such as line charts, heat maps) to show the changing trend of dynamic characteristics, select appropriate machine learning or statistical models (such as linear regression, random forest, LSTM, etc.) to predict the available occupancy time of fixed parking spaces, prepare training data sets, including historical parking time, vehicle dynamic characteristics and real-time status information, divide the data sets into training sets and test sets, use the training set to train the model: features include: vehicle entry and exit frequency, historical parking time, current occupancy status, etc., use cross-validation method to evaluate the prediction performance of the model, adjust hyperparameters to improve accuracy, and use the trained model to predict the available occupancy time of the current parking space: input the current real-time status information and dynamic characteristics, output the estimated available occupancy time, generate prediction results, and record the available occupancy time of each fixed parking space for subsequent scheduling and management.

[0030] Step S2: Obtaining traffic flow data of the target parking area; performing multi-section traffic flow analysis on the traffic flow data of the target parking area, and performing time series trend evolution of the traffic flow to generate real-time road status characteristics of the target area; In this embodiment, traffic flow sensors, such as video surveillance cameras, geomagnetic sensors, or infrared sensors, are installed on the main roads and intersections in the target parking area to monitor vehicle flow in real time. Configure the sensors to ensure that they can record the number of vehicles passing by, the speed, and the timestamp. The data should be uploaded to the central database regularly. The collected traffic flow data is stored in a structured database for subsequent query and analysis. The data format should include information such as timestamp, section number, and traffic volume. The collected data is cleaned to remove invalid data (such as duplicate records or erroneous data) and missing values. Convert the data format to a structure suitable for analysis, such as formatting the timestamp as a date and time type to ensure that all data is unified. Integrate the traffic flow data of different sections to form a traffic data set containing multiple sections. Extract key information from the integrated data, such as the traffic volume, average speed, and peak hours of each section. Calculate the traffic flow characteristics of each section in different time periods, including: average traffic volume, Peak traffic volume and standard deviation of traffic volume. Use Python's Pandas library or R language to analyze data and generate data reports. Use data visualization tools (such as Matplotlib, Seaborn, or Tableau) to generate traffic flow trend charts to show the changes in traffic volume on different sections. Organize traffic flow data into time series format to ensure that the traffic volume in each time period corresponds to the time label. Divide the data by time (such as hour, day, week) to analyze trends and periodic changes. Select appropriate time series analysis methods, such as: moving average method, exponential smoothing method, ARIMA model, and apply the selected time series analysis model to model historical traffic flow data to identify trends and seasonal components in the data. Generate traffic flow forecasts for a period of time in the future and analyze their changing trends. Based on the analysis results, extract real-time road status features, including: current traffic flow status (such as congestion, unblocked), traffic flow change trends during peak hours, and predicted future traffic flow. Record the generated real-time road state features in the database to form a report for use by management personnel and dispatching systems.

[0031] Step S3: Performing a time-series parking demand analysis on the parking lot's historical parking monitoring logs, and performing a dynamic parking demand forecast for the target parking lot based on the real-time road status characteristics of the target area, thereby generating a dynamic parking demand forecast value; In this embodiment, historical parking monitoring logs containing parking time, parking space number, entry and exit time are extracted from the database, the extracted historical data are cleaned, invalid records (such as duplicate or missing values) are removed, data integrity is ensured, the historical parking data are converted into a structured format, and the timestamp format is ensured to be consistent (for example, using Python's Pandas library for processing), key information is extracted from the historical parking data, such as: the average parking time of each parking space, the parking demand per hour and per day (the number of vehicles entering and exiting the parking space), the parking demand is grouped according to time (such as hour, day, week), and the parking demand for each time period is calculated, the groupby method of Pandas is used for aggregation analysis, and a demand data table is generated, and time series analysis methods (such as seasonal decomposition and ARIMA model) are applied to analyze the parking demand: identify the trend, seasonality and cyclical changes in demand, use Python's statsmodels library for time series modeling and analysis, and use visualization tools (such as Matplotlib or Seaborn) to generate a parking demand change trend chart to help understand the historical parking demand pattern, and obtain the road status characteristics of the target area from the real-time traffic monitoring system. , including real-time traffic flow, road congestion and peak hours information, integrating real-time road status features with historical parking demand data to form an information set containing historical demand and real-time status, selecting appropriate prediction models, such as: linear regression model, time series prediction model (such as LSTM, ARIMA), machine learning model (such as random forest, support vector machine), selecting the features required for prediction, including: historical parking demand, real-time road status features, other factors that may affect parking demand (such as weather, holidays, etc.), dividing the integrated data set into training set and test set, usually 70% as training set and 30% as test set, using the training set to train the selected model, adjusting the model parameters to improve the prediction accuracy, applying the cross-validation method to evaluate the performance of the model to ensure the generalization ability of the model, using the test set to verify the prediction effect of the model, calculating the prediction accuracy and error (such as RMSE, MAE), using the trained model to predict current and future parking demand, output dynamic parking demand prediction value, generate prediction results, including the expected parking demand and time period, and record the generated dynamic parking demand prediction value in the database to form an easy-to-query report for use by managers and decision-making systems.

[0032] Step S4: performing parking load peak prediction and parking lot capacity satisfaction rate evaluation based on the dynamic parking demand prediction value, thereby obtaining a parking lot capacity evaluation result; In this embodiment, historical parking demand data is obtained, including parking lot utilization rate, peak time period, weather factors, holiday impact, etc., missing values ​​and outliers are processed to ensure data accuracy and completeness, features that affect parking demand, such as time (hour, date), weather (sunny, rainy), special events, etc., are extracted, time series analysis methods (such as ARIMA, SARIMA) or machine learning models (such as random forest, XGBoost) are used to predict demand, historical data are used to train the selected model, parameters are adjusted to optimize the prediction effect, the prediction accuracy of the model is evaluated by cross-validation or holdout method to ensure the effectiveness of the model, the trained model is used to predict parking demand in future time periods, especially the demand during peak hours, a parking load curve is generated based on the prediction results, the parking demand changes in different time periods are intuitively displayed, the actual capacity of the parking lot (such as the number of parking spaces) is obtained, the satisfaction rate is calculated by comparing the predicted parking demand with the parking lot capacity, the satisfaction rate of the parking lot in different time periods is evaluated, possible supply and demand contradictions are identified, and data visualization tools (such as Matplotlib, Seaborn) are used to visualize the parking demand. or Tableau) to display the forecast results and satisfaction rates as charts, write detailed reports, summarize the results of parking demand forecast, load peak and capacity assessment, and put forward corresponding management suggestions.

[0033] Step S5: Based on the parking lot capacity assessment result and the predicted occupancy time of the fixed parking spaces, a parking guidance decision for the vacant parking spaces is made, and an occupancy scheduling decision is made to obtain a parking guidance strategy for the vacant parking spaces and an occupancy scheduling strategy for the fixed parking spaces; In this embodiment, real-time data of the current parking lot is obtained, including the number of free parking spaces, the occupancy status of each parking space, the predicted occupancy time, etc., and the evaluation results are analyzed: based on the parking lot capacity evaluation results of the previous step, the saturation level of the parking lot and the distribution of free parking spaces in different time periods are determined; based on historical data and current real-time data, time series analysis or machine learning models (such as LSTM, random forest) are used to predict the occupancy time of fixed parking spaces, and an occupancy schedule is generated: an occupancy schedule is created to list the predicted availability status of each fixed parking space in future time periods; according to the layout of the parking lot and the location of the free parking spaces, guidance rules are formulated, such as giving priority to guiding to parking spaces closer to the entrance; a real-time guidance system is designed, and electronic display screens or mobile phone applications are used to provide vehicles entering the parking lot with information and guidance directions for free parking spaces; a path optimization algorithm (such as Dijkstra Algorithms) provide vehicles with the best driving routes to reduce the time spent searching for parking spaces. Based on the predicted available time and free parking space information, a scheduling model is built to determine which vehicles can use fixed parking spaces within a specific time. Scheduling algorithms (such as priority queues and genetic algorithms) are used to optimize the allocation of parking spaces to ensure that parking space utilization is maximized during peak hours. Scheduling strategies are dynamically adjusted based on real-time data (such as vehicle entry and exit conditions, temporary demand changes) to ensure flexible response to different situations. The guidance system and scheduling strategies are integrated into the parking management system to ensure the flow and feedback of real-time data, continuously monitor the usage of parking spaces and the effectiveness of guidance strategies, and collect user feedback to evaluate system performance.

[0034] Step S6: Perform intelligent parking collaborative management on the parking guidance strategy for the vacant parking spaces and the optimization scheduling strategy for the occupied time period, and build an intelligent parking collaborative management model.

[0035] In this embodiment, relevant data of parking guidance strategies for vacant parking spaces and optimized scheduling strategies for occupied time periods are extracted from the database, real-time parking space usage, historical parking data, traffic flow data, and user feedback information are collected, and the above data are integrated into a comprehensive data set to ensure that the data format is consistent and easy to analyze. Data processing tools (such as Pandas) are used to convert the data into a structured format, and a suitable intelligent management model architecture is selected, such as a rule-based system, a machine learning model, or a hybrid model. The input and output of the model are determined, including: input: real-time parking space status, traffic flow, historical parking demand, user behavior data, etc., output: optimized guidance strategy, scheduling decision, parking space prediction information, etc., feature extraction and selection are performed on the input data to improve the prediction ability of the model, including features such as time features (weekdays, weekends), location features (parking space location), historical occupancy rate, etc., and a suitable algorithm is selected for model development, for example: supervised learning algorithms (such as random forests, support vector machines) are used for demand prediction, and reinforcement learning algorithms are used for dynamic scheduling and strategy optimization. , divide the integrated dataset into training set and test set, use the training set to train the model, apply cross-validation and hyperparameter tuning to ensure the accuracy and generalization ability of the model, use the test set to evaluate the performance of the model, calculate the model's accuracy, recall rate, F1 score and other indicators, iteratively optimize the model, adjust the model parameters and structure according to the evaluation results, deploy the trained model as a real-time decision-making system, analyze the input data in real time and generate decisions. The system can automatically adjust the idle parking space guidance strategy and occupancy scheduling strategy according to the real-time input, ensure the coordination between the guidance strategy and the scheduling strategy, avoid policy conflicts, set priority rules, such as giving priority to real-time traffic and user needs during peak hours, implement a real-time monitoring system, track the operation status of the parking lot, including parking space usage, user feedback and traffic flow, collect data to evaluate the effectiveness of the guidance and scheduling strategies, analyze the collected feedback data, identify problems and improvement opportunities in the system, and use data analysis tools (such as Python and R) for data visualization to help managers understand system performance.

[0036] In this embodiment, refer to Figure 2 , is a flowchart of detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include: Step S11: Acquire the real-time status information of the parking lot and the historical parking monitoring log of the parking lot; Step S12: Analyze the parking space status of the real-time parking lot status information to obtain free parking space data and fixed parking space data; Step S13: analyzing the dynamic characteristics of vehicles in fixed parking spaces based on the historical parking monitoring logs of the parking lot, thereby obtaining a behavior profile of the owners of the fixed parking spaces; Step S14: predicting the available occupancy time of the fixed parking space data according to the behavior profile of the owner of the fixed parking space, thereby generating the predicted available occupancy time of the fixed parking space.

[0037] In this embodiment, it is ensured that real-time monitoring equipment (such as cameras, sensors) and a parking management system are installed in the parking lot to collect parking space status information in real time, configure a data storage system, ensure the data integrity and accessibility of historical parking monitoring logs, collect parking lot status information in real time through sensors or monitoring equipment, including whether the parking space is occupied, license plate recognition, timestamp, etc., and mark the geographic location (such as parking space number) and time when recording data to ensure the timeliness and accuracy of the data, access the historical parking monitoring logs in the parking lot database, including the historical occupancy of each fixed parking space, parking time, owner information, etc. information, etc., to ensure that the data format is consistent for subsequent analysis, organize the real-time collected parking space status information, create a data table, indicate the status of each parking space (free or occupied), analyze the real-time status information, and identify free parking spaces and fixed parking spaces: Free parking spaces: parking spaces that are not currently occupied, fixed parking spaces: parking spaces that have been identified as long-term use, usually reserved or owned by car owners, store the analysis results (free parking space data and fixed parking space data) in the database for subsequent query and analysis, extract fixed parking space data from historical parking monitoring logs, including parking duration, arrival time, departure time, etc., and record the owner's The vehicle type, usage frequency, parking habits and other information of the owner are collected, and the dynamic feature analysis of the vehicle data of fixed parking spaces is performed using statistical analysis methods (such as time series analysis and cluster analysis): the parking behavior patterns of car owners are identified, such as peak parking time, average parking time, frequent parking days, etc. Based on the analysis results, a behavioral portrait of the owner of a fixed parking space is constructed, covering the following aspects: the owner's regular parking time period, the changing trend of parking time, the owner's vehicle usage frequency, and the selection of a suitable prediction model (such as linear regression, time series prediction, machine learning algorithm, such as random forest or LSTM) to predict the occupancy rate of fixed parking spaces. Use time, use historical parking data and fixed parking space owner behavior portraits as training data, train the prediction model: input features include the owner's parking time period, parking duration, historical occupancy rate, etc., use the trained model to predict the future occupancy time of fixed parking spaces: according to the owner's behavior pattern, predict the availability of parking spaces in the next time period, generate the predicted occupancy time of fixed parking spaces, including the estimated idle time and occupied time period, store the prediction results in the database, generate a data report on the occupancy time, provide decision support for the parking lot management system, and help managers optimize parking space allocation and parking strategies.

[0038] In this embodiment, the specific steps of step S13 are: Based on the parking lot's historical parking monitoring logs, the fixed parking space data is analyzed for multiple entry and exit time points, and multiple entry and exit time nodes are extracted; Calculate the vehicle dwell time for each of the multiple entry and exit time nodes and generate the dwell time for each time; Perform parking time fluctuation analysis on each stop time to obtain parking time fluctuation data; Perform time series variation fitting on the parking time fluctuation data and construct a parking time time series variation curve; Calculate the average length of stay for each stay to obtain the average length of stay; The parking demand time of fixed parking spaces is quantified based on the average stay time, thereby generating the parking demand time of vehicles in fixed parking spaces; The dynamic behavior characteristics of the parking time series change curve and the parking demand time of vehicles in fixed parking spaces are analyzed to obtain the dynamic behavior habit characteristics of vehicles in fixed parking spaces; The dynamic behavior habit characteristics of vehicles in fixed parking spaces are used to evolve the personalized characteristics of the owners and construct a behavioral profile of the owners of fixed parking spaces.

[0039] In this embodiment, the entry and exit records of fixed parking spaces are extracted from the historical parking monitoring log of the parking lot, and the data is ensured to contain information such as timestamp, parking space number, and license plate number. The extracted data is processed to identify the entry and exit time of each fixed parking space: a data processing tool (such as Python's Pandas library) is used to filter and sort the timestamps, and all entry and exit time nodes of each parking space are recorded to form a time node list. For each pair of entry and exit time nodes, the vehicle's stay time is calculated, and the stay time = exit time − entry time. Each stay time is analyzed to calculate the volatility of the stay time: the mean, standard deviation and other indicators of each stay time are counted to understand the range of variation of the stay time, and the fluctuation data of each stay time is recorded, including the maximum value, minimum value and mean value. Statistical analysis methods (such as variance analysis and standard deviation calculation) are used to quantify the fluctuation situation, and the stay time fluctuation data is organized into time series data to ensure that the timestamp corresponds to the stay time one by one. Time series analysis methods (such as ARIMA model and exponential smoothing method) are used to analyze the stay time. Fitting long data: Identify trends and seasonal components in the data, construct a time-series curve of parking time, record fitting results and parameters, average all dwell time data to obtain the average dwell time, which is the total dwell time / number of dwell times. According to the average dwell time, quantify the parking demand time for fixed parking spaces: Consider the usage frequency and dwell time of fixed parking spaces, generate an estimate of the parking demand time, record the parking demand time for each fixed parking space, organize the time-series curve of parking time and the parking demand time data for fixed parking spaces, analyze dynamic behavior characteristics, and identify the parking behavior habits of car owners: for example, analyze peak hours, usage frequency, demand changes, etc., use visualization tools (such as Matplotlib or Seaborn) to display the dynamic characteristics of parking behavior, and construct a behavioral portrait of the owner of a fixed parking space based on the dynamic behavior habit characteristics: including personalized characteristics such as the owner's parking habits, common time periods, and dwell time. With the continuous input of new data, the behavioral portrait is regularly updated to ensure that it reflects the latest behavior habits of the owner.

[0040] In this embodiment, refer to Figure 3 , is a flowchart of detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include: Step S21: Acquire traffic flow data of the target parking lot area based on regional road sensors; Step S22: performing a multi-section traffic flow analysis on the target parking lot area traffic flow data, thereby obtaining traffic flow characteristics of multiple sections; Step S23: performing spatial distribution analysis on the traffic flow characteristics of multiple road sections to generate traffic flow spatial distribution data; Step S24: performing time series trend evolution of vehicle flow on the spatial distribution data of vehicle flow, thereby generating time series distribution trend characteristics of vehicle flow; Step S25: Perform real-time road status mining on the time series distribution trend characteristics of the traffic flow to generate real-time road status characteristics of the target area. In this embodiment, road sensors (such as video surveillance, infrared sensors or geomagnetic sensors) are installed at each main entrance and exit of the target parking area, and the sensors are configured to ensure that they can monitor the number of vehicles passing by, vehicle speed and other data in real time. The sensors are started to collect traffic flow data of the target area in real time, including timestamp, license plate recognition, traffic flow and other information, and ensure that the data is stored in a structured format (such as CSV or database) to facilitate subsequent analysis. The traffic flow data is extracted from the data storage and sorted according to time and road section. A data table is created to ensure that the traffic data of each road section is clearly visible, and the traffic flow of each road section is statistically analyzed: the average traffic flow, peak flow and minimum flow of each road section in different time periods are calculated, and data analysis tools (such as Python's Pandas library) are used for data processing and statistics. The traffic flow characteristics of multiple road sections are extracted from the analysis, such as: changes in traffic flow in different time periods, peak traffic hours, etc., and the road section traffic flow characteristic data is sorted to ensure that the traffic statistics and location information of each road section are included. A geographic information system (GIS) tool (such as ArcGIS or Use QGIS) or data visualization tools for spatial analysis: visualize the traffic flow data of road sections, generate traffic flow heat maps, and display the traffic flow distribution of different sections. Record the generated traffic flow spatial distribution data in the database for subsequent query and analysis. Convert the spatial distribution data into time series data format to ensure that the changes in traffic flow over time for each section are clearly recorded. Use time series analysis methods (such as ARIMA and exponential smoothing) to analyze the time series data of traffic flow: identify the long-term trend and seasonal fluctuations of traffic flow, generate the time series distribution trend characteristics of traffic flow, including trend lines, seasonal changes, etc., for subsequent analysis. Combine real-time traffic flow data with time series trend characteristics to provide a basis for real-time status analysis, ensure that the system can update data in real time, so as to reflect traffic conditions in a timely manner. Use data mining technology (such as cluster analysis and anomaly detection) to analyze the time series distribution trend characteristics of traffic flow: identify the real-time road status (such as congestion, smoothness, slowness) and generate corresponding road status characteristics. Record the mined real-time road status characteristics of the target area in the database for subsequent scheduling and decision support.

[0041] In this embodiment, refer to Figure 4 , is a flowchart of detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include: Step S31: Performing a quantitative evaluation of historical parking vehicles on the parking lot historical parking monitoring log to generate the number of historical parking vehicles; Step S32: performing a time-series parking demand analysis on the number of historical parked vehicles to generate parking lot time-series parking demand data; Step S33: identifying periodic difference changes in the parking lot time series parking demand data to generate parking demand periodic difference change data; Step S34: Perform dynamic parking demand prediction for the target parking lot based on the parking demand cycle difference change data and the real-time road status characteristics of the target area, thereby generating a dynamic parking demand prediction value.

[0042] In this embodiment, the historical parking monitoring log of the parking lot is extracted from the database to ensure that the data contains timestamps, parking space numbers, license plate information, etc. The data is cleaned to remove invalid or duplicate records to ensure data quality. The data is summarized by time (such as by day, week, or month) for subsequent analysis. The number of historical parking vehicles in each time period is calculated using statistical methods: for example, the number of parked vehicles on each day is counted to generate time series data of the historical number of parking vehicles. The calculation results are recorded in the database to generate a report on the number of historical parking vehicles. The historical number of parking vehicles is organized into a time series format to ensure that the number of vehicles and timestamps in each time period correspond one to one. Time series analysis methods, such as moving average method, exponential smoothing method, or ARIMA model are applied to analyze parking demand: trends, seasonal changes, and periodic patterns in parking demand are identified. Time series parking demand data of the parking lot is generated based on the analysis results, including comparisons between predicted demand and actual demand in each time period. Time series analysis tools (such as Python's Statsmodels library) are used to analyze the periodic characteristics of parking demand data: different Changes in parking demand over time periods (such as weekdays and weekends, holidays and non-holidays), calculate the difference in parking demand between different periods: for example, compare the average parking demand on weekdays and weekends, record the magnitude of the change, record the results of the cycle difference change in the database, generate a parking demand cycle difference change report, integrate the parking demand cycle difference change data with the real-time road status characteristics of the target area (such as traffic flow, congestion, etc.), select a suitable prediction model (such as regression model, time series prediction model or machine learning model, such as random forest, LSTM) to perform dynamic parking demand prediction, use the integrated data to train the prediction model, and ensure that the model can capture the relationship between parking demand and road status: input features include historical parking demand, cycle difference changes, real-time road status, etc. In a real-time environment, use the trained model to predict the dynamic parking demand of the target parking lot: generate dynamic parking demand prediction values ​​for the current and future time periods (such as the expected number of demand vehicles), record the dynamic parking demand prediction values ​​in the database, and generate a prediction report to provide decision support for parking lot management.

[0043] In this embodiment, step S4 includes the following steps: Step S41: performing real-time situation change analysis on the idle parking space data to generate real-time situation change data of the idle parking spaces; Step S42: quantifying the parking lot load based on the real-time status change data of the vacant parking spaces to obtain the parking load data of the target parking lot; Step S43: predicting the parking load peak value of the target parking lot parking load data, thereby obtaining a predicted parking load peak value; Step S44: evaluating the parking lot capacity satisfaction rate of the predicted parking load peak based on the dynamic parking demand prediction value, thereby obtaining a parking lot capacity evaluation result.

[0044] In this embodiment, the current free parking space data, including timestamp, parking space number, parking space status (free or occupied) and other information, are extracted from the parking lot management system to ensure that the data is updated in real time to reflect the current status of the parking lot. The change trend of the free parking spaces is analyzed using statistical analysis methods (such as change rate calculation, moving average): the increase and decrease of free parking spaces in each time period is calculated, and the change pattern is identified, such as the decrease of free parking spaces during peak hours and the increase of parking spaces at night. The results of the real-time situation change analysis are recorded in the database, and a real-time situation change data report of free parking spaces is generated. The load quantification method is determined, such as the use of parking space utilization calculation: parking space utilization = (total number of parking spaces - number of free parking spaces) / Total number of parking spaces. Calculate the current parking lot load based on real-time situation change data: count the current number of free parking spaces and the total number of parking spaces, calculate the load, record the calculation results in the database, generate parking load data, use visualization tools (such as Matplotlib, Tableau) to display the parking lot load so that managers can quickly obtain information, organize parking load data, and ensure that timestamps and corresponding load values ​​are included. Select a suitable prediction model to predict the parking load peak, such as: time series model (such as ARIMA, seasonal decomposition), machine learning model (such as random forest, support vector machine), use historical parking load data to train the selected prediction model: divide the training set and test set, use the training set to fit the model, use the test set to verify the prediction accuracy of the model, and adjust the model parameters, use the trained model to predict future parking loads, generate predicted parking load peak data, record the prediction results in the database, and generate a parking load peak prediction report for managers to refer to, extract dynamic parking demand prediction values ​​and predicted parking load peak data from the database, and calculate the parking lot capacity satisfaction rate: Capacity satisfaction rate = (current parking lot capacity - predicted parking load peak) / The current parking lot capacity, evaluate the calculation results, and determine whether the parking lot capacity can meet the expected parking demand: if the satisfaction rate is lower than a certain threshold, measures may need to be taken (such as adding parking spaces, optimizing parking management), record the parking lot capacity assessment results in the database, and generate a capacity assessment report, using visualization tools to display the assessment results so that managers can make decisions.

[0045] In this embodiment, the specific steps of step S5 are: Step S51: when the parking lot capacity assessment result is that the capacity meets the demand prediction value, a parking guidance decision for an idle parking space is made and an idle parking space parking guidance strategy is constructed; Step S52: when the parking lot capacity assessment result is that the capacity does not meet the demand prediction value, a parking time prediction is performed on the dynamic parking demand prediction value, thereby obtaining parking time prediction data; Step S53: dynamically matching the predicted available occupancy time of fixed parking spaces with the available occupancy time of fixed parking spaces based on the parking duration prediction data, thereby obtaining the optimal occupancy matching parking space; Step S54: Make an occupancy scheduling decision for the optimal occupancy matching parking space and construct a fixed parking space occupancy scheduling strategy.

[0046] In this embodiment, the parking lot capacity assessment result is extracted from the database to check whether it meets the demand forecast value, and a threshold is set. If the capacity meets the demand, the parking guidance decision is continued to obtain the information of the current free parking space, including the parking space number, location, availability, etc. The parking guidance decision is constructed: based on the free parking space data and the parking lot layout, a free parking space parking guidance strategy is constructed: guidance rules are formulated, such as giving priority to free parking spaces close to the entrance, using algorithms (such as Dijkstra or A* algorithms) to calculate the optimal path from the entrance to each free parking space, and the parking guidance strategy is published to vehicles entering the parking lot through the parking lot information system (such as electronic display screens, mobile phone applications) to guide drivers to the free parking spaces. The parking lot capacity assessment result is extracted from the database to check whether it does not meet the demand forecast value, and the current dynamic parking demand forecast value is obtained. These values ​​reflect the parking demand expected in a certain period of time in the future. A suitable parking time prediction model (such as regression analysis, time series prediction model LSTM, etc.) is selected. The model should be able to predict the time based on historical parking data and current dynamic demand forecasts. The selected model is used to analyze the parking demand data to generate parking time prediction data, including the expected parking time of each vehicle. The system extracts the relevant information of fixed parking spaces from the database, including the parking space number, current occupancy status, historical usage data, etc. Based on the parking time prediction data, the available occupancy time of each fixed parking space is calculated: the historical parking time and predicted parking time of each parking space are considered, the availability of each parking space in the future is evaluated, and the matching algorithm (such as the Hungarian algorithm or linear programming) is applied to dynamically match the available occupancy time of fixed parking spaces: the goal is to maximize the utilization rate of parking spaces while ensuring that the needs of car owners are met, and the optimal occupancy matching parking space information, including the parking space number and the estimated available occupancy time, is recorded for subsequent scheduling. Based on the information of the optimal occupied matching parking spaces, a fixed parking space occupancy scheduling strategy is constructed: determine which parking spaces are available for new cars to enter and when, formulate corresponding scheduling rules, and use scheduling algorithms (such as priority scheduling and polling scheduling) to make scheduling decisions for the optimal occupied matching parking spaces: ensure that the scheduling strategy can be flexibly adjusted under real-time changing parking needs, and publish the scheduling decisions to drivers through the parking lot information system, including information on available parking spaces and estimated idle time. After implementing the scheduling strategy, the parking space usage is monitored in real time, and feedback data is collected: the scheduling strategy is adjusted according to the feedback to ensure maximum parking space utilization and user satisfaction.

[0047] In this embodiment, the specific steps of step S6 are: Step S61: Real-time entry monitoring of vehicles in fixed parking spaces to generate vehicle entry data; Step S62: Performing a fixed parking space occupancy and expulsion warning based on the vehicle entry data to generate an occupancy and expulsion warning signal; Step S63: optimizing the occupancy time period of the fixed parking space occupancy scheduling strategy based on the occupancy and expulsion warning signal, and constructing an occupancy time period optimization scheduling strategy; Step S64: Perform intelligent parking collaborative management on the parking guidance strategy for the vacant parking spaces and the optimization scheduling strategy for the occupied time period, and construct an intelligent parking collaborative management model.

[0048] In this embodiment, a vehicle identification system (such as a license plate recognition camera or sensor) is installed at the entrance of the parking lot to monitor the entry of vehicles in real time. When a vehicle enters, the system automatically records the vehicle information, including the license plate number, entry time, parking space number, etc., generates vehicle entry data, ensures that the data is stored in a structured format (such as JSON or a database) for subsequent analysis, and updates the vehicle status of the parking lot in real time to ensure that the entry data and the occupancy status of fixed parking spaces are always synchronized. The occupancy status of fixed parking spaces is continuously monitored, with special attention paid to parking spaces that have been occupied but need to be evicted. Warning conditions are set according to the parking lot management strategy, such as parking spaces whose occupancy time exceeds a set threshold, parking spaces that are illegally parked or improperly occupied. When the warning conditions are met, the system automatically generates an occupation and expulsion warning signal, including information such as the parking space number, occupancy time, and warning level, and sends the warning signal to the monitoring system or mobile device of the management personnel for timely processing. The data of the occupation and expulsion warning signal are collected, and the occupancy status and expulsion requirements of the relevant parking spaces are analyzed. The occupancy of each parking space is evaluated according to the warning signal. Time period: Identify which parking spaces can be released within a specific time period and which parking spaces need to be given priority. Use optimization algorithms (such as linear programming or genetic algorithms) to optimize the parking space occupation time period. Based on the optimization results, build an optimized scheduling strategy for the occupied time period to clarify which parking spaces can be released or used at what time. Record the optimized scheduling strategy in the system for subsequent scheduling and use. Integrate the parking guidance strategy for idle parking spaces and the optimized scheduling strategy for the occupied time period to ensure the synergy between the two. Identify the intersection and mutual influence of different strategies to optimize the overall parking management efficiency. Based on existing data and strategies, build an intelligent parking collaborative management model: the model should consider multiple factors such as vehicle entry, parking space occupancy, eviction warning and dynamic scheduling. Use machine learning algorithms (such as decision trees and random forests) to train the model to improve the system's intelligent decision-making ability. In actual operation, the system monitors the parking lot status in real time and makes dynamic adjustments based on the decisions output by the model: for example, update the guidance strategy in real time, adjust the guidance information according to the parking space occupancy, collect management effect feedback, and continuously optimize the intelligent management model.

[0049] In this embodiment, a parking management system based on data analysis is provided, which is used to execute the parking management method based on data analysis as described above, including: The vehicle dynamic feature module is used to obtain the real-time status information of the parking lot and the historical parking monitoring log of the parking lot; analyze the dynamic features of vehicles in fixed parking spaces based on the real-time status information of the parking lot, and make an occupancy time prediction, thereby generating the predicted occupancy time of fixed parking spaces; The road state feature module is used to obtain the traffic flow data of the target parking area; perform multi-section traffic flow analysis on the traffic flow data of the target parking area, and perform the time series trend evolution of the traffic flow to generate real-time road state features of the target area; The parking demand prediction module is used to perform time-series parking demand analysis on the parking lot's historical parking monitoring logs, and to perform dynamic parking demand prediction on the target parking lot based on the real-time road status characteristics of the target area, thereby generating a dynamic parking demand prediction value; The load peak prediction module is used to predict the parking load peak and evaluate the parking lot capacity satisfaction rate based on the dynamic parking demand prediction value, so as to obtain the parking lot capacity evaluation result; The scheduling decision module is used to make parking guidance decisions for free parking spaces based on the parking lot capacity assessment results and the predicted occupancy time of fixed parking spaces, and make occupancy scheduling decisions to obtain parking guidance strategies for free parking spaces and occupancy scheduling strategies for fixed parking spaces; The collaborative management module is used to perform intelligent parking collaborative management on the parking guidance strategy for vacant parking spaces and the optimization scheduling strategy for occupied time periods, and to build an intelligent parking collaborative management model.

[0050] The present invention helps the system understand the dynamic characteristics and parking conditions of vehicles in the parking lot by acquiring real-time parking lot status information and historical parking monitoring logs. By analyzing the dynamic characteristics of vehicles in fixed parking spaces and predicting the available occupancy time, the system can accurately predict the available occupancy time of fixed parking spaces and optimize the utilization rate of fixed parking spaces. Acquiring traffic flow data in the target parking lot area helps the system understand the traffic conditions of surrounding roads and provide a reference basis for parking demand prediction. By analyzing the traffic flow and time series trend evolution, the system can generate real-time road status characteristics in the target area to help more accurately predict parking demand and optimize parking resource allocation. Parking demand prediction based on historical parking monitoring logs and road status characteristics helps the system more accurately predict the dynamic parking demand of the parking lot. Through the dynamic parking demand prediction value, the system can adjust the parking resource allocation according to the real-time road status characteristics, improve the resource utilization efficiency of the parking lot, and optimize the parking demand. Calculating the predicted value for parking load peak prediction and capacity satisfaction rate assessment can help the system to timely adjust the allocation of parking resources and optimize parking lot management. Obtaining the parking lot capacity assessment results can help the system to reasonably arrange parking resources, avoid parking congestion and improve the operating efficiency of the parking lot. Making idle parking guidance decisions and available scheduling decisions based on capacity assessment results and the predicted available time of fixed parking spaces can help the system to realize intelligent scheduling of parking resources. Constructing idle parking space parking guidance strategies and fixed parking space occupancy scheduling strategies can improve the utilization rate and service quality of parking lots and optimize parking processes. Intelligent parking collaborative management of idle parking space parking guidance strategies and occupied time period optimization scheduling strategies can help integrate information from various modules and realize comprehensive management and optimization of parking lot resources. Constructing an intelligent parking collaborative management model can improve the overall efficiency of parking lots, optimize the allocation of parking resources, and enhance user parking experience and management efficiency.

[0051] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0052] The above is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A parking management method based on data analysis, characterized in that: The following steps are involved: Step S1: obtaining the real-time status information of the parking lot and the historical parking monitoring log of the parking lot; analyzing the dynamic characteristics of vehicles in fixed parking spaces in the real-time status information of the parking lot, and predicting the available occupancy time, thereby generating the predicted available occupancy time of the fixed parking spaces; Step S2: Obtaining traffic flow data of the target parking area; performing multi-section traffic flow analysis on the traffic flow data of the target parking area, and performing time series trend evolution of the traffic flow to generate real-time road status characteristics of the target area; Step S3: Performing a time-series parking demand analysis on the parking lot's historical parking monitoring logs, and performing a dynamic parking demand forecast for the target parking lot based on the real-time road status characteristics of the target area, thereby generating a dynamic parking demand forecast value; Step S4: performing parking load peak prediction and parking lot capacity satisfaction rate evaluation based on the dynamic parking demand prediction value, thereby obtaining a parking lot capacity evaluation result; Step S5: Based on the parking lot capacity assessment result and the predicted occupancy time of the fixed parking spaces, a parking guidance decision for the vacant parking spaces is made, and an occupancy scheduling decision is made to obtain a parking guidance strategy for the vacant parking spaces and an occupancy scheduling strategy for the fixed parking spaces; Step S6: Perform intelligent parking collaborative management on the parking guidance strategy for the vacant parking spaces and the optimization scheduling strategy for the occupied time period, and build an intelligent parking collaborative management model.

2. The parking management method based on data analysis according to claim 1, characterized in that: The specific steps of step S1 are: Step S11: Acquire the real-time status information of the parking lot and the historical parking monitoring log of the parking lot; Step S12: Analyze the parking space status of the real-time parking lot status information to obtain free parking space data and fixed parking space data; Step S13: analyzing the dynamic characteristics of vehicles in fixed parking spaces based on the historical parking monitoring logs of the parking lot, thereby obtaining a behavior profile of the owners of the fixed parking spaces; Step S14: predicting the available occupancy time of the fixed parking space data according to the behavior profile of the owner of the fixed parking space, thereby generating the predicted available occupancy time of the fixed parking space.

3. The parking management method based on data analysis according to claim 2 is characterized in that: The specific steps of step S13 are: Based on the parking lot's historical parking monitoring logs, the fixed parking space data is analyzed for multiple entry and exit time points, and multiple entry and exit time nodes are extracted; Calculate the vehicle dwell time for each of the multiple entry and exit time nodes and generate the dwell time for each time; Perform parking time fluctuation analysis on each stop time to obtain parking time fluctuation data; Perform time series variation fitting on the parking time fluctuation data and construct a parking time time series variation curve; Calculate the average length of stay for each stay to obtain the average length of stay; The parking demand time of fixed parking spaces is quantified based on the average stay time, thereby generating the parking demand time of vehicles in fixed parking spaces; The dynamic behavior characteristics of the parking time series change curve and the parking demand time of vehicles in fixed parking spaces are analyzed to obtain the dynamic behavior habit characteristics of vehicles in fixed parking spaces; The dynamic behavior habit characteristics of vehicles in fixed parking spaces are used to evolve the personalized characteristics of the owners and construct a behavioral profile of the owners of fixed parking spaces.

4. The parking management method based on data analysis according to claim 1, characterized in that: The specific steps of step S2 are: Step S21: Acquire traffic flow data of the target parking lot area based on regional road sensors; Step S22: performing a multi-section traffic flow analysis on the target parking lot area traffic flow data, thereby obtaining traffic flow characteristics of multiple sections; Step S23: performing spatial distribution analysis on the traffic flow characteristics of multiple road sections to generate traffic flow spatial distribution data; Step S24: performing time series trend evolution of vehicle flow on the spatial distribution data of vehicle flow, thereby generating time series distribution trend characteristics of vehicle flow; Step S25: Perform real-time road status mining on the time series distribution trend characteristics of the traffic flow to generate real-time road status characteristics of the target area.

5. The parking management method based on data analysis according to claim 1, characterized in that: The specific steps of step S3 are: Step S31: Performing a quantitative evaluation of historical parking vehicles on the parking lot historical parking monitoring log to generate the number of historical parking vehicles; Step S32: performing a time-series parking demand analysis on the number of historical parked vehicles to generate parking lot time-series parking demand data; Step S33: identifying periodic difference changes in the parking lot time series parking demand data, and generating parking demand periodic difference change data; Step S34: Perform dynamic parking demand prediction for the target parking lot based on the parking demand cycle difference change data and the real-time road status characteristics of the target area, thereby generating a dynamic parking demand prediction value.

6. The parking management method based on data analysis according to claim 1, characterized in that: The specific steps of step S4 are: Step S41: performing real-time situation change analysis on the idle parking space data to generate real-time situation change data of the idle parking spaces; Step S42: quantifying the parking lot load based on the real-time status change data of the vacant parking spaces to obtain the parking load data of the target parking lot; Step S43: predicting the parking load peak value of the target parking lot parking load data, thereby obtaining a predicted parking load peak value; Step S44: evaluating the parking lot capacity satisfaction rate of the predicted parking load peak based on the dynamic parking demand prediction value, thereby obtaining a parking lot capacity evaluation result.

7. The parking management method based on data analysis according to claim 1, characterized in that: The specific steps of step S5 are: Step S51: when the parking lot capacity assessment result is that the capacity meets the demand prediction value, a parking guidance decision for an idle parking space is made and an idle parking space parking guidance strategy is constructed; Step S52: when the parking lot capacity assessment result is that the capacity does not meet the demand prediction value, a parking time prediction is performed on the dynamic parking demand prediction value, thereby obtaining parking time prediction data; Step S53: dynamically matching the predicted available occupancy time of fixed parking spaces with the available occupancy time of fixed parking spaces based on the parking duration prediction data, thereby obtaining the optimal occupancy matching parking space; Step S54: Make an occupancy scheduling decision for the optimal occupancy matching parking space and construct a fixed parking space occupancy scheduling strategy.

8. The parking management method based on data analysis according to claim 1, characterized in that: The specific steps of step S6 are: Step S61: Real-time entry monitoring of vehicles in fixed parking spaces to generate vehicle entry data; Step S62: Performing a fixed parking space occupancy and expulsion warning based on the vehicle entry data to generate an occupancy and expulsion warning signal; Step S63: optimizing the occupancy time period of the fixed parking space occupancy scheduling strategy based on the occupancy and expulsion warning signal, and constructing an occupancy time period optimization scheduling strategy; Step S64: Perform intelligent parking collaborative management on the parking guidance strategy for the vacant parking spaces and the optimization scheduling strategy for the occupied time period, and construct an intelligent parking collaborative management model.

9. A parking management system based on data analysis, characterized in that: The method for executing the parking management method based on data analysis as claimed in claim 1 comprises: The vehicle dynamic feature module is used to obtain the real-time status information of the parking lot and the historical parking monitoring log of the parking lot; analyze the dynamic features of vehicles in fixed parking spaces based on the real-time status information of the parking lot, and make an occupancy time prediction, thereby generating the predicted occupancy time of fixed parking spaces; The road state feature module is used to obtain the traffic flow data of the target parking area; perform multi-section traffic flow analysis on the traffic flow data of the target parking area, and perform the time series trend evolution of the traffic flow to generate real-time road state features of the target area; The parking demand prediction module is used to perform time-series parking demand analysis on the parking lot's historical parking monitoring logs, and to perform dynamic parking demand prediction on the target parking lot based on the real-time road status characteristics of the target area, thereby generating a dynamic parking demand prediction value; The load peak prediction module is used to predict the parking load peak and evaluate the parking lot capacity satisfaction rate based on the dynamic parking demand prediction value, so as to obtain the parking lot capacity evaluation result; The scheduling decision module is used to make parking guidance decisions for free parking spaces based on the parking lot capacity assessment results and the predicted occupancy time of fixed parking spaces, and make occupancy scheduling decisions to obtain parking guidance strategies for free parking spaces and occupancy scheduling strategies for fixed parking spaces; The collaborative management module is used to perform intelligent parking collaborative management on the parking guidance strategy for vacant parking spaces and the optimization scheduling strategy for occupied time periods, and to build an intelligent parking collaborative management model.

Images