Parking management method and device, computer equipment and medium storage medium

Abstract

The invention relates to the technical field of intelligent transportation and intelligent parking. The invention relates to a parking management method and device, computer equipment and a medium, and the method comprises the steps: obtaining the parking number information in a parking region, predicting the parking number information in the parking region through a trained ARIMA model, obtaining the use condition of a future parking region, and carrying out the prediction of the parking number information in the parking region according to the use condition of the future parking region. And dynamically adjusting the charging standard of the parking area to obtain the adjusted charging standard of the parking area, recalculating the parking fee according to the adjusted charging standard of the parking area to obtain the final parking fee, and sending the final parking fee to the mobile terminal. The method has the effects of improving the parking resource utilization rate and optimizing the parking fee.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent transportation and smart parking, and in particular to a parking management method, device, computer equipment and media storage medium. Background Art

[0002] With the rapid pace of urbanization and the dramatic increase in the number of cars, parking has become a major challenge for urban transportation. Traditional parking management methods often rely on fixed fees that cannot be flexibly adjusted based on parking demand and space usage. This leads to inefficient parking resource utilization and a poor parking experience for drivers. Therefore, there is an urgent need for a parking management method that can intelligently predict parking demand and dynamically adjust fees. Summary of the Invention

[0003] In order to improve the utilization rate of parking resources and optimize parking fees, the present application provides a parking management method, apparatus, computer equipment and storage medium.

[0004] The above-mentioned invention objective of this application is achieved through the following technical solutions: A parking management method, comprising: Get the number of parking spaces in the parking area; The trained ARIMA model is used to predict the number of parking spaces in the parking area to obtain the future usage of the parking area. Dynamically adjusting the charging standard of the parking area according to the future usage of the parking area to obtain an adjusted charging standard of the parking area; The parking fee is recalculated according to the adjusted parking area charging standard to obtain a final parking fee, and the final parking fee is sent to the mobile terminal.

[0005] By implementing the above technical solution and using the trained ARIMA model, the system can predict future parking area usage. Knowing peak and off-peak hours in advance helps better allocate parking resources. Based on the predictions, the system can increase parking fees during high-demand periods to encourage short-term parking, achieve faster turnover, and improve parking space utilization. It can also reduce parking fees during low-demand periods to attract more drivers and prevent vacant spaces. Adjusting fees based on demand: Parking fees are dynamically adjusted to ensure revenue increases during peak demand periods, while lowering fees during off-peak periods to attract more vehicles and increase overall revenue. The final parking fee is recalculated based on the driver's actual parking time and the adjusted fee schedule to ensure reasonable pricing and enhance user satisfaction.

[0006] In a preferred example, the present application may be further configured as follows: before obtaining the vehicle information in the parking area, the method further includes: Historical vehicle information and historical parking space information in a parking area are obtained, and a preset ARIMA model is trained using the historical vehicle information and the historical parking space information in the parking area to obtain the trained ARIMA model.

[0007] By adopting the above technical solution, obtaining and analyzing historical vehicle and parking space information and training the ARIMA model, more accurate parking demand forecasting, dynamic resource management and charging optimization can be achieved.

[0008] In a preferred example, the present application may be further configured as follows: acquiring historical vehicle information and historical parking space information in a parking area, training a preset ARIMA model with the historical vehicle information and the historical parking space information in the parking area to obtain the trained ARIMA model, and further comprising: The cross-validation method was used to verify the stability and predictive ability of the preset ARIMA model.

[0009] By employing these technical solutions, cross-validation ensures that the model performs well on the training data and also maintains stability on unseen data by dividing the data into multiple training and validation sets, preventing the model from overfitting to a specific dataset. More accurate parking demand forecasts enable parking lot managers to more precisely allocate parking resources, reducing vacancies and overcrowding.

[0010] In a preferred example, the present application may be further configured as follows: the trained ARIMA model is used to predict the number of parking spaces in the parking area to obtain the future usage of the parking area, including: The trained ARIMA model is used to recursively predict the future usage of the parking area based on historical data before the current time point.

[0011] By adopting the above technical solutions and accurately predicting future parking needs, we can understand the parking space demand during peak and off-peak hours in advance, reasonably allocate parking space resources, and reduce parking vacancies.

[0012] Optimize parking space scheduling: Dynamically adjust parking space openings and closings based on predicted parking demand to improve parking space utilization. For example, during peak demand periods, increase parking space availability; during low demand periods, reduce the number of available spaces for maintenance and management. Recursive forecasting provides timely understanding of future parking demand trends, enabling proactive response and increased flexibility and effectiveness in responding to emergencies. More accurate demand forecasting and parking space management reduce driver search time and enhance the user parking experience. Dynamically adjust parking fees based on predicted future parking demand. Increase parking fees during peak demand periods to balance demand; reduce fees during low demand periods to attract more drivers and maximize parking revenue. Dynamic pricing smooths out parking revenue fluctuations and ensures optimal revenue levels across time periods. Recalculating parking fees based on predicted demand and driver parking duration ensures transparent, fair, and reasonable pricing, enhancing user trust and satisfaction. Recursive forecasting provides timely understanding of future parking demand trends and allows for flexible adjustment of pricing to ensure optimal pricing across time periods.

[0013] In a preferred example, the present application may be further configured as follows: recalculating the parking fee according to the adjusted parking area charging standard to obtain a final parking fee, and sending the final parking fee to the mobile terminal, including: determining a high-demand period for parking spaces and a low-demand period for parking spaces based on the future usage of the parking area; Increase parking prices during periods of high demand for parking spaces and reduce parking prices during periods of low demand for parking spaces; The final parking fee is sent to the mobile terminal.

[0014] By implementing the above technical solution, increasing parking prices during periods of high demand can curb excessive demand, ensure that parking spaces are used by those who truly need them, and avoid wasting parking resources. Lowering parking prices during periods of low demand can attract more drivers to park during low-demand periods, balance the distribution of parking demand across time periods, and improve overall parking space utilization. Increased revenue during peak periods: By raising parking prices during periods of high demand, parking lots can increase peak-period revenue and maximize profits. Lowering parking prices during periods of low demand attracts more drivers to park, increases off-peak revenue, and optimizes the overall parking lot revenue structure. Adjusting parking fees based on real-time demand ensures reasonable and fair pricing, increasing user satisfaction and trust in parking lot management. Final parking fees are delivered promptly via mobile devices, allowing users to know and understand the pricing standards in advance.

[0015] In a preferred example, the present application can be further configured as follows: the parking management method further includes: Obtain expected parking time information, dynamically adjust parking spaces in the parking area, and obtain adjusted parking spaces; By using a priority allocation algorithm, when the expected parking duration information is high, the parking space is allocated to the user with the high expected parking duration; The distance between the parking space and the owner's destination is calculated through the distance optimal allocation algorithm, and parking spaces with shorter distances are allocated first.

[0016] By adopting the above technical solution, the management system can dynamically adjust parking space allocation strategies by collecting and analyzing users' expected parking duration information, achieving refined management and improving overall management efficiency. Based on real-time expected parking duration data, the management system can flexibly adjust parking space allocation strategies to ensure the rational allocation and efficient utilization of parking resources. By prioritizing parking spaces to users with high expected parking durations, this ensures that parking spaces are effectively used for extended periods of time, reducing frequent parking turnover and vacant time. Allocating parking spaces based on the driver's expected parking duration and distance to their destination optimizes parking space usage, reduces traffic congestion within the parking lot, and improves parking space utilization efficiency. Using a distance-optimal allocation algorithm, parking spaces are allocated to the spaces closest to the driver's destination, reducing search time and improving parking convenience. Intelligent allocation based on the user's expected parking duration ensures that drivers can quickly find a suitable space.

[0017] The second object of the present invention is achieved through the following technical solutions: A parking management device, comprising: An information acquisition module is used to obtain parking quantity information in a parking area; A model output module is used to predict the number of parking spaces in the parking area using the trained ARIMA model to obtain the future usage of the parking area; A charging standard module, configured to dynamically adjust the charging standard of the parking area according to the future usage of the parking area, and obtain an adjusted charging standard of the parking area; The fee sending module is used to recalculate the parking fee according to the adjusted parking area charging standard to obtain the final parking fee, and send the final parking fee to the mobile terminal.

[0018] By implementing the above technical solution and using the trained ARIMA model, the system can predict future parking area usage. Knowing peak and off-peak hours in advance helps better allocate parking resources. Based on the predictions, the system can increase parking fees during high-demand periods to encourage short-term parking, achieve faster turnover, and improve parking space utilization. It can also reduce parking fees during low-demand periods to attract more drivers and prevent vacant spaces. Adjusting fees based on demand: Parking fees are dynamically adjusted to ensure revenue increases during peak demand periods, while lowering fees during off-peak periods to attract more vehicles and increase overall revenue. The final parking fee is recalculated based on the driver's actual parking time and the adjusted fee schedule to ensure reasonable pricing and enhance user satisfaction.

[0019] A parking management device, further comprising: The parking duration module is used to obtain expected parking duration information, dynamically adjust the parking spaces in the parking area, and obtain the adjusted parking spaces; a priority allocation algorithm module, configured to allocate a parking space to a user with a long expected parking time by using a priority allocation algorithm when the expected parking time information is long; The distance optimal allocation algorithm module is used to calculate the distance from the parking space to the owner's destination through the distance optimal allocation algorithm, and give priority to allocating parking spaces with shorter distances.

[0020] By adopting the above technical solution, the management system can dynamically adjust parking space allocation strategies by collecting and analyzing users' expected parking duration information, achieving refined management and improving overall management efficiency. Based on real-time expected parking duration data, the management system can flexibly adjust parking space allocation strategies to ensure the rational allocation and efficient utilization of parking resources. By prioritizing parking spaces to users with high expected parking durations, this ensures that parking spaces are effectively used for extended periods of time, reducing frequent parking turnover and vacant time. Allocating parking spaces based on the driver's expected parking duration and distance to their destination optimizes parking space usage, reduces traffic congestion within the parking lot, and improves parking space utilization efficiency. Using a distance-optimal allocation algorithm, parking spaces are allocated to the spaces closest to the driver's destination, reducing search time and improving parking convenience. Intelligent allocation based on the user's expected parking duration ensures that drivers can quickly find a suitable space.

[0021] The third objective of this application is achieved through the following technical solutions: A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the parking management method are implemented.

[0022] The fourth objective of this application is achieved through the following technical solutions: A computer-readable storage medium stores a computer program, which implements the steps of the parking management method when executed by a processor.

[0023] In summary, this application includes at least one of the following beneficial technical effects: 1. Through the trained ARIMA model, the system can predict the future usage of parking areas. Knowing the peak and off-peak hours in advance will help better allocate parking resources. Based on the prediction results, the system can increase parking fees during high-demand periods to encourage short-term parking, quick turnover, and improve parking space utilization. Reduce parking fees during low-demand periods to attract more car owners to park and avoid vacant parking spaces. Adjust charges based on demand: Dynamically adjust parking fee standards to ensure that revenue is increased by increasing fees during peak parking demand periods, and at the same time attract more vehicles and increase overall revenue by reducing fees during off-peak periods. Recalculate the final parking fee based on the actual parking time of the car owner and the adjusted fee standards to ensure reasonable charges and enhance user satisfaction; 2. Increasing parking prices during periods of high demand for parking spaces can curb excessive demand, ensure that parking spaces can be used by users who really need them, and avoid wasting parking resources. Lowering parking prices during periods of low demand for parking spaces can attract more car owners to park during low-demand periods, balance the time distribution of parking demand, and improve the overall utilization rate of parking spaces. Increased revenue during peak periods: By raising parking prices during periods of high demand for parking spaces, parking lots can increase revenue during peak periods and maximize revenue. Lowering parking prices during periods of low demand can attract more car owners to park, increase revenue during low-peak periods, and optimize the overall revenue structure of parking lots. Adjust parking fees based on real-time demand to ensure the rationality and fairness of charges and enhance user satisfaction and trust in parking lot management. Send the final parking fee promptly via mobile devices so that users can know and understand the charging standards in advance; 3. By collecting and analyzing users' expected parking duration information, the management system can dynamically adjust parking space allocation strategies, achieving refined management and improving overall management efficiency. Based on real-time expected parking duration data, the management system can flexibly adjust parking space allocation strategies to ensure the rational allocation and efficient utilization of parking resources. By prioritizing parking spaces to users with high expected parking durations, parking spaces can be effectively used for extended periods of time, reducing frequent parking turnover and vacant time. Allocating parking spaces based on the driver's expected parking duration and the distance to their destination optimizes parking space usage, reduces traffic congestion within the parking lot, and improves parking space utilization efficiency. Using the optimal distance allocation algorithm, parking spaces are allocated to the spaces closest to the driver's destination, reducing the driver's search time and improving parking convenience. Intelligent allocation based on the user's expected parking duration ensures that drivers can quickly find a suitable parking space. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 This is a flowchart of a parking management method in one embodiment of the present application; Figure 2 This is a flowchart of the implementation of the parking management method before step S10 in one embodiment of the present application; Figure 3 This is a flowchart of the implementation of step S101 of the parking management method in one embodiment of the present application; Figure 4 This is a flowchart of the implementation of step S20 of the parking management method in one embodiment of the present application; Figure 5 This is a flowchart of the implementation of step S40 of the parking management method in one embodiment of the present application; Figure 6 This is a flowchart of the implementation of the parking management method after step S40 in one embodiment of the present application; Figure 7 This is a principle block diagram of a parking management method in one embodiment of the present application; Figure 8 It is a schematic diagram of a device in one embodiment of the present application. DETAILED DESCRIPTION

[0025] The present application is further described in detail below with reference to the accompanying drawings.

[0026] In one embodiment, if Figure 1 As shown, the present application discloses a parking management method, which specifically includes the following steps: S10: obtaining parking quantity information in the parking area.

[0027] In this embodiment, the parking quantity information in the parking area refers to the number of vehicles currently parked in the parking area and the occupancy status of each parking space.

[0028] Specifically, by installing geomagnetic sensors on the ground of each parking space. Detect whether the parking space is occupied by a vehicle, and obtain the real-time occupancy status of each parking space through the geomagnetic sensor status (such as "free" or "occupied"). Detect the occupancy status of the parking space in real time, and transmit the parking space occupancy data to the central management system via wireless. Install a high-definition camera at the entrance of the parking lot, equipped with a license plate recognition system to record the entry and exit time and parking location of the vehicle. The central management system integrates the geomagnetic sensor and camera data to calculate the number of parking spaces in the current parking area. For example, the central management system integrates sensor and camera data to calculate the number of parking spaces in the current parking area. For example, the sensor data shows that 50 parking spaces are occupied, the entrance camera records 10 vehicles entering, and the exit camera records 5 vehicles leaving. The total number of parking spaces is 50+10-5=55 vehicles.

[0029] S20: Using the trained ARIMA model, the parking quantity information in the parking area is predicted to obtain the future usage of the parking area.

[0030] In this embodiment, the trained ARIMA model refers to an ARIMA model trained and optimized using historical parking quantity data. The future parking area usage refers to the predicted result of the parking quantity in the future based on the trained ARIMA model.

[0031] Specifically, a trained ARIMA model is used to predict future parking area usage. This model, developed based on historical parking data through data preprocessing, model selection and training, validation, and optimization, accurately predicts future parking demand. Future parking area usage includes predictions for daily or hourly parking demand, peak hour identification, and the number of available parking spaces.

[0032] S30: Dynamically adjust the charging standard of the parking area according to the future usage of the parking area to obtain an adjusted charging standard of the parking area.

[0033] In this embodiment, the parking area charging standard refers to the pricing rules for parking fees charged by the parking lot to car owners. The adjusted parking area charging standard refers to the pricing rules after dynamically adjusting the existing charging standard based on the future usage of the parking area.

[0034] Specifically, these rates are dynamically adjusted based on future parking demand predicted by the trained ARIMA model. For example, rates can be raised during peak hours to accommodate high parking demand, while rates can be lowered during off-peak hours to attract more drivers. Furthermore, rates can be temporarily adjusted based on predicted demand during holidays and special events, as well as differentiated adjustments for different parking types and locations.

[0035] S40: Recalculating the parking fee according to the adjusted parking area charging standard to obtain a final parking fee, and sending the final parking fee to the mobile terminal.

[0036] In this embodiment, the final parking fee refers to the actual fee payable calculated according to the dynamically adjusted parking area charging standard.

[0037] Specifically, the system calculates the initial parking fee by obtaining information about the driver's expected parking duration and the real-time usage of the parking area. Then, based on the ARIMA model's prediction of future parking demand, it dynamically adjusts the parking fee schedule for each parking area. The final parking fee is recalculated based on the adjusted fee schedule and the actual parking duration. Finally, the final parking fee is communicated to the driver via a mobile app, where the driver can view and pay the fee.

[0038] In one embodiment, if Figure 2 As shown, before step S10, that is, before obtaining the vehicle information in the parking area, the process further includes: S101: Acquire historical vehicle information and historical parking space information in a parking area, and train a preset ARIMA model with the historical vehicle information and the historical parking space information in the parking area to obtain the trained ARIMA model.

[0039] In this example, historical vehicle information within a parking area refers to the data on vehicles entering and leaving the parking lot over the past period. Historical parking space information refers to the usage of each parking space in the parking lot over the past period. The pre-set ARIMA model is a time series analysis model that is pre-set before training.

[0040] Specifically, historical time series data is collected from the parking area, including the number of parking lots at each time point. Before applying the ARIMA model, data preprocessing is required to ensure the stationarity of the time series. This is usually achieved using a difference operation. t Defined as: Δy t =y t -y t-1, repeat the difference operation until the series is stationary. Determine the parameters p, d, and q values ​​of the preset ARIMA model, where p is the order of the autoregressive term and q is the order of the moving average term. Autoregressive order (p): determined by analyzing the partial autocorrelation function (PACF). Difference order (d): determined by the unit root test to ensure that the data is stationary. Moving average order (q): determined by analyzing the autocorrelation function (ACF). The historical vehicle information and the historical parking space information in the parking area are usually divided into training sets and test sets in chronological order, such as the first 80% of the historical vehicle information and the historical parking space information are used for training, and the last 20% of the historical vehicle information and the historical parking space information are used for testing. Fit the ARIMA model on the training set, estimate the simulation parameters φi and θj, and minimize the residual error of the model:

[0041] Where yt is the parking space occupancy at time t, c is the constant term, φi is the autoregressive coefficient, θj is the moving average coefficient, ∈t is the white noise error term, p is the order of the autoregressive term, and q is the order of the moving average term. Use the test set to verify the model's prediction performance and evaluate the prediction error: in, is the predicted value of the model at time t.

[0042] Get the trained ARIMA model:

[0043] In one embodiment, if Figure 3 As shown, in step S101, that is, obtaining historical vehicle information and historical parking space information in the parking area, training the preset ARIMA model with the historical vehicle information and the historical parking space information in the parking area to obtain the trained ARIMA model, further comprising: S1011: Use a cross-validation method to verify the stability and predictive ability of the preset ARIMA model.

[0044] In this embodiment, the cross-validation method refers to splitting the time series data into multiple training sets and validation sets, repeatedly training and validating the ARIMA model, and thus evaluating its stability and predictive ability.

[0045] Specifically, the training set includes all data from the start time to the end time of the current window. The validation set includes data for one or more time steps after the end time of the current window. Train the ARIMA model on each training set and make predictions on the corresponding validation set. Calculate the prediction error index. Suppose the time series data y is divided into n rolling windows, and the training set and validation set of each window are as follows: the i-th training set, Ti = {y1, y2, ..., y ti}. The i-th validation set, Vi={y ti+1 ,y ti+2 ,...,y ti+k}. Train the ARIMA model on the training set Ti and obtain the model parameters. Use the trained ARIMA model to predict the validation set Vi and obtain the predicted value Calculate the prediction error on the validation set: When the prediction error reaches a preset error, the cross-validation is completed.

[0046] In one embodiment, if Figure 4 As shown, in step S20, the trained ARIMA model is used to predict the number of parking spaces in the parking area to obtain the future usage of the parking area, including: S21: Utilizing the trained ARIMA model, based on historical data before the current time point, recursively predict the future usage of the parking area.

[0047] Specifically, the trained ARIMA model is used to predict the number of parking spaces at the first future time point based on historical data prior to the current time point. The first predicted value is used as input to predict the number at the next future time point. This process is repeated until all desired future time points have been predicted. The prediction results are used to dynamically adjust parking management strategies and pricing to optimize parking area utilization and service quality.

[0048] In one embodiment, if Figure 5 As shown, in step S40, the parking fee is recalculated according to the adjusted parking area charging standard to obtain a final parking fee, and the final parking fee is sent to the mobile terminal, including: S41: Determine a period of high parking demand and a period of low parking demand based on the future usage of the parking area.

[0049] Specifically, a trained ARIMA model is used to predict parking demand for each future time period. The ARIMA model analyzes historical parking data to generate parking demand forecasts for each future time period. The predicted parking demand data is analyzed to identify periods of high and low parking demand. Threshold determination: Based on the distribution of the predicted data, high and low demand thresholds are set. The upper and lower quartiles are typically used as the dividing lines between high and low demand. Time periods are marked: Based on the predicted parking demand, periods above the high demand threshold are marked as high demand periods, periods below the low demand threshold are marked as low demand periods, and the remaining periods are marked as normal demand periods. Parking fees are dynamically adjusted based on demand levels, and a base fee is determined as the standard for normal demand periods. During high demand periods, the fee is increased, for example, by 50%. During low demand periods, the fee is reduced, for example, by 25%. The corresponding fee is applied based on the marked demand levels.

[0050] S42: Raise the parking price during the period of high demand for parking spaces, and lower the parking price during the period of low demand for parking spaces.

[0051] Specifically, a base parking fee standard is determined as the charging standard during normal demand periods. During high-demand periods, the base fee standard is increased, for example, by 50%. During low-demand periods, the base fee standard is reduced, for example, by 25%. Using this adjusted fee standard, parking prices are dynamically adjusted based on demand levels during each time period.

[0052] S43: Send the final parking fee to the mobile terminal.

[0053] Specifically, by recording the actual parking time of the vehicle, the adjusted final parking fee is calculated, and the fee information is sent to the user's mobile terminal in real time using a message push service or a RESTful API.

[0054] In one embodiment, if Figure 6 As shown, after step S40, the parking management method further includes: S50: Obtain expected parking time information, dynamically adjust parking spaces in the parking area, and obtain adjusted parking spaces.

[0055] In this embodiment, the expected parking duration information refers to the estimated parking duration input by the user through the mobile application before entering the parking lot.

[0056] Specifically, users enter their expected parking time into the mobile app. This information is then transmitted to the backend management system via the network. The backend system uses this information, combined with real-time parking space usage, to dynamically adjust parking allocation strategies. Based on the adjusted parking space allocation, the system updates the available parking space information displayed on the mobile app in real time and provides users with recommended parking locations or suggestions.

[0057] S60: When the expected parking duration information is high, the parking space is allocated to the user with the high expected parking duration through a priority allocation algorithm.

[0058] Specifically, users enter their expected parking duration through a mobile app. Parking duration is set as a priority indicator, meaning users with longer expected parking times are given priority for parking spaces. The system monitors current parking space usage and users' expected parking durations in real time. Users are prioritized based on their expected parking durations, with those with longer expected parking times being prioritized for parking space allocation. Based on the allocation strategy, available parking spaces are displayed, for example, at the parking lot entrance or in the mobile app, indicating which spaces are suitable for users with longer parking needs.

[0059] S70: Calculate the distance from the parking space to the car owner's destination using an optimal distance allocation algorithm, and prioritize allocating parking spaces that are closer.

[0060] Specifically, the user enters or authorizes the acquisition of destination location information in the mobile application. The geographic location of each parking space in the parking lot has been pre-recorded or obtained in real time through on-site sensors. Using Euclidean distance, the actual distance from each parking space to the owner's destination is calculated. The coordinates of the parking space and the destination are obtained. Parking space coordinates: the geographic coordinates of each parking space (e.g., longitude and latitude). Destination coordinates: the geographic coordinates of the destination (e.g., longitude and latitude) entered or authorized by the owner. The distance from each parking space to the destination is calculated using the Euclidean distance formula in two-dimensional space: Where (x1, y1) are the coordinates of the parking space. (x2, y2) are the coordinates of the destination. Parking spaces are prioritized based on the calculated distance from the parking space to the destination, with closer spaces given priority. Based on the ranking results, the system displays available parking spaces at the parking lot entrance or in the mobile app, indicating the closest parking space to the user's destination. If there are multiple parking spaces with similar distances, further optimization is performed based on parking duration, parking space type, and other factors.

[0061] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0062] In one embodiment, a parking management device is provided, which corresponds one-to-one with the parking management method in the above embodiment. Figure 7 As shown, the parking management device includes an information acquisition module, a model output module, a charging standard module, a fee sending module, a parking duration module, a priority allocation algorithm module, and a distance optimal allocation algorithm module. The functional modules are described in detail as follows: An information acquisition module is used to obtain parking quantity information in a parking area; A model output module is used to predict the number of parking spaces in the parking area using the trained ARIMA model to obtain the future usage of the parking area; A charging standard module, configured to dynamically adjust the charging standard of the parking area according to the future usage of the parking area, and obtain an adjusted charging standard of the parking area; The fee sending module is used to recalculate the parking fee according to the adjusted parking area charging standard to obtain the final parking fee, and send the final parking fee to the mobile terminal.

[0063] The parking duration module is used to obtain expected parking duration information, dynamically adjust the parking spaces in the parking area, and obtain the adjusted parking spaces; a priority allocation algorithm module, configured to allocate a parking space to a user with a long expected parking time by using a priority allocation algorithm when the expected parking time information is long; The distance optimal allocation algorithm module is used to calculate the distance from the parking space to the owner's destination through the distance optimal allocation algorithm, and give priority to allocating parking spaces with shorter distances.

[0064] Optionally, the information acquisition module includes: The training submodule is used to obtain historical vehicle information and historical parking space information in the parking area, and train a preset ARIMA model with the historical vehicle information and the historical parking space information in the parking area to obtain the trained ARIMA model.

[0065] Optionally, the training submodule also includes: The cross-validation unit is used to verify the stability and predictive ability of the preset ARIMA model using a cross-validation method.

[0066] Optionally, the model output module includes: The result output submodule is used to use the trained ARIMA model to recursively predict the future usage of the parking area based on historical data before the current time point.

[0067] Optionally, the fee sending module includes: a charging standard adjustment submodule, configured to obtain the periods of high and low parking demand based on the future parking area usage, and dynamically adjust the parking charging standard; A price adjustment submodule, configured to increase parking prices during periods of high parking demand and reduce parking prices during periods of low parking demand; The price sending submodule is used to send the final parking fee to the mobile terminal.

[0068] The specific definition of the parking management device can be found in the definition of the parking management method above and will not be repeated here. Each module in the aforementioned parking management device may be implemented in whole or in part through software, hardware, or a combination thereof. Each module may be embedded in or independent of a processor in a computer device in hardware form, or may be stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0069] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 8 As shown. The computer device includes a processor, memory, a network interface, and a database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used for central database management. The network interface of the computer device is used to communicate with an external terminal via a network connection. When executed by the processor, the computer program implements a parking management method.

[0070] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps are performed: Get the number of parking spaces in the parking area; The trained ARIMA model is used to predict the number of parking spaces in the parking area and to obtain the future usage of the parking area. Dynamically adjust the parking area charging standards based on future parking area usage to obtain adjusted parking area charging standards; The parking fee is recalculated according to the adjusted parking area charging standard to obtain the final parking fee, and the final parking fee is sent to the mobile terminal.

[0071] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: Get the number of parking spaces in the parking area; The trained ARIMA model is used to predict the number of parking spaces in the parking area to obtain the future usage of the parking area. Dynamically adjusting the charging standard of the parking area according to the future usage of the parking area to obtain an adjusted charging standard of the parking area; The parking fee is recalculated according to the adjusted parking area charging standard to obtain a final parking fee, and the final parking fee is sent to the mobile terminal.

[0072] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0073] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0074] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A parking management method, characterized in that: The parking management method comprises: Get the parking quantity information in the parking area; The trained ARIMA model is used to predict the parking quantity information in the parking area to obtain the future usage of the parking area; Dynamically adjust the charging standard of the parking area according to the future usage of the parking area to obtain an adjusted charging standard of the parking area; The parking fee is recalculated according to the adjusted parking area charging standard to obtain a final parking fee, and the final parking fee is sent to the mobile terminal.

2. The parking management method according to claim 1, characterized in that: Before obtaining the vehicle information in the parking area, the method further includes: The historical vehicle information and the historical parking space information in the parking area are obtained, and a preset ARIMA model is trained using the historical vehicle information and the historical parking space information in the parking area to obtain the trained ARIMA model.

3. The parking management method according to claim 2, characterized in that: The acquiring of historical vehicle information and historical parking space information in the parking area, training a preset ARIMA model with the historical vehicle information and the historical parking space information in the parking area to obtain the trained ARIMA model, further comprising: The cross-validation method was used to verify the stability and predictive ability of the preset ARIMA model.

4. The parking management method according to claim 1, characterized in that: The trained ARIMA model is used to predict the parking quantity information in the parking area to obtain the future usage of the parking area, including: The trained ARIMA model is used to recursively predict the usage of the future parking area based on historical data before the current time point.

5. The parking management method according to claim 1, characterized in that: The recalculating the parking fee according to the adjusted parking area charging standard to obtain the final parking fee, and sending the final parking fee to the mobile terminal includes: Determine a time period with high parking demand and a time period with low parking demand based on the usage of the future parking area; Increase the parking price during the period of high demand for parking spaces, and reduce the parking price during the period of low demand for parking spaces; The final parking fee is sent to the mobile terminal.

6. The parking management method according to claim 1, characterized in that: The parking management method further includes: Obtain expected parking time information, dynamically adjust parking spaces in the parking area, and obtain adjusted parking spaces; By using a priority allocation algorithm, when the expected parking time information is high, the parking space is allocated to the user with a high expected parking time; The distance from the parking space to the owner's destination is calculated through the distance optimal allocation algorithm, and parking spaces with short distances are allocated preferentially.

7. A parking management device, characterized in that: The parking management device comprises: An information acquisition module is used to obtain parking quantity information in a parking area; A model output module is used to predict the parking quantity information in the parking area through the trained ARIMA model to obtain the future usage of the parking area; A charging standard module, used to dynamically adjust the charging standard of the parking area according to the future usage of the parking area, and obtain the adjusted charging standard of the parking area; The fee sending module is used to recalculate the parking fee according to the adjusted parking area charging standard to obtain the final parking fee, and send the final parking fee to the mobile terminal.

8. The parking management device according to claim 7, characterized in that: The fee sending module also includes: The parking duration module is used to obtain the expected parking duration information, dynamically adjust the parking spaces in the parking area, and obtain the adjusted parking spaces; A priority allocation algorithm module, configured to allocate a parking space to a user with a high expected parking time by using a priority allocation algorithm when the expected parking time information is high; The distance optimal allocation algorithm module is used to calculate the distance from the parking space to the owner's destination through the distance optimal allocation algorithm, and give priority to allocating parking spaces with short distances.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the parking management method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the parking management method according to any one of claims 1 to 6 are implemented.

Images