Digital dynamic sensing method for parking space of internet of vehicles integration

Abstract

The application relates to the field of Internet of Vehicles sensing technology and discloses an Internet of Vehicles integrated parking space digital dynamic sensing method. The method comprises the following steps: constructing a parking space state model based on a target area of an Internet of Vehicles system, and associating a parking space sensing process with the target area; constructing a sensing strategy model for controlling data collection and processing output of the parking space state model; coupling simulation is performed on the two models according to selected parking scene points, and simulation results are obtained; whether there is a sensing error in the parking space sensing process is judged according to the simulation results, and if there is, the control parameters of the sensing strategy model are adjusted; the parameters are coupled and simulated again based on the adjusted parameters, and target simulation results with sensing errors within an allowable range are obtained. The method takes advantage of multi-source information interaction of the Internet of Vehicles, optimizes a sensing strategy, improves parking space sensing accuracy and applicability, reduces hardware cost, adapts to different parking scenes, and helps efficient use of parking space resources.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of Internet of Vehicles perception technology, in particular to a parking space digital dynamic perception method based on Internet of Vehicles fusion. BACKGROUND

[0002] With the acceleration of urbanization and the continuous growth of motor vehicle ownership, parking difficulty has become an important factor affecting the efficiency of urban traffic operation and the travel experience of residents. Traditional parking space management methods rely on manual inspection or fixed sensor information collection, which has obvious limitations. Manual inspection not only consumes a lot of labor costs, but also has a lag in information updating, making it difficult to reflect the dynamic changes of parking spaces in real time. When vehicles are densely entering and exiting the parking lot, information misjudgment is likely to occur, which makes it difficult for drivers to obtain accurate parking space information in a timely manner, increasing the invalid driving mileage.

[0003] Fixed sensors such as geomagnetic and ultrasonic waves can achieve parking space state monitoring to some extent, but have the problems of high installation and maintenance costs and limited coverage. Such sensors usually need to be individually deployed under or around each parking space. For large parking lots or open parking areas, the construction difficulty is great, and the subsequent equipment troubleshooting and replacement are also relatively cumbersome. At the same time, the sensing range of fixed sensors is limited by physical location, making it difficult to deal with complex scenarios such as temporary parking of vehicles and blurred parking lines, and prone to missed or false detection.

[0004] Under the background of the gradual development of Internet of Vehicles technology, information exchange between vehicles and infrastructure and between vehicles becomes possible, but the existing Internet of Vehicles applications have low fusion degree in parking space perception. Most systems can only achieve simple parking space information transmission, and lack dynamic modeling of parking space state and optimization adjustment of perception strategy. When the parking scenario changes, such as increased vehicle flow during peak hours and changed accessibility of parking spaces due to temporary traffic control, the existing system cannot adjust the perception parameters in a timely manner, resulting in a large deviation between the perception results and the actual parking space state, affecting the efficient use of parking space resources. In addition, the perception needs in different parking scenarios are different, such as short-term parking needs in shopping mall parking lots and long-term parking needs in residential areas. The existing methods do not design personalized perception for different scenarios, further reducing the accuracy and applicability of parking space perception. SUMMARY

[0005] The present application aims to provide a parking space digital dynamic perception method based on Internet of Vehicles fusion to solve the problems raised in the background.

[0006] To achieve the above-mentioned purpose, the present application provides a parking space digital dynamic perception method based on Internet of Vehicles fusion, which comprises:

[0007] constructing a parking space state model of a vehicle networking system based on a target area of the vehicle networking system, the target area being an area related to a parking space sensing process;

[0008] constructing a sensing strategy model for controlling data collection and processing output in the parking space state model;

[0009] coupling simulation of the sensing strategy model and the parking space state model according to selected parking scene points to obtain corresponding simulation results;

[0010] determining whether there is a sensing error in the parking space sensing process according to the simulation results;

[0011] adjusting control parameters in the sensing strategy model in the case of a sensing error;

[0012] re-coupling simulation of the sensing strategy model and the parking space state model based on the adjusted control parameters until a target simulation result is obtained, the target simulation result being a result indicating that the parking space sensing error is within an allowable range.

[0013] Preferably, in the case where the target area includes a parking space grid, a vehicle sensor, and a vehicle communication module, the constructing of the parking space state model of the vehicle networking system based on the target area of the vehicle networking system comprises:

[0014] constructing a parking space grid model, a vehicle sensor model, and a vehicle communication model based on the target area of the vehicle networking system;

[0015] initializing input parameters of the vehicle sensor model using state data of the parking space grid model;

[0016] configuring a transmission strategy of the vehicle communication model using output data of the vehicle sensor model to construct the parking space state model of the vehicle networking system.

[0017] Preferably, the constructing of the sensing strategy model comprises:

[0018] discretizing the sensing strategy into equivalent control algorithm models according to data collection frequency and processing delay requirements;

[0019] integrating the control algorithm models through a parameter optimization element and setting an update period to construct the sensing strategy model.

[0020] Preferably, the coupling simulation of the sensing strategy model and the parking space state model according to selected parking scene points to obtain corresponding simulation results comprises:

[0021] According to the selected parking scene point, a control signal output by a perception strategy model is used to adjust a data acquisition rate of the parking space state model to obtain a real-time state of a target area;

[0022] In a case where the parking space state model reaches a stable state, a processing coefficient output by the perception strategy model is used to control data output accuracy of the parking space state model to realize data interaction between the parking space state model and the perception strategy model and obtain a corresponding simulation result.

[0023] Preferably, the method further comprises:

[0024] In a case where the simulation result meets a first preset condition or a second preset condition, it is determined that there is a perception error in the parking space perception process;

[0025] The first preset condition is that, in the coupled simulation parking perception process, a deviation between state data of a parking space grid model in the parking space state model and actual measurement data is greater than or equal to a preset deviation threshold;

[0026] The second preset condition is that, in the coupled simulation parking perception process, noise interference occurs in a vehicle sensor model output and a noise intensity is greater than a set threshold.

[0027] Preferably, the method further comprises:

[0028] At each time point, a uniformity correction is performed on the parking space state based on an initial occupancy matrix corresponding to each time point to obtain a corrected occupancy matrix of the parking space at each time point;

[0029] A target occupancy rate required to be maintained by the parking space is determined, the parking space state perception is controlled based on a corrected occupancy matrix corresponding to the target occupancy rate, and an actual occupancy rate of the parking space is measured by a sensor;

[0030] In a case where a difference between the target occupancy rate and the actual occupancy rate is greater than or equal to a preset deviation threshold, a deviation occupancy matrix is determined according to the corrected occupancy matrix corresponding to the target occupancy rate and an occupancy matrix corresponding to the actual occupancy rate;

[0031] The corrected occupancy matrix corresponding to the target occupancy rate is adjusted based on the deviation occupancy matrix to obtain an adjusted occupancy matrix corresponding to the target occupancy rate;

[0032] The adjusted occupancy matrix corresponding to the target occupancy rate is taken as a new corrected occupancy matrix corresponding to the target occupancy rate, and the step of controlling parking space state perception based on the corrected occupancy matrix corresponding to the target occupancy rate is returned until the difference between the target occupancy rate and the actual occupancy rate is less than the preset deviation threshold.

[0033] Preferably, the uniformity correction of the parking space state based on the initial occupancy matrix corresponding to each of the time points obtains the corrected occupancy matrix of the parking space at each of the time points, comprising:

[0034] For any of the time points, based on the initial occupancy matrix corresponding to the time point, the parking space state is controlled, and real-time data of the parking space is obtained by using a vehicle networking device, and an actual occupancy matrix is extracted from the real-time data;

[0035] According to the actual occupancy matrix, a standard deviation of occupancy uniformity is determined;

[0036] In the case where the standard deviation of occupancy uniformity is greater than or equal to a preset standard deviation threshold, an actual state matrix corresponding to the actual occupancy matrix is determined based on a pre-constructed occupancy relationship model;

[0037] An iterative state matrix corresponding to the actual state matrix is obtained by using a state matrix iterative model to iterate the actual state matrix;

[0038] The iterative state matrix is taken as the initial occupancy matrix, and the step of controlling the parking space state perception based on the initial occupancy matrix corresponding to each of the time points is returned until the standard deviation of occupancy uniformity is less than the preset standard deviation threshold;

[0039] The iterative state matrix is taken as the corrected occupancy matrix.

[0040] Preferably, the method further comprises:

[0041] Based on vehicle movement trajectory data, analyze the vehicle movement mode in the region, and generate a movement trajectory prediction model;

[0042] Based on multi-source data, predict changes in regional parking demand, and generate a parking demand prediction result;

[0043] Based on a time-varying network model, extract parking demand features, and identify the spatio-temporal variation law of parking demand;

[0044] Based on a scoring system, calculate adjustment priority and resource allocation ratio, and realize forward-looking parking resource layout;

[0045] Adaptive execution of perception strategy adjustment ensures that the perception process is pre-adapted to changes in parking demand.

[0046] Preferably, the vehicle movement trajectory data-based analysis of the vehicle movement pattern in the region generates a movement trajectory prediction model, comprising:

[0047] Collecting anonymized vehicle position data at multiple time points in the region, performing data cleaning, outlier removal and spatio-temporal feature extraction;

[0048] Dividing the region into grids, counting the vehicle density of each grid at different times, and constructing a regional movement heat map;

[0049] Applying a spatio-temporal trajectory clustering algorithm to analyze the vehicle movement trajectory, identifying typical movement patterns and key paths;

[0050] Based on the trajectory clustering results, a path flow prediction function is established to predict the flow of each key path at a specific time point in combination with the time factor.

[0051] Compared with the prior art, the present application has the following advantages:

[0052] By constructing the parking space state model of the Internet of Vehicles system, the multi-source information interaction advantage brought by the Internet of Vehicles technology can be fully utilized, and information related to parking space perception from multiple aspects such as vehicles and infrastructure is included in the model construction process, breaking the limitation of information isolation in traditional perception methods, making the parking space state model more in line with the dynamic changes of actual parking scenarios. Compared with the traditional perception method relying on fixed sensors, this model does not need to deploy a large number of hardware devices in each parking space, reducing the cost investment of hardware installation and later maintenance, and at the same time, through the extensive coverage characteristics of the Internet of Vehicles system, the range of parking space perception is expanded, which can realize comprehensive perception of different scale parking scenarios such as large parking lots and open parking areas, avoiding the problem of limited coverage range of fixed sensors.

[0053] The construction of the perception strategy model provides a flexible control mechanism for the data collection and processing output of the parking space state model. Traditional perception methods often use fixed collection frequency and processing methods, which cannot be adjusted according to the changes of parking scenarios, while the perception strategy model in this method can dynamically adjust parameters such as data collection frequency and data processing priority according to different parking scenario requirements, making data collection more targeted and data processing more efficient. For example, during the parking peak period, when vehicles enter and exit frequently and parking space status changes quickly, the perception strategy model can increase the data collection frequency to ensure timely capture of every change in parking space status; during the parking valley period, the collection frequency is appropriately reduced to reduce unnecessary data redundancy and reduce system running load.

[0054] By selecting parking scene points to couple the perception strategy model and the parking space state model, the perception effect can be verified in advance before actual application, and possible problems in the perception process can be found in time. Traditional methods often need to put the perception system into actual use to find problems, which requires a lot of time and resources to adjust. However, the present method can simulate the perception process in a virtual environment under different parking scenarios, quickly obtain simulation results and determine whether there is a perception error, greatly shortening the problem discovery and adjustment cycle and reducing the risk in actual application.

[0055] When there is a perception error, the control parameters in the perception strategy model are adjusted and coupled simulation is performed again until the target simulation result is obtained, forming a closed loop of continuous optimization. Traditional perception methods often have difficulty in accurately locating the error source after a perception error occurs, and the adjustment process is largely blind. However, the present method can adjust the control parameters of the perception strategy model to specifically address perception errors caused by different reasons, such as missed detection due to low data collection frequency, which can be improved by increasing the collection frequency parameter; processing delay caused by unreasonable processing algorithm priority setting, which can be optimized by adjusting the processing priority parameter. This precise adjustment method can effectively reduce the deviation between the perception result and the actual parking space state, ensure that the perception error is controlled within the allowed range, and improve the accuracy of parking space perception.

[0056] This method can achieve individualized perception adaptation for different parking scenarios by coupling simulation and parameter adjustment for different parking scene points. Whether it is the short-term high-frequency parking demand of a shopping mall parking lot or the long-term low-frequency parking demand of a residential area, simulation can be performed by selecting corresponding scene points to adjust the perception strategy parameters that meet the needs of the scene, so that the perception method can maintain high perception performance in different scenarios, avoiding the problem of large differences in perception effect in different scenarios in traditional methods, further improving the applicability of parking space perception, helping to improve the utilization efficiency of parking space resources, reducing invalid driving caused by inaccurate parking space information obtained by drivers, relieving traffic congestion, and improving the overall travel experience. BRIEF DESCRIPTION OF DRAWINGS

[0057] Figure 1 A working principle diagram of the Internet of Vehicles integrated parking space digital dynamic perception method described in the present application;

[0058] Figure 2 A flowchart for constructing a parking space state model;

[0059] Figure 3 A flowchart for coupling simulation and data interaction. DETAILED DESCRIPTION

[0060] With reference to the drawings of the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of the present application.

[0061] With reference to the drawings of the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of the present application. Figure 1 The present application provides a parking space digital dynamic sensing method based on Internet of Vehicles, which comprises: constructing a parking space state model in a target area of an Internet of Vehicles system, the target area being defined as a physical or logical area related to a parking space sensing process, including parking space grid, vehicle sensor and vehicle communication module components. The parking space state model simulates the occupancy state and dynamic change of the parking space through mathematical modeling, and the sensing strategy model is responsible for the logic of controlling data collection and processing output, which is realized by parameterized design to achieve adaptive adjustment. According to the selected parking scene point, the sensing strategy model and the parking space state model are coupled and simulated, the coupling process involves data interaction and state synchronization, and the simulation result is used to evaluate the sensing error. If there is a sensing error, the control parameters in the sensing strategy model, such as data collection frequency or processing delay, are adjusted, and the coupling simulation is performed again, and the iteration process continues until the sensing error is reduced to the allowable range, so as to obtain the target simulation result. The method realizes the accuracy and real-time performance of parking space sensing through model coupling and parameter optimization.

[0062] With reference to the drawings of the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of the present application. Figure 2 The construction of the parking space state model is based on the target area of the Internet of Vehicles system, which includes parking space grid, vehicle sensor and vehicle communication module components; first, the parking space grid model is established, which uses discrete grid units to represent the spatial distribution of parking spaces, each grid unit corresponds to a parking space state, and the state data includes occupancy state (such as idle or occupied), time stamp and location identifier, which reflect the physical state of the parking space in real time through digital mapping. The vehicle sensor model is then constructed, which simulates the sensor data collection behavior, the input parameters are initialized by the state data of the parking space grid model, for example, the sensor detection threshold and sampling interval are dynamically set according to the grid state to ensure the accuracy and adaptability of data collection, and the sensor model output includes reading data and time series information for subsequent processing. The vehicle communication model is responsible for data transmission and communication protocol processing, and its transmission strategy is configured by the output data of the vehicle sensor model, the transmission strategy involves data packet size, sending frequency and error correction mechanism to ensure reliable data transmission in the Internet of Vehicles environment; by integrating the parking space grid model, the vehicle sensor model and the vehicle communication model, the parking space state model forms a complete system representation, which can simulate the dynamic change and interaction of the parking space.

[0063] In constructing the perception strategy model, the process begins with discretizing the perception strategy into equivalent control algorithm models based on data acquisition frequency and processing delay requirements; the data acquisition frequency defines the rate of sensor data acquisition, while the processing delay requirement specifies the timeliness constraints of data processing, the control algorithm models are implemented using state machines or rule engines, for example, based on IF-THEN logic conditions or PID control principles to adjust perception behavior, ensuring the flexibility and responsiveness of the strategy. The core function of the control algorithm model is to convert continuous perception strategies into discrete executable instructions that can dynamically adjust data acquisition and processing flows; parameter optimization elements are then introduced, which integrate the control algorithm model, including optimization functions and constraint processing modules, optimization functions may be based on gradient descent or heuristic algorithms to search for the optimal parameter set, and constraint processing modules ensure that parameter adjustments comply with system limitations such as resource availability or real-time requirements. Setting the update period is a key step in the construction of the perception strategy model, the update period is based on simulation time or event-triggered mechanisms to adjust parameters periodically, such as triggering re-optimization every certain time interval or when system state changes exceed a threshold, ensuring the continuous adaptability and efficiency of the perception strategy; the entire perception strategy model can adaptively adjust control parameters through a loop optimization process to cope with dynamic changes and uncertainties in parking space perception.

[0064] In the construction process of the parking space state model and the perception strategy model, the detailed implementation involves the coordination of multiple sub-steps; the initialization of the parking space grid model includes defining the grid resolution, cell attributes, and state update logic, the grid resolution is determined according to the size of the target area and the density of parking spaces, the cell attributes include location coordinates, state identifiers, and historical data, and the state update logic keeps the model synchronized with the real environment through event-driven or timed polling. The input parameter initialization of the vehicle sensor model depends on the state data of the parking space grid model, for example, when the grid cell state changes, the sensor model's detection threshold will automatically adjust to prioritize processing high-priority areas, and the sampling interval will dynamically shorten or lengthen according to the occupancy rate to balance data accuracy and resource consumption; the sensor model output data includes raw readings, filtered data, and timestamps, which are used to configure the transmission strategy of the vehicle communication model, for example, when the sensor output shows high data volume, the transmission strategy will increase the data packet size or compression ratio to reduce network load, and the error correction mechanism will choose retransmission or forward error correction methods according to data importance. The transmission strategy configuration of the vehicle communication model also considers network conditions such as bandwidth limitations or delays, and adjusts the sending frequency and protocol parameters through adaptive algorithms to ensure efficient data transmission in the vehicle networking environment; the discretization process of the perception strategy model involves decomposing high-level strategies into low-level operation instructions, the specific implementation of the control algorithm model may use finite state machines to manage state transitions, or rule engines to execute conditional actions, so that the perception strategy can be accurately executed.

[0065] The integration of parameter optimization elements is achieved through an algorithmic module that traverses the parameter space to find the optimal settings, for example, adjusting the data acquisition frequency and processing delay parameters using an iterative method, while the constraint processing module imposes boundary conditions such as minimum sampling interval or maximum allowed delay to prevent unrealistic parameter values; the setting of the update period is based on system monitoring feedback, with the period length dynamically adjusted according to the rate of environmental change, for example, shortening the update period during peak hours to quickly respond to changes, and lengthening the period during low activity to save resources. The entire implementation process emphasizes the interactivity and real-time nature of the model, with the parking space status model providing basic data and the perception strategy model imposing control logic, both tightly coupled through data flow and signal exchange; this design ensures the accuracy and efficiency of parking space perception, laying the foundation for subsequent simulation and error adjustment. Fixed values or assumed effects are avoided in implementation, and instead focus is placed on method flow and component interaction.

[0066] Referring to Figure 3 , the parking scenario points represent typical parking situations in the real world, such as dense parking during peak hours in commercial areas or scattered parking at night in residential areas; selection criteria include historical parking data, traffic flow patterns, or pre-set experimental conditions, aiming to cover a variety of operating environments to verify the robustness of the method. According to the selected parking scenario points, the perception strategy model and the parking space status model start coupled simulation, and the simulation engine coordinates the execution timing and data exchange of the two models; the perception strategy model outputs control signals, which are digital instructions or parameter adjustment commands, directly adjusting the data acquisition rate of the parking space status model, which affects the activation frequency and sampling period of the embedded vehicle sensor model, thereby achieving dynamic acquisition of the real-time status of the target area. The adjustment mechanism is based on a feedback loop, for example, when the perception strategy detects accelerated state changes, the control signal increases the sampling rate to capture more detailed data, and vice versa to save resources; the real-time status of the target area includes the parking space occupancy bitmap, sensor reading time series, and network communication status, which are continuously recorded for subsequent analysis.

[0067] During the running of the parking space state model, a key judgment point is when it reaches a steady state, which is defined as the fluctuation amplitude of the model output variables persistently being below a preset threshold and remaining for a certain duration, which indicates that the system has transitioned from the initial transient to predictable behavior; once the steady state is reached, the perception strategy model further outputs processing coefficients, which are numerical parameters or algorithm selection identifiers, for controlling the data output accuracy of the parking space state model. Data output accuracy adjustment is achieved by modifying the configuration of the data processing module, such as increasing the filter order to improve noise suppression or using data compression algorithms to reduce redundancy, thereby balancing accuracy and processing load; the data interaction between the parking space state model and the perception strategy model relies on shared memory interfaces or message passing mechanisms, and the interactive data includes state queries, parameter updates, and event notifications, ensuring that the two models evolve synchronously on the simulation timeline. The execution of coupled simulation produces corresponding simulation results, which are output in the form of structured log files or database records, containing timestamps, model state snapshots, performance indicators, and raw sensor data; simulation results are used to comprehensively evaluate the dynamic behavior of the perception process.

[0068] According to the simulation results, the process of determining whether there is a perception error in the parking space perception process is based on the logical evaluation of preset conditions; the first preset condition checks the deviation between the state data of the parking space grid model in the parking space state model and the actual measurement data, which comes from a calibration data set of real sensor deployment or a high-precision reference system, and the deviation is calculated using the Euclidean distance or absolute error sum metric. The preset deviation threshold is set according to the fault tolerance requirements of the application scenario, for example, the threshold is lower in precise navigation scenarios. If the deviation exceeds or equals the threshold, the condition triggers, indicating that there is a perception error; the second preset condition monitors the noise interference in the vehicle sensor model output, which is identified and quantified through signal processing algorithms such as Fourier analysis or statistical variance, and the noise intensity is represented as a signal-to-noise ratio or amplitude value, and the threshold is set based on the sensor specifications and environmental noise baseline. When the noise intensity persistently exceeds the threshold, the condition triggers, also indicating a perception error. The determination logic is integrated into the simulation post-processing module, which automatically scans the result data and marks abnormal events; if either condition is met, the system confirms that there is a perception error and triggers the subsequent parameter adjustment process, otherwise it continues to simulate or outputs the final results. The entire implementation process emphasizes objective measurement of conditions and automated decision-making, avoiding subjective judgment, thereby ensuring the reliability and consistency of error detection.

[0069] The technical details of the coupling simulation involve the fine design of multiple sub-processes; the selection of parking scene points uses clustering algorithms or random sampling to generate from a scene library, ensuring diversity in spatial and temporal dimensions, such as including different geographical locations, weather conditions, or event-driven scenarios like sports events. The simulation engine manages the time advancement and event scheduling of the model, using discrete event simulation or time-stepping mechanisms, coordinating the execution of the perception strategy model and the parking space state model; the specific implementation of control signal regulation data collection rate includes modifying the timer interrupt frequency of the sensor model or adjusting the size of the data buffer, real-time state acquisition is achieved by periodically querying model state variables and recording to a log. The detection of steady state is achieved by monitoring the sliding window variance of key output variables such as parking space occupancy, when the variance is below a threshold and lasts for several simulation time units, it is marked as a steady state; when processing coefficient control data output precision, different algorithm instances can be selected, such as switching between Kalman filter and moving average filter, or adjusting the data quantization bit depth. The data interaction mechanism ensures the consistency between models, such as using atomic operations or transaction locks to prevent data races; the recording of simulation results uses standardized formats for easy parsing, including CSV files or SQL databases, containing fields such as timestamp, model ID, parameter value, and error indicators.

[0070] The implementation of the perception error judgment condition focuses on configurability and extensibility; the deviation calculation in the first preset condition supports multiple measurement methods, and the preset deviation threshold is stored in a configuration file to allow dynamic adjustment; the access to actual measurement data is handled through a data adapter interface to handle different formats of input sources. The noise interference detection in the second preset condition integrates signal processing library functions, and the threshold can be calibrated according to the sensor type, for example, ultrasonic sensors and optical sensors have different noise characteristics; the judgment module automatically performs scanning and generates a report listing the time points and detailed context of the triggering conditions, providing a basis for subsequent debugging. The entire process is orchestrated through scripts or workflow engines to achieve end-to-end automated simulation and error analysis, ensuring efficient execution and repeatability of the method.

[0071] An optimization procedure is initiated upon identifying a perception error in the parking space sensing process; the control parameters in the perception strategy model are optimized using iterative search algorithms, such as gradient descent or Bayesian optimization methods, which systematically adjust parameters like data acquisition frequency, filtering coefficients, or processing delays to minimize the perception error metric. The initial values of the control parameters are extracted from the current perception strategy model, and the optimization objective function is defined as the weighted sum of error measures (such as bias or noise intensity), with constraints including system resource limitations and real-time requirements; the optimization process is performed in a simulation environment by evaluating the performance of multiple parameter combinations to select the optimal settings. Based on the optimized control parameters, the perception strategy model and the parking space state model are recoupled and simulated again, using the updated parameter configurations in the simulation process, which is consistent with the initial run but uses new parameters, and the iteration is performed until the target simulation result is obtained, which requires the parking space perception error to be reduced to the allowable range, which is predefined by the accuracy requirements of the application scenario.

[0072] At each time point, a uniformity correction is performed based on the initial occupancy matrix corresponding to the time point, which is a two-dimensional array representing the binary occupancy status of parking spaces (1 for occupied, 0 for free); the uniformity correction aims to balance the occupancy distribution of the parking area by adjusting the matrix values through mathematical transformation. For each time point, the initial occupancy matrix at that time point is used to control the parking space state perception, and the perception process activates the connected vehicle sensor network to collect real-time data, including vehicle detection signals and location information; the actual occupancy matrix is extracted from the real-time data, and the extraction algorithm involves data analysis and state mapping, such as converting sensor readings into matrix element values. According to the actual occupancy matrix, the occupancy uniformity standard deviation is calculated, which measures the dispersion of the parking space occupancy distribution, and the calculation formula is:

[0073]

[0074] where: denotes the occupancy uniformity standard deviation, is the total number of parking spaces, is the occupancy status of the th parking space (0 or 1), is the average occupancy rate. If the occupancy uniformity standard deviation is greater than or equal to a preset standard deviation threshold, the preset threshold is set based on the area capacity and ideal distribution, then determine the actual state matrix corresponding to the actual occupancy matrix based on the pre-constructed occupancy relationship model, the occupancy relationship model uses regression or neural network to map the occupancy matrix to the state space. The actual state matrix captures the deep features of parking such as clustering trend or abnormal pattern; iterate the actual state matrix using the state matrix iterative model, the iterative model applies numerical methods such as Jacobi iteration or conjugate gradient method, gradually adjusts the state value until convergence, and obtains the post-iteration state matrix. Take the post-iteration state matrix as the new initial occupancy matrix, and return to the step of controlling the parking space state perception, and the cycle continues until the occupancy uniformity standard deviation is less than the preset standard deviation threshold, and finally the post-iteration state matrix is output as the corrected occupancy matrix.

[0075] Determine the target occupancy rate required to maintain the parking space, the target occupancy rate is derived from urban planning or real-time demand prediction, expressed as a percentage value; based on the corrected occupancy matrix corresponding to the target occupancy rate, control the parking space state perception, the perception system configures the sensor network to operate according to the specified parameters, and measures the actual occupancy rate of the parking space through the sensor, the actual occupancy rate is calculated from real-time data. In the case where the difference between the target occupancy rate and the actual occupancy rate is greater than or equal to a preset deviation threshold, the preset deviation threshold is set according to the operation accuracy, calculate the difference of each parking space according to the corrected occupancy matrix corresponding to the target occupancy rate and the occupancy matrix corresponding to the actual occupancy rate, and construct the occupancy deviation matrix, the occupancy deviation matrix is a real matrix, the element value represents the deviation size of the corresponding parking space. Based on the occupancy deviation matrix, adjust the corrected occupancy matrix corresponding to the target occupancy rate, adjust using optimization algorithms such as least squares fitting or heuristic rules, modify the matrix elements to reduce the deviation, and obtain the adjusted occupancy matrix corresponding to the target occupancy rate; take this adjusted occupancy matrix as the corrected occupancy matrix corresponding to the new target occupancy rate, and return to the step of controlling the parking space state perception, and execute the cycle until the difference between the target occupancy rate and the actual occupancy rate is less than the preset deviation threshold, thereby realizing dynamic calibration and error compensation.

[0076] The entire implementation process emphasizes automation and iterative optimization, parameter optimization adopts closed loop control, uniformity correction is based on statistical evaluation, and occupancy rate adjustment is realized through matrix operation; these steps ensure that the parking space perception system can adapt to environmental changes and maintain high precision. In the implementation, assumptions about performance data are avoided, and instead focus is placed on method flow and algorithm interaction, meeting the requirements of detail and operability of the patent application.

[0077] The initial occupancy matrix corrects the uniformity of the parking space state, which is illustrated by an example of a hypothetical parking area; consider a small parking lot with 9 parking spaces (numbered P1 to P9), arranged in a 3x3 grid, at each time point, the occupancy state of the parking spaces is represented by an initial occupancy matrix, which is a two-dimensional array, with element values of 1 indicating occupancy and 0 indicating vacancy. For a certain time point, the initial occupancy matrix may exhibit an uneven distribution, for example, the central area is densely occupied while the edge area is vacant, such unevenness will affect the effective use of parking resources; based on the initial occupancy matrix corresponding to this time point, the control system starts the parking space state perception, through the deployment of Internet of Vehicles devices (such as geomagnetic sensors or cameras) in the parking lot to obtain real-time data. Real-time data includes vehicle presence signals detected by sensors, timestamps and location coordinates, from these data, the actual occupancy matrix is extracted, the extraction process involves data cleaning and state mapping, such as converting sensor signals into matrix element values, forming a matrix reflecting the current real occupancy state.

[0078] According to the actual occupancy matrix, the occupancy uniformity standard deviation is calculated, which quantifies the dispersion degree of the parking space occupancy distribution; assume that the actual occupancy matrix is as shown in the following table, refer to Table 1, which shows the occupancy of 9 parking spaces.

[0079] Table 1: Actual occupancy matrix of parking spaces

[0080]

[0081] Based on the data in the above table, the occupancy state values are 0 or 1, the average occupancy rate μ is 5 / 9 ≈ 0.555, and the occupancy uniformity standard deviation σ is calculated as the square root of the average of the square sum of the deviation of each state value from the mean; if the calculated σ is greater than or equal to the preset standard deviation threshold (assuming the threshold is 0.2), uniformity correction is needed. The preset standard deviation threshold is set according to the design capacity and ideal distribution of the parking lot, which is used to judge whether the distribution is too concentrated or dispersed; based on the pre-constructed occupancy relationship model, the actual state matrix corresponding to the actual occupancy matrix is determined, the occupancy relationship model may be trained by machine learning method, which maps the occupancy matrix to a state space containing hidden features (such as vehicle flow pattern or regional attraction). The actual state matrix captures the deep characteristics of the parking spaces, for example, some parking spaces are vacant but have high demand potential; the actual state matrix is iterated using a state matrix iteration model, the iteration model uses numerical optimization techniques (such as relaxation iteration method) to gradually adjust the state values to promote uniform distribution, and the iteration process continues until the state matrix converges.

[0082] The iteration state matrix is taken as the new initial occupancy matrix, and the step of parking space state perception control is returned, the system reacquires real-time data and calculates a new occupancy uniformity standard deviation; the loop continues until σ is less than the preset standard deviation threshold, indicating that the occupancy distribution has reached a sufficiently uniform level. Finally, the iteration state matrix is output as the corrected occupancy matrix for subsequent parking management and guidance; throughout the process, the Internet of Vehicles device continuously provides real-time data to ensure that the correction is based on the latest information, and the iterative optimization automatically handles the uneven distribution. This implementation shows the complete process of uniformity correction through a specific example, highlighting the characteristics of data-driven and adaptive adjustment, avoiding subjective intervention and relying on mathematical calculations and model reasoning.

[0083] The vehicle movement trajectory data and analysis implement a method for forward-looking parking resource layout, which is illustrated by taking a medium-sized urban business district as an example; the business district covers an area of about 2 square kilometers, including multiple shopping centers, office buildings and entertainment facilities, with a large daily vehicle flow and obvious tidal characteristics. Anonymous vehicle position data at multiple time points in the region is collected, including vehicle-mounted GPS devices, mobile applications and roadside units, with a collection time span of 30 consecutive days, covering different time periods such as weekdays, weekends and holidays; anonymous processing removes personal identifiers and encrypts location information to ensure privacy compliance. Data cleaning, outlier removal and spatiotemporal feature extraction are performed, data cleaning handles missing values and duplicate records, outlier removal filters out trajectory points with sudden speed changes or location jumps, and spatiotemporal feature extraction involves calculating vehicle speed, acceleration, travel direction and dwell time, etc.

[0084] The region is divided into 500m x 500m grids, and the vehicle density of each grid at different times is counted, with hourly granularity, recording the number of vehicles in each grid; a regional movement heat map is constructed, with the heat map using a color gradient to represent density levels, with dark red indicating high-density areas and blue indicating low-density areas, and visualization tools helping to identify traffic flow aggregation points and idle areas. A spatiotemporal trajectory clustering algorithm is applied to analyze vehicle movement trajectories, which uses an improved DBSCAN variant that considers both spatial proximity and temporal continuity; typical movement patterns and key paths are identified, including early morning peak commuting flow (from residential areas to business districts), midday short shopping flow, and late evening peak dispersion flow, and key paths refer to frequently occurring vehicle travel routes, such as main roads and connecting lines.

[0085] Based on the trajectory clustering results, a path flow prediction function is established, which uses time series analysis combined with machine learning models (such as ARIMA or LSTM network), and the input variables include time, day of the week, weather conditions and special event markers; combined with time factors to predict the flow of each key path at a specific time point, the prediction output is the estimated value of the number of vehicles within 1 hour or less in the future. Predict regional parking demand changes based on multi-source data, including historical parking records, traffic flow sensor readings, business activity schedules and social media event information; generate parking demand prediction results, the results are output in the form of probability distribution, indicating the parking demand intensity of different sub-regions in the future period. Extract parking demand features based on time-varying network models, time-varying network models simulate the changes of road network capacity and connectivity at different times; identify the spatio-temporal variation pattern of parking demand, including the mode that the morning peak demand of weekdays concentrates in office areas, the afternoon demand of weekends shifts to commercial areas, and the night demand drops to the lowest.

[0086] Based on the scoring system to calculate the adjustment priority and resource allocation ratio, the scoring system uses a multi-criteria decision method, considering factors including demand urgency (based on the difference between predicted demand and current capacity), resource availability (number of free parking spaces), economic benefit (parking rate) and user satisfaction (historical complaint data); calculate the adjustment priority score of each sub-region, the higher the score, the more need for priority processing, the resource allocation ratio allocates parking guidance signals and variable parking space signs according to the score by weight. Realize forward-looking parking resource layout, layout actions include dynamically adjusting parking rates, opening backup parking lots, modifying lane directions, and pushing idle parking space information through APP; adaptively execute perception strategy adjustment, adjustment based on real-time feedback loop, automatically recalculate parameters when the predicted demand and actual demand deviation exceeds the threshold, to ensure that the perception process pre-adapts to changes in parking demand.

[0087] The whole implementation process is demonstrated by the actual data flow of the business district. The vehicle moving trajectory analysis reveals that the commuting mode is that the number of vehicles entering the business district increases from 7 to 9 in the morning, there is a short shopping peak from 14 to 16 in the afternoon, and there is a departure peak from 17 to 19 in the evening. The path flow prediction function accurately captures these patterns, for example, it predicts that the traffic flow of the main road at 8 am on Monday is 40% higher than at the same time on Sunday. The parking demand prediction result shows that the demand peak of the office area is 85% from 8 to 10 on weekdays, while the demand of the business district is high from 14 to 18 on weekends. The time-varying network model identifies the feature that the connecting road capacity decreases by 20% during the peak period. The scoring system calculates the priority score of the office area during the morning peak as 0.8 (full score 1.0), and the resource allocation ratio points 70% of the guidance signal to the area. After the implementation of the layout action, the system adaptively adjusts the sensing strategy, such as increasing the sensor sampling frequency in the high demand area, thereby optimizing the overall parking resource utilization rate. The method shows the complete chain from data collection to layout implementation through specific examples, highlights the data-driven and adaptive characteristics, and meets the development trend of intelligent parking management.

[0088] It should be noted that, in the present document, relational terms such as first and second and the like can be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises", "comprising", or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0089] While embodiments of the application have been shown and described, it is to be understood that the application is not limited to the details of the embodiments described, since numerous further modifications and changes can be apparent to one skilled in the art without departing from the scope and spirit of the application. The scope of the application is defined by the appended claims and their equivalents.

Claims

1. A digital dynamic perception method for parking spaces integrating vehicle-to-everything (V2X) technology, characterized in that: The method includes: A parking space status model of the vehicle-to-everything (V2X) system is constructed based on the target area of ​​the V2X system, wherein the target area is the area related to the parking space perception process. A perception strategy model is constructed, which is used to control the data acquisition and processing output in the parking space status model; Based on the selected parking lot attractions, the perception strategy model and the parking space state model are coupled and simulated to obtain the corresponding simulation results; Based on the simulation results, determine whether there are any perception errors in the parking space perception process; In the presence of perception error, the control parameters in the perception strategy model are adjusted; Based on the adjusted control parameters, the perception strategy model and the parking space state model are re-coupled and simulated until the target simulation result is obtained. The target simulation result is a result that characterizes the parking space perception error as being within the allowable range. When the target area includes a parking space grid, vehicle sensors, and a vehicle communication module, the construction of a parking space status model based on the vehicle-to-everything (V2X) system for the target area includes: Construct a parking space grid model, a vehicle sensor model, and a vehicle communication model based on the target area of ​​the vehicle-to-everything (V2X) system. The input parameters of the vehicle sensor model are initialized using the state data of the parking space grid model; The vehicle communication model's transmission strategy is configured using the output data of the vehicle sensor model to construct a parking space status model for obtaining the vehicle network system. The construction of the perception strategy model includes: Based on the data acquisition frequency and processing delay requirements, the perception strategy is discretized into an equivalent control algorithm model; The control algorithm model is integrated by parameter optimization components, and an update cycle is set to construct a perception strategy model. The process involves coupled simulation of the perception strategy model and the parking space state model based on the selected parking lot location to obtain corresponding simulation results, including: Based on the selected parking lot attractions, the data acquisition rate of the parking space status model is adjusted by outputting control signals through the perception strategy model in order to obtain the real-time status of the target area. When the parking space state model reaches a stable state, the data output accuracy of the parking space state model is controlled by the processing coefficient output by the perception strategy model, so as to realize the data interaction between the parking space state model and the perception strategy model and obtain the corresponding simulation results. The data acquisition frequency defines the rate at which sensor data is acquired, the processing latency requirement specifies the timeliness constraints of data processing, and the control algorithm model is implemented using a state machine or rule engine to adjust the sensing behavior. The core function of the control algorithm model is to transform continuous sensing strategies into discrete executable instructions, which can dynamically adjust the data acquisition and processing flow. The parameter optimization element includes an optimization function and a constraint processing module. The optimization function searches for the optimal parameter set based on gradient descent or heuristic algorithms, and the constraint processing module ensures that parameter adjustments meet system constraints.

2. The vehicle-to-everything (V2X) fusion parking space digital dynamic perception method according to claim 1, characterized in that, The step of determining whether there is a perception error in the parking space perception process based on the simulation results includes: If the simulation results meet the first or second preset conditions, it is determined that there is a perception error in the parking space perception process; The first preset condition is that during the coupled simulation parking perception process, the deviation between the state data of the parking space grid model in the parking space state model and the actual measurement data is greater than or equal to a preset deviation threshold. The second preset condition is that during the coupled simulation parking perception process, noise interference occurs in the output of the vehicle sensor model and the noise intensity is greater than a set threshold.

3. The vehicle-to-everything (V2X) integrated parking space digital dynamic perception method according to claim 1, characterized in that, The method further includes: At each time point, based on the initial occupancy matrix corresponding to each time point, the parking space status is corrected for uniformity to obtain the corrected occupancy matrix of the parking space at each time point. Determine the target occupancy rate that the parking space needs to maintain, control the parking space status perception based on the corrected occupancy matrix corresponding to the target occupancy rate, and measure the actual occupancy rate of the parking space through sensors; If the difference between the target occupancy rate and the actual occupancy rate is greater than or equal to a preset deviation threshold, the occupancy deviation matrix is ​​determined based on the corrected occupancy matrix corresponding to the target occupancy rate and the occupancy matrix corresponding to the actual occupancy rate. Based on the occupancy deviation matrix, the corrected occupancy matrix corresponding to the target occupancy rate is adjusted to obtain the adjusted occupancy matrix corresponding to the target occupancy rate; The adjusted occupancy matrix corresponding to the target occupancy rate is used as the new corrected occupancy matrix corresponding to the target occupancy rate, and the step of controlling the parking space status perception based on the corrected occupancy matrix corresponding to the target occupancy rate is returned until the difference between the target occupancy rate and the actual occupancy rate is less than the preset deviation threshold.

4. The vehicle-to-everything (V2X) fusion parking space digital dynamic perception method according to claim 3, characterized in that, The process of performing uniformity correction on the parking space status based on the initial occupancy matrix corresponding to each of the aforementioned time points to obtain the corrected occupancy matrix of the parking spaces at each of the aforementioned time points includes: For any given time point, based on the initial occupancy matrix corresponding to the time point, the parking space status perception is controlled, and real-time data of the parking space is obtained using vehicle networking devices, and the actual occupancy matrix is ​​extracted from the real-time data. Determine the standard deviation of occupancy uniformity based on the actual occupancy matrix; If the standard deviation of the occupancy uniformity is greater than or equal to a preset standard deviation threshold, the actual state matrix corresponding to the actual occupancy matrix is ​​determined based on a pre-constructed occupancy relationship model. The actual state matrix is ​​iterated using a state matrix iterative model to obtain the iterated state matrix corresponding to the actual state matrix; The iterative state matrix is ​​used as the initial occupancy matrix, and the initial occupancy matrix based on the time point is returned to control the parking space status perception step until the occupancy uniformity standard deviation is less than the preset standard deviation threshold. The iterative state matrix is ​​used as the corrected occupancy matrix.

5. The vehicle-to-everything (V2X) fusion parking space digital dynamic perception method according to claim 1, characterized in that, The method further includes: Based on vehicle movement trajectory data, analyze vehicle movement patterns within the area and generate a movement trajectory prediction model; Based on multi-source data, predict changes in regional parking demand and generate parking demand prediction results; Parking demand features are extracted based on time-varying network models to identify the spatiotemporal variation patterns of parking demand; Based on the scoring system, priorities and resource allocation ratios are adjusted to achieve a forward-looking parking resource layout; Adaptive execution of perception strategy adjustments ensures that the perception process anticipates changes in parking demand.

6. The vehicle-to-everything (V2X) fusion-based digital dynamic perception method for parking spaces according to claim 5, characterized in that, The process of analyzing vehicle movement patterns within a region based on vehicle movement trajectory data and generating a movement trajectory prediction model includes: Anonymized vehicle location data from multiple time points within the region were collected, and data cleaning, outlier removal, and spatiotemporal feature extraction were performed. The region is divided into grids, and the vehicle density of each grid at different times is statistically analyzed to construct a regional movement heat map. Spatiotemporal trajectory clustering algorithm is applied to analyze vehicle movement trajectories and identify typical movement patterns and critical paths; Based on trajectory clustering results, a path traffic prediction function is established, which combines time factors to predict the traffic of each critical path at a specific time point.

Images