Regional parking space management system and its application based on big data analysis

Abstract

The present invention mainly relates to a regional parking space management system based on big data analysis, including: a perception layer, which is configured to collect the initial information of the external environment of the system, i.e., the region, and classify the collected initial information, and then pass it to the service layer; a service layer, which is configured to integrate, process and analyze the initial information, perform business logic processing to obtain regional statistical information, and provide the regional statistical information to the application layer; an application layer, which is configured to process requests from underlying components such as user interfaces and network interfaces, and call other lower-level services to complete the operations required by users. The system can significantly improve parking efficiency, reduce parking waiting time and traffic congestion, improve the regional parking environment, and can predict parking data in the region, so as to facilitate regional security personnel to make targeted adjustments to parking control measures.

Description

Technical Field

[0001] The present invention mainly relates to the technical field of parking space management systems, and in particular to a regional parking space management system and application based on big data analysis. Background Art

[0002] At present, the number of cars in my country continues to rise, and urban parking spaces are becoming increasingly tight. The difficulty in parking has led some vehicles to park directly in non-parking areas such as the sides of the road and in front of shops, which not only seriously aggravates traffic congestion, but also poses a great safety hazard. Some areas, such as public institutions such as colleges and universities and hospitals, need to assume certain social service functions. While accepting personnel and vehicles of their own units, they also need to accept social personnel and vehicles to enter to ease the traffic pressure in the city. Among them, colleges and universities have a large area, narrow roads, large and cyclical personnel mobility, and a large number of non-motorized vehicles shuttle back and forth, which makes it difficult for social vehicles to quickly find parking spaces after entering the university campus. There may be random parking, which is easy to cause traffic congestion, parking disputes and even traffic accidents, and poses a certain threat to the safety of teachers, students and staff.

[0003] There are many factors that contribute to the difficulty of parking on campus, including: 1) High cost: The campus is densely populated with trees, and surveillance cameras are easily affected by the growing trees. During construction, the campus trees need to be pruned, which results in high construction costs. During later maintenance, regular observations are required to see if they are blocked, resulting in high operation and maintenance costs; 2) Low accuracy: The parking status of surveillance cameras; 3) Impact on the image of colleges and universities: Parking spaces on campus are scattered, and the large number of surveillance cameras required and the high poles are not conducive to the later construction of the campus; 4) Difficulty in management: The manual management of non-motor vehicle parking on campus is difficult and there is no real-time notification method; 5) Low efficiency: Without data support, campus managers cannot have new parking space planning references and cannot discover hidden parking problems in advance. Therefore, it is necessary to develop a parking space management system with high parking efficiency, low monitoring cost, visualization, and easy implementation.

[0004] The above-mentioned record of background technical knowledge is intended to help ordinary technicians in this field understand the existing technologies that are relatively close to the present invention, and at the same time facilitate the understanding of the inventive concept and technical solution of this application. It should be clear that in the absence of clear evidence that the above-mentioned content has been disclosed before the filing date of this patent application, the above-mentioned background technology should not be used to evaluate the novelty of the technical solution of this application. Summary of the invention

[0005] In order to solve at least one of the technical problems mentioned in the above background technology, the purpose of the present invention is to provide a regional parking space management system based on big data analysis. The system can significantly improve parking efficiency, reduce parking waiting time and traffic congestion, improve the regional parking environment, and predict parking data in the area, so as to facilitate regional security personnel to make targeted adjustments to parking control methods.

[0006] Regional parking space management system based on big data analysis, including:

[0007] The perception layer is configured to collect initial information about the external environment of the system, i.e., the area, and classify the collected initial information before passing it to the service layer;

[0008] The service layer is configured to integrate, process and analyze the initial information, perform business logic processing to obtain regional statistical information, and provide the regional statistical information to the application layer;

[0009] The application layer is configured to handle requests from underlying components such as user interfaces and network interfaces, and call other lower-level services to complete the operations required by users.

[0010] As a preferred embodiment of the technical solution of the present application, the initial information collected by the perception layer includes: non-motor vehicle parking area information, whether there are vehicles parked in the motor vehicle parking spaces, and whether the motor vehicles in the parking spaces meet the parking standards.

[0011] As a preferred embodiment of the technical solution of the present application, the non-motor vehicle parking area information includes the vacant non-motor vehicle parking area, whether there are motor vehicles parked in the non-motor vehicle parking area, and whether there are non-motor vehicles parked outside the non-motor vehicle parking area.

[0012] As a preferred embodiment of the technical solution of the present application, the sensing layer collects initial information of the external environment of the system, i.e., the area, through three detection methods: geomagnetism, radar, and light illumination.

[0013] As a preferred embodiment of the technical solution of the present application, other information is also pre-input into the service layer, including: motor vehicle routes, place names near motor vehicle routes, non-motor vehicle routes, place names near non-motor vehicle routes, and the distances between each place name.

[0014] As a preferred embodiment of the technical solution of the present application, the service layer is also configured to store the regional statistical information in a database.

[0015] As a preferred embodiment of the technical solution of the present application, the application layer is also configured to display the remaining parking space information of the parking area and guide the car owner to park.

[0016] As a preferred embodiment of the technical solution of the present application, the application layer is also configured to generate visualization models such as regional parking heat maps, regional parking time analysis tables, and regional car owner portraits.

[0017] As a preferred embodiment of the technical solution of the present application, the method for displaying the remaining parking space information of the parking area at the application layer includes:

[0018] 1) Placing information display screens on the driving routes of motor vehicles to guide vehicles to find suitable parking areas; and / or

[0019] 2) The driver sends a request to the system through his mobile device to obtain the remaining space data of each parking area, and after entering the destination area, he can guide the vehicle to the parking area closest to the destination with remaining space to guide the car owner to park.

[0020] The perception layer collects initial information within the area, such as non-motor vehicle parking area information, whether there are vehicles parked in the parking spaces, and whether motor vehicles are parked in standard manner. The service layer generates a parking heat map of regional parking users based on the initial information. The heat map includes the number of vacant spaces in each parking lot area in the area, and provides real-time information release and query services to the public through induction screens or mobile devices, making it convenient for the public to quickly find suitable parking areas.

[0021] As a preferred embodiment of the technical solution of the present application, when the service layer receives information that a motor vehicle in place does not meet the parking standards, the system automatically sends a notification to the owner of the motor vehicle.

[0022] As a preferred embodiment of the technical solution of the present application, the service layer is aware of whether there are vehicles not parked in the parking spaces based on the number of parking spaces in the overall area, the number of existing vehicles in the overall area, and the number of empty parking spaces, and obtains the last location of the illegal vehicle through the induction screen to guide security personnel to that location for processing.

[0023] As a preferred option for the technical solution of this application, when security personnel observe that a non-motor vehicle is not parked in the designated area, they interact with the campus intranet by scanning the non-motor vehicle QR code, obtain vehicle information, and post a notice. At the same time, the platform sends text messages to teachers and students through Alibaba Cloud SMS service to handle the matter as soon as possible.

[0024] As a preferred embodiment of the technical solution of the present application, the service layer is also configured to predict parking data through an embedded prediction model, and provide the prediction results including daily inbound and outbound vehicle flow, daytime parking space utilization, nighttime parking space utilization, average parking time and parking space turnover rate to the application layer.

[0025] As a preferred embodiment of the technical solution of the present application, the prediction model is specifically established through the following steps:

[0026] 1) Obtain parking data for the last two cycles in the area, including: daily in-and-out vehicle flow, daytime parking space utilization rate, nighttime parking space utilization rate, average parking time, and parking space turnover rate;

[0027] 2) Differentiate the parking data to obtain a first-order difference d1 = [Y2-Y1, Y3-Y2, ..., Y n -Y n-1,], where Y1, Y2, ..., Y n That is, the value of the original parking data Y at each time, Y = [Y1, Y2, ..., Y i , ..., Y n ],Y i represents the value at the i-th moment;

[0028] 3) Perform AR fitting on the time series after difference, and the AR(p) model is expressed as Among them, c is a constant term, The coefficient of the AR(p) model is the autoregressive coefficient, d t-i represents the value of the time series at time point ti after differentiation, ε t represents the random error term;

[0029] 4) Based on the AR fitting, the MA term is added, and the MA(q) model is expressed as:

[0030]

[0031] Among them, θ j The coefficient of the MA model is the moving average coefficient, ε t-j Represents the value of the random error term at time point tj; the moving average coefficient is obtained based on the least squares method in autoregression;

[0032] 5) Combine the AR and MA parts to get the complete ARIMA (p, d, q) model:

[0033]

[0034] Among them, Y t represents the value of the current moment t; Y t-i-d Represents the value of tid at the past time; d represents the order of difference, generally the first order difference; R represents the special event coefficient; the predicted data for the future cycle in the parking lot is obtained, including the daily in-and-out traffic flow, daytime parking space utilization rate, nighttime parking space utilization rate, average parking time and parking space turnover rate, so as to facilitate regional security personnel to make targeted adjustments to parking control measures.

[0035] As a preferred embodiment of the technical solution of the present application, the period is at least one of a week, a month, a quarter, and a year.

[0036] As a preferred embodiment of the technical solution of the present application, in step 3), the autoregressive coefficient of the AR(p) model is estimated using the least squares method. The goal is to minimize the sum of squared residuals between the observed values ​​and the model's predicted values. The specific steps are as follows:

[0037] 1. Prepare data: Prepare time series data as Y = [Y1, Y2, ..., Y n ] form;

[0038] 2. Set the AR order: Determine the order p of the AR model, that is, consider the values ​​of the past p moments;

[0039] 3. Construct independent variables and dependent variables: construct independent variables X′ and dependent variables Y′, where Y′ is the pth to nth elements of time series data Y, and X′ is the p-1th to n-1th elements of time series data Y;

[0040] 4 Perform linear regression: Use the least squares method to perform linear regression and estimate the autoregressive coefficients of the AR model

[0041] As a preferred embodiment of the technical solution of the present application, in step 3), statsmodels in the statistical software package Python or lm function in R language is used to automatically perform linear regression and parameter estimation. The order p of the AR model needs to be selected according to the characteristics of the data and the fitting effect, and information criteria (such as AIC, BIC) and other indicators can be used to evaluate the advantages and disadvantages of models of different orders.

[0042] As a preferred embodiment of the technical solution of the present application, in the ARIMA (p, d, q) model, when it is determined that no special event occurs during the forecast period, R=0; when a special event occurs during the forecast period, the special event coefficient R is represented by the range of the parking data in the previous period where the special event occurred. The special event refers to an event that will cause a drastic change in the parking data of the area. When the area is a college, the special event includes but is not limited to at least one of the following: freshmen admission, vacation, major events held by the school, and activities of student clubs or social organizations. When new students are enrolled or major events are held, the parking data during this period may change dramatically compared to when no events are held. For example, the number of vehicles on campus will inevitably increase exponentially when new students are enrolled, while the number of vehicles on campus will decrease significantly during holidays. Therefore, adding special event factors to the prediction model can more accurately predict the daily inbound and outbound traffic volume, daytime parking space utilization rate, nighttime parking space utilization rate, average parking time and parking space turnover rate in the next cycle. This will help regional security personnel to predict the number of vehicles entering and leaving the area and the parking time during the period when special events occur, so that they can adjust the parking control measures in a targeted manner, thereby avoiding traffic congestion or even traffic accidents due to special collective activities, and maintaining regional safety to the greatest extent.

[0043] The application of the aforementioned regional parking space management system based on big data analysis in university parking management.

[0044] The present invention uses hardware devices such as geomagnetism, radar and illumination to collect parking information in an area such as a campus, manage parking spaces in the campus, and transmit the parking information to the service layer for integration, processing and analysis. The vacant parking space data is sent to the parking guidance screen or the owner's mobile device by wired or wireless means to guide the owner to drive to an area with vacant parking spaces for rapid and safe parking. At the same time, the system supports management personnel to automatically contact the owner of non-motor vehicles or motor vehicles parked randomly in the area, and can also obtain the last location of the vehicle through the guidance screen, and guide the security personnel to the location for processing. The security personnel take photos of the vehicle through a handheld device for evidence collection and record, and the vehicle license plate is associated with the owner's personnel information in the campus system, and management is achieved by offline ticketing and online SMS notification to the owner.

[0045] The platform obtains the parking data of car owners on campus to generate visualization models such as university parking heat maps, university parking time analysis tables, and university car owner portraits. It further uses the parking data prediction model to predict the parking data in the region for a future period, and provides the prediction results including daily inbound and outbound traffic, daytime parking space utilization rate, nighttime parking space utilization rate, average parking time, and parking space turnover rate to the application layer, making it convenient for regional security personnel to make targeted adjustments to parking control measures.

[0046] The beneficial effects of this application are:

[0047] 1. Improve parking efficiency: The parking guidance system can automatically adjust the allocation of parking spaces by monitoring the usage of parking spaces in real time, so that vehicles can quickly find suitable parking spaces and reduce parking time and waiting time.

[0048] 2. Reduce traffic congestion: The parking guidance system can automatically adjust the allocation of parking spaces according to real-time traffic conditions to avoid overcrowding of parking spaces and reduce the risk of traffic congestion and accidents.

[0049] 3. Improve parking environment: The parking guidance system can reasonably allocate parking spaces, improve the parking environment and increase the utilization rate of parking lots by real-time monitoring of parking space usage.

[0050] 4. Improve parking safety: The parking guidance system can monitor the use of parking spaces in real time, detect obstacles in parking spaces in time, avoid vehicle collisions, and improve parking safety.

[0051] 5. Reduce parking costs: The parking guidance system can automatically adjust the allocation of parking spaces by real-time monitoring of parking space usage, thereby reducing the number of vehicle parking times and reducing parking costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to make the above and / or other purposes, features, advantages and examples of the present invention more obvious and easy to understand, the drawings required for use in the specific implementation of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without paying creative work.

[0053] Figure 1 The overall system architecture diagram of the regional parking management system based on big data analysis;

[0054] Figure 2 The overall business process diagram of the regional parking management system based on big data analysis;

[0055] Figure 3 A flowchart showing what to do when parking is not done in accordance with regulations. DETAILED DESCRIPTION

[0056] Those skilled in the art can refer to the content of this article and appropriately replace and / or modify the process parameters to achieve the same. However, it should be particularly noted that all similar replacements and / or modifications are obvious to those skilled in the art and are considered to be included in the present invention. The products and preparation methods described in the present invention have been described through preferred examples. It is obvious that relevant personnel can modify or appropriately change and combine the products and preparation methods described herein without departing from the content, spirit and scope of the present invention to implement and apply the technology of the present invention.

[0057] Unless otherwise defined, technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the invention belongs. The present invention uses the methods and materials described herein; however, other suitable methods and materials known in the art may also be used. The materials, methods, and examples described herein are illustrative only and are not intended to be limiting. All publications, patent applications, patents, provisional applications, database entries, and other references mentioned herein are incorporated herein by reference in their entirety. In the event of a conflict, the present specification, including definitions, shall prevail.

[0058] Unless specifically stated, the materials, methods, and examples described herein are illustrative only and not limiting. Although methods and materials similar or equivalent to those described herein can be used in the practice or testing of the present invention, suitable methods and materials are still described herein.

[0059] The present invention is described in detail below.

[0060] Embodiment 1:

[0061] A regional parking space management system based on big data analysis is provided, which includes a perception layer, a service layer and an application layer from bottom to top, wherein the service layer is also called a cloud platform layer, and the perception layer, the service layer and the application layer are connected by wire and / or wireless. The overall system architecture is shown in the figure below. Figure 1 shown.

[0062] The perception layer is the bottom layer of the system, and is configured to collect the initial information of the external environment of the system, i.e. the area, through three detection methods: geomagnetism, radar and light intensity. The initial information includes: the location of non-motor vehicle parking areas, the vacancy of non-motor vehicle parking areas, whether there are motor vehicles parked in non-motor vehicle parking areas, whether there are non-motor vehicles parked outside non-motor vehicle parking areas, whether there are vehicles parked in motor vehicle parking spaces, and whether the parking standards of motor vehicles in place are met; the collected initial information is classified and then passed to the service layer. Figure 2 As shown, the overall business process of the system includes: the perception layer detects whether there is a car in the parking space, and wirelessly transmits the data packet to the service layer of the system; the service layer organizes the parking data of each area and transmits it wirelessly and / or wired to the control card of the induction screen at the service layer; the induction screen displays the remaining space information through the control card protocol to guide the car owner to park.

[0063] The service layer is a cloud platform layer, which is configured to integrate, process and analyze the initial information transmitted by the perception layer and other pre-input information, the other information including: motor vehicle routes, place names near motor vehicle routes, non-motor vehicle routes, place names near non-motor vehicle routes, and the distances between each place name; then business logic processing is performed to obtain regional statistical information, and the regional statistical information is provided to the application layer.

[0064] The application layer is further configured to display the remaining parking space information of the parking area and guide the car owner to park, and the method includes:

[0065] 1) Place information display screens on the driving routes of motor vehicles to guide vehicles to find suitable parking areas; or

[0066] 2) The driver sends a request to the system through his mobile device to obtain the remaining space data of each parking area, and after entering the destination area, the vehicle can be guided to the parking area with remaining space closest to the destination to guide the owner to park. Through the induction screen display, the vehicle can quickly find a suitable parking area with remaining space, avoiding the vehicle from being stranded on the motor vehicle driving route for a long time and avoiding overcrowding of parking; further, after the driver enters the destination, the system can guide the driver to the parking area closest to the destination, which not only improves parking efficiency, but also allows the vehicle to be parked in a parking area near the driver's destination, reducing the walking distance and time after the driver parks, and improving work efficiency.

[0067] The service layer is also configured to store the regional statistical information in a database.

[0068] The application layer is also configured to generate visualization models such as regional parking heat maps, regional parking time analysis tables, and regional car owner portraits.

[0069] When the service layer receives information that a motor vehicle is not parked according to the parking standards, the system automatically sends a notification to the owner of the motor vehicle.

[0070] The service layer learns whether there are vehicles not parked in the parking spaces based on the number of parking spaces in the overall area, the number of existing vehicles in the overall area, and the number of empty parking spaces, and learns the last location of the illegal vehicle through the guidance screen, and guides the security personnel to that location for processing.

[0071] like Figure 3 As shown, for non-motor vehicles that are not parked in accordance with regulations, if the security personnel observe that the non-motor vehicle is not parked in the designated area, they can interact with the campus intranet by scanning the non-motor vehicle QR code, obtain vehicle information, and post a notice. At the same time, the platform will send text messages through Alibaba Cloud SMS service to notify teachers and students and handle it as soon as possible.

[0072] The application layer is configured to handle requests from underlying components such as user interfaces and network interfaces, and call other lower-level services to complete the operations required by users.

[0073] Embodiment 2:

[0074] On the basis of the aforementioned embodiment, a regional parking space management system based on big data analysis is improved. Specifically, a prediction model is embedded in the service layer to predict parking data including daily in-and-out traffic flow, daytime parking space utilization rate, nighttime parking space utilization rate, average parking time and parking space turnover rate, and the prediction results are provided to the application layer.

[0075] The prediction model is specifically established through the following steps 1) to 5).

[0076] Step 1) Obtain parking data for the past two months in the area, including:

[0077] Daily in-and-out traffic volume: the number of vehicles entering and leaving the area in a single day;

[0078] Daytime parking space utilization rate: the ratio of the number of parking spaces actually used in the parking lot to the total number of parking spaces during the day (08:00-20:00), which is counted every hour and the average value is taken to represent the day;

[0079] Nighttime parking space utilization rate: the ratio of the number of parking spaces actually used to the total number of parking spaces in the parking lot at night (20:00-08:00 the next day), which is counted every hour and the average value is taken to represent the day;

[0080] Average parking time: calculate the average time that vehicles leaving the parking lot stay in the parking lot every day;

[0081] The parking space turnover rate is calculated by dividing the number of vehicles entering the parking lot each day by the number of parking spaces in the parking lot.

[0082] Step 2) Differentiate the parking data in step 1) to obtain the first-order difference d1 = [Y2-Y1, Y3-Y2, ..., Y n -Y n-1 ,], where Y1, Y2, ..., Y n That is, the value of the original parking data Y at each time, Y = [Y1, Y2, ..., Y i , ..., Y n ],Y i Represents the value at the i-th moment.

[0083] Step 3) Perform AR fitting on the time series after difference, and the AR(p) model is expressed as Among them, c is a constant term, The coefficient of the AR(p) model is the autoregressive coefficient, d t-i represents the value of the time series at time point ti after differentiation, ε t represents the random error term.

[0084] Estimate the autoregressive coefficients of the AR(p) model using the least squares method The goal is to minimize the sum of squared residuals between the observed values ​​and the model's predicted values. The specific steps are as follows:

[0085] 3.1 Data preparation: Prepare time series data as Y = [Y1, Y2, ..., Y n ] form;

[0086] 3.2 Setting the AR order: Determine the order p of the AR model, that is, consider the values ​​of the past p moments;

[0087] 3.3 Construct independent variables and dependent variables: Construct independent variables X′ and dependent variables Y′, where Y′ is the pth to nth elements of time series data Y, and X′ is the p-1th to n-1th elements of time series data Y;

[0088] 3.4 Perform linear regression: Use the least squares method to perform linear regression and estimate the autoregressive coefficients of the AR model

[0089] Step 4) Based on the AR fitting, the MA term is added, and the MA(q) model is expressed as:

[0090]

[0091] Among them, θ j The coefficient of the MA model is the moving average coefficient, ε t-j Represents the value of the random error term at time point tj; the moving average coefficient is obtained based on the least squares method in autoregression.

[0092] Step 5) Combine the AR and MA parts to get the complete ARIMA (p, d, q) model:

[0093]

[0094] Among them, Y t represents the value of the current moment t; Y t-i-d Represents the value of tid at the past time; d represents the order of difference, generally the first order difference; R represents the special event coefficient; the predicted data for the future cycle in the parking lot is obtained, including the daily in-and-out traffic flow, daytime parking space utilization rate, nighttime parking space utilization rate, average parking time and parking space turnover rate, so as to facilitate regional security personnel to make targeted adjustments to parking control measures.

[0095] In the ARIMA (p, d, q) model, when it is determined that no special event occurs within the prediction period, R = 0; when a special event occurs within the prediction period, the special event coefficient R is represented by the range of the parking data in the previous period where the special event occurred, and it is limited to the special event occurring at time t. For example, for a certain university, September 1-4 every year is the enrollment time for new students. During these days, the daily in-and-out traffic flow, daytime parking space utilization rate and average parking time all increase sharply. In order to predict the parking data for September of this year, it is necessary to consider the range of the parking data for September of the previous year based on the parking data prediction results from September 1-4. The application of the special event coefficient can quantify the impact of special events on regional parking in a precise manner, which is beneficial for regional security personnel to predict parking data when special events occur, so as to adjust the parking control measures in a targeted manner and maintain regional safety.

[0096] The conventional techniques in the above embodiments are prior arts known to those skilled in the art, and thus will not be described in detail here.

[0097] The specific embodiments described herein are merely examples of the spirit of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in similar ways, but they will not deviate from the spirit of the present invention or exceed the scope defined by the appended claims.

[0098] Although the present invention has been described in detail and some specific embodiments have been cited, it is obvious to those skilled in the art that various changes and modifications can be made without departing from the spirit and scope of the present invention.

[0099] Although the above-mentioned specific embodiments have been shown, described and pointed out the novel features applied to various embodiments, it should be understood that various omissions, substitutions and changes can be made to the form and details of the described device or method without departing from the spirit of the present disclosure. In addition, the above-mentioned various features and methods can be used independently of each other, or can be combined in various ways. All possible combinations and sub-combinations are intended to fall within the scope of the present disclosure. Many of the above-mentioned embodiments include similar components, and therefore, these similar components are interchangeable in different embodiments. Although the present invention has been disclosed in the context of certain embodiments and examples, it should be understood by those skilled in the art that the present invention can extend beyond the specifically disclosed embodiments to other alternative embodiments and / or applications and obvious modifications and equivalents thereof. Therefore, the present invention is not intended to be limited by the specific disclosure of the preferred embodiments herein.

[0100] Matters not covered in the present invention are all known technologies.

Claims

1. Regional parking space management system based on big data analysis, characterized by include: The perception layer is configured to collect the initial information of the external environment of the system, i.e., the area, including: the location of the motor vehicle parking area, the vacancy of the non-motor vehicle parking area, whether there are motor vehicles parked in the non-motor vehicle parking area, whether there are non-motor vehicles parked outside the non-motor vehicle parking area, whether there are vehicles parked in the motor vehicle parking space, and whether the motor vehicles in the parking space meet the parking standards; and classify the collected initial information and then pass it to the service layer; The service layer is configured to integrate, process and analyze the initial information, perform business logic processing to obtain regional statistical information, and provide the regional statistical information to the application layer; The application layer is configured to process requests from the user interface and the underlying components of the network interface to complete the operations required by the user; If security personnel observe that a non-motor vehicle is not parked in the designated area, they will scan the non-motor vehicle QR code to interact with the campus intranet, obtain vehicle information, and post a notice. At the same time, the platform will send a text message to teachers and students through Alibaba Cloud SMS service to handle the matter as soon as possible; The service layer is further configured to predict parking data through an embedded prediction model, and provide prediction results including daily in-and-out vehicle flow, daytime parking space utilization rate, nighttime parking space utilization rate, average parking time, and parking space turnover rate to the application layer; The prediction model is specifically established through the following steps: 1) Obtain parking data for the last two cycles in the area, including: daily in-and-out vehicle flow, daytime parking space utilization rate, nighttime parking space utilization rate, average parking time, and parking space turnover rate; 2) Differentiate the parking data to obtain the first-order difference ,in The original parking data The value at each moment, , Indicates The value at a moment; 3) Perform the differential time series Fitting, The model is represented as ,in, is a constant term, express The coefficients of the model are the autoregressive coefficients, Indicates the time series after difference at time point The value of represents the random error term; estimated using the least squares method The autoregressive coefficients of the model , the goal is to minimize the residual sum of squares between the observed value and the model predicted value. The specific steps are as follows: 3.1) Data preparation: Prepare time series data as form; 3.2) Setup Degree: Determine The order of the model , that is, to consider the past The value at a moment; 3.3) Constructing independent and dependent variables: Constructing independent variables and the dependent variable ,in It is time series data No. to elements, It is time series data No. to elements; 3.4) Perform linear regression: Use the least squares method to perform linear regression and estimate The autoregressive coefficients of the model ; 4) In Based on the fitting, add Item, expressed as: in, express The coefficients of the model are the moving average coefficients, represents the random error term at time point The moving average coefficient is obtained by the least square method in autoregression; The model is: in, Indicates the current time The value of Indicates past time The value of represents the difference order; Indicates the special event coefficient; obtains the predicted data for the parking lot in the future cycle, including the daily in-and-out traffic volume, daytime parking space utilization rate, nighttime parking space utilization rate, average parking time and parking space turnover rate, so as to facilitate regional security personnel to make targeted adjustments to parking control measures; Said In the model, when no special events occur during the forecast period, When a special event occurs during the forecast period, the special event coefficient is expressed as the range of the parking data in the previous period where the special event occurred. , and is limited to special events occurring at time t. When the area is a college, the special event includes at least one of the following: enrollment of new students, vacations, major events held by the school, and activities of student clubs or social organizations.

2. The regional parking space management system based on big data analysis according to claim 1 is characterized by: The perception layer collects initial information about the system's external environment, i.e., the area, through three detection methods: geomagnetism, radar, and light illumination.

3. The regional parking space management system based on big data analysis according to claim 1 or 2, characterized in that: The application layer is also configured to display the remaining space information of the parking area and guide the car owner to park.

4. The regional parking space management system based on big data analysis according to claim 3 is characterized by: The method for displaying the remaining parking space information of the parking area at the application layer includes: 1) Placing information display screens on the driving routes of motor vehicles to guide vehicles to find suitable parking areas; and / or 2) The driver sends a request to the system through his mobile device to obtain the remaining space data of each parking area, and after entering the destination area, he can guide the vehicle to the parking area closest to the destination with remaining space to guide the car owner to park.

5. The regional parking space management system based on big data analysis according to claim 1, 2 or 4, characterized in that: The application layer is also configured to generate a regional parking heat map, a regional parking time analysis table, and a regional car owner portrait visualization model.

6. The regional parking space management system based on big data analysis according to claim 1, 2 or 4, characterized in that: The service layer learns whether there are vehicles not parked in the parking spaces based on the number of parking spaces in the overall area, the number of existing vehicles in the overall area, and the number of empty parking spaces, and learns the last location of the illegal vehicle through the guidance screen, and guides the security personnel to that location for processing.

7. Application of the regional parking space management system based on big data analysis as described in any one of claims 1 to 6 in parking management in universities.

Images