Public parking space occupancy prediction and scheduling method and system based on traffic large model

Abstract

The present invention relates to the technical field of parking space scheduling, and specifically relates to a public parking space occupancy prediction and scheduling method based on a traffic large model. The scheduling method comprises: acquiring sensor data on a parking space, comprising real-time vehicle entry / exit status, parking space occupancy data and historical data; establishing a time series model on the basis of the historical data and influencing parameters to predict parking space occupancy for each future time period; establishing a parking space allocation and scheduling model on the basis of real-time and predicted parking space occupancy; and performing real-time parking space scheduling decision-making on the basis of the parking space allocation and scheduling model. A prediction and scheduling system comprises: a data acquisition module, a parking space prediction module, a parking space allocation and scheduling module, and a scheduling decision-making module. The present invention establishes the time series model to predict the parking space occupancy for each future time period, and then establishes the parking space allocation and scheduling model on the basis of the occupancy, achieving advance scheduling and analysis and improving parking efficiency.

Description

A public parking space occupation prediction and scheduling method and system based on a traffic big model TECHNICAL FIELD

[0001] The application belongs to the technical field of parking space scheduling, and particularly relates to a public parking space occupation prediction and scheduling method and system based on a traffic big model. BACKGROUND

[0002] Public parking spaces refer to parking lots or parking spaces demarcated and managed by governments or social public institutions for free or paid use by the general public. These parking spaces are usually located in public places, commercial areas, residential areas and the like, and are convenient for the public to park vehicles and relieve urban traffic congestion. At the same time, public parking spaces also help to regulate parking order and protect the parking rights and interests of the public. The public parking space occupation prediction and scheduling method and system based on traffic big data is a kind of method for predicting and optimizing the utilization mode of parking space resources by using advanced data collection, processing and analysis technologies to monitor and analyze vehicle information in parking lots in real time.

[0003] The existing scheduling method and system cannot accurately predict parking spaces, and the scheduling method is single, which is easy to cause congestion and parking difficulties, resulting in low parking efficiency.

[0004] SUMMARY

[0005] In view of the deficiencies of the prior art, the application provides a public parking space occupation prediction and scheduling method and system based on a traffic big model to solve the above technical problems.

[0006] To achieve the above purpose, the application provides the following technical scheme: a public parking space occupation prediction and scheduling method based on a traffic big model, the scheduling method comprising:

[0007] S1: acquiring sensor data on the parking space, including real-time vehicle entry and exit conditions, parking space occupation data and historical data;

[0008] S2: establishing a time series model based on historical data and influence parameters to predict the occupation of parking spaces in each time period in the future;

[0009] S3: establishing a parking space allocation and scheduling model according to the real-time and predicted parking space occupation;

[0010] S4: making real-time parking space scheduling decisions based on the parking space allocation and scheduling model.

[0011] Preferably, S1 specifically comprises:

[0012] The sensor is configured to transmit real-time data to a data collection system;

[0013] The sensor is configured to periodically upload data to a cloud platform for data storage.

[0014] After the data arrives, real-time preprocessing is performed, including data cleaning, denoising, and time series data processing.

[0015] Encryption and access control measures are taken during data transmission.

[0016] Preferably, S2 specifically includes:

[0017] Obtain historical parking space occupancy data, including timestamps and corresponding occupancy;

[0018] Perform preliminary analysis on the data, including viewing time series graphs, viewing trends, and seasonality.

[0019] Based on the preliminary analysis data, establish a time series model to predict the occupancy of parking spaces in each future time period.

[0020] Preferably, based on the preliminary analysis data, establishing a time series model to predict the occupancy of parking spaces in each future time period includes:

[0021] wherein the time series model formula is: t = c + g1J t-1 +…+g p J t-p +γ1ε t-1 +…+γ q ε t-q +ε t

[0022] wherein J t is the occupancy value of the parking space at time t, c is a constant term, g1…g p are influence parameters of past p observation values on the current value, J t-1 is the parking space occupancy value at time t-1, J t-p is the parking space occupancy value at time t-p, γ1…γ q are influences of errors at lag q time points on the current value, and ε t is white noise error.

[0023] Preferably, S3 specifically includes:

[0024] Real-time prediction is performed using the time series model, and based on the current time data, a prediction result of the parking space occupancy is generated, and in combination with real-time data, parking space allocation and scheduling are performed.

[0025] According to the real-time predicted parking space occupancy, a specific parking space allocation and scheduling strategy is formulated, the number of open parking spaces is increased or decreased based on the scheduling strategy, and the utilization rate of the parking lot is optimized;

[0026] The scheduling model formula is:

[0027] In the formula, C t is the number of open parking spaces at time period t, J t is the predicted value of the occupancy of the parking space at time t in the time series, k is the adjustment parameter, and round is the rounding function.

[0028] Preferably, based on the calculation results of the scheduling model formula, the demand patterns of different time periods are divided into peak periods and valley periods;

[0029] For the time period t of the peak period, the predicted parking occupancy value J t is higher, and k is set to 1.2

[0030] For the time period t of the valley period, the predicted parking occupancy value J t is lower, and k is set to 0.8.

[0031] The formulated scheduling strategy is implemented into the parking management system to ensure real-time response and adjustment;

[0032] The accuracy of real-time data and model prediction is continuously monitored;

[0033] User feedback and parking data are collected to evaluate the effectiveness of the scheduling strategy.

[0034] Preferably, S4 specifically includes:

[0035] Updating the actual number of open parking spaces in the parking lot;

[0036] Adjusting the signs, indicators, and parking space allocation system to guide vehicle owners to designated parking areas;

[0037] Monitoring the actual parking space usage and real-time demand to ensure the effectiveness of the scheduling strategy;

[0038] Analyzing real-time data and the effectiveness of scheduling decisions, including parking space utilization and user satisfaction.

[0039] The public parking space occupancy prediction and scheduling system based on the traffic big model includes:

[0040] Data acquisition module: used for acquiring sensor data on the parking space, including real-time vehicle entry and exit, parking space occupancy data, and historical data;

[0041] Parking space prediction module: the parking space prediction module is electrically connected with the data acquisition module, and the parking space prediction module is used for establishing a time series model based on historical data and influence parameters to predict the occupancy of parking spaces in each future time period;

[0042] Parking space allocation and scheduling module: the parking space allocation and scheduling module is electrically connected with the parking space prediction module and the data acquisition module, and the parking space allocation and scheduling module is used for establishing a parking space allocation and scheduling model according to the real-time and predicted parking space occupancy;

[0043] Scheduling decision module: the scheduling decision module is electrically connected with the parking space allocation and scheduling module, the parking space prediction module and the data acquisition module, and the scheduling decision module is used for making real-time parking space scheduling decisions based on the parking space allocation and scheduling model.

[0044] Preferably, the parking space prediction module comprises:

[0045] Historical data acquisition module: used for acquiring historical parking space occupancy data, including time stamp and corresponding occupancy;

[0046] Data preliminary analysis module: used for preliminary analysis of data, including viewing time series chart, viewing trend and seasonality;

[0047] Parking space prediction module: used for establishing a time series model based on the data after preliminary analysis to predict the occupancy of parking spaces in each future time period.

[0048] Preferably, the parking space allocation and scheduling module comprises:

[0049] Prediction result acquisition unit: used for generating a prediction result of parking space occupancy based on the data of the current moment, combining real-time data to allocate and schedule parking spaces;

[0050] Parking space allocation and scheduling unit formulates specific parking space allocation and scheduling strategies according to the real-time predicted parking space occupancy;

[0051] Demand mode allocation unit: used for dividing the demand mode of different time periods into peak period and valley period based on the calculation result of the scheduling model formula;

[0052] Scheduling implementation unit: implements the formulated scheduling strategy into the parking management system.

[0053] Compared with the prior art, the present application has the following beneficial effects:

[0054] The application can predict the occupancy of parking spaces in each time period in the future by establishing a time series model based on historical data and influence parameters, can establish a parking space allocation and scheduling model according to the occupancy, completes the advance scheduling and analysis, makes the parking efficiency higher, and brings a better use prospect. BRIEF DESCRIPTION OF DRAWINGS

[0055] Fig. 1 is a step flow chart of the application;

[0056] Fig. 2 is a system framework diagram of the application. DETAILED DESCRIPTION

[0057] For a better understanding of the present application, various aspects of the present application will be described in more detail below with reference to the accompanying drawings. It is to be understood that the detailed description is merely descriptive of exemplary embodiments of the present application and is not intended to limit the scope of the present application in any way. Throughout the description, like reference numerals refer to like elements. The expression "and / or" includes any and all combinations of one or more of the associated listed items.

[0058] In the drawings, the size, dimensions, and shapes of the elements have been slightly adjusted for ease of illustration. The drawings are merely examples and are not strictly drawn to scale. As used in this document, the terms "approximately," "about," and similar terms are used as terms of approximation and not as terms of degree, and are intended to account for the inherent deviations in a measuring device or measuring methodology that would be recognized by those of ordinary skill in the art. In addition, in the present application, the order of the steps of the process described does not necessarily indicate the order in which the processes appear in actual operation, unless there is an explicit other limitation or can be derived from the context.

[0059] It should also be understood that expressions such as "include", "including", "have", "has", "contain" and / or "containing" and the like, are open-ended terms that are intended to mean that the listed elements are present, but that one or more other elements can also be present, in addition to the listed elements. In addition, when expressions such as "at least one of" appear after a list of elements, it modifies the entire list of elements and not just the individual elements in the list. In addition, when describing embodiments of the present application, the use of "may" means "one or more embodiments of the present application". And, the term "exemplary" is intended to mean an example or illustration.

[0060] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

[0061] It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0062] The present application provides a technical solution: a public parking space occupation prediction and scheduling method based on a traffic big model, the scheduling method comprising:

[0063] S1: obtaining sensor data on the parking space, including real-time vehicle entry and exit, parking space occupation data and historical data;

[0064] S2: establishing a time series model based on historical data and influence parameters to predict the occupation of the parking space in each future time period;

[0065] S3: establishing a parking space allocation and scheduling model according to the real-time and predicted parking space occupation;

[0066] S4: making real-time parking space scheduling decisions based on the parking space allocation and scheduling model.

[0067] Further, S1 specifically includes:

[0068] Configuring sensors to transmit real-time data to a data collection system;

[0069] Setting the sensor to upload data to the cloud platform regularly for data storage;

[0070] After the data arrives, real-time preprocessing is performed, which includes data cleaning, denoising and time series data processing;

[0071] Encryption and access control measures are taken during data transmission.

[0072] Further, S2 specifically includes:

[0073] Obtaining historical parking space occupation data, including timestamps and corresponding occupation;

[0074] Preliminary analysis of the data, including viewing time series graphs, viewing trends and seasonality;

[0075] Based on the data after preliminary analysis, a time series model is established to predict the occupation of the parking space in each future time period.

[0076] Further, based on the data after preliminary analysis, a time series model is established to predict the occupancy of parking spaces in each future time period, including:

[0077] The time series model formula is: t = c + g1J t-1 +…+g p J t-p +γ1ε t-1 +…+γ q ε t-q +ε t

[0078] In the formula, J t is the occupancy value of the parking space at time t, c is a constant term, g1…g p are influence parameters of past p observation values on the current value, J t-1 is the parking space occupancy value at time t-1, J t-p is the parking space occupancy value at time t-p, γ1…γ q are influences of errors at q lags on the current value, and ε t is white noise error.

[0079] Further, S3 specifically includes:

[0080] Real-time prediction is performed using the time series model, the prediction result of the parking space occupancy is generated based on the data at the current time, and the parking space allocation and scheduling are performed in combination with real-time data;

[0081] According to the real-time prediction of the parking space occupancy, a specific parking space allocation and scheduling strategy is formulated, the number of open parking spaces is increased and decreased based on the scheduling strategy, and the utilization rate of the parking lot is optimized;

[0082] The scheduling model formula is:

[0083] In the formula, C t is the number of open parking spaces at time t, J t is the predicted value of the occupancy of the parking space at time t, k is a regulation parameter, and round is a rounding function.

[0084] Further, based on the calculation result of the scheduling model formula, the demand patterns of different time periods are divided into

[0085] peak and low

[0086] valley periods;

[0087] For peak hours period t, predicted parking occupancy value J t Higher, set k = 1.2

[0088] For off-peak hours period t, predicted parking occupancy value J t Lower, set k = 0.8;

[0089] Implement the formulated scheduling strategy into the parking management system, ensuring real-time response and adjustment;

[0090] Continuously monitor real-time data and the accuracy of model predictions;

[0091] Collect user feedback and parking data to evaluate the effectiveness of the scheduling strategy.

[0092] Further, S4 specifically includes:

[0093] Update the actual number of open parking spaces in the parking lot;

[0094] Adjust the signs, indicators, and parking space allocation system to guide drivers to designated parking areas;

[0095] Monitor actual parking space usage and real-time demand to ensure the effectiveness of the scheduling strategy;

[0096] Analyze real-time data and the effectiveness of scheduling decisions, including parking space utilization and user satisfaction.

[0097] The public parking space occupancy prediction and scheduling system based on the traffic big model includes:

[0098] Data acquisition module: for acquiring sensor data on parking spaces, including real-time vehicle entry and exit conditions, parking space occupancy data, and historical data;

[0099] Parking space prediction module: the parking space prediction module is electrically connected with the data acquisition module, and the parking space prediction module is used to establish a time series model based on historical data and influence parameters to predict the occupancy of parking spaces in each future time period;

[0100] Parking space allocation and scheduling module: the parking space allocation and scheduling module is electrically connected with the parking space prediction module and the data acquisition module, and the parking space allocation and scheduling module is used to establish a parking space allocation and scheduling model according to real-time and predicted parking space occupancy;

[0101] Scheduling decision module: the scheduling decision module is electrically connected with the parking space allocation and scheduling module, the parking space prediction module, and the data acquisition module, and the scheduling decision module is used to make real-time parking space scheduling decisions based on the parking space allocation and scheduling model.

[0102] Further, the parking space prediction module includes:

[0103] The historical data acquisition module is used to acquire historical parking space occupancy data, including time stamps and corresponding occupancy conditions.

[0104] The data preliminary analysis module is used to preliminarily analyze the data, including viewing time series graphs, viewing trends and seasonality.

[0105] The parking space prediction module is used to establish a time series model based on the preliminarily analyzed data, and predict the occupancy conditions of parking spaces in each time period in the future.

[0106] Further, the parking space allocation and scheduling module comprises:

[0107] The prediction result acquisition unit is used to generate a prediction result of the parking space occupancy condition based on the data of the current time, and combine real-time data to allocate and schedule parking spaces.

[0108] The parking space allocation and scheduling unit formulates specific parking space allocation and scheduling strategies according to the real-time predicted parking space occupancy condition.

[0109] The demand mode allocation unit is used to divide the demand modes of different time periods into peak periods and trough periods based on the calculation results of the scheduling model formula.

[0110] The scheduling implementation unit implements the formulated scheduling strategies into the parking management system.

[0111] The use steps of the application are as follows:

[0112] Step 1: Configure the sensor to transmit real-time data to the data collection system.

[0113] Step 2: Set the sensor to periodically upload data to the cloud platform for data storage.

[0114] Step 3: After the data arrives, real-time preprocessing is performed, which includes data cleaning, denoising and time series data processing.

[0115] Step 4: Acquire historical parking space occupancy data, including time stamps and corresponding occupancy conditions.

[0116] Step 5: Preliminarily analyze the data, including viewing time series graphs, viewing trends and seasonality.

[0117] Step 6: Establish a time series model based on the preliminarily analyzed data, and predict the occupancy conditions of parking spaces in each time period in the future.

[0118] Step 7: Use the time series model to perform real-time prediction, generate a prediction result of the parking space occupancy condition based on the data of the current time, and combine real-time data to allocate and schedule parking spaces.

[0119] Step eight: Based on the real-time prediction of parking space occupancy, specific parking space allocation and scheduling strategies are developed, and the number of open parking spaces is increased or decreased based on the scheduling strategy to optimize the utilization of the parking lot;

[0120] Step nine: Update the actual number of open parking spaces in the parking lot;

[0121] Step ten: Adjust the signs, indicators and parking allocation system to guide drivers to designated parking areas;

[0122] Step eleven: Monitor the actual parking space usage and real-time demand to ensure the effectiveness of the scheduling strategy;

[0123] Step twelve: Collect user feedback to evaluate the parking experience.

[0124] It should be noted that the relational terms herein such as first and second and the like are used solely to distinguish one entity or action from another, without necessarily requiring or implying any such actual 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.

[0125] Although embodiments of the present application have been shown and described, it is to be understood that various modifications, substitutions, alternatives, and variations can be made in the embodiments without departing from the spirit and scope of the present application as defined by the appended claims and their equivalents.

Claims

1. A public parking space occupancy prediction and dispatching method based on a traffic large model, characterized in that, The scheduling method comprises: S1: Obtain sensor data on parking spaces, including real-time vehicle entry and exit conditions, parking space occupancy data, and historical data; S2: Based on historical data and influence parameters, establish a time series model to predict the occupancy of parking spaces in each future time period; S3: Based on real-time and predicted parking space occupancy, establish a parking space allocation and scheduling model; S4: Based on the parking space allocation and scheduling model, make real-time parking space scheduling decisions. 2.The traffic macro-model based public parking occupancy prediction and scheduling method according to claim 1, wherein, S1 specifically includes: Configure sensors to transmit real-time data to a data collection system; Set the sensor to upload data to the cloud platform regularly for data storage; After the data arrives, perform real-time preprocessing, which includes data cleaning, denoising, and time series data processing; Encryption and access control measures are taken during data transmission. 3.The traffic macro-model based public parking occupancy prediction and scheduling method according to claim 2, characterized in that, S2 specifically includes: Obtain historical parking space occupancy data, including timestamps and corresponding occupancy; Preliminary analysis of the data, including viewing time series graphs, viewing trends, and seasonality; Based on the preliminary analysis of the data, establish a time series model to predict the occupancy of parking spaces in each future time period.

4. The method of claim 3, wherein, Based on the preliminary analysis of the data, establish a time series model to predict the occupancy of parking spaces in each future time period Includes: Wherein, the time series model formula is: J t = c + g1J t-1 +…+g p J t-p +γ1∈ t-1 +…+γ q ∈ t-q +∈ t where J t is the occupancy value of the parking space at time t, c is a constant term, g1…g p are influence parameters of the observation values at the past p time points on the current value, J t-1 is the occupancy value of the parking space at time t-1, J t-p is the occupancy value of the parking space at time t-p, γ1…γ q is the influence of the error at the lag q time point on the current value, ∈ t is white noise error. 5.The traffic macro-model based public parking occupancy prediction and scheduling method according to claim 4, wherein, S3 specifically includes: Use the time series model for real-time prediction, generate a prediction result of parking space occupancy based on the current time data, and combine real-time data to allocate and schedule parking spaces; Based on the real-time prediction of parking space occupancy, develop specific parking space allocation and scheduling strategies, increase or decrease the number of open parking spaces based on the scheduling strategy, and optimize the utilization rate of the parking lot; The scheduling model formula is: In the formula, C t is the number of parking spaces opened in the time period t, J t is the predicted value of the occupancy value of the parking space at time t in the time series, k is an adjustment parameter, and round is a rounding function.

6. The public parking space occupancy prediction and scheduling method based on the traffic big model according to claim 5, characterized in that: Based on the calculation results of the scheduling model formula, the demand patterns in different time periods are divided into peak and valley periods; For the time period t of the peak hours, the predicted parking occupancy value J t Higher, set k = 1.2 For the time period t of the low valley, the predicted parking occupancy value J t Lower, set k = 0.8; Implement the developed scheduling strategy into the parking management system to ensure real-time response and adjustment; Continuously monitor the accuracy of real-time data and model prediction; Collect user feedback and parking data to evaluate the effectiveness of the scheduling strategy.

7. The method of claim 6, wherein the method further comprises: S4 specifically includes: Update the actual number of open parking spaces in the parking lot; Adjust the signs, indicators, and parking space allocation system to guide drivers to designated parking areas; Monitor the actual parking space usage and real-time demand to ensure the effectiveness of the scheduling strategy; Analyze real-time data and scheduling decisions, including parking space utilization and user satisfaction.

8. A public parking space occupancy prediction and dispatching system based on a traffic macro model, characterized in that: The prediction and scheduling system comprises: A data acquisition module for acquiring sensor data on parking spaces, including real-time vehicle entry and exit conditions, parking space occupancy data, and historical data; A parking space prediction module electrically connected to the data acquisition module, the parking space prediction module is used to establish a time series model based on historical data and influence parameters to predict the occupancy of parking spaces in each future time period; Parking space allocation scheduling module: the parking space allocation scheduling module is electrically connected with the parking space prediction module and the data acquisition module, and is used for establishing a parking space allocation scheduling model according to real-time and predicted parking space occupation conditions; Scheduling decision module: the scheduling decision module is electrically connected with the parking space allocation scheduling module, the parking space prediction module and the data acquisition module, and is used for making real-time parking space scheduling decisions based on the parking space allocation scheduling model. 9.The public parking occupancy prediction and dispatching system based on traffic big model according to claim 8, wherein, The parking space prediction module comprises: A historical data acquisition module: used for acquiring historical parking space occupation data, including time stamps and corresponding occupation conditions; A data preliminary analysis module: used for preliminarily analyzing data, including viewing time series graphs, viewing trends and seasonality; A parking space prediction module: used for establishing a time series model based on the preliminarily analyzed data to predict the occupation conditions of parking spaces in each time period in the future. 10.The public parking occupancy prediction and scheduling system based on traffic big model according to claim 8, wherein, The parking space allocation scheduling module comprises: A prediction result acquisition unit: used for generating a prediction result of parking space occupation conditions based on current time data, combining real-time data to allocate and schedule parking spaces; A parking space allocation scheduling unit formulates specific parking space allocation and scheduling strategies according to real-time predicted parking space occupation conditions; A demand mode allocation unit: used for dividing demand modes of different time periods into peak and off-peak periods based on calculation results of the scheduling model formula; A scheduling implementation unit: implements the formulated scheduling strategies into a parking management system.

Images