Urban planning design method and system

Abstract

The invention discloses an urban planning design method and system, and relates to the technical field of urban planning, and the method specifically comprises the following steps: determining a key traffic flow line and a potential congestion point of an underground parking lot entrance in a business district of an urban center in the shopping peak period of festivals and holidays, configuring a traffic flow information collection system, and defining a traffic flow information collection rule; acquiring and storing traffic flow information of the traffic flow at the shopping peak in festivals and holidays; the stored traffic flow information is analyzed, the adjustment requirement and the congestion condition of the parking lot entrance traffic flow line in the peak period are evaluated, and the parking lot entrance traffic flow line is dynamically optimized according to the evaluation result; in the vehicle flow line optimization process, the vehicle flow information is updated in real time, the vehicle flow line adjustment demand and the congestion condition are periodically recalculated, and the vehicle flow line optimization scheme is dynamically adjusted. According to the invention, the problem of unbalance of the traffic flow line in the peak period is solved, and the traffic efficiency and traffic mobility of the parking lot entrance are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of urban planning, and in particular to an urban planning design method and system. Background Art

[0004] The prior art has the following deficiencies:

[0005] During the peak shopping season during holidays, when a large number of vehicles rush into the underground parking lots in the city center business district in a short period of time, there will be a serious imbalance in the flow of traffic at the entrance. Due to the sharp increase in traffic volume and the concentration of entry time, the existing urban planning and design technology usually relies on the average traffic volume for traffic flow design, but ignores the dynamic changes in traffic flow under special circumstances such as peak hours, resulting in the inability of the traffic dispatching system at the entrance of the parking lot to cope with the sudden surge in traffic. This will cause vehicles to queue and congest for a long time at the entrance of the parking lot, and the efficiency of entry and exit will be greatly reduced. At the same time, it may cause traffic accidents or cause traffic disorder on the roads around the business district. In addition, long-term vehicle detention will also lead to increased exhaust emissions, have a negative impact on air quality, and further aggravate environmental pollution problems. In this case, the failure of existing technologies will seriously affect traffic management and environmental protection during the shopping peak period, resulting in a decrease in the overall urban operation efficiency.

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0007] The purpose of the present invention is to provide an urban planning and design method and system to solve the problems in the above-mentioned background technology.

[0008] In order to achieve the above object, the present invention provides the following technical solution: an urban planning design method, specifically comprising the following steps:

[0009] During the peak shopping season during holidays, determine the key traffic flow lines and potential congestion points at the entrances of underground parking lots in the city center business district, configure the traffic information collection system, and define the traffic information collection rules;

[0010] Obtain and store traffic information during holiday shopping peak periods;

[0011] Analyze the stored traffic flow information, evaluate the adjustment needs and congestion of the parking lot entrance traffic flow lines during peak hours, and dynamically optimize the parking lot entrance traffic flow lines based on the evaluation results;

[0012] During the traffic flow optimization process, the traffic flow information is updated in real time, the traffic flow adjustment demand and congestion situation are recalculated regularly, and the traffic flow optimization plan is adjusted dynamically;

[0013] Generate traffic flow reports regularly, monitor the effect of traffic flow adjustment at the entrance of the underground parking lot during peak hours in real time based on the report content, and put forward optimization suggestions.

[0014] Preferably, the stored traffic flow information is analyzed to evaluate the adjustment demand and congestion of the traffic flow line at the parking lot entrance during peak hours, and the traffic flow line at the parking lot entrance is dynamically optimized according to the evaluation results, specifically including the following steps:

[0015] Extracting traffic pressure information, congestion diffusion information and traffic line adjustment information from the stored traffic information, and performing preprocessing after extraction;

[0016] Analyze the pre-processed traffic pressure information, congestion diffusion information and traffic line adjustment information to generate the traffic pressure coefficient, congestion diffusion index and traffic line adjustment coefficient respectively;

[0017] The generated traffic pressure coefficient, congestion diffusion index and traffic flow line adjustment coefficient are used to construct a traffic flow line optimization evaluation model to generate a traffic flow line optimization index;

[0018] Determine a preset threshold interval for the vehicle flow line optimization index, and compare the generated vehicle flow line optimization index with the threshold interval. According to the comparison results, evaluate the adjustment demand level and congestion level of the vehicle flow line at the parking lot entrance during peak hours, and dynamically optimize the vehicle flow line at the parking lot entrance according to the evaluation results.

[0019] Preferably, the logic for obtaining the traffic pressure coefficient is as follows:

[0020] Extract the vehicle arrival rate at different times within a period of time at the entrance of the parking lot, the maximum number of vehicles processed per unit time, the length of the vehicle queue and the corresponding time points from the pre-processed traffic pressure information, and represent the vehicle arrival rate and vehicle queue length at different times within a period of time at the entrance of the parking lot by functions A(t) and Q(t) respectively according to the time series, where t is the time point, A(t) represents the vehicle arrival rate at the entrance of the parking lot at time t within a period of time, Q(t) represents the length of the vehicle queue at the entrance of the parking lot at a time within a period of time, and the maximum number of vehicles processed per unit time at the entrance of the parking lot is calibrated as C, and the time period is defined as [t1, t2];

[0021] Calculate the traffic pressure coefficient. The specific calculation formula is as follows:

[0022]

[0023] Where TFPC is the traffic pressure coefficient, It is the ratio between the vehicle arrival rate at the parking lot entrance at different times within a period of time and the maximum number of vehicles processed by the parking lot entrance per unit time. It is an exponential function of the ratio of the length of the vehicle queue at the parking lot entrance at different times over a period of time to the maximum number of vehicles processed by the parking lot entrance per unit time.

[0024] Preferably, the acquisition logic of the congestion diffusion index is as follows:

[0025] Extract the entrance traffic density, average vehicle speed, average vehicle retention time and corresponding time points at different times within a period of time at the entrance of the parking lot from the preprocessed congestion diffusion information, and represent the entrance traffic density and average vehicle speed at different times within a period of time at the entrance of the parking lot by functions P(t) and V(t) respectively according to the time series, t is the time point, P(t) represents the traffic density at time t within a period of time at the entrance of the parking lot, V(t) represents the average vehicle speed at time t within a period of time at the entrance of the parking lot, define the time period as [t1, t2], and mark the average vehicle retention time at the entrance of the parking lot in the time period [t1, t2] as TS;

[0026] Calculate the congestion diffusion index. The specific calculation formula is as follows:

[0027]

[0028] Where CPI is the congestion diffusion index, is the ratio between the entrance traffic density and the average vehicle speed at different times during a period of time at the entrance of the parking lot. It represents the cumulative impact of changes in traffic density and speed on congestion diffusion at the entrance of a parking lot over a period of time.

[0029] Preferably, the acquisition logic of the vehicle flow line adjustment coefficient is as follows:

[0030] Extract the vehicle inflow time interval, vehicle outflow time interval, vehicle average waiting time and corresponding time points at different times within a period of time at the entrance of the parking lot from the pre-processed traffic line adjustment information, and represent the vehicle inflow time interval and vehicle outflow time interval at different times within a period of time at the entrance of the parking lot by functions TI(t) and TO(t) respectively according to the time series, where t is the time point, TI(t) represents the vehicle inflow time interval at time t within a period of time at the entrance of the parking lot, TO(t) represents the vehicle outflow time interval at time t within a period of time at the entrance of the parking lot, and the time period is defined as [t1, t2], and the average waiting time of vehicles within the time period [t1, t2] at the entrance of the parking lot is calibrated as TDD;

[0031] Calculate the vehicle flow adjustment coefficient. The specific calculation formula is as follows:

[0032]

[0033] Where AF is the traffic flow adjustment coefficient, It represents the ratio of the difference between the inflow time interval and the outflow time interval to the average waiting time.

[0034] Preferably, the generated traffic pressure coefficient, congestion diffusion index and traffic flow line adjustment coefficient are used to construct a traffic flow line optimization evaluation model to generate a traffic flow line optimization index, which specifically includes the following steps:

[0035] Collect several traffic pressure coefficients, several congestion diffusion indexes, several traffic flow adjustment coefficients and corresponding traffic flow optimization indexes generated in the past period of time, and calibrate them as TFPC m , CPI m , AF m and OI m , m represents the serial numbers of several traffic pressure coefficients, several congestion diffusion indexes, several traffic flow line adjustment coefficients and corresponding traffic flow line optimization indexes generated in the past period of time, m = 4, 5, 6, ..., h, h is a positive integer, and the data collected in the past period of time is formed into a historical data set;

[0036] The multivariate regression model is selected as the vehicle flow optimization evaluation model, and is trained through historical data sets to determine the value of the regression coefficient according to the formula:

[0037] OI m =β0+β1*TFPC m +β2*CPI m +β3*AF m

[0038] Where β0, β1, β2 and β3 are regression coefficients;

[0039] By minimizing the error between the predicted value and the actual value, the regression coefficient is optimized, and finally the values ​​of the regression coefficients β0, β1, β2 and β3 are determined;

[0040] The finally determined regression coefficient is used to construct the traffic flow optimization evaluation model, and the real-time generated traffic pressure coefficient TFPC, congestion diffusion index CPI and traffic flow adjustment coefficient AF are input to generate the traffic flow optimization index OI in real time.

[0041] Preferably, a preset traffic flow line optimization index threshold range [OI1, OI2] is determined, and the generated traffic flow line optimization index OI is compared with this threshold range [OI1, OI2]. According to the comparison result, the adjustment requirement level and congestion situation level of the traffic flow line at the parking lot entrance during the peak period are evaluated, and the traffic flow line at the parking lot entrance is dynamically optimized based on the evaluation result. The specific comparison and analysis are as follows:

[0042] If OI < OI1, the traffic flow pressure of the current traffic flow line at the parking lot entrance is small, then both the adjustment requirement level and congestion situation level of the traffic flow line at the parking lot entrance are at a low level, and there is no need to optimize the traffic flow line at the parking lot entrance;

[0043] If OI1 ≤ OI ≤ OI2, the traffic flow pressure of the current traffic flow line at the parking lot entrance is at a medium level, then both the adjustment requirement level and congestion situation level of the traffic flow line at the parking lot entrance are at a medium level, and it is necessary to optimize the traffic flow line at the parking lot entrance, specifically including adjusting the signal light duration and temporarily increasing the diversion measures;

[0044] If OI > OI2, the traffic flow pressure of the current traffic flow line at the parking lot entrance is large, then both the adjustment requirement level and congestion situation level of the traffic flow line at the parking lot entrance are at a high level, and it is urgent to optimize the traffic flow line at the parking lot entrance, specifically including reconfiguring the entrance and exit channels, opening additional temporary channels, and implementing real-time emergency response measures.

[0045] Preferably, an urban planning and design system includes a traffic flow line key point identification module, a peak period traffic flow data collection and storage module, a traffic flow line demand evaluation and optimization module, a real-time traffic flow information update and dynamic adjustment module, and a traffic flow line monitoring and feedback optimization module;

[0046] The traffic flow line key point identification module determines the key traffic flow lines and potential congestion points at the underground parking lot entrance within the urban central business district during the peak period of holiday shopping, configures a traffic flow information collection system, and defines traffic flow information collection rules;

[0047] The peak period traffic flow data collection and storage module obtains the traffic flow information of the traffic flow during the peak period of holiday shopping and stores it;

[0048] The traffic flow line demand evaluation and optimization module analyzes the stored traffic flow information, evaluates the adjustment requirements and congestion situation of the traffic flow line at the parking lot entrance during the peak period, and dynamically optimizes the traffic flow line at the parking lot entrance according to the evaluation result;

[0049] The real-time traffic flow information update and dynamic adjustment module, during the process of optimizing the traffic flow line, updates the traffic flow information in real time, recalculates the traffic flow line adjustment requirements and congestion situation regularly, and dynamically adjusts the traffic flow line optimization plan;

[0050] The vehicle flow monitoring and feedback optimization module generates vehicle flow reports regularly, monitors the effect of vehicle flow adjustment at the entrance of the underground parking lot during peak hours in real time based on the report content, and puts forward optimization suggestions.

[0051] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0052] 1. The present invention can effectively evaluate and dynamically optimize the traffic flow lines at the entrances of underground parking lots in the city center business district by real-time collection, storage and analysis of traffic flow data during holiday shopping peaks. The calculation and application of the traffic pressure coefficient, congestion diffusion index and traffic flow line adjustment coefficient in the present invention ensure that the system can timely identify potential congestion points during peak periods, and respond to sudden traffic surges in real time by dynamically adjusting traffic flow lines. This real-time monitoring and feedback mechanism not only improves the traffic efficiency of vehicles, but also effectively reduces traffic congestion and accident risks caused by long-term vehicle queues.

[0053] 2. The present invention is highly adaptable and intelligent, especially in dealing with the surge in traffic during peak hours. Through the traffic flow optimization index generated by the multivariate regression model, the system can accurately predict and dynamically adjust the optimization requirements of the traffic flow, avoiding the lag and inefficiency caused by the reliance on average traffic flow design in traditional technologies. The present invention not only improves the traffic efficiency of the parking lot entrance, but also ensures the long-term effectiveness and sustainability of the solution by regularly generating reports and continuous optimization suggestions.

[0054] 3. The present invention seamlessly integrates data collection, real-time analysis, dynamic optimization and feedback mechanisms, making urban planning and design more flexible and responsive when dealing with complex traffic conditions during peak hours. Compared with traditional urban planning and design methods, the present invention pays more attention to real-time and dynamic adjustment, which can effectively alleviate traffic pressure during peak hours, reduce congestion time and environmental pollution, and thus significantly improve the overall operational efficiency and environmental quality of the city center area. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0056] Figure 1 The present invention is a flowchart of a city planning design method and system.

[0057] Figure 2 The present invention is a module schematic diagram of an urban planning and design method and system. DETAILED DESCRIPTION

[0058] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0059] The present invention provides Figure 1 The urban planning design method shown in the figure specifically comprises the following steps:

[0060] During the peak shopping season during holidays, determine the key traffic flow lines and potential congestion points at the entrances of underground parking lots in the city center business district, configure the traffic information collection system, and define the traffic information collection rules;

[0061] During the holiday shopping peak, the key traffic flow lines and potential congestion points at the entrances of underground parking lots in the city center business district can be determined through a series of data-driven analysis methods. First, through the analysis of historical traffic data, the main paths and high-frequency entry and exit points of peak traffic are identified, and the traffic flow line model is established with the help of big data analysis technology. Secondly, combined with real-time GPS data and traffic monitoring videos, traffic flow simulation software is used to dynamically analyze the driving paths and speed changes of vehicles in different time periods to determine the most common traffic flow lines during peak hours. At the same time, through the congestion detection algorithm, a multi-point sensor network is used to monitor the traffic speed and density near the parking lot entrance in real time, identify areas where the traffic speed drops significantly and the vehicle density increases suddenly, and accurately determine potential congestion points. This process can be achieved through traffic simulation models and algorithm optimization tools to ensure that the identification of traffic flow lines and congestion points can be accurately completed in the complex traffic environment during peak hours.

[0062] Configuring the traffic information collection system and defining traffic information collection rules are key steps to ensure the accuracy of traffic monitoring and analysis during peak hours. By setting up the system, it is possible to capture information such as vehicle entry and exit, flow, speed, and path in real time, providing accurate basic data for subsequent analysis and optimization. The specific implementation method includes deploying multiple types of sensors, such as cameras, ground sensor coils, and wireless transmission equipment at the entrance of the parking lot and its surrounding roads to capture and transmit detailed traffic information. At the same time, combined with license plate recognition technology and GPS positioning data, the collected information is accurate and timely. When defining the collection rules, it is necessary to clarify the frequency, scope, and filtering conditions of data collection, such as high-frequency data collection during peak hours and filtering out noise data to ensure the high quality and relevance of the collected information. These rules can be set by writing parameter configuration files of the collection system or through a graphical user interface, so that the system can flexibly adapt to different peak scenarios and provide accurate data support.

[0063] During the peak shopping season during holidays, the key traffic flow lines and potential congestion points at the entrances of underground parking lots in the city center business district are identified, and a traffic information collection system is configured and collection rules are defined in order to achieve accurate monitoring and optimized management of traffic flow dynamics during peak periods. By identifying key traffic flow lines and potential congestion points, we can know in advance where traffic will be concentrated and in which time periods, so as to deploy the collection system in a targeted manner and ensure that the most representative and practical traffic information is obtained. After real-time collection and analysis, this information can provide accurate data support for the dynamic optimization of traffic flow lines, help the system to adjust the duration of traffic lights and change the order of entrances in a timely manner to alleviate potential congestion problems. In this way, the technical solution can effectively respond to the sudden increase in traffic, reduce congestion at the entrance of the parking lot, improve the efficiency of vehicle entry and exit, and ultimately achieve intelligent management of urban traffic during peak periods.

[0064] Obtain and store traffic information during holiday shopping peak periods;

[0065] During the peak shopping season during holidays, traffic information can be obtained in a variety of ways to ensure the comprehensiveness and accuracy of the data. First, high-precision cameras and ground-sensing coil sensors are deployed at the entrance of the parking lot and its surrounding roads to capture data such as vehicle entry and exit times, vehicle speeds, and traffic volume in real time. These devices can automatically detect vehicle movement and generate key information such as timestamps, vehicle types, and vehicle speeds. Secondly, GPS positioning and license plate recognition technology are used to obtain the specific driving paths of vehicles and flow information in and out of the parking lot. In addition, the traffic density and queue length inside and outside the parking lot can be monitored in real time through wireless sensor networks. Traffic information specifically includes vehicle arrival rate, maximum capacity, vehicle queue length, traffic density, average speed, vehicle detention time, inflow time interval, outflow time interval, and average waiting time of vehicles. This information is automatically summarized by the data acquisition system and transmitted as real-time data to the central management system for further analysis.

[0066] After the traffic flow information is acquired, it needs to be stored in an efficient data storage system for subsequent analysis and processing. First, the collected real-time traffic flow information will be directly transmitted to the central server or cloud database through a wireless network or wired connection. In the process of data storage, distributed database technology, such as NoSQL database, is used to ensure high concurrent processing capabilities and fast access speed of data. Data storage adopts a structured method to store different types of traffic flow information (such as traffic pressure information, congestion diffusion information, and line adjustment information) in the database according to a predefined field format for subsequent rapid query and analysis. In addition, in order to improve the reliability and security of the data, data redundancy and encryption technology can be used to store traffic flow information in multiple backup nodes, and data backup can be performed regularly to prevent information loss or damage. During the storage process, the system automatically performs data verification and formatting to ensure the consistency and integrity of the information.

[0067] Analyze the stored traffic flow information, evaluate the adjustment needs and congestion of the parking lot entrance traffic flow lines during peak hours, and dynamically optimize the parking lot entrance traffic flow lines based on the evaluation results;

[0068] In this embodiment, the stored traffic flow information is analyzed to evaluate the adjustment demand and congestion of the traffic flow line at the parking lot entrance during peak hours, and the traffic flow line at the parking lot entrance is dynamically optimized according to the evaluation results, specifically including the following steps:

[0069] Extracting traffic pressure information, congestion diffusion information and traffic line adjustment information from the stored traffic information, and performing preprocessing after extraction;

[0070] Extracting traffic pressure information, congestion diffusion information, and traffic line adjustment information from stored traffic information can be achieved by building an efficient data query and extraction mechanism. First, the system can quickly locate and extract relevant information based on conditions such as timestamps, location identifiers, and data types through pre-defined query commands. Using the query language of SQL or NoSQL databases, the required traffic information can be efficiently extracted from the storage unit, and the system will extract data from the database to the analysis and processing module based on these query conditions. When extracting data specifically, the system can obtain data in batches or in real time, such as batch extracting all traffic information within a peak period according to a time window, or extracting the latest traffic data through a real-time data stream. In order to ensure the accuracy and efficiency of the extraction, the system can also use a cache mechanism to temporarily store commonly used or recent data in a fast-access cache area to reduce the time delay for extracting data from the main storage unit.

[0071] Preprocessing is to ensure that the extracted traffic information is of high quality and consistency during the analysis and evaluation process. First, preprocessing helps to remove noise and outliers in the data, which may be inaccurate data due to sensor failure, communication errors, etc. Preprocessing also includes standardization of data formats, such as unifying data from different sources into the same time format, unit and precision so that subsequent analysis can be carried out under consistent standards. The specific preprocessing process includes the application of noise filtering algorithms, the removal or correction of abnormal vehicle speed and flow data, and interpolation methods to fill in the gaps caused by data loss. At the same time, data standardization will adjust the data to a unified scale and range through conversion and normalization, ensuring that different types of traffic information can be effectively analyzed under the same framework. After preprocessing is completed, the data will enter the subsequent analysis in a clean, standardized and formatted state, improving the accuracy and reliability of the traffic flow optimization evaluation model.

[0072] Analyze the pre-processed traffic pressure information, congestion diffusion information and traffic line adjustment information to generate the traffic pressure coefficient, congestion diffusion index and traffic line adjustment coefficient respectively;

[0073] The generated traffic pressure coefficient, congestion diffusion index and traffic flow line adjustment coefficient are used to construct a traffic flow line optimization evaluation model to generate a traffic flow line optimization index;

[0074] Determine a preset threshold interval for the vehicle flow line optimization index, and compare the generated vehicle flow line optimization index with the threshold interval. According to the comparison results, evaluate the adjustment demand level and congestion level of the vehicle flow line at the parking lot entrance during peak hours, and dynamically optimize the vehicle flow line at the parking lot entrance according to the evaluation results.

[0075] Determining the pre-set threshold interval of the vehicle flow optimization index can be achieved through historical data analysis, simulation and comprehensive evaluation of the expert system. First, the system will collect a large amount of historical traffic data, especially the traffic conditions at the entrance of the parking lot during peak hours, including data such as the past traffic pressure coefficient, congestion diffusion index and traffic flow adjustment coefficient. Through statistical analysis tools, cluster analysis and regression analysis are performed on these historical data to identify the range and change trend of common vehicle flow optimization indexes. Next, traffic simulation software is used to simulate the traffic flow conditions under different peak scenarios to further verify and adjust the rationality of the threshold interval. On this basis, combined with the experience of traffic management experts, the expert system is used to revise and optimize the thresholds set initially, and finally determine a set of vehicle flow optimization index threshold intervals that can reflect historical trends and respond to future emergencies. This process can be achieved through software automation, including the integration of data analysis, simulation and expert advice to ensure the scientificity and effectiveness of the threshold interval.

[0076] In this embodiment, the logic for obtaining the traffic pressure coefficient is as follows:

[0077] Extract the vehicle arrival rate at different times within a period of time at the entrance of the parking lot, the maximum number of vehicles processed per unit time, the length of the vehicle queue and the corresponding time points from the pre-processed traffic pressure information, and represent the vehicle arrival rate and vehicle queue length at different times within a period of time at the entrance of the parking lot by functions A(t) and Q(t) respectively according to the time series, where t is the time point, A(t) represents the vehicle arrival rate at the entrance of the parking lot at time t within a period of time, Q(t) represents the length of the vehicle queue at the entrance of the parking lot at a time within a period of time, and the maximum number of vehicles processed per unit time at the entrance of the parking lot is calibrated as C, and the time period is defined as [t1, t2];

[0078] Extracting the arrival rate of parking lot entrance vehicles, the maximum number of vehicles processed, the length of vehicle queues, and the corresponding time points from the preprocessed traffic pressure information can be achieved by building an efficient data query and extraction mechanism. First, the system will extract relevant data from the data storage unit through the SQL query language or the query command of the NoSQL database according to the pre-set query conditions, such as time period, data type, and the identification of the specific monitoring point. In the specific extraction process, the system will obtain the vehicle arrival rate, the maximum number of vehicles processed by the parking lot, and the length of the vehicle queue within a period of time in batches or in real time according to the set time window and parameter type. After extraction, these data will be automatically loaded into the memory for further processing to ensure that they can be quickly applied to subsequent analysis and calculation processes. In addition, in order to improve the efficiency of data extraction, the system can adopt a cache mechanism to temporarily store frequently queried data in the cache area so that the required data can be quickly accessed and extracted in subsequent queries.

[0079] Calculate the traffic pressure coefficient. The specific calculation formula is as follows:

[0080]

[0081] Where TFPC is the traffic pressure coefficient, It is the ratio between the vehicle arrival rate at the parking lot entrance at different times within a period of time and the maximum number of vehicles processed by the parking lot entrance per unit time. It is an exponential function of the ratio of the length of the vehicle queue at the parking lot entrance at different times over a period of time to the maximum number of vehicles processed by the parking lot entrance per unit time.

[0082] This expression represents the ratio between the arrival rate of vehicles at the parking lot entrance at time t, A(t), and the maximum number of vehicles C that the parking lot entrance can process per unit time. It reflects the relationship between the actual vehicle flow and the parking lot entrance processing capacity at a specific point in time. If the ratio is close to or greater than 1, it means that the vehicle arrival rate is close to or exceeds the parking lot processing capacity, indicating that congestion may occur.

[0083] This expression represents an exponential function of the ratio of the length of the vehicle queue Q(t) to the maximum number of vehicles C that can be processed per unit time at the parking lot entrance. The use of the exponential function indicates that as the length of the vehicle queue increases, the traffic pressure will increase exponentially. This expression emphasizes the nonlinear effect of the queue length on the parking lot entrance pressure, and longer queue lengths will have a greater impact on traffic pressure.

[0084] The calculation formula of the traffic pressure coefficient comprehensively considers the ratio of traffic volume to parking lot processing capacity within a time period. and the nonlinear effect of vehicle queue length By integrating the traffic pressure in the time period [t1, t2], the formula can accumulate the pressure values ​​at different times to reflect the overall traffic conditions. This calculation method can not only capture the instantaneous pressure, but also integrate and accumulate the pressure changes at different time points, thereby providing a more comprehensive pressure assessment. The introduction of the exponential function ensures that the queue length plays a significant role in the pressure assessment, and strengthens the sensitivity and accuracy of the formula to the actual traffic conditions.

[0085] The size of the traffic pressure coefficient directly reflects the traffic load at the parking lot entrance during peak hours, and is closely related to the adjustment demand level of the traffic flow line and the congestion level. When the traffic pressure coefficient is small, it means that the traffic volume at the parking lot entrance basically matches the processing capacity, the queue length is short, and usually there is no need to make major adjustments to the traffic flow line, and the congestion is relatively mild. When the traffic pressure coefficient is large, it means that the vehicle arrival rate is close to or exceeds the processing capacity of the parking lot, and the queue length increases significantly. At this time, more active adjustments to the traffic flow line are required to prevent or alleviate serious congestion. Therefore, the traffic pressure coefficient can be used as an important basis for evaluating and judging whether the parking lot entrance needs to adjust the traffic flow line during peak hours and the severity of congestion.

[0086] In this embodiment, the logic for obtaining the congestion diffusion index is as follows:

[0087] Extract the entrance traffic density, average vehicle speed, average vehicle retention time and corresponding time points at different times within a period of time at the entrance of the parking lot from the preprocessed congestion diffusion information, and represent the entrance traffic density and average vehicle speed at different times within a period of time at the entrance of the parking lot by functions P(t) and V(t) respectively according to the time series, t is the time point, P(t) represents the traffic density at time t within a period of time at the entrance of the parking lot, V(t) represents the average vehicle speed at time t within a period of time at the entrance of the parking lot, define the time period as [t1, t2], and calibrate the average vehicle retention time at the entrance of the parking lot in the time period [t1, t2] as tS;

[0088] Extracting the entrance traffic density, average speed, average vehicle retention time and their corresponding time points from the preprocessed congestion diffusion information can be achieved by building an automated data query system. First, the system will extract relevant data from the data storage unit through the SQL query language or the query command of the NoSQL database according to the pre-set conditions, such as time period, data type and identification of the specific monitoring point. The system can set a timed or real-time query strategy to automatically extract the traffic density, average speed and vehicle retention time data at different times within a specified time interval (such as every minute or every hour). In the specific extraction process, the system will arrange these data according to the time series at time t to form a complete time series data set. The extracted data will be loaded into the memory for further processing and analysis to ensure that it can be quickly applied to subsequent calculations. In addition, in order to improve the efficiency and accuracy of data extraction, the system can combine caching technology to temporarily store commonly used data in the cache area to reduce the time delay of extracting data from the main storage unit and ensure the consistency and integrity of the data.

[0089] Calculate the congestion diffusion index. The specific calculation formula is as follows:

[0090]

[0091] Where CPI is the congestion diffusion index, is the ratio between the entrance traffic density and the average vehicle speed at different times during a period of time at the entrance of the parking lot. It represents the cumulative impact of changes in traffic density and speed on congestion diffusion at the entrance of a parking lot over a period of time.

[0092] This expression represents the reciprocal of the average detention time TS of vehicles in a specific time period. This reciprocal is used to weight the calculation of the congestion diffusion index, indicating that the shorter the vehicle detention time, the greater the impact of congestion diffusion may be, and vice versa. By using the reciprocal, the formula emphasizes the importance of detention time in congestion assessment.

[0093] This expression represents the ratio between the traffic density P(t) and the average vehicle speed V(t) at time t. It is used to evaluate the relationship between vehicle density and flow speed at a specific point in time. The larger the ratio, the higher the traffic density and the lower the speed, and the more serious the risk of congestion.

[0094] This expression represents the cumulative impact of the ratio of traffic density to speed in the time period [t1, t2], and is processed by the logarithmic function ln. The use of the logarithmic function helps to smooth the cumulative impact and avoid excessive influence of extreme values ​​on the final result, while also ensuring the sensitivity of the exponent to changes in a small range. The overall meaning of this expression is to evaluate the impact of changes in traffic density and speed on congestion diffusion in a given time period.

[0095] The calculation formula of the congestion diffusion index comprehensively considers the relationship between the average detention time of vehicles in a time period, traffic density, and vehicle speed. First, the inverse of the vehicle detention time is used to weight the index, indicating that the risk of congestion diffusion is higher when the detention time is shorter. Then, the formula calculates the cumulative impact of the ratio of traffic density to speed in the time period by integration, reflecting the dynamic changes of congestion diffusion. Finally, through the processing of the logarithmic function ln, the formula smoothes the cumulative impact and provides a more robust congestion diffusion index for evaluating and predicting the congestion diffusion of parking lot entrances during peak hours.

[0096] The size of the congestion diffusion index directly reflects the dynamic relationship between the traffic density and vehicle flow speed at the parking lot entrance during peak hours, and is closely related to the adjustment demand level of the traffic flow line and the congestion level. When the congestion diffusion index is small, it means that the traffic density is low and the vehicle flow speed is relatively fast, indicating that the current traffic flow line can cope with the traffic volume well. At this time, the congestion risk at the parking lot entrance is low, and it is usually not necessary to adjust the traffic flow line significantly. However, when the congestion diffusion index is large, it means that the traffic density increases and the vehicle flow speed slows down significantly, indicating that the traffic flow line cannot effectively disperse the traffic flow, and congestion may spread rapidly in a short time. At this time, it is necessary to quickly optimize and adjust the traffic flow line, such as reconfiguring the traffic order of the entrance and exit or opening additional temporary channels to avoid or alleviate potential congestion. The congestion diffusion index can therefore be used as a key indicator to help decision makers evaluate the traffic conditions at the parking lot entrance during peak hours and make timely traffic line adjustments to maintain smooth traffic.

[0097] In this embodiment, the logic for obtaining the vehicle flow line adjustment coefficient is as follows:

[0098] Extract the vehicle inflow time interval, vehicle outflow time interval, vehicle average waiting time and corresponding time points at different times within a period of time at the entrance of the parking lot from the pre-processed traffic line adjustment information, and represent the vehicle inflow time interval and vehicle outflow time interval at different times within a period of time at the entrance of the parking lot by functions TI(t) and TO(t) respectively according to the time series, where t is the time point, TI(t) represents the vehicle inflow time interval at time t within a period of time at the entrance of the parking lot, TO(t) represents the vehicle outflow time interval at time t within a period of time at the entrance of the parking lot, and the time period is defined as [t1, t2], and the average waiting time of vehicles within the time period [t1, t2] at the entrance of the parking lot is calibrated as TDD;

[0099] Extracting the vehicle inflow time interval, vehicle outflow time interval, vehicle average waiting time and their corresponding time points from the pre-processed traffic line adjustment information can be achieved through an automated data query and processing system. First, the system will use the database query language (such as SQL) to extract relevant information from the data storage unit according to the pre-set query conditions, such as time period, monitoring point identification and data type. The system will set a timed or real-time query strategy to automatically extract the vehicle inflow time interval, vehicle outflow time interval, and vehicle average waiting time data at different times within the specified time period. In the specific extraction process, the system will arrange these data in order according to the time series and load them into the memory for further processing. The extracted data will also undergo format standardization and consistency checks to ensure the integrity and accuracy of the data so that it can be directly applied to subsequent calculations and analysis links. In order to improve query efficiency, the system can combine caching technology to temporarily store commonly used or recent data in the cache, reduce time delays in the data extraction process, and ensure rapid data response and processing.

[0100] Calculate the vehicle flow adjustment coefficient. The specific calculation formula is as follows:

[0101]

[0102] Where AF is the traffic flow adjustment coefficient, It represents the ratio of the difference between the inflow time interval and the outflow time interval to the average waiting time.

[0103] This expression represents the ratio of the difference between the vehicle inflow time interval TI(t) and the vehicle outflow time interval TO(t) at the parking lot entrance at time t to the average vehicle waiting time TDD. This ratio reflects the difference in vehicle inflow and outflow speeds at a certain moment, and normalizes this difference with the average waiting time. Specifically, when the inflow time interval TI(t) is greater than the outflow time interval TO(t), the ratio is positive, indicating that the vehicle enters the parking lot faster, which may lead to an increase in waiting time; on the contrary, when TI(t) is less than TO(t), the ratio is negative, indicating that the vehicle outflow speed is faster, which may lead to a decrease in the parking lot entrance pressure. Therefore, this expression is used to evaluate whether the vehicle flow line at the parking lot entrance at different times needs to be adjusted.

[0104] The calculation formula of the vehicle flow adjustment coefficient is to calculate the ratio of the difference between the inflow time interval and the outflow time interval to the average waiting time in the time period [t1, t2], and square the ratio to emphasize the impact of large flow differences on the need for vehicle flow adjustment. Then, by integrating this square value, the difference in the entire time period is accumulated to reflect the balance state of the vehicle flow at the parking lot entrance during this period. Finally, the vehicle flow adjustment coefficient AF is calculated through the square root operation. This coefficient is used to quantify the degree of adjustment demand for the vehicle flow at the parking lot entrance. The higher the value, the greater the need for vehicle flow adjustment.

[0105] The size of the traffic flow adjustment coefficient directly reflects the balance of the time intervals between vehicle inflow and outflow at the parking lot entrance during peak hours, as well as the impact of this balance on the overall traffic flow. When the traffic flow adjustment coefficient is small, it means that the difference between the inflow and outflow time intervals is small, the flow of vehicles at the parking lot entrance is relatively smooth, and the average waiting time is stable, indicating that the existing traffic flow design can cope with the current traffic volume. At this time, the congestion risk at the parking lot entrance is low and the adjustment demand is small. However, when the traffic flow adjustment coefficient is large, it means that the difference between the inflow and outflow time intervals is significant, and the waiting time of vehicles may increase significantly due to the unbalanced traffic flow. In this case, the traffic flow at the parking lot entrance may not be able to effectively disperse the traffic flow, which is prone to cause serious congestion, especially during peak hours. Therefore, the traffic flow adjustment coefficient can be used as a key indicator to help managers evaluate and predict the traffic flow adjustment needs at the parking lot entrance during peak hours, and take timely measures to optimize the traffic flow design to avoid or alleviate congestion.

[0106] In this embodiment, the generated traffic pressure coefficient, congestion diffusion index and traffic flow line adjustment coefficient are used to construct a traffic flow line optimization evaluation model to generate a traffic flow line optimization index, which specifically includes the following steps:

[0107] Collect several traffic pressure coefficients, several congestion diffusion indexes, several traffic flow adjustment coefficients and corresponding traffic flow optimization indexes generated in the past period of time, and calibrate them as TFPC m , CPI m , AF m and OI m , m represents the serial numbers of several traffic pressure coefficients, several congestion diffusion indexes, several traffic flow line adjustment coefficients and corresponding traffic flow line optimization indexes generated in the past period of time, m = 4, 5, 6, ..., h, h is a positive integer, and the data collected in the past period of time is formed into a historical data set;

[0108] The automated data collection and storage system can be used to collect several traffic pressure coefficients, several congestion diffusion indexes, several traffic flow adjustment coefficients, and corresponding traffic flow optimization indexes generated in the past period of time. The specific implementation method is that the system pre-sets the time interval and conditions for data collection, obtains traffic information at each moment through real-time monitoring equipment and sensors, and then calculates the corresponding traffic pressure coefficient, congestion diffusion index, and traffic flow adjustment coefficient through the data processing module. Next, these data are stored in the database together with the corresponding traffic flow optimization index. The system can set a scheduled task to automatically collect and update these indicator data according to the specified time period to ensure the continuity and integrity of the data.

[0109] After collecting the traffic pressure coefficient, congestion diffusion index, traffic flow adjustment coefficient and traffic flow optimization index, the system arranges these data in chronological order or other specified order, and organizes them into a structured historical data set. The specific implementation method is to extract these data from the database through the data management system, and load them into the memory in the form of a table or array for formatting. The system will divide the data according to the set time period to ensure that each set of data sets contains various indicators within the corresponding time period. Finally, the processed data set will be stored in a specific file or database table in the system for subsequent regression model training and optimization.

[0110] The range of m is set to an integer greater than or equal to 4, which is based on the characteristics of the target equation and the requirements of regression analysis. Because there are four unknowns in the regression model (i.e., regression coefficients β0, β1, β2, and β3), according to the most basic linear equation solution, at least four independent sets of sample data are required to uniquely determine these regression coefficients. Therefore, the minimum value of m is 4 to ensure that the regression equation has enough data for calculation and solution. For more precise regression analysis, the value of m can be larger, and usually the system will automatically collect more sample data to improve the accuracy and robustness of the regression model.

[0111] The multivariate regression model is selected as the vehicle flow optimization evaluation model, and is trained through historical data sets to determine the value of the regression coefficient according to the formula:

[0112] OI m =β0+β1*TFPC m +β2*CPI m +β3*AF m

[0113] Where β0, β1, β2 and β3 are regression coefficients;

[0114] The multiple regression model is a statistical method used to analyze the impact of multiple independent variables (or explanatory variables) on a dependent variable (or response variable). In this model, the degree of influence of each independent variable on the dependent variable is determined by minimizing the error between the predicted value and the actual value, and a regression coefficient is assigned to each independent variable. The reason for choosing the multiple regression model as the traffic flow optimization evaluation model is that the model can simultaneously consider three important factors: traffic pressure coefficient, congestion diffusion index, and traffic flow adjustment coefficient, and quantify their combined impact on the traffic flow optimization index. This method can capture the relationship between multiple variables and provide a more accurate evaluation basis for subsequent optimization.

[0115] In the multiple regression model, the regression coefficients β0, β1, β2, and β3 respectively represent the degree of influence of each independent variable on the dependent variable. Specifically, β0 is the intercept term of the model, which represents the estimated value of the dependent variable when all independent variables are zero; β1 is the weight of the influence of the traffic pressure coefficient on the traffic flow optimization index; β2 is the weight of the influence of the congestion diffusion index on the traffic flow optimization index; β3 is the weight of the influence of the traffic flow adjustment coefficient on the traffic flow optimization index. By optimizing these regression coefficients, the model can accurately predict and evaluate the optimization needs of parking lot traffic flow during peak hours. The advantage of this method is that it can be trained with historical data and automatically adjust the coefficients to improve the prediction accuracy, so that the model can make more accurate judgments on the adjustment needs of the actual traffic flow.

[0116] By minimizing the error between the predicted value and the actual value, the regression coefficient is optimized, and finally the values ​​of the regression coefficients β0, β1, β2 and β3 are determined;

[0117] In a multiple regression model, optimizing the regression coefficients by minimizing the error between the predicted values and the actual values is to ensure the prediction accuracy of the model. Specifically, the purpose of minimizing the error is to find the optimal regression coefficients β0, β1, β2, and β3 such that the model can be closest to the actually observed vehicle flow line optimization index under the given inputs. This can be achieved by using optimization algorithms such as the gradient descent method. The software can iteratively adjust the regression coefficients to gradually reduce the mean squared error (MSE) between the predicted values and the actual values. In each iteration, the system calculates the difference between the predicted value and the actual value under the current regression coefficients and adjusts the values of the regression coefficients according to this difference until the error reaches the minimum, finally determining the optimal regression coefficients. This optimization process can be automated in the software to ensure that the model can adapt to the actual data and provide accurate prediction results.

[0118] Using the finally determined regression coefficients, for the constructed vehicle flow line optimization evaluation model, input the real-time generated traffic flow pressure coefficient TFPC, congestion diffusion index CPI, and vehicle flow line adjustment coefficient AF to generate the real-time vehicle flow line optimization index OI.

[0119] In this embodiment, determine the pre-set vehicle flow line optimization index threshold interval [OI1, OI2], and compare the generated vehicle flow line optimization index OI with this threshold interval [OI1, OI2]. According to the comparison results, evaluate the adjustment demand level and congestion situation level of the vehicle flow line at the parking lot entrance during the peak period, and dynamically optimize the vehicle flow line at the parking lot entrance according to the evaluation results. The specific comparison and analysis are as follows:

[0120] If OI < OI1, the traffic flow pressure at the current parking lot entrance vehicle flow line is small, then both the adjustment demand level and the congestion situation level of the parking lot entrance vehicle flow line are at a low level, and there is no need to optimize the parking lot entrance vehicle flow line;

[0121] When OI < OI1, it means that the traffic flow pressure at the current parking lot entrance is small, and the vehicle flow line can handle the traffic flow well. The evaluated adjustment demand level and congestion situation level are both at a low level. In this case, the vehicle flow at the parking lot entrance is smooth, and vehicles can enter and exit smoothly without obvious congestion risks. To maintain this state, the software can be set to have an automatic monitoring and regular evaluation function to continuously monitor the traffic flow situation and run basic traffic flow data analysis in the background to ensure that once the traffic flow situation changes, the system can issue a warning in a timely manner. At this time, no adjustment needs to be made to the vehicle flow line, and the system is mainly responsible for monitoring and data recording.

[0122] If OI1≤OI≤OI2, the current traffic pressure of the parking lot entrance traffic flow line is at a medium level, and the adjustment demand level and congestion level of the parking lot entrance traffic flow line are both medium. The parking lot entrance traffic flow line needs to be optimized, including adjusting the signal light duration and temporarily adding diversion measures;

[0123] When OI1≤OI≤OI2, it indicates that the traffic pressure at the entrance of the current parking lot is at a medium level, and local congestion may occur. The adjustment demand level and congestion level evaluated by the system are medium. At this time, the traffic flow needs to be moderately optimized to prevent the congestion from worsening. Real-time dynamic adjustment strategies can be set through software, such as adjusting the duration of traffic lights, controlling the speed of traffic, or starting temporary traffic guidance measures during periods of heavy traffic to optimize the distribution of traffic. Specific operations include using software to adjust traffic light control parameters, setting temporary traffic signs, or identifying potential congestion points in advance through traffic prediction models, and taking corresponding preventive measures.

[0124] If OI>OI2, the current traffic pressure of the parking lot entrance traffic flow line is high, and the adjustment demand level and congestion level of the parking lot entrance traffic flow line are both high. It is urgent to optimize the parking lot entrance traffic flow line, including reconfiguring the entrance and exit channels, opening additional temporary channels, and real-time emergency response measures.

[0125] When OI>OI2, it means that the traffic pressure at the entrance of the parking lot is relatively high, and the existing traffic flow line design can no longer effectively cope with the traffic flow during peak hours, which may lead to serious traffic congestion. At this time, it is necessary to take urgent and substantial optimization measures. Specific countermeasures include reconfiguring entrance and exit channels, such as temporarily changing some exits to entrances, opening additional temporary channels to divert traffic, or implementing temporary one-way measures. In addition, the system can also initiate emergency plans, increase the configuration of on-site traffic management personnel, and quickly respond to emergencies through real-time scheduling of intelligent traffic control systems to minimize the impact of congestion on overall traffic.

[0126] During the traffic flow optimization process, the traffic flow information is updated in real time, the traffic flow adjustment demand and congestion situation are recalculated regularly, and the traffic flow optimization plan is adjusted dynamically;

[0127] In the process of optimizing traffic flow, traffic information can be continuously updated by building an automated real-time monitoring system and data collection system. Specifically, the system collects traffic data in real time through cameras, sensors and license plate recognition equipment installed at the entrance and periphery of the parking lot, such as the time interval between vehicle inflow and outflow, vehicle retention time, traffic density and other information. These data will be transmitted to the central server for preprocessing, and combined with the previously calculated traffic pressure coefficient, congestion diffusion index and traffic flow adjustment coefficient, the system will recalculate the adjustment needs and congestion of the traffic flow at a set time interval (such as every minute or every hour). According to the latest traffic flow optimization index, the system will automatically adjust the signal light duration at the entrance of the parking lot, dynamically modify the traffic strategies of the entrance and exit, or enable temporary channels to achieve real-time optimization and management of traffic.

[0128] The reason for doing so is to ensure that the system can respond to sudden surges in traffic volume during peak hours in a timely manner and avoid traffic imbalance and congestion caused by the lag in traffic flow design. By updating traffic flow information in real time, the system can accurately reflect the current traffic conditions and adjust the traffic flow optimization plan in a timely manner based on the latest data to ensure that the traffic at the parking lot entrance can be effectively managed. Regularly recalculating the adjustment needs and congestion of traffic flow can dynamically optimize the traffic flow, reduce the time vehicles stay at the entrance, prevent long queues and congestion, and thus improve overall traffic efficiency. In addition, this method can also help managers discover potential traffic bottlenecks in advance, take preventive measures in a timely manner, and reduce the negative impact of emergencies during peak hours on the overall traffic order.

[0129] Generate traffic flow reports regularly, monitor the effect of traffic flow adjustment at the entrance of the underground parking lot during peak hours in real time based on the report content, and put forward optimization suggestions.

[0130] This step can be achieved through an automated data analysis and report generation system. First, the system automatically collects traffic data at the entrance of the parking lot on a regular basis (such as every hour or every day), including key indicators such as vehicle inflow and outflow time, queue length, and travel time. Then, the software analyzes this data through a built-in algorithm to generate a traffic flow report, which includes the performance of the current traffic flow, traffic flow trends, and congestion. After the report is generated, the system will compare the report content with the set threshold or historical data to monitor the effect of adjusting the traffic flow at the entrance of the underground parking lot during peak hours in real time. If the system detects that the performance of the traffic flow does not meet expectations, or there is a trend of increasing congestion, the system will automatically make optimization suggestions, such as adjusting the duration of traffic lights, reconfiguring entrance and exit channels, etc., and indicate these suggestions in the report for managers' reference.

[0131] The purpose of regularly generating traffic flow reports and monitoring the traffic flow adjustment effect at the entrance of the parking lot during peak hours in real time is to ensure that the system can quickly respond to changes in traffic volume during peak hours and avoid congestion. Through continuous data analysis and real-time monitoring, the system can promptly discover and respond to problems in the traffic flow, thereby optimizing the vehicle traffic path and reducing traffic pressure during peak hours. This approach not only improves the traffic efficiency at the entrance of the parking lot, but also effectively prevents traffic accidents and ensures the smooth operation of the underground parking lot and its surrounding roads. At the same time, the generation of regular reports and optimization suggestions enables managers to keep abreast of traffic conditions at all times, implement targeted adjustments, and maintain long-term improvements in overall traffic mobility.

[0132] like Figure 2 An urban planning and design system shown includes a vehicle flow line key point identification module, a peak period vehicle flow data collection and storage module, a vehicle flow line demand evaluation and optimization module, a real-time vehicle flow information update and dynamic adjustment module, and a vehicle flow line monitoring and feedback optimization module;

[0133] The key point identification module for traffic flow lines determines the key traffic flow lines and potential congestion points at the entrances of underground parking lots in the city center business district during the holiday shopping peak, configures the traffic information collection system, and defines the traffic information collection rules;

[0134] Peak traffic data collection and storage module, which obtains and stores traffic information during the holiday shopping peak period;

[0135] The vehicle flow demand assessment and optimization module analyzes the stored vehicle flow information, assesses the adjustment demand and congestion situation of the vehicle flow at the parking lot entrance during peak hours, and dynamically optimizes the vehicle flow at the parking lot entrance based on the assessment results;

[0136] Real-time traffic flow information update and dynamic adjustment module: During the traffic flow optimization process, the traffic flow information is updated in real time, the traffic flow adjustment demand and congestion situation are recalculated regularly, and the traffic flow optimization plan is adjusted dynamically;

[0137] The vehicle flow monitoring and feedback optimization module generates vehicle flow reports regularly, monitors the effect of vehicle flow adjustment at the entrance of the underground parking lot during peak hours in real time based on the report content, and puts forward optimization suggestions.

[0138] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0139] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center containing one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0140] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0141] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0142] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0143] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0144] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0145] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for urban planning and design, characterized in that: The specific steps include: During the peak shopping season during holidays, determine the key traffic flow lines and potential congestion points at the entrances of underground parking lots in the city center business district, configure the traffic information collection system, and define the traffic information collection rules; Obtain and store traffic information during holiday shopping peak periods; Analyze the stored traffic flow information, evaluate the adjustment needs and congestion of the parking lot entrance traffic flow lines during peak hours, and dynamically optimize the parking lot entrance traffic flow lines based on the evaluation results; During the traffic flow optimization process, the traffic flow information is updated in real time, the traffic flow adjustment demand and congestion situation are recalculated regularly, and the traffic flow optimization plan is adjusted dynamically; Generate traffic flow reports regularly, monitor the effect of traffic flow adjustment at the entrance of the underground parking lot during peak hours in real time based on the report content, and put forward optimization suggestions.

2. The urban planning and design method according to claim 1, characterized in that: The stored traffic flow information is analyzed to evaluate the adjustment demand and congestion of the traffic flow lines at the parking lot entrance during peak hours, and the traffic flow lines at the parking lot entrance are dynamically optimized according to the evaluation results, which specifically includes the following steps: Extracting traffic pressure information, congestion diffusion information and traffic line adjustment information from the stored traffic information, and performing preprocessing after extraction; Analyze the pre-processed traffic pressure information, congestion diffusion information and traffic line adjustment information to generate the traffic pressure coefficient, congestion diffusion index and traffic line adjustment coefficient respectively; The generated traffic pressure coefficient, congestion diffusion index and traffic flow line adjustment coefficient are used to construct a traffic flow line optimization evaluation model to generate a traffic flow line optimization index; Determine a preset threshold interval for the vehicle flow line optimization index, and compare the generated vehicle flow line optimization index with the threshold interval. According to the comparison results, evaluate the adjustment demand level and congestion level of the vehicle flow line at the parking lot entrance during peak hours, and dynamically optimize the vehicle flow line at the parking lot entrance according to the evaluation results.

3. The urban planning and design method according to claim 2, characterized in that: The logic for obtaining the traffic pressure coefficient is as follows: Extract the vehicle arrival rate at different times within a period of time at the entrance of the parking lot, the maximum number of vehicles processed per unit time, the length of the vehicle queue and the corresponding time points from the pre-processed traffic pressure information, and represent the vehicle arrival rate and vehicle queue length at different times within a period of time at the entrance of the parking lot by functions A(t) and Q(t) respectively according to the time series, where t is the time point, A(t) represents the vehicle arrival rate at the entrance of the parking lot at time t within a period of time, Q(t) represents the length of the vehicle queue at the entrance of the parking lot at time t within a period of time, and the maximum number of vehicles processed per unit time at the entrance of the parking lot is calibrated as C, and the time period is defined as [t1, t2]; Calculate the traffic pressure coefficient. The specific calculation formula is as follows: Where TFPC is the traffic pressure coefficient, It is the ratio between the vehicle arrival rate at the parking lot entrance at different times within a period of time and the maximum number of vehicles processed by the parking lot entrance per unit time. It is an exponential function of the ratio of the length of the vehicle queue at the parking lot entrance at different times over a period of time to the maximum number of vehicles processed by the parking lot entrance per unit time.

4. The urban planning and design method according to claim 3, characterized in that: The acquisition logic of the congestion diffusion index is as follows: Extract the entrance traffic flow density, average vehicle speed, average vehicle residence time, and corresponding time points at different moments within a period of time at the parking lot entrance from the preprocessed congestion diffusion information. Represent the entrance traffic flow density and average vehicle speed at different moments within a period of time at the parking lot entrance as functions P(t) and V(t) respectively according to the time series, where t is the time point, P(t) represents the traffic flow density at time t within a period of time at the parking lot entrance, and V(t) represents the average vehicle speed at time t within a period of time at the parking lot entrance. Define the time period as [t1, t2], and calibrate the average vehicle residence time within the time period [t1, t2] at the parking lot entrance as TS; Calculate the congestion diffusion index. The specific calculation formula is as follows: Where CPI is the congestion diffusion index, is the ratio between the entrance traffic density and the average vehicle speed at different times during a period of time at the entrance of the parking lot. It represents the cumulative impact of changes in traffic density and speed on congestion diffusion at the entrance of a parking lot over a period of time.

5. The urban planning and design method according to claim 4, characterized in that: The acquisition logic of the vehicle traffic flow line adjustment coefficient is as follows: Extract the vehicle inflow time interval, vehicle outflow time interval, average vehicle waiting time, and corresponding time points at different moments within a period of time at the parking lot entrance from the preprocessed traffic flow line adjustment information. Represent the vehicle inflow time interval and vehicle outflow time interval at different moments within a period of time at the parking lot entrance as functions TI(t) and TO(t) respectively according to the time series, where t is the time point, TI(t) represents the vehicle inflow time interval at time t within a period of time at the parking lot entrance, and TO(t) represents the vehicle outflow time interval at time t within a period of time at the parking lot entrance. Define the time period as [t1, t2], and calibrate the average vehicle waiting time within the time period [t1, t2] at the parking lot entrance as TDD; Calculate the vehicle traffic flow line adjustment coefficient. The specific calculation formula is as follows: Where AF is the traffic flow adjustment coefficient, It represents the ratio of the difference between the inflow time interval and the outflow time interval to the average waiting time.

6. The urban planning and design method according to claim 5, characterized in that: Construct a vehicle traffic flow line optimization evaluation model with the generated traffic flow pressure coefficient, congestion diffusion index, and vehicle traffic flow line adjustment coefficient, and generate a vehicle traffic flow line optimization index. The specific steps are as follows: Collect several traffic pressure coefficients, several congestion diffusion indexes, several traffic flow adjustment coefficients and corresponding traffic flow optimization indexes generated in the past period of time, and calibrate them as TFPC m 、CPI m , AF m and OI m , m represents the serial numbers of several traffic pressure coefficients, several congestion diffusion indexes, several traffic flow line adjustment coefficients and corresponding traffic flow line optimization indexes generated in the past period of time, m = 4, 5, 6, ..., h, h is a positive integer, and the data collected in the past period of time is formed into a historical data set; Select a multiple regression model as the vehicle traffic flow line optimization evaluation model, and train it through a historical data set to determine the values of the regression coefficients. According to the formula: OI m =β0+β1*TFPC m +β2*CPI m +β3*AF m In the formula, β0, β1, β2, and β3 are regression coefficients; Optimize the regression coefficients by minimizing the error between the predicted value and the actual value, and finally determine the values of the regression coefficients β0, β1, β2, and β3; Use the finally determined regression coefficients to input the real-time generated traffic flow pressure coefficient TFPC, congestion diffusion index CPI, and vehicle traffic flow line adjustment coefficient AF into the constructed vehicle traffic flow line optimization evaluation model to generate the real-time vehicle traffic flow line optimization index OI.

7. The urban planning and design method according to claim 6, characterized in that: Determine the preset vehicle traffic flow line optimization index threshold interval [OI1, OI2], compare the generated vehicle traffic flow line optimization index OI with this threshold interval [OI1, OI2], evaluate the adjustment demand level and congestion situation level of the vehicle traffic flow line at the parking lot entrance during the peak period according to the comparison result, and dynamically optimize the vehicle traffic flow line at the parking lot entrance according to the evaluation result. The specific comparison and analysis are as follows: If OI < OI1, the traffic flow pressure of the current vehicle traffic flow line at the parking lot entrance is small, then both the adjustment demand level and congestion situation level of the vehicle traffic flow line at the parking lot entrance are at a low level, and there is no need to optimize the vehicle traffic flow line at the parking lot entrance; If OI1≤OI≤OI2, the current traffic pressure of the parking lot entrance traffic flow line is at a medium level, and the adjustment demand level and congestion level of the parking lot entrance traffic flow line are both medium. The parking lot entrance traffic flow line needs to be optimized, including adjusting the signal light duration and temporarily adding diversion measures; If OI>OI2, the current traffic pressure of the parking lot entrance traffic flow line is high, and the adjustment demand level and congestion level of the parking lot entrance traffic flow line are both high. It is urgent to optimize the parking lot entrance traffic flow line, including reconfiguring the entrance and exit channels, opening additional temporary channels, and real-time emergency response measures.

8. An urban planning and design system, used to implement an urban planning and design method as described in any one of claims 1 to 7, characterized in that: It includes a vehicle flow line key point identification module, a peak period vehicle flow data collection and storage module, a vehicle flow line demand assessment and optimization module, a real-time vehicle flow information update and dynamic adjustment module, and a vehicle flow line monitoring and feedback optimization module; The key point identification module for traffic flow lines determines the key traffic flow lines and potential congestion points at the entrances of underground parking lots in the city center business district during the holiday shopping peak, configures the traffic information collection system, and defines the traffic information collection rules; Peak traffic data collection and storage module, which obtains and stores traffic information during the holiday shopping peak period; The vehicle flow demand assessment and optimization module analyzes the stored vehicle flow information, assesses the adjustment demand and congestion situation of the vehicle flow at the parking lot entrance during peak hours, and dynamically optimizes the vehicle flow at the parking lot entrance based on the assessment results; Real-time traffic flow information update and dynamic adjustment module: During the traffic flow optimization process, the traffic flow information is updated in real time, the traffic flow adjustment demand and congestion situation are recalculated regularly, and the traffic flow optimization plan is adjusted dynamically; The vehicle flow monitoring and feedback optimization module generates vehicle flow reports regularly, monitors the effect of vehicle flow adjustment at the entrance of the underground parking lot during peak hours in real time based on the report content, and puts forward optimization suggestions.

Images