Intelligent planning method and system for urban building parking areas based on pedestrian flow data

Abstract

The present invention discloses an intelligent planning method and system for parking areas of urban buildings based on pedestrian flow data, which relates to the field of building planning and solves the problem of inaccurate parking lot planning. The method comprises collecting historical pedestrian flow data and historical vehicle flow data of matching urban buildings of the same type as the target urban buildings in the previous quarter; analyzing the historical pedestrian flow data of the matching urban buildings in the previous quarter and dividing the matching urban buildings into first-category buildings or second-category buildings; performing category analysis on the matching urban buildings according to categories and obtaining the expected number of additional parking spaces for the matching urban buildings; formulating a parking lot planning scheme for the target urban building according to the expected number of additional parking spaces for the matching urban buildings and generating a planning completion signal or a pending signal; and receiving the pending signal or the planning completion signal corresponding to the target urban building. The present invention realizes accurate planning of parking lots of urban buildings.

Description

Technical Field

[0001] The present invention relates to the technical field of building planning, and in particular to an intelligent planning method and system for parking areas in urban buildings based on pedestrian flow data. Background Art

[0002] With the acceleration of urbanization and the rapid increase in urban motor vehicles, parking issues are becoming increasingly prominent. Traditional manually managed parking lots can no longer meet the efficiency, safety, performance, and management needs of users and managers. Parking difficulties not only cause inconvenience to car owners, but also exacerbate urban traffic congestion and affect the normal operation of cities. The construction and management of intelligent parking lots have become an important way to solve urban parking problems.

[0003] However, at present, when planning parking lots for urban buildings, traffic flow data is often used as the basis for planning and design. However, traffic flow data can only reflect the flow of vehicles, but cannot reflect parking demand. However, pedestrian flow data can more directly reflect people's travel needs and activity patterns. Therefore, planning and designing parking lots based on pedestrian flow can more accurately predict parking demand.

[0004] To this end, the present invention proposes an intelligent planning method and system for urban building parking areas based on pedestrian flow data. Summary of the Invention

[0005] The purpose of the present invention is to propose a method for automatically mapping the topology of an electric grid in an important power supply guaranteeing location, so as to solve the problems raised in the above background technology.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] In the first aspect, a method for intelligently planning parking areas in urban buildings based on pedestrian flow data comprises the following steps:

[0008] Step S1: Collect historical pedestrian and vehicle traffic data from the previous quarter for buildings of the same type as the target city buildings;

[0009] Step S2, analyzing the historical pedestrian flow data of the matching city buildings in the previous quarter, and classifying the matching city buildings into first category buildings or second category buildings;

[0010] Step S3, performing category analysis on the matching city buildings according to their categories to obtain the expected number of additional parking spaces for the matching city buildings;

[0011] Step S4: formulate a parking lot planning scheme for the target city building based on the expected number of additional parking spaces for the matching city building, and generate a planning completion signal or a pending signal.

[0012] Furthermore, the historical pedestrian flow data includes the number of people retained and the number of people commuting each day, and the historical vehicle flow data includes the number of vehicles commuting and the number of vehicles retained in the parking lot.

[0013] Furthermore, step S2 includes the following sub-steps:

[0014] Step S21, obtaining historical pedestrian flow data of the matching city building, and obtaining the number of commuting times of the corresponding matching city building every day in the previous quarter;

[0015] Step S22: add up the number of commutes per day in the previous quarter and take the average value to obtain the average number of commutes for the corresponding matching city building in the previous quarter;

[0016] Step S23, calculating the standard deviation of commuting of people in the corresponding matching city buildings in the previous quarter;

[0017] Step S24: The average number of commuters plus the standard deviation of commuting personnel is used as the first cutoff value, and the average number of commuters minus the standard deviation of commuting personnel is used as the second cutoff value; the first cutoff value is used as the right endpoint, and the second cutoff value is used as the left endpoint to obtain a screening interval for matching the historical pedestrian flow data corresponding to the city building;

[0018] Step S25: Compare the daily commuting times of the matching city building in the previous quarter with the screening interval; if the commuting times are within the screening interval, retain the historical passenger flow data for the corresponding days, and record the date corresponding to the retained historical passenger flow data as the retention date;

[0019] If the number of commuting times is outside the screening range, the historical passenger flow data for the corresponding days will be discarded.

[0020] Furthermore, the step S2 further includes the following sub-steps:

[0021] Step S26, obtaining the number of personnel commutes corresponding to the reserved days, and then obtaining the number of vehicle commutes corresponding to the reserved days;

[0022] Step S27: Add the number of commutes of people corresponding to the reserved days and take the average value to obtain the average number of commutes of people corresponding to the reserved days; add the number of commutes of vehicles corresponding to the reserved days and take the average value to obtain the average number of commutes of vehicles corresponding to the reserved days;

[0023] Step S28, calculating the correlation coefficient between human commuting and vehicle commuting;

[0024] Step S29, compare the correlation coefficient with the correlation coefficient threshold. If the correlation coefficient is greater than the correlation coefficient threshold, the corresponding matching city building is recorded as a first category building; if the correlation coefficient is less than the correlation threshold, the corresponding matching city building is recorded as a second category building.

[0025] Furthermore, step S3 includes the following sub-steps:

[0026] Step S31, performing a first category analysis on a first category of buildings;

[0027] Step S32: performing a second category analysis on the second category buildings.

[0028] Furthermore, the first category analysis includes the following steps:

[0029] Step S311, obtaining historical passenger flow data corresponding to the retention days of the first category of buildings, and obtaining the number of people retained in the matching city buildings for the retention days;

[0030] Step S312, drawing a personnel time distribution diagram corresponding to the first category of buildings based on the number of personnel retention corresponding to the retention days;

[0031] Step S313, obtaining a maximum value point based on the personnel time distribution graph, and recording the largest maximum value point as the peak point;

[0032] Step S314, obtaining the number of vehicles retained and the number of parking spaces in the parking lot corresponding to the maximum value point;

[0033] Step S315: If the number of retained vehicles is greater than or equal to the number of parking spaces in the parking lot, the corresponding maximum point is recorded as a calculated maximum point; if the number of retained vehicles is less than the number of parking spaces in the parking lot, the corresponding maximum point is recorded as a training maximum point.

[0034] Furthermore, the first category analysis further includes the following steps:

[0035] Step S316: Draw a retention correlation diagram based on the number of retained personnel and the number of retained vehicles corresponding to the training maximum value points of multiple retention days, and then perform function fitting based on the retention correlation diagram to obtain a corresponding correlation function expression;

[0036] Step S317: Substitute the number of personnel retention corresponding to the calculated maximum value point into the correlation function expression to calculate the expected number of vehicles retained corresponding to the calculated maximum value point; add up the multiple expected vehicle retention numbers and take the average value to obtain the average expected vehicle retention number;

[0037] Step S318: The expected number of additional parking spaces corresponding to the first category of buildings is obtained by subtracting the number of parking spaces in the parking lot from the average expected number of retained vehicles.

[0038] Furthermore, the second category analysis further includes the following steps:

[0039] Step S321, obtaining historical vehicle data corresponding to the retention days of the second category building, and obtaining the number of vehicles retained at different times corresponding to the retention days;

[0040] Step S322, obtaining the number of parking spaces in the parking lot corresponding to the second category building, and counting the congestion duration when the number of vehicles remaining in the second category building is greater than or equal to the number of parking spaces in the parking lot;

[0041] Step S323, the congestion rate of the corresponding retention days is obtained by dividing the congestion duration by the total duration of each day;

[0042] Step S324: add up the congestion rates of all the retained days and take the average value to obtain the parking lot congestion rate corresponding to the second category of buildings;

[0043] Step S325: Compare the parking lot congestion rate with the congestion rate threshold. If the parking lot congestion rate is greater than or equal to the first congestion rate threshold, add P1 parking spaces for the second category building. If the parking lot congestion rate is less than the first congestion rate threshold and greater than or equal to the second congestion rate threshold, add P2 parking spaces for the second category building. If the parking lot congestion rate is less than the second congestion rate threshold, no additional parking spaces are added.

[0044] Wherein, the first congestion rate threshold is greater than the second congestion rate threshold, 0<P1<P2;

[0045] In step S326 , P1 or P2 is recorded as the expected number of additional parking spaces corresponding to the second category of buildings.

[0046] Furthermore, step S4 includes the following sub-steps:

[0047] Step S41: Obtain the number of parking spaces in the parking lot corresponding to the matching city building and the expected number of additional parking spaces, and obtain the required number of parking spaces corresponding to the target city building by adding the number of parking spaces in the parking lot to the expected number of additional parking spaces;

[0048] Step S42: Obtain the floor area of ​​the preset parking lot corresponding to the building in the target city, and obtain the number of plannable parking spaces for the building in the target city by dividing the floor area of ​​the preset parking lot corresponding to the building in the target city by the floor area of ​​the standard parking spaces;

[0049] Step S43: If the number of available parking spaces is greater than or equal to the required number of parking spaces, then parking spaces are planned according to the preset parking lot; if the number of available parking spaces is less than the required number of parking spaces, then subsequent steps are executed;

[0050] Step S44, obtaining the existence of vacant areas on the road section where the target city building is located; if vacant areas exist, setting up temporary parking spaces in priority to the vacant areas; obtaining the floor area of ​​the vacant areas, and dividing the floor area of ​​the vacant areas by the floor area of ​​the standard parking spaces to obtain the number of additional parking spaces in the vacant areas.

[0051] Furthermore, the step S4 further includes the following sub-steps:

[0052] Step S45 , comparing the number of additional parking spaces in the vacant area with the expected number of additional parking spaces, and if the number of additional parking spaces in the vacant area is greater than or equal to the expected number of additional parking spaces, setting up temporary parking spaces in the vacant area;

[0053] If the number of additional parking spaces is less than the expected number of additional parking spaces, parking spaces will be supplemented by combining vacant areas with on-street parking spaces;

[0054] Step S46: When there is no vacant area, only on-street parking spaces are considered for supplementation;

[0055] Step S47: Count the total number of on-street parking spaces and vacant parking spaces. If the total number of actually added parking spaces is greater than or equal to the expected number of additional parking spaces, generate a planning completion signal.

[0056] Step S48: If the total number of parking spaces actually added is less than the expected number of parking spaces added, a pending signal is generated.

[0057] Secondly, an intelligent planning system for urban building parking areas based on pedestrian flow data, which includes:

[0058] The data collection module is used to collect the historical pedestrian and vehicle flow data of the buildings of the same type as the target city in the previous quarter, and send it to the pedestrian flow analysis module and the building analysis module;

[0059] A pedestrian flow analysis module is used to analyze the historical pedestrian flow data of the matching city buildings in the previous quarter, classify the matching city buildings into first-category buildings or second-category buildings, and send the data to the building analysis module;

[0060] The building analysis module is used to analyze the matching city buildings according to their categories, obtain the expected number of additional parking spaces for the matching city buildings, and send it to the parking space planning module;

[0061] The parking space planning module is used to formulate a parking lot planning scheme for the target city building based on the expected number of additional parking spaces for the matching city building, generate a planning completion signal or a pending signal and send it to the user terminal;

[0062] The user terminal is used to receive the pending signal or planning completion signal corresponding to the target city building.

[0063] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0064] 1. The present invention first collects historical pedestrian flow data and historical vehicle flow data of matching city buildings of the same type as the target city buildings in the previous quarter; then analyzes the historical pedestrian flow data of the matching city buildings in the previous quarter and classifies the matching city buildings into first-category buildings or second-category buildings; then, classifies the matching city buildings according to category to obtain the expected number of additional parking spaces for the matching city buildings. The present invention realizes the calculation of the expected number of additional parking spaces corresponding to the matching city buildings.

[0065] 2. The present invention first formulates a parking lot planning scheme for the target city building based on the expected number of additional parking spaces for the matching city building, generates a planning completion signal or a pending signal, and receives the pending signal or planning completion signal corresponding to the target city building. If it is a pending signal, the user decides whether to adopt the corresponding parking space addition scheme. The present invention realizes intelligent planning of the parking areas corresponding to the city buildings. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] To facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0067] Figure 1 is a flow chart of the method of the present invention;

[0068] Figure 2 It is the personnel time distribution diagram of the present invention;

[0069] Figure 3 It is the retained association diagram of the present invention;

[0070] Figure 4 This is a block diagram of the overall system of the present invention. DETAILED DESCRIPTION

[0071] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0072] Example 1: Please refer to Figure 1-Figure 3 As shown, the technical solution provided by the present invention is: an intelligent planning method for urban building parking areas based on pedestrian flow data, the method comprising the following steps:

[0073] Step S1: Collect historical pedestrian and vehicle traffic data from the previous quarter for buildings of the same type as the target city buildings;

[0074] Among them, the target city buildings are the city buildings that need to be constructed, and the matching city buildings are the city buildings with the same expected construction specifications as the target city buildings; the historical pedestrian flow data specifically includes the number of people retained and the number of people commuting every day, and the historical vehicle flow data includes the number of vehicles commuting and the number of vehicles retained in the parking lot.

[0075] Step S2, analyzing the historical pedestrian flow data of the matching city buildings in the previous quarter, and classifying the matching city buildings into first category buildings or second category buildings;

[0076] In this embodiment, step S2 includes the following sub-steps:

[0077] Step S21: Obtain historical pedestrian flow data for the matching city buildings, and obtain the daily commuting times RTQi for the corresponding matching city buildings in the previous quarter, where i is the number of the day, i=1, 2, ..., z, and z is the upper limit of the number;

[0078] Step S22: add up the number of commuting times per day in the previous quarter and take the average value to obtain the average number of commuting times PTQ of the corresponding matching city building in the previous quarter;

[0079] In step S23, the standard deviation of commuting of people in the corresponding matching city building in the previous quarter is calculated using the formula BZC. The specific formula is:

[0080] ;

[0081] Step S24: The average number of commuters plus the standard deviation of commuting personnel is used as the first cutoff value, and the average number of commuters minus the standard deviation of commuting personnel is used as the second cutoff value; the first cutoff value is used as the right endpoint, and the second cutoff value is used as the left endpoint to obtain a screening interval for matching the historical pedestrian flow data corresponding to the city building;

[0082] Step S25: Compare the daily commuting times of the matching city building in the previous quarter with the screening interval; if the commuting times are within the screening interval, retain the historical traffic data for the corresponding days, and record the date corresponding to the retained historical traffic data as the retention date b, where b = 1, 2, ..., x, where x is a positive integer and x ≤ z;

[0083] If the number of commutes is outside the screening range, the historical passenger flow data of the corresponding days will be discarded;

[0084] Step S26, obtaining the number of personnel commuting times RTQb corresponding to the reserved days, and obtaining the number of vehicle commuting times CTQb corresponding to the reserved days;

[0085] Step S27: summing up the number of commuting times for people corresponding to the reserved days and taking the average value to obtain the average number of commuting times for people corresponding to the reserved days, PRT; summing up the number of commuting times for vehicles corresponding to the reserved days and taking the average value to obtain the average number of commuting times for vehicles corresponding to the reserved days, PCT;

[0086] Step S28: Calculate the correlation coefficient XG between human commuting and vehicle commuting using the formula:

[0087] ; Among them, the value of XG is greater than zero and less than or equal to one; the closer XG is to one, the stronger the correlation between human commuting and vehicle commuting;

[0088] Step S29, compare the correlation coefficient with the correlation coefficient threshold. If the correlation coefficient is greater than the correlation coefficient threshold, the corresponding matching city building is recorded as a first category building; if the correlation coefficient is less than the correlation threshold, the corresponding matching city building is recorded as a second category building.

[0089] Step S3, performing category analysis on the matching city buildings according to their categories to obtain the expected number of additional parking spaces for the matching city buildings;

[0090] Among them, the parking situation of the first category of buildings is correlated with the flow of people; the parking situation of the second category of buildings has no correlation with the flow of people, or the correlation is very low and can be ignored;

[0091] In this embodiment, step S3 includes the following sub-steps:

[0092] Step S31, performing a first category analysis on a first category of buildings;

[0093] The first category analysis process is as follows:

[0094] Step S311, obtaining historical passenger flow data corresponding to the retention days of the first category of buildings, and obtaining the number of people retained in the matching city buildings for the retention days;

[0095] Step S312, as Figure 2 As shown, a personnel time distribution diagram corresponding to the first category of buildings is drawn based on the number of personnel retained corresponding to the retention days;

[0096] Step S313: Obtain a maximum point based on the personnel time distribution graph, and record the largest maximum point as the peak point. Multiple maximum points may exist in the graph. A maximum point is the horizontal coordinate of the maximum value within a certain subinterval in the function graph. The function graph in front of the maximum point shows an upward trend, while the graph behind the maximum point shows a downward trend.

[0097] Step S314, obtaining the number of vehicles retained and the number of parking spaces in the parking lot corresponding to the maximum value point;

[0098] Step S315: If the number of vehicles remaining is greater than or equal to the number of parking spaces in the parking lot, the corresponding maximum point is recorded as a calculation maximum point; if the number of vehicles remaining is less than the number of parking spaces in the parking lot, the corresponding maximum point is recorded as a training maximum point.

[0099] Step S316: Draw a retention correlation diagram based on the number of retained personnel and the number of retained vehicles corresponding to the training maximum value points of multiple retention days, and then perform function fitting based on the retention correlation diagram to obtain a corresponding correlation function expression;

[0100] Among them, function fitting is a mathematical method used to find a function (usually some type of mathematical model or formula) that can approximate or describe a given set of data points as closely as possible;

[0101] Step S317: Substitute the number of personnel retention corresponding to the calculated maximum value point into the correlation function expression to calculate the expected number of vehicles retained corresponding to the calculated maximum value point; add up the multiple expected vehicle retention numbers and take the average value to obtain the average expected vehicle retention number;

[0102] Step S318, obtaining the expected number of additional parking spaces corresponding to the first category of buildings by subtracting the number of parking spaces in the parking lot from the average expected number of vehicles retained;

[0103] Step S32, performing a second category analysis on the second category buildings;

[0104] The second category analysis includes the following sub-steps:

[0105] Step S321, obtaining historical vehicle data corresponding to the retention days of the second category building, and obtaining the number of vehicles retained at different times corresponding to the retention days;

[0106] Step S322, obtaining the number of parking spaces in the parking lot corresponding to the second category building, and counting the congestion duration when the number of vehicles remaining in the second category building is greater than or equal to the number of parking spaces in the parking lot;

[0107] Step S323, the congestion rate of the corresponding retention days is obtained by dividing the congestion duration by the total duration of each day;

[0108] Step S324: add up the congestion rates of all the retained days and take the average value to obtain the parking lot congestion rate corresponding to the second category of buildings;

[0109] Step S325: Compare the parking lot congestion rate with the congestion rate threshold. If the parking lot congestion rate is greater than or equal to the first congestion rate threshold, add P1 parking spaces for the second category building. If the parking lot congestion rate is less than the first congestion rate threshold and greater than or equal to the second congestion rate threshold, add P2 parking spaces for the second category building. If the parking lot congestion rate is less than the second congestion rate threshold, no additional parking spaces are added.

[0110] Wherein, the first congestion rate threshold is greater than the second congestion rate threshold, 0<P1<P2;

[0111] In step S326 , P1 or P2 is recorded as the expected number of additional parking spaces corresponding to the second category of buildings.

[0112] Step S4, formulating a parking lot planning scheme for the target city building based on the expected number of additional parking spaces for the matching city building, and generating a planning completion signal or a pending signal;

[0113] In this embodiment, step S4 includes the following sub-steps:

[0114] Step S41: Obtain the number of parking spaces in the parking lot corresponding to the matching city building and the expected number of additional parking spaces, and obtain the required number of parking spaces corresponding to the target city building by adding the number of parking spaces in the parking lot to the expected number of additional parking spaces;

[0115] Step S42: Obtain the floor area of ​​the preset parking lot corresponding to the building in the target city, and obtain the number of plannable parking spaces for the building in the target city by dividing the floor area of ​​the preset parking lot corresponding to the building in the target city by the floor area of ​​the standard parking spaces;

[0116] Step S43: If the number of available parking spaces is greater than or equal to the required number of parking spaces, then parking spaces are planned according to the preset parking lot; if the number of available parking spaces is less than the required number of parking spaces, then subsequent steps are executed;

[0117] Step S44: Obtain the presence of vacant areas on the road section where the target city building is located; if vacant areas exist, establish temporary parking spaces in preference to the vacant areas; obtain the area occupied by the vacant areas, and calculate the number of additional parking spaces to be provided in the vacant areas by dividing the area occupied by the standard parking spaces.

[0118] Step S45 , comparing the number of additional parking spaces in the vacant area with the expected number of additional parking spaces, and if the number of additional parking spaces in the vacant area is greater than or equal to the expected number of additional parking spaces, setting up temporary parking spaces in the vacant area;

[0119] If the number of additional parking spaces is less than the expected number of additional parking spaces, parking spaces will be supplemented by combining vacant areas with on-street parking spaces;

[0120] Step S46: When there is no vacant area, only on-street parking spaces are considered for supplementation;

[0121] On-street parking spaces cannot be set up on the following roads:

[0122] 1. Sidewalks and urban road green belts;

[0123] 2. Road sections with a two-way traffic width of less than eight meters or a one-way traffic width of less than six meters;

[0124] 3. Fire escape passages, barrier-free passages, and medical rescue passages;

[0125] 4. Within 50 meters of the motor vehicle lanes on both sides of the entrances and exits of hospitals, schools, kindergartens, and nurseries; and within 5 meters of the entrances and exits of other government agencies, organizations, enterprises, institutions, and residential areas;

[0126] 5. Urban expressways, urban trunk roads and other urban roads with heavy traffic volume;

[0127] 6. Temporary parking spaces on urban roads shall not be marked on both sides of urban roads with a two-way traffic width of less than 12 meters or a one-way traffic width of less than 9 meters;

[0128] 7. Other road sections where parking spaces are prohibited;

[0129] Step S47: Count the total number of on-street parking spaces and vacant parking spaces. If the total number of actually added parking spaces is greater than or equal to the expected number of additional parking spaces, generate a planning completion signal.

[0130] Step S48: If the total number of parking spaces actually added is less than the expected number of parking spaces added, a pending signal is generated.

[0131] Step S5, receiving a pending signal or a planning completion signal corresponding to a building in the target city;

[0132] In practice, if it is a pending signal, the user can decide whether to adopt the corresponding parking space addition plan.

[0133] In this application, if a corresponding calculation formula appears, the above calculation formula is dimensionless and its numerical calculation is performed. The weight coefficient, proportional coefficient and other coefficients in the formula are set to a result value obtained by quantifying each parameter. Regarding the size of the weight coefficient and the proportional coefficient, as long as it does not affect the proportional relationship between the parameter and the result value, it is acceptable.

[0134] Example 2: Figure 4 As shown, based on another concept of the same invention, an urban building parking area intelligent planning system based on pedestrian flow data is proposed, including a data acquisition module, a pedestrian flow analysis module, a building analysis module, a parking space planning module and a user terminal;

[0135] The data collection module is used to collect historical pedestrian flow data and historical vehicle flow data of the same type of buildings in the target city in the previous quarter and send them to the pedestrian flow analysis module and the building analysis module;

[0136] The pedestrian flow analysis module is used to analyze the historical pedestrian flow data of the matching city buildings in the previous quarter, classify the matching city buildings into first category buildings or second category buildings, and send the data to the building analysis module;

[0137] The building analysis module is used to perform category analysis on the matching city buildings according to categories, obtain the expected number of additional parking spaces for the matching city buildings and send it to the parking space planning module;

[0138] The parking space planning module is used to formulate a parking lot planning scheme for a target city building based on the expected number of additional parking spaces for the matching city building, generate a planning completion signal or a pending signal and send it to the user terminal;

[0139] The user terminal is used to receive a pending signal or a planning completion signal corresponding to a building in a target city. If it is a pending signal, the user decides whether to adopt the corresponding parking space addition plan.

[0140] The preferred embodiments of the present invention disclosed above are intended only to help illustrate the present invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the present invention to specific embodiments. Obviously, many modifications and variations are possible based on the contents of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. An intelligent planning method for urban building parking areas based on pedestrian flow data, characterized in that: The method comprises the following steps: Step S1: Collect historical pedestrian and vehicle traffic data from the previous quarter for buildings of the same type as the target city buildings; Step S2, analyzing the historical pedestrian flow data of the matching city buildings in the previous quarter, and classifying the matching city buildings into first category buildings or second category buildings; Wherein, the step S2 includes the following sub-steps: Step S21, obtaining historical pedestrian flow data of the matching city building, and obtaining the number of commuting times of the corresponding matching city building every day in the previous quarter; Step S22: add up the number of commutes per day in the previous quarter and take the average value to obtain the average number of commutes for the corresponding matching city building in the previous quarter; Step S23, calculating the standard deviation of commuting of people in the corresponding matching city buildings in the previous quarter; Step S24: The average number of commuters plus the standard deviation of commuting personnel is used as the first cutoff value, and the average number of commuters minus the standard deviation of commuting personnel is used as the second cutoff value; the first cutoff value is used as the right endpoint, and the second cutoff value is used as the left endpoint to obtain a screening interval for matching the historical pedestrian flow data corresponding to the city building; Step S25: Compare the daily commuting times of the matching city building in the previous quarter with the screening interval; if the commuting times are within the screening interval, retain the historical passenger flow data for the corresponding days, and record the date corresponding to the retained historical passenger flow data as the retention date; If the number of commutes is outside the screening range, the historical passenger flow data of the corresponding days will be discarded; Step S26, obtaining the number of personnel commutes corresponding to the reserved days, and then obtaining the number of vehicle commutes corresponding to the reserved days; Step S27: Add the number of commutes of people corresponding to the reserved days and take the average value to obtain the average number of commutes of people corresponding to the reserved days; add the number of commutes of vehicles corresponding to the reserved days and take the average value to obtain the average number of commutes of vehicles corresponding to the reserved days; Step S28, calculating the correlation coefficient between human commuting and vehicle commuting; Step S29: Compare the correlation coefficient with the correlation coefficient threshold. If the correlation coefficient is greater than the correlation coefficient threshold, the corresponding matching city building is recorded as a first category building; if the correlation coefficient is less than the correlation threshold, the corresponding matching city building is recorded as a second category building. Step S3, performing category analysis on the matching city buildings according to their categories to obtain the expected number of additional parking spaces for the matching city buildings; Step S4: formulate a parking lot planning scheme for the target city building based on the expected number of additional parking spaces for the matching city building, and generate a planning completion signal or a pending signal.

2. The method for intelligent planning of urban building parking areas based on pedestrian flow data according to claim 1 is characterized in that: Historical pedestrian flow data includes the number of people retained and the number of people commuting each day, and historical vehicle flow data includes the number of vehicles commuting and the number of vehicles retained in the parking lot.

3. The method for intelligent planning of urban building parking areas based on pedestrian flow data according to claim 1 is characterized in that: The step S3 includes the following sub-steps: Step S31, performing a first category analysis on a first category of buildings; Step S32: performing a second category analysis on the second category buildings.

4. The method for intelligent planning of urban building parking areas based on pedestrian flow data according to claim 3 is characterized in that: The first category analysis includes the following steps: Step S311, obtaining historical passenger flow data corresponding to the retention days of the first category of buildings, and obtaining the number of people retained in the matching city buildings for the retention days; Step S312, drawing a personnel time distribution diagram corresponding to the first category of buildings based on the number of personnel retention corresponding to the retention days; Step S313, obtaining a maximum value point based on the personnel time distribution graph, and recording the largest maximum value point as the peak point; Step S314, obtaining the number of vehicles retained and the number of parking spaces in the parking lot corresponding to the maximum value point; Step S315: If the number of retained vehicles is greater than or equal to the number of parking spaces in the parking lot, the corresponding maximum point is recorded as a calculated maximum point; if the number of retained vehicles is less than the number of parking spaces in the parking lot, the corresponding maximum point is recorded as a training maximum point.

5. The method for intelligent planning of urban building parking areas based on pedestrian flow data according to claim 4 is characterized in that: The first category analysis further comprises the following steps: Step S316: Draw a retention correlation diagram based on the number of retained personnel and the number of retained vehicles corresponding to the training maximum value points of multiple retention days, and then perform function fitting based on the retention correlation diagram to obtain a corresponding correlation function expression; Step S317: Substitute the number of personnel retention corresponding to the calculated maximum value point into the correlation function expression to calculate the expected number of vehicles retained corresponding to the calculated maximum value point; add up the multiple expected vehicle retention numbers and take the average value to obtain the average expected vehicle retention number; Step S318: The expected number of additional parking spaces corresponding to the first category of buildings is obtained by subtracting the number of parking spaces in the parking lot from the average expected number of retained vehicles.

6. The method for intelligent planning of urban building parking areas based on pedestrian flow data according to claim 3 is characterized in that: The second category analysis includes the following steps: Step S321, obtaining historical vehicle data corresponding to the retention days of the second category building, and obtaining the number of vehicles retained at different times corresponding to the retention days; Step S322, obtaining the number of parking spaces in the parking lot corresponding to the second category building, and counting the congestion duration when the number of vehicles remaining in the second category building is greater than or equal to the number of parking spaces in the parking lot; Step S323, the congestion rate of the corresponding retention days is obtained by dividing the congestion duration by the total duration of each day; Step S324: add up the congestion rates of all the retained days and take the average value to obtain the parking lot congestion rate corresponding to the second category of buildings; Step S325: Compare the parking lot congestion rate with the congestion rate threshold. If the parking lot congestion rate is greater than or equal to the first congestion rate threshold, add P1 parking spaces for the second category building. If the parking lot congestion rate is less than the first congestion rate threshold and greater than or equal to the second congestion rate threshold, add P2 parking spaces for the second category building. If the parking lot congestion rate is less than the second congestion rate threshold, no additional parking spaces are added. Wherein, the first congestion rate threshold is greater than the second congestion rate threshold, 0<P1<P2; In step S326 , P1 or P2 is recorded as the expected number of additional parking spaces corresponding to the second category of buildings.

7. The method for intelligent planning of urban building parking areas based on pedestrian flow data according to claim 6, characterized in that: The step S4 includes the following sub-steps: Step S41: Obtain the number of parking spaces in the parking lot corresponding to the matching city building and the expected number of additional parking spaces, and obtain the required number of parking spaces corresponding to the target city building by adding the number of parking spaces in the parking lot to the expected number of additional parking spaces; Step S42: Obtain the floor area of ​​the preset parking lot corresponding to the building in the target city, and obtain the number of plannable parking spaces for the building in the target city by dividing the floor area of ​​the preset parking lot corresponding to the building in the target city by the floor area of ​​the standard parking spaces; Step S43: If the number of available parking spaces is greater than or equal to the required number of parking spaces, then parking spaces are planned according to the preset parking lot; if the number of available parking spaces is less than the required number of parking spaces, then subsequent steps are executed; Step S44, obtaining the existence of vacant areas on the road section where the target city building is located; if vacant areas exist, setting up temporary parking spaces in priority to the vacant areas; obtaining the floor area of ​​the vacant areas, and dividing the floor area of ​​the vacant areas by the floor area of ​​the standard parking spaces to obtain the number of additional parking spaces in the vacant areas.

8. The method for intelligent planning of urban building parking areas based on pedestrian flow data according to claim 7 is characterized in that: The step S4 further includes the following sub-steps: Step S45 , comparing the number of additional parking spaces in the vacant area with the expected number of additional parking spaces, and if the number of additional parking spaces in the vacant area is greater than or equal to the expected number of additional parking spaces, setting up temporary parking spaces in the vacant area; If the number of additional parking spaces is less than the expected number of additional parking spaces, parking spaces will be supplemented by combining vacant areas with on-street parking spaces; Step S46: When there is no vacant area, only on-street parking spaces are considered for supplementation; Step S47: Count the total number of on-street parking spaces and vacant parking spaces. If the total number of actually added parking spaces is greater than or equal to the expected number of additional parking spaces, generate a planning completion signal. Step S48: If the total number of parking spaces actually added is less than the expected number of parking spaces added, a pending signal is generated.

9. An intelligent planning system for urban building parking areas based on pedestrian flow data, characterized in that: The method for intelligent planning of parking areas for urban buildings based on pedestrian flow data according to any one of claims 1 to 8 is implemented, and the system comprises: The data collection module is used to collect the historical pedestrian and vehicle flow data of the buildings of the same type as the target city in the previous quarter, and send it to the pedestrian flow analysis module and the building analysis module; A pedestrian flow analysis module is used to analyze the historical pedestrian flow data of the matching city buildings in the previous quarter, classify the matching city buildings into first-category buildings or second-category buildings, and send the data to the building analysis module; The building analysis module is used to analyze the matching city buildings according to their categories, obtain the expected number of additional parking spaces for the matching city buildings, and send it to the parking space planning module; The parking space planning module is used to formulate a parking lot planning scheme for the target city building based on the expected number of additional parking spaces for the matching city building, generate a planning completion signal or a pending signal and send it to the user terminal; The user terminal is used to receive a pending signal or a planning completion signal corresponding to a building in a target city. If it is a pending signal, the user decides whether to adopt the corresponding parking space addition plan.

Images