Intelligent parking lot dynamic allocation and scheduling system and method

Abstract

The present invention discloses a system and method for dynamic allocation and scheduling of parking spaces in an intelligent parking lot, which belongs to the field of parking management. The method includes: planning a number of parking trajectories for entering each parking space; screening out the optimal parking trajectory from the entrance of the parking lot to the parking space based on the track experience points on each parking trajectory and the convenience coefficient; obtaining the vehicle data entering the parking lot at each time period of each day in history, constructing a prediction model for predicting the vehicle data entering the parking lot at each time period of each day, and screening out the optimal prediction model based on the accuracy coefficient; constructing an open allocation model for parking spaces in the parking lot according to the optimal parking trajectory of each parking space, and allocating and scheduling the parking spaces that need to be opened at each time period in the parking lot tomorrow. The system includes a license plate recognition system, a guidance and scheduling system, an information collection module, a charging pile management module and a data processing center. The dynamic allocation and scheduling of different types of parking spaces in the parking lot are realized, and the utilization rate and management efficiency of parking space resources are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of parking management, and in particular to a system and method for dynamically allocating and dispatching parking spaces in an intelligent parking lot. Background Art

[0002] With the acceleration of urbanization, the number of motor vehicles has increased dramatically, and the problem of parking difficulties has become increasingly prominent. There are many drawbacks in the traditional parking lot management method, such as unreasonable allocation of parking spaces, which leads to congestion in some areas and idleness in other areas; it takes a long time for vehicles to enter parking spaces, resulting in serious vehicle congestion in parking lots, too long time to find parking spaces, and low parking efficiency. In addition, with the continuous development of new energy vehicles, the number of new energy vehicles has also increased rapidly, and the charging of new energy vehicles needs to become the key to parking lot services. Many parking lots install charging piles on parking spaces to meet the charging needs of new energy vehicles. However, due to the insufficient management of new energy parking spaces in parking lots, many new energy parking spaces are occupied by fuel vehicles, the utilization rate of charging piles is low, and charging resources are wasted. At the same time, the charging piles on unused new energy parking spaces are always in the on state, resulting in waste of electricity. In order to solve these problems, intelligent parking lot technology has emerged, and it is urgent to propose a dynamic allocation and scheduling system and method for parking spaces in intelligent parking lots. Summary of the invention

[0003] In view of the above-mentioned deficiencies in the prior art, the present invention provides a system and method for dynamically allocating and scheduling parking spaces in an intelligent parking lot, so as to achieve efficient utilization of parking space resources in the parking lot, reduce the time consumed by vehicle parking, and optimize the traffic flow in the parking lot.

[0004] In order to achieve the above-mentioned object of the invention, the technical solution adopted by the present invention is:

[0005] A method for dynamically allocating and scheduling parking spaces in an intelligent parking lot is provided, comprising:

[0006] Step S1: constructing a three-dimensional model of the parking lot based on the design parameters of the parking lot, and planning several parking trajectories for entering each parking space according to the distribution of parking spaces and public lanes in the parking lot;

[0007] Step S2: Calculate the convenience coefficient of each parking trajectory according to the track experience points on each parking trajectory, and select the optimal parking trajectory from the entrance of the parking lot to the parking space according to the convenience coefficient;

[0008] Step S3: Obtain historical data on vehicles entering the parking lot at each time period each day, the vehicle data including vehicle type and quantity data, construct a prediction model for predicting vehicle data entering the parking lot at each time period each day, train the prediction model, and calculate the accuracy coefficient of the prediction model based on the error coefficient between the predicted vehicle data and the actual vehicle data, and select the optimal prediction model based on the accuracy coefficient;

[0009] Step S4: Input the vehicle data entering the parking lot at each time period on each day in the past into the optimal prediction model, predict the vehicle data entering the parking lot at each time period tomorrow, and calculate the number of parking spaces that need to be open at each time period in the parking lot tomorrow. According to the optimal parking trajectory of each parking space, an open allocation model for parking spaces in the parking lot is constructed to allocate and schedule the parking spaces that need to be open at each time period in the parking lot tomorrow.

[0010] Further, step S1 includes:

[0011] Step S11: construct a three-dimensional model of the parking lot based on the design parameters of the parking lot, and establish a two-dimensional coordinate system for each floor of the parking lot on the three-dimensional model, and obtain the coordinates of the center of each parking space planned in each floor of the parking lot in the corresponding two-dimensional coordinate system. , n is the number of floors where the parking lot is located, i For the n Parking space number of the multi-storey parking lot;

[0012] Step S12: Draw the public lanes in the two-dimensional coordinate system, and obtain the intersection coordinates between the two intersecting public lanes according to the distribution of each public lane. , e is the number of the public lane, u For the e The number of the intersection coordinates on the public lane;

[0013] Step S13: Establish the straight line equation of each public lane ;

[0014] ;

[0015] in, are two points located on the straight line where the public lane is located;

[0016] Step S14: According to the coordinates of the parking space Calculate the equation of the line on which each public lane lies The vertical point between , and calculate the coordinates With vertical point The distance between

[0017] ;

[0018] Step S15: Constructing and screening parking spaces i The constraints of the public lanes where the parking spaces are located are obtained i Public lanes planned at the location , the vehicle is parked from the public lane Entering the parking space i ;

[0019] ;

[0020] in, E It is the collection of straight lines where all public lanes of the parking lot are located;

[0021] Step S16: Parking space i The public lane where it is located The vertical point between the straight lines is taken as the end point of the parking trajectory, and the entrance of the parking lot is taken as the starting point of the parking trajectory. The public lane path from the starting point of the parking trajectory to the end point of the parking trajectory is planned, and the result is N Parking tracks , For the N Parking tracks.

[0022] Further, step S2 includes:

[0023] Step S21: Take the vertical point on each parking trajectory and the intersection point between two public lanes as the trajectory passing point, and calculate the travel distance of each parking trajectory according to the coordinates of two adjacent trajectory passing points on the parking trajectory. ; For the N The parking track w Trajectory experience points, For the N The parking track w The coordinates of the trajectory experience points adjacent to the trajectory experience points, To drive from the parking lot entrance to the parking space located at n The fixed distance that needs to be traveled in the multi-storey parking lot, W is the number of trajectory experience points on the parking trajectory;

[0024] Step S22: Calculate the convenience coefficient of each parking trajectory according to the driving distance of each parking trajectory ;

[0025] ;

[0026] in, u is the number of the parking track, w is the number of the trajectory point, For the u Trajectory experience points on the parking trajectory w With trajectory experience point w -1 distance between For the u The number of public lanes that a parking trajectory has passed through, are the impact weights of parking distance and number of turns on parking convenience, and ;

[0027] Step S23: Based on the convenience coefficient of each parking trajectory Filter out the parking lot entrance to the parking space i The optimal parking trajectory .

[0028] Further, step S3 includes:

[0029] Step S31: Obtain the type and quantity data of vehicles entering the parking lot at each time period every day;

[0030] ;

[0031] ;

[0032] in, For the number of historical days, Number the historical days. For each historical day, is the time period number, For the history Day time The number of fuel trucks entering the parking lot, For the history Day time The number of new energy vehicles entering the parking lot;

[0033] Step S32: Extract the corresponding time period of each day in history The vehicle data is used as the training data set , , , For the period The number of vehicles entering the parking lot, and the construction of a prediction model to predict the number of vehicles entering the parking lot at different times of the day ;

[0034] ;

[0035] in, Forecast period Number of parking lots to enter, is the regression coefficient, p is the number of the regression coefficient, P is the number of regression terms, is the error term, For the previous day The number of vehicles entering the parking lot;

[0036] Step S33: Take the training data set in reverse order Middle and back P Data Input into the prediction model, , output the trained regression coefficient and error term, and obtain the fuel vehicle prediction model after training;

[0037] Step S34: Get training data set Data in Input the fuel vehicle prediction model after training, and output the history Day time Predicted number of fuel vehicles entering the parking lot , and calculate the actual number of vehicles The error coefficient ;

[0038] ;

[0039] Step S35: Return to step S34 and obtain the training data set Data in Input the prediction model after training and calculate the error coefficient ;

[0040] Step S36: until the training data set is calculated Data in forward P After the error coefficients related to the data, the accuracy coefficient of the fuel vehicle prediction model at the end of training is calculated ;

[0041] ;

[0042] Step S37: Repeat steps S33-S36, according to the training data set The number of training data that can be extracted from the combination is used to obtain several fuel vehicle prediction models that have been trained to form a fuel vehicle prediction model set ;

[0043] Step S38: Construct the constraint conditions for selecting the optimal fuel vehicle prediction model, and obtain the optimal prediction model for predicting the number of fuel vehicles entering the parking lot at each time period every day. ;

[0044] ;

[0045] Step S39: Repeat steps S33-S38, using the training data set Training prediction models with data from , and obtain the optimal prediction model for predicting the number of new energy vehicles entering the parking lot at different times of the day .

[0046] Further, step S4 includes:

[0047] Step S41: Input the optimal prediction model according to the number of fuel vehicles and new energy vehicles entering the parking lot at each day and time period in history and the optimal prediction model In the forecast, the number of new energy vehicles entering the parking lot at different times tomorrow is predicted. and the number of fuel vehicles ;

[0048] Step S42: Utilize the number of new energy vehicles and the number of fuel vehicles Calculate the number of new energy parking spaces that need to be open at different times tomorrow and number of fuel parking spaces ; This is the largest number of new energy vehicles entering the parking lot in history. This is the largest number of fuel vehicles entering the parking lot in history. are the corresponding reservation coefficients respectively;

[0049] Step S43: Construct an open allocation model for new energy parking spaces and fuel parking spaces in the parking lot based on the distribution of parking spaces in the parking lot and the convenience coefficient corresponding to each parking space ;

[0050] ;

[0051] in, According to the number of new energy parking spaces A collection of allocated new energy parking spaces, Collection for new energy parking spaces The number of the new energy parking space in It is a collection of new energy parking spaces in the parking lot. To reach the new energy parking space from the parking lot entrance The convenience coefficient corresponding to the optimal parking trajectory is: According to the number of fuel parking spaces Assigned fuel parking space collection, Assemble for fuel parking The number of the fuel parking space in For the fuel parking spaces in the parking lot, To get to the fuel parking space from the parking lot entrance The convenience coefficient corresponding to the optimal parking trajectory;

[0052] Step S44: According to the open allocation model After allocating the new energy parking spaces and fuel parking spaces that need to be open at different times in the parking lot tomorrow, the license plate recognition system at the entrance of the parking lot will identify the vehicle type and use the parking guidance system in the parking lot to guide and dispatch the vehicles to the corresponding parking spaces based on the parking space allocation. The charging piles in the unallocated new energy parking spaces will be shut down.

[0053] A system for dynamically allocating and scheduling parking spaces in an intelligent parking lot is provided, which executes the above-mentioned method for dynamically allocating and scheduling parking spaces in an intelligent parking lot, including:

[0054] The license plate recognition system is installed at the entrance of the parking lot to identify the type of vehicles entering the parking lot, including new energy vehicles and fuel vehicles;

[0055] Guidance and dispatching system, electronic traffic guidance signs installed in the parking lot, parking locks installed on parking spaces, electronic traffic guidance signs display corresponding traffic guidance signs, guide vehicles into the parking area according to the allocation of new energy parking spaces and fuel parking spaces in the parking lot, and lock the unallocated parking spaces in the parking lot;

[0056] An information collection module is connected to the license plate recognition system, the guidance and dispatching system, and the charging pile management module through a wireless module or a wired communication module to collect information fed back by the license plate recognition system, the guidance and dispatching system, and the charging pile management module;

[0057] The charging pile management module is connected to the charging piles on the new energy parking spaces and controls the start or shut down of the charging piles according to the allocation of new energy parking spaces;

[0058] The data processing center is used to store and analyze historical vehicle information in the parking lot, and to allocate and schedule parking spaces that need to be opened in the parking lot.

[0059] The beneficial effects of the present invention are as follows: the present invention constructs an optimal prediction model for predicting vehicle data based on the historical vehicle data of the parking lot, which is used to predict the number of new energy vehicles and fuel vehicles entering the parking lot tomorrow, and allocates and schedules new energy parking spaces and fuel parking spaces based on the convenience experienced in the process of reaching each parking space from the parking lot entrance, ensuring that vehicles are parked along the optimal route, increasing the utilization rate of parking spaces while improving the mobility of vehicles in the parking lot, reducing the power consumption of idle charging piles, realizing the dynamic allocation and scheduling of different types of parking spaces in the parking lot, improving the utilization rate and management efficiency of parking space resources, and having significant innovation and practicality. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 The present invention is a flow chart of a method for dynamically allocating and scheduling parking spaces in an intelligent parking lot. DETAILED DESCRIPTION

[0061] The specific implementation modes of the present invention are described below so that those skilled in the art can understand the present invention. However, it should be clear that the present invention is not limited to the scope of the specific implementation modes. For those of ordinary skill in the art, as long as various changes are within the spirit and scope of the present invention as defined and determined by the attached claims, these changes are obvious, and all inventions and creations utilizing the concept of the present invention are protected.

[0062] like Figure 1 As shown, a method for dynamic allocation and scheduling of parking spaces in an intelligent parking lot includes:

[0063] Step S1: construct a three-dimensional model of the parking lot based on the design parameters of the parking lot, and plan several parking trajectories for entering each parking space according to the distribution of parking spaces and public lanes in the parking lot. Step S1 specifically includes:

[0064] Step S11: construct a three-dimensional model of the parking lot based on the design parameters of the parking lot, and establish a two-dimensional coordinate system for each floor of the parking lot on the three-dimensional model. The two-dimensional coordinate system is located on the plane where the parking lot is located, and obtain the coordinates of the center of each parking space planned in each floor of the parking lot in the corresponding two-dimensional coordinate system. , n is the number of floors where the parking lot is located, i For the n Parking space number of the multi-storey parking lot;

[0065] Step S12: Draw the public lanes in the two-dimensional coordinate system, and obtain the intersection coordinates between the two intersecting public lanes according to the distribution of each public lane. , e is the number of the public lane, u For the eThe coordinates of the intersections on the public lanes are numbered; the present invention regards the straight driving passage in the parking lot as a public lane, and the public lanes intersect to form intersections. A public lane may intersect with multiple public lanes, and there are multiple intersections thereon.

[0066] Step S13: Establish the straight line equation of each public lane ;

[0067] ;

[0068] in, are two points located on the straight line where the public lane is located;

[0069] Step S14: According to the coordinates of the parking space Calculate the equation of the line on which each public lane lies The vertical point between , and calculate the coordinates With vertical point The distance between

[0070] ;

[0071] Step S15: Constructing and screening parking spaces i The constraints of the public lanes where the parking spaces are located are obtained i Public lanes planned at the location , the vehicle is parked from the public lane Entering the parking space i ;

[0072] ;

[0073] in, E It is the set of straight lines where all public lanes in the parking lot are located; if the parking space is located closest to the vertical point on the public lane, it means that the parking spaces are distributed on both sides of the public lane, and the vehicle needs to enter the parking space through the public lane when parking.

[0074] Step S16: Parking space i The public lane where it is located The vertical point between the straight lines is taken as the end point of the parking trajectory, and the entrance of the parking lot is taken as the starting point of the parking trajectory. The public lane path from the starting point of the parking trajectory to the end point of the parking trajectory is planned, and the result is N Parking tracks , For the N Parking tracks.

[0075] Step S2: Calculate the convenience coefficient of each parking trajectory according to the track experience points on each parking trajectory, and select the optimal parking trajectory from the entrance of the parking lot to the parking space according to the convenience coefficient. Step S2 specifically includes:

[0076] Step S21: The vertical point on each parking trajectory and the intersection point between two public lanes are used as trajectory experience points. The trajectory travel distance can be calculated based on the coordinates of the intersection point and the vertical point on the trajectory. The travel distance of each parking trajectory is calculated based on the coordinates of two adjacent trajectory experience points on the parking trajectory. ; For the N The parking track w Trajectory experience points, For the N The parking track w The coordinates of the trajectory experience points adjacent to the trajectory experience points, To drive from the parking lot entrance to the parking space located at n The fixed distance that needs to be traveled in the multi-storey parking lot, W is the number of trajectory experience points on the parking trajectory;

[0077] Step S22: Calculate the convenience coefficient of each parking trajectory according to the driving distance of each parking trajectory ;

[0078] ;

[0079] in, u is the number of the parking track, w is the number of the trajectory point, For the u Trajectory experience points on the parking trajectory w With trajectory experience point w -1 distance between For the u The number of public lanes that a parking trajectory has passed through, are the impact weights of parking distance and number of turns on parking convenience, and , generally speaking, Take 0.25, Take 0.75; the present invention evaluates the convenience of parking from the distance traveled and the number of turns in the parking lot. The more public lanes the vehicle passes through on the parking trajectory, the more times the vehicle turns. When the vehicle is inserted into another public lane, the load of vehicle convergence will increase, and the parking time will be consumed.

[0080] Step S23: Based on the convenience coefficient of each parking trajectory Filter out the parking lot entrance to the parking spacei The optimal parking trajectory .

[0081] Step S3: Obtain the historical data of vehicles entering the parking lot at each time period every day, including vehicle type and quantity data, build a prediction model for predicting the data of vehicles entering the parking lot at each time period every day, train the prediction model, and calculate the accuracy coefficient of the prediction model based on the error coefficient between the predicted vehicle data and the actual vehicle data, and select the optimal prediction model based on the accuracy coefficient. Step S3 specifically includes:

[0082] Step S31: Obtain the type and quantity data of vehicles entering the parking lot at each time period every day;

[0083] ;

[0084] ;

[0085] in, For the number of historical days, Number the historical days. For each historical day, is the time period number, For the history Day time The number of fuel trucks entering the parking lot, For the history Day time The number of new energy vehicles entering the parking lot;

[0086] Step S32: Extract the corresponding time period of each day in history The vehicle data is used as the training data set , , , For the period The number of vehicles entering the parking lot, and the construction of a prediction model to predict the number of vehicles entering the parking lot at different times of the day ;

[0087] ;

[0088] in, Forecast period Number of parking lots to enter, is the regression coefficient, p is the number of the regression coefficient, P is the number of regression terms, is the error term, For the previous day The number of vehicles entering the parking lot;

[0089] Step S33: Take the training data set in reverse order Middle and back P Data Input into the prediction model, , output the trained regression coefficient and error term, and obtain the fuel vehicle prediction model after training;

[0090] Step S34: Get training data set Data in Input the fuel vehicle prediction model after training, and output the history Day time Predicted number of fuel vehicles entering the parking lot , and calculate the actual number of vehicles The error coefficient ;

[0091] ;

[0092] Step S35: Return to step S34 and obtain the training data set Data in Input the prediction model after training and calculate the error coefficient ;

[0093] Step S36: until the training data set is calculated Data in forward P After the error coefficients related to the data, the accuracy coefficient of the fuel vehicle prediction model at the end of training is calculated ;

[0094] ;

[0095] Step S37: Repeat steps S33-S36, according to the training data set The number of training data that can be extracted from the combination is used to obtain several fuel vehicle prediction models that have been trained to form a fuel vehicle prediction model set ;

[0096] The present invention extracts historical vehicle data in reverse order and determines the number of polynomials in the prediction model according to the precision coefficient, and the number of polynomials corresponds to the data volume of the training data.

[0097] Step S38: Construct the constraint conditions for selecting the optimal fuel vehicle prediction model, and obtain the optimal prediction model for predicting the number of fuel vehicles entering the parking lot at each time period every day. ;

[0098] ;

[0099] Step S39: Repeat steps S33-S38, using the training data set Training prediction models with data from , and obtain the optimal prediction model for predicting the number of new energy vehicles entering the parking lot at different times of the day .

[0100] Step S4: Input the vehicle data entering the parking lot at each time period on each day in the past into the optimal prediction model, predict the vehicle data entering the parking lot at each time period tomorrow, and calculate the number of parking spaces that need to be opened at each time period in the parking lot tomorrow. According to the optimal parking trajectory of each parking space, an open allocation model for parking spaces in the parking lot is constructed to allocate and schedule the parking spaces that need to be opened at each time period in the parking lot tomorrow. Step S4 specifically includes:

[0101] Step S41: Input the optimal prediction model according to the number of fuel vehicles and new energy vehicles entering the parking lot at each day and time period in history and the optimal prediction model In the forecast, the number of new energy vehicles entering the parking lot at different times tomorrow is predicted. and the number of fuel vehicles ;

[0102] Step S42: Utilize the number of new energy vehicles and the number of fuel vehicles Calculate the number of new energy parking spaces that need to be open at different times tomorrow and number of fuel parking spaces ; This is the largest number of new energy vehicles entering the parking lot in history. This is the largest number of fuel vehicles entering the parking lot in history. are the corresponding reservation coefficients respectively;

[0103] Step S43: Construct an open allocation model for new energy parking spaces and fuel parking spaces in the parking lot based on the distribution of parking spaces in the parking lot and the convenience coefficient corresponding to each parking space ;

[0104] ;

[0105] in, According to the number of new energy parking spaces A collection of allocated new energy parking spaces, Collection for new energy parking spaces The number of the new energy parking space in It is a collection of new energy parking spaces in the parking lot. To reach the new energy parking space from the parking lot entrance The convenience coefficient corresponding to the optimal parking trajectory is: According to the number of fuel parking spaces Assigned fuel parking space collection, Assemble for fuel parking The number of the fuel parking space in For the fuel parking spaces in the parking lot, To get to the fuel parking space from the parking lot entrance The convenience coefficient corresponding to the optimal parking trajectory;

[0106] Step S44: According to the open allocation model After allocating the new energy parking spaces and fuel parking spaces that need to be open at different times in the parking lot tomorrow, the license plate recognition system at the entrance of the parking lot will identify the vehicle type and use the parking guidance system in the parking lot to guide and dispatch the vehicles to the corresponding parking spaces based on the parking space allocation. The charging piles in the unallocated new energy parking spaces will be shut down.

[0107] A system for dynamically allocating and dispatching parking spaces in an intelligent parking lot, which executes the above-mentioned method for dynamically allocating and dispatching parking spaces in an intelligent parking lot, comprises:

[0108] The license plate recognition system is installed at the entrance of the parking lot to identify the type of vehicles entering the parking lot, including new energy vehicles and fuel vehicles;

[0109] Guidance and dispatching system, electronic traffic guidance signs installed in the parking lot, parking locks installed on parking spaces, electronic traffic guidance signs display corresponding traffic guidance signs, guide vehicles into the parking area according to the allocation of new energy parking spaces and fuel parking spaces in the parking lot, and lock the unallocated parking spaces in the parking lot;

[0110] An information collection module is connected to the license plate recognition system, the guidance and dispatching system, and the charging pile management module through a wireless module or a wired communication module to collect information fed back by the license plate recognition system, the guidance and dispatching system, and the charging pile management module;

[0111] The charging pile management module is connected to the charging piles on the new energy parking spaces and controls the start or shut down of the charging piles according to the allocation of new energy parking spaces;

[0112] The data processing center is used to store and analyze historical vehicle information in the parking lot, and to allocate and schedule parking spaces that need to be opened in the parking lot.

[0113] The present invention constructs an optimal prediction model for predicting vehicle data based on the historical vehicle data of the parking lot, which is used to predict the number of new energy vehicles and fuel vehicles entering the parking lot tomorrow, and allocates and schedules new energy parking spaces and fuel parking spaces based on the convenience experienced in the process of reaching each parking space from the parking lot entrance, ensuring that vehicles are parked along the optimal route, increasing the utilization rate of parking spaces while improving the mobility of vehicles in the parking lot, reducing the power consumption of idle charging piles, realizing the dynamic allocation and scheduling of different types of parking spaces in the parking lot, improving the utilization rate and management efficiency of parking space resources, and having significant innovation and practicality.

Claims

1. A method for dynamic allocation and scheduling of parking spaces in an intelligent parking lot, characterized in that: include: Step S1: constructing a three-dimensional model of the parking lot based on the design parameters of the parking lot, and planning several parking trajectories for entering each parking space according to the distribution of parking spaces and public lanes in the parking lot; Step S2: Calculate the convenience coefficient of each parking trajectory according to the track experience points on each parking trajectory, and select the optimal parking trajectory from the entrance of the parking lot to the parking space according to the convenience coefficient; Step S3: Obtain historical data on vehicles entering the parking lot at each time period each day, the vehicle data including vehicle type and quantity data, construct a prediction model for predicting vehicle data entering the parking lot at each time period each day, train the prediction model, and calculate the accuracy coefficient of the prediction model based on the error coefficient between the predicted vehicle data and the actual vehicle data, and select the optimal prediction model based on the accuracy coefficient; Step S4: input the vehicle data entering the parking lot at each time period on each day in the past into the optimal prediction model, predict the vehicle data entering the parking lot at each time period tomorrow, and calculate the number of parking spaces that need to be opened at each time period in the parking lot tomorrow, build an open allocation model for parking spaces in the parking lot according to the optimal parking trajectory of each parking space, and allocate and schedule the parking spaces that need to be opened at each time period in the parking lot tomorrow; The step S1 comprises: Step S11: construct a three-dimensional model of the parking lot based on the design parameters of the parking lot, and establish a two-dimensional coordinate system for each floor of the parking lot on the three-dimensional model, and obtain the coordinates of the center of each parking space planned in each floor of the parking lot in the corresponding two-dimensional coordinate system. , n is the number of floors where the parking lot is located, i For the n Parking space number of the multi-storey parking lot; Step S12: Draw the public lanes in the two-dimensional coordinate system, and obtain the intersection coordinates between the two intersecting public lanes according to the distribution of each public lane. , e is the number of the public lane, u For the e The coordinate number of the intersection point on the public lane; Step S13: Establish the straight line equation of each public lane ; ； in, are two points located on the straight line where the public lane is located; Step S14: According to the coordinates of the parking space Calculate the equation of the line on which each public lane lies The vertical point between , and calculate the coordinates With vertical point The distance between ； Step S15: Constructing and screening parking spaces i The constraints of the public lanes where the parking spaces are located are obtained i Public lanes planned at the location , the vehicle is parked from the public lane Entering the parking space i ; ； in, E It is the collection of straight lines where all public lanes of the parking lot are located; Step S16: Parking space i The public lane where it is located The vertical point between the straight lines is taken as the end point of the parking trajectory, and the entrance of the parking lot is taken as the starting point of the parking trajectory. The public lane path from the starting point of the parking trajectory to the end point of the parking trajectory is planned, and the result is N Parking tracks , For the N Parking tracks; The step S2 comprises: Step S21: Take the vertical point on each parking trajectory and the intersection point between two public lanes as the trajectory passing point, and calculate the travel distance of each parking trajectory according to the coordinates of two adjacent trajectory passing points on the parking trajectory. ; For the N The parking track w Trajectory experience points, For the N The parking track w The coordinates of the trajectory experience points adjacent to the trajectory experience points, To drive from the parking lot entrance to the parking space located at n The fixed distance that needs to be traveled in the multi-storey parking lot, W is the number of trajectory experience points on the parking trajectory; Step S22: Calculate the convenience coefficient of each parking trajectory according to the driving distance of each parking trajectory ; ； in, u is the number of the parking track, w is the number of the trajectory point, For the u Trajectory experience points on the parking trajectory w With trajectory experience point w -1 distance between For the u The number of public lanes that a parking trajectory has passed through, are the impact weights of parking distance and number of turns on parking convenience, and ; Step S23: Based on the convenience coefficient of each parking trajectory Filter out the parking lot entrance to the parking space i The optimal parking trajectory .

2. The method for dynamic allocation and scheduling of parking spaces in an intelligent parking lot according to claim 1 is characterized in that: The step S3 comprises: Step S31: Obtain the type and quantity data of vehicles entering the parking lot at each time period every day; ； ； in, For the number of historical days, Number the historical days. For each historical day, is the time period number, For the history Day time The number of fuel trucks entering the parking lot, For the history Day time The number of new energy vehicles entering the parking lot; Step S32: Extract the corresponding time period of each day in history The vehicle data is used as the training data set , , , For the period The number of vehicles entering the parking lot, and the construction of a prediction model to predict the number of vehicles entering the parking lot at different times of the day ; ； in, Forecast period Number of parking lots to enter, is the regression coefficient, p is the number of the regression coefficient, P is the number of regression terms, is the error term, For the previous day The number of vehicles entering the parking lot; Step S33: Take the training data set in reverse order Middle and back P Data Input into the prediction model, , output the trained regression coefficient and error term, and obtain the fuel vehicle prediction model after training; Step S34: Get training data set Data in Input the fuel vehicle prediction model after training, and output the history Day time Predicted number of fuel vehicles entering the parking lot , and calculate the actual number of vehicles The error coefficient ; ； Step S35: Return to step S34 and obtain the training data set Data in Input the prediction model after training and calculate the error coefficient ; Step S36: until the training data set is calculated Data in forward P After the error coefficients related to the data, the accuracy coefficient of the fuel vehicle prediction model at the end of training is calculated ; ； Step S37: Repeat steps S33-S36, according to the training data set The number of training data that can be extracted from the combination is used to obtain several fuel vehicle prediction models that have been trained to form a fuel vehicle prediction model set ; Step S38: Construct the constraint conditions for selecting the optimal fuel vehicle prediction model, and obtain the optimal prediction model for predicting the number of fuel vehicles entering the parking lot at each time period every day. ; ； Step S39: Repeat steps S33-S38, using the training data set Training prediction models with data from , and obtain the optimal prediction model for predicting the number of new energy vehicles entering the parking lot at different times of the day .

3. The method for dynamic allocation and scheduling of parking spaces in an intelligent parking lot according to claim 2 is characterized in that: The step S4 comprises: Step S41: Input the optimal prediction model according to the number of fuel vehicles and new energy vehicles entering the parking lot at each day and time period in history and the optimal prediction model In the forecast, the number of new energy vehicles entering the parking lot at different times tomorrow is predicted. and the number of fuel vehicles ; Step S42: Utilize the number of new energy vehicles and the number of fuel vehicles Calculate the number of new energy parking spaces that need to be open at different times tomorrow and number of fuel parking spaces ; This is the largest number of new energy vehicles entering the parking lot in history. This is the largest number of fuel vehicles entering the parking lot in history. are the corresponding reservation coefficients respectively; Step S43: Construct an open allocation model for new energy parking spaces and fuel parking spaces in the parking lot based on the distribution of parking spaces in the parking lot and the convenience coefficient corresponding to each parking space ; ； in, According to the number of new energy parking spaces A collection of allocated new energy parking spaces, Collection for new energy parking spaces The number of the new energy parking space in It is a collection of new energy parking spaces in the parking lot. To reach the new energy parking space from the parking lot entrance The convenience coefficient corresponding to the optimal parking trajectory is: According to the number of fuel parking spaces Assigned fuel parking space collection, Assemble for fuel parking The number of the fuel parking space in For the fuel parking spaces in the parking lot, To get to the fuel parking space from the parking lot entrance The convenience coefficient corresponding to the optimal parking trajectory; Step S44: According to the open allocation model After allocating the new energy parking spaces and fuel parking spaces that need to be open at different times in the parking lot tomorrow, the license plate recognition system at the entrance of the parking lot will identify the vehicle type and use the parking guidance system in the parking lot to guide and dispatch the vehicles to the corresponding parking spaces based on the parking space allocation. The charging piles in the unallocated new energy parking spaces will be shut down.

4. A smart parking lot parking space dynamic allocation and scheduling system, executing the smart parking lot parking space dynamic allocation and scheduling method according to any one of claims 1 to 3, characterized in that: include: The license plate recognition system is installed at the entrance of the parking lot to identify the type of vehicles entering the parking lot, including new energy vehicles and fuel vehicles; Guidance and dispatching system, electronic traffic guidance signs installed in the parking lot, parking locks installed on parking spaces, electronic traffic guidance signs display corresponding traffic guidance signs, guide vehicles into the parking area according to the allocation of new energy parking spaces and fuel parking spaces in the parking lot, and lock the unallocated parking spaces in the parking lot; An information collection module is connected to the license plate recognition system, the guidance and dispatching system, and the charging pile management module through a wireless module or a wired communication module to collect information fed back by the license plate recognition system, the guidance and dispatching system, and the charging pile management module; The charging pile management module is connected to the charging piles on the new energy parking spaces and controls the start or shut down of the charging piles according to the allocation of new energy parking spaces; The data processing center is used to store and analyze historical vehicle information in the parking lot, and to allocate and schedule parking spaces that need to be opened in the parking lot.

Images