Intelligent multiplexing method for parking space of intelligent building and parking space server

Abstract

The invention discloses an intelligent multiplexing method for parking space of an intelligent building and a parking space server. The method comprises the steps that the parking time length of an entering vehicle is intelligently predicted based on historical parking data, and when the predicted parking time length is smaller than the available time length of a loading and unloading area, a server can select the most suitable target virtual parking unit from a plurality of virtual parking units of the loading and unloading area to serve as a target parking space of the entering vehicle based on a priority coefficient. According to the invention, the contradiction between the shortage of parking spaces and the idle resources of the loading and unloading area in the peak period of the intelligent building is effectively solved, and the utilization efficiency of parking resources is improved.

Description

Technical Field

[0001] This application relates to intelligent building parking management, and more particularly to an intelligent building parking space intelligent reuse method and parking space server. Background Technology

[0002] With the acceleration of urbanization and the rapid growth of vehicle ownership, the problem of urban parking difficulties has become increasingly prominent. As an important component of modern urban infrastructure, how to maximize the utilization efficiency of parking resources in limited spaces has become a significant technological challenge for modern intelligent buildings.

[0003] In related technologies, intelligent building parking lots generally use physical partitions to divide the site into regular parking areas and loading / unloading areas. Regular parking areas are equipped with geomagnetic sensors and monitoring servers to detect parking space occupancy in real time. Loading / unloading areas are scheduled using pre-programmed schedules, opening to logistics vehicles for operations during specific time periods.

[0004] In practice, loading and unloading areas are typically either open or closed as a single, complete space. During peak hours, parking spaces in regular parking areas are scarce, so these areas are either completely unused due to physical enclosure, or the limited space occupied by parked vehicles results in underutilization of the space. Consequently, the space in loading and unloading areas cannot be used flexibly according to actual needs, affecting the efficient utilization of the overall parking lot space. Summary of the Invention

[0005] This application provides a method for intelligent reuse of parking space in smart buildings and a parking space server, which can be used to plan temporary parking in loading and unloading areas during idle periods, effectively solving the contradiction between parking space shortage and idle resources in loading and unloading areas during peak hours in smart buildings.

[0006] In a first aspect, this application provides a method for intelligent reuse of parking space in smart buildings, applied to a parking space server. The method includes: when the number of vacant parking spaces in a parking lot is less than a preset value and the remaining time for the unloading area to have no unloading tasks is a first duration, identifying a first vehicle waiting to park through a camera at the entrance of the parking lot, wherein the first duration is greater than a preset buffer duration; determining the predicted parking duration of the first vehicle waiting to park based on a historical parking database; when the predicted parking duration is determined to be less than the first duration, determining the target virtual parking unit from among multiple virtual parking units divided based on standard parking spaces in the unloading area, wherein the highest priority coefficient among the remaining virtual parking units is selected, and the priority coefficient is determined based on the distance of each virtual parking unit from the unloading channel, the distribution of surrounding obstacles, and historical usage frequency; determining a first parking space boundary from the vacant area of ​​the unloading area based on the target virtual parking unit; projecting the first parking space boundary onto the ground through a ground projection device to obtain a first temporary parking space located in the unloading area; and sending guidance information to guide the first vehicle waiting to park from the parking lot entrance to the first temporary parking space.

[0007] In the above embodiments, the parking space server dynamically matches the parking space occupancy status of the parking lot with the task time window of the loading and unloading area. When it is determined that the vehicle waiting to park meets the temporary parking conditions by combining the prediction of the vehicle parking time, the server quickly provides a suitable temporary parking space for the vehicle waiting to park through the priority evaluation of the virtual parking unit. This realizes the efficient conversion of temporary parking resources during the idle period of the loading and unloading area, effectively solves the contradiction between the shortage of parking spaces and the idle resources in the loading and unloading area during peak hours in smart buildings, and improves the overall space utilization efficiency of the building.

[0008] In conjunction with some embodiments of the first aspect, in some embodiments, before the step of identifying the first waiting vehicle through the camera at the entrance of the parking lot when the number of vacant parking spaces in the parking lot is less than a preset value and the remaining time without loading and unloading tasks in the loading and unloading area is a first time, the method further includes: issuing a lifting command to the lifting isolation column at the boundary of the loading and unloading area when it is determined that the remaining time without loading and unloading tasks in the loading and unloading area is less than a preset buffer time.

[0009] In the above embodiment, the parking space server first determines whether the remaining time without loading / unloading tasks in the loading / unloading area is less than a preset buffer time. If it is less than the preset buffer time, a raising command is issued to raise the lifting isolation pillars at the boundary of the loading / unloading area, thereby physically preventing external vehicles from entering. This predictive mechanism avoids vehicles entering the loading / unloading area when loading / unloading tasks are about to begin, reducing vehicle entry and exit conflicts. Simultaneously, by setting a preset buffer time as a judgment criterion, the system can reserve space and time in advance for upcoming loading / unloading tasks, enhancing the resource utilization efficiency of the loading / unloading area.

[0010] In conjunction with some embodiments of the first aspect, in some embodiments, the step of determining the predicted parking duration of the first vehicle to be parked based on a historical parking database specifically includes: comparing the current entry time with historical entry times to determine the similarity of time characteristics between different historical records and the current record, wherein the similarity of time characteristics is determined based on the same weekday or weekend, similar time period, and similar season; and calculating the predicted parking duration by assigning different weights to different historical records based on the degree of time similarity.

[0011] In the above embodiment, the parking space server assigns different weights to the determined historical records based on their temporal similarity; historical records with higher temporal similarity receive a larger weight coefficient, while those with lower similarity receive a smaller weight. Through this weighted calculation method, the system ultimately arrives at a more reasonable predicted parking duration. This differentiated weight allocation mechanism effectively solves the deficiency of the traditional simple averaging method, which treats all historical data equally, making the prediction results more reflective of parking behavior characteristics in the current time context, and improving the accuracy and practicality of parking space allocation decisions.

[0012] In conjunction with some embodiments of the first aspect, in some embodiments, the step of determining the boundary of the first parking space from the vacant area of ​​the loading and unloading area based on the target virtual parking unit specifically includes: performing spatial overlap analysis based on the preliminary parking space boundary and the no-parking area to determine whether the target virtual parking unit can meet the parking needs of the first vehicle waiting to park. The preliminary parking space boundary is determined based on the actual outline of the first vehicle waiting to park and the width of a preset buffer zone. The no-parking area is determined based on the volume and position of obstacles within the target virtual parking unit. The parking needs are that the overlap area between the preliminary parking space boundary and the no-parking area is less than a preset threshold and the vehicle's key operating points are not obstructed. If the parking needs of the first vehicle waiting to park cannot be met, a curve boundary re-division method is used to re-divide the boundary between the target virtual parking unit and the adjacent virtual parking unit based on the spline curve generated according to the actual vehicle outline and operating needs. Based on the re-divided boundary of the target virtual parking unit, an irregular rectangular first parking space boundary is determined from the vacant area of ​​the loading and unloading area.

[0013] In the above embodiment, the parking space server accurately assesses the overlap between the initial parking space boundary and the no-parking zone through spatial overlap analysis, and determines whether the dual conditions of the overlapping area being less than a preset threshold and the vehicle's key operating points being unobstructed are met. This boundary determination method based on actual vehicle characteristics and environmental constraints greatly improves the rationality of parking space allocation and the safety of vehicle parking.

[0014] In conjunction with some embodiments of the first aspect, in some embodiments, if the parking needs of the first vehicle waiting to be parked cannot be met, a curve boundary re-division method is adopted. After the step of re-dividing the boundary between the target virtual parking unit and the adjacent virtual parking unit based on the spline curve generated according to the actual vehicle outline and operational requirements, the method further includes: when a first adjacent vehicle is parked in the first adjacent unit of the adjacent virtual parking units, determining the shared area of ​​the first adjacent vehicle and the first vehicle waiting to be parked based on spatial overlap analysis of the space formed by the spline curve and the actual parking space of the first adjacent vehicle; and determining the boundary between the target virtual parking unit and the first adjacent unit based on the shared area.

[0015] In the above embodiments, the parking space server can scientifically determine the actual boundary between the target virtual parking unit and the first adjacent unit based on the shared area. This boundary determination technology based on the shared area effectively solves the problem of improving the utilization rate of parking space, while ensuring a reasonable distance between vehicles and reducing parking difficulties and vehicle damage risks caused by improper space allocation.

[0016] In conjunction with some embodiments of the first aspect, in some embodiments, after the step of sending guidance information to guide the first vehicle to be parked from the parking lot entrance to the first temporary parking space, the method further includes: if it is determined that the remaining time is less than a preset buffer time and the first vehicle to be parked has not left, calculating a safety index for the intelligent moving robot to move the first vehicle to be parked from the first temporary parking space to each sampled virtual parking unit, wherein the sampled virtual parking unit is an idle virtual parking unit within a sampling partition, the sampling partition is obtained by partitioning idle virtual parking units with priority coefficients higher than a specified coefficient according to the priority coefficient, and the safety index is calculated based on path width, turning radius, and obstacle avoidance space sufficiency; determining the sampled virtual parking unit with the highest comprehensive index as the target moving parking unit based on a comprehensive index obtained by weighting the safety index and priority coefficient of the sampled virtual parking units; and sending a moving instruction to the intelligent moving robot based on the target moving parking space boundary determined by the target moving parking unit, the moving instruction including the vehicle position, vehicle characteristic parameters, and target moving parking space boundary of the first vehicle to be parked.

[0017] In the above embodiment, the parking space server continuously monitors the remaining time in the loading and unloading area. When the remaining time is less than the preset buffer time and the first waiting vehicle has not yet left, the vehicle relocation plan is automatically activated. By comparing the comprehensive index of different sampled virtual parking units, the system can intelligently determine the unit with the highest comprehensive index as the target parking unit to be relocated. This comprehensive decision-making mechanism considers both the safety of vehicle relocation and the priority of parking spaces, achieving optimal allocation of parking resources and improving the operational efficiency and safety of the loading and unloading area.

[0018] In conjunction with some embodiments of the first aspect, in some embodiments, the step of determining the sampled virtual parking unit with the highest comprehensive index as the target parking unit based on the comprehensive index obtained by weighting the safety index and priority coefficient of the sampled virtual parking units specifically includes: excluding first sampled virtual parking units with a comprehensive index lower than the minimum acceptable comprehensive index threshold based on the comprehensive index obtained by weighting the safety index and priority coefficient of the sampled virtual parking units; determining the safety index and comprehensive index of a second sampled virtual parking unit located in the same sampling interval as the first sampled virtual parking unit, wherein the second sampled virtual parking unit is different from the first sampled virtual parking unit; and determining the sampled virtual parking unit with the highest comprehensive index as the target parking unit.

[0019] In the above embodiment, the parking space server sets a minimum acceptable comprehensive index threshold to perform preliminary screening of the calculation results and automatically exclude the first sampled virtual parking units whose comprehensive index is lower than the threshold. This multi-screening strategy avoids the system from selecting parking units with poor comprehensive performance based solely on relative comparison, thereby enhancing the reliability and security of scheduling decisions and ensuring the basic quality standards of the vehicle dispatching process.

[0020] In a second aspect, embodiments of this application provide a parking space server, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, and the memory is used to store computer program code, which includes computer instructions, and the one or more processors call the computer instructions to cause the parking space server to perform the method described in the first aspect and any possible implementation thereof.

[0021] Thirdly, embodiments of this application provide a computer program product containing instructions that, when the computer program product is run on a parking space server, cause the parking space server to perform the method described in the first aspect and any possible implementation thereof.

[0022] Fourthly, embodiments of this application provide a computer-readable storage medium including instructions that, when executed on a parking space server, cause the parking space server to perform the method described in the first aspect and any possible implementation thereof.

[0023] Understandably, the parking space server provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the methods provided in the embodiments of this application. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.

[0024] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages: 1. By dynamically matching parking space occupancy with the task time window of the loading and unloading area, and quickly providing suitable temporary parking spaces for waiting vehicles through priority evaluation of virtual parking units, the system achieves efficient conversion of temporary parking resources during idle periods in the loading and unloading area. This effectively solves the contradiction between parking space shortages and idle resources in the loading and unloading area during peak hours in smart buildings, and improves the overall space utilization efficiency of the building.

[0025] 2. By adopting boundary determination technology based on shared areas, reasonable spacing between vehicles is ensured, effectively solving the parking difficulties caused by improper space allocation in existing technologies, thereby improving the utilization rate of parking space.

[0026] 3. By employing a comprehensive index calculated by weighting the safety index and priority coefficient of sampled virtual parking units, and determining the sampled virtual parking unit with the highest comprehensive index as the target parking unit to be moved, this comprehensive decision-making mechanism considers both the safety of moving the vehicle and the priority of the parking space. It effectively solves the limitations of the single-dimensional evaluation of vehicle moving decisions in existing technologies, improves the operational efficiency and safety of the loading and unloading area, and thus achieves dynamic optimization of parking resource allocation. Attached Figure Description

[0027] Figure 1 This is a flowchart illustrating a method for intelligent reuse of parking space in smart buildings, as described in this application. Figure 2 This is another flowchart illustrating a method for intelligent reuse of parking space in intelligent buildings, as described in this application. Figure 3 This is a schematic diagram of the physical device structure of a parking space server in an embodiment of this application. Detailed Implementation

[0028] The terminology used in the following embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. As used in the specification of this application, the singular expressions “a,” “an,” “the,” “the,” and “this” are intended to include the plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this application refers to any or all possible combinations including one or more of the listed items.

[0029] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature, and in the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more.

[0030] The following describes a method for intelligent reuse of parking space in smart buildings, as described in an embodiment of this application: Please see Figure 1 This is a flowchart illustrating a method for intelligent reuse of parking space in smart buildings, as described in this application.

[0031] S101. When the number of vacant parking spaces in the parking lot is less than the preset value and the remaining time when there is no loading or unloading task in the loading and unloading area is the first time, the first vehicle to be parked is identified by the camera at the entrance of the parking lot.

[0032] The parking lot refers to a specific area for temporary or long-term parking of vehicles. It is usually equipped with a historical parking record system, a license plate recognition system, and a parking guidance system. In this technical solution, the parking lot is divided into two functional areas: a general parking area and a loading and unloading area, which serve different types of vehicles and parking needs respectively.

[0033] The parking space server can first detect the number of occupied parking spaces in the ordinary parking area of ​​the parking lot in real time through the license plate recognition system, and then use the total number of parking spaces minus the number of occupied parking spaces to obtain the real-time number of vacant parking spaces in the parking lot.

[0034] The parking space server can also query the task database of the loading and unloading area (including historical loading and unloading tasks and scheduled loading and unloading tasks) to find out whether the loading and unloading area is currently empty. If it is empty, no loading and unloading task has been performed. When the loading and unloading area is detected to be empty, the remaining time without loading and unloading tasks in the loading and unloading area is calculated as the first time.

[0035] When the number of vacant parking spaces in the parking lot is less than the preset value and the first duration is greater than the preset buffer duration, the parking space server identifies and obtains the vehicle information of the entering vehicle (the first vehicle waiting to park) through the camera at the entrance of the parking lot, including the license plate number, vehicle size parameters, and entry timestamp.

[0036] The preset values ​​are used to assess the scarcity of parking spaces in the parking lot. They are set based on a certain percentage of the total number of parking spaces, usually 15%-20%, but no specific limit is set here. The preset buffer time is a predetermined safety margin to ensure that temporary parking will not affect subsequent loading and unloading operations. The entry timestamp is the precise time data automatically recorded by the server when a vehicle passes through the parking lot entrance, including year, month, day, hour, minute, second, and millisecond information.

[0037] It is understood that there are many ways to determine the preset buffer duration: in some embodiments, the preset buffer duration can be determined by calculating the average difference between the actual start time and the predetermined start time of historical loading and unloading tasks; in some embodiments, the preset buffer duration can also be determined based on the average operation time of vehicles entering and leaving the loading and unloading area, which is not limited here.

[0038] In some embodiments, the server first determines whether the remaining time without loading or unloading tasks in the loading and unloading area is less than a preset buffer time. If it determines that the time is less than the preset buffer time, it issues a rejection command to raise the lifting isolation column at the boundary of the loading and unloading area, thereby physically preventing external vehicles from entering.

[0039] S102. Determine the predicted parking duration of the first vehicle to be parked based on the historical parking database.

[0040] The historical parking record database represents a data storage system that stores all vehicle parking information, including vehicle information and parking duration.

[0041] When the first vehicle waiting to park arrives at the parking lot entrance and is recognized by the server, the server determines whether the vehicle is suitable for temporary parking in the loading and unloading area by evaluating the vehicle's predicted parking duration.

[0042] In some embodiments, the predicted parking duration is the average historical parking duration of the first vehicle waiting to be parked.

[0043] In other embodiments, the predicted parking duration is obtained by weighting the historical parking durations of the first vehicle waiting to park. Specifically: the parking server first retrieves all historical parking records for the vehicle with the license plate number and entry timestamp from the historical parking record database, constructing an analysis dataset that includes historical entry timestamps and corresponding parking durations. Based on the analysis dataset, the server compares the temporal similarity between the current entry time and historical entry times (e.g., same weekday or weekend, similar time period, similar season). Different weights are assigned to different historical records based on the degree of temporal similarity (records with higher similarity have greater weight). Finally, the server applies these weights to calculate a weighted average of the historical parking durations to obtain a predicted parking duration value.

[0044] S103. When it is determined that the predicted parking time is less than the first time, the target virtual parking unit is determined from the multiple virtual parking units that are divided into standard parking spaces for the loading and unloading area. The unit with the highest priority coefficient among the remaining virtual parking units is selected.

[0045] The parking space server first determines that the predicted parking time of the first vehicle waiting to park is less than the remaining time when there are no loading or unloading tasks in the loading and unloading area, indicating that the vehicle can temporarily use the loading and unloading area without affecting subsequent loading and unloading operations. At the same time, the server acquires images of the loading and unloading area through cameras and uses computer vision to accurately match the captured images with a pre-stored virtual parking unit map, thereby accurately identifying all unoccupied virtual parking units (remaining virtual parking units). From the internally stored virtual parking unit map database, the server extracts the priority coefficient of each remaining virtual parking unit and sorts these remaining units from high to low priority coefficient to form a candidate unit list. The virtual parking unit with the highest priority coefficient is selected as the target virtual parking unit.

[0046] It should be noted that the parking space server internally stores a high-precision parameter map of the loading and unloading area, and this map has been systematically preprocessed: First, the parking space server accurately divides the map into multiple virtual parking units based on standard parking space dimensions, and assigns a unique ID number to each unit. The standard parking space dimensions are pre-designed, standardized parking space dimensions obtained from standard documents. Then, the parking space server establishes a one-to-one data link relationship between the ID number of each unit and its corresponding precise geographic coordinates and boundary contours. Next, the parking space server periodically performs priority evaluation calculations for each virtual parking unit. Finally, this information is integrated to construct a structured virtual parking unit map database.

[0047] In some embodiments, the priority coefficient is the distance from the loading / unloading channel, with greater distance resulting in higher priority. In other embodiments, the priority coefficient is the distribution density of surrounding obstacles, with lower obstacle density and greater distance resulting in higher priority. In some embodiments, the priority coefficient is the historical usage frequency, with higher historical usage frequency resulting in higher priority. In still other embodiments, the priority coefficient is obtained by weighting the distance from the loading / unloading channel, the distribution density of surrounding obstacles, and the historical usage frequency. It is understood that other methods can also be used to generate and evaluate the priority coefficient, such as using a predictive model trained based on historical allocation success rate and user satisfaction feedback data using machine learning algorithms; this is not limited here.

[0048] S104. Based on the target virtual parking unit, determine the boundary of the first parking space from the vacant area of ​​the loading and unloading area.

[0049] The boundary of the first parking space is the boundary outline of the target virtual parking unit.

[0050] After identifying the target virtual parking unit, the parking space server extracts the precise coordinate data and boundary contour of the target virtual parking unit from the virtual parking unit map database; based on the precise coordinate data and boundary contour, it determines the positions of the four vertices of the first parking space boundary within the loading and unloading area and connects them to form a closed polygonal area, which serves as the parking space boundary for the first vehicle waiting to park.

[0051] S105. The boundary of the first parking space is projected onto the ground using a ground projection device to obtain the first temporary parking space located in the loading and unloading area.

[0052] Among them, ground projection equipment refers to hardware devices used to project parking space boundaries onto the ground, such as smart projectors; smart projectors refer to devices that can receive instructions from parking space servers and automatically project parking space boundaries.

[0053] Understandably, multiple projectors were pre-arranged in a grid pattern on the ceiling of the loading and unloading area, with each projector responsible for projecting coverage of a specific area.

[0054] After determining the parking space boundary, the parking space server activates one or more projectors in the corresponding area based on the coordinate data of the first parking space boundary, and moves these projectors above the parking space via a sliding rail. Then, these projectors automatically adjust the projection angle and content through collaborative calibration technology to form a complete and distortion-free parking space boundary projection.

[0055] Specifically, the collaborative calibration technology first deploys specific markers in the corresponding projection area of ​​the loading and unloading area through the boundary of the first parking space to establish a correspondence with the actual physical space. Then, the server calculates the position, angle and projection distortion parameters of each projection device relative to the projection target surface to generate an accurate projection matrix. Next, the server pre-deforms the original parking space boundary image based on these parameters so that it can present the correct shape and proportion on the ground after projection.

[0056] S106. Send guidance information to guide the first vehicle waiting to park from the parking lot entrance to the first temporary parking space.

[0057] Among them, guidance information refers to the navigation and instruction data provided by the parking space server to the driver, which refers to the route guidance and location description to help vehicles accurately find temporary parking spaces; the parking guidance system is a special combination of hardware and software responsible for calculating the best route and providing guidance instructions.

[0058] After the ground projection of the first temporary parking space is completed, the parking server provides precise guidance to the driver of the first waiting vehicle so that he can find the assigned temporary parking space smoothly.

[0059] Specifically, the parking space server first sends the current exact location of the first vehicle waiting to park (usually the parking lot entrance) and the precise coordinates of the first temporary parking space to the parking lot's parking guidance system. The parking guidance system takes into account real-time factors such as current road congestion, distribution of temporary obstacles, and one-way street settings within the building to calculate the optimal path. Then, the parking space server combines the path data with the precise location information of the first temporary parking space to form complete guidance information. Finally, the parking space server sends the guidance information to the electronic display screen at the entrance for display.

[0060] It is understandable that parking guidance systems are existing technology, and will not be explained here.

[0061] In this embodiment, by dynamically matching the parking space occupancy status with the task time window of the loading and unloading area, and combining the prediction of vehicle parking duration to determine that the waiting vehicle meets the temporary parking conditions, a suitable temporary parking space is quickly provided to the waiting vehicle through priority evaluation of the virtual parking unit. This achieves efficient conversion of temporary parking resources during idle periods in the loading and unloading area, effectively solves the contradiction between the shortage of parking spaces and the idle resources in the loading and unloading area during peak hours in smart buildings, and improves the overall space utilization efficiency of the building.

[0062] The embodiments described above demonstrate that by planning temporary parking for vehicles during the off-peak hours in the loading and unloading area, the resource utilization of parking space can be improved, and the parking burden during peak hours can be reduced. However, in practical applications, the dynamic division of the loading and unloading area is also a key factor affecting the rational allocation of temporary parking spaces in intelligent buildings. Therefore, combining this with non-fixed division of parking space boundaries can effectively help the parking space server flexibly adjust the location and size of temporary parking spaces according to different vehicle sizes and the real-time status of the loading and unloading area, maximizing the utilization of available space resources.

[0063] like Figure 2 The diagram shown is another flowchart illustrating a method for intelligent reuse of parking space in smart buildings, as provided in an embodiment of this application. The method is described in detail below: S201. When the number of vacant parking spaces in the parking lot is less than the preset value and the remaining time when there is no loading or unloading task in the loading and unloading area is the first time, the first vehicle to be parked is identified by the camera at the entrance of the parking lot.

[0064] S202. Determine the predicted parking duration of the first vehicle to be parked based on the historical parking database.

[0065] S203. When it is determined that the predicted parking time is less than the first time, the target virtual parking unit is determined from the remaining virtual parking units that are divided into multiple virtual parking units based on standard parking spaces in the loading and unloading area.

[0066] Steps S201 to S203 are similar to steps S101 to S103, and will not be described again here.

[0067] S204. Perform spatial overlap analysis on the space formed by the initial parking space boundary and the no-parking zone around the target virtual parking unit to obtain the size of the overlap area between the two spaces.

[0068] The parking space server first uses laser scanning technology to directly measure the actual outline dimensions of the entering vehicle. Then, it adds a preset buffer width in each direction of the vehicle's outline to obtain the initial parking space boundary. The preset buffer width is a safety distance added outside the vehicle outline, typically 0.5-0.8 meters, but not limited here. When the initial parking space boundary is completely inside the target virtual parking unit, the server performs spatial overlap analysis to determine whether the initial parking space boundary overlaps with the no-parking zone and the area of ​​overlap.

[0069] Specifically, the parking space server first converts the initial parking space boundaries and no-parking areas into a finite set of vertices, forming a polygon or polyhedron representation; then it transforms the two regions into the same coordinate system and uses computational geometry algorithms (such as scanline algorithm, divide-and-conquer algorithm, etc.) to calculate the intersection of the two regions; finally, it calculates the volume, area, and boundary of the intersection region.

[0070] It should be noted that no-parking zones are recorded in the virtual parking unit map database. After each loading and unloading task is completed in the loading and unloading area, the parking space server obtains the existence and specific location data of obstacles in the loading and unloading area through scanning equipment.

[0071] S205. Based on the size of the overlapping area and whether the key operation points are obstructed, determine whether the target virtual parking unit can meet the parking needs of the first vehicle waiting to park.

[0072] Among them, the key operating points of the vehicle are the driver's side door, the passenger side door, and the vehicle's trunk or cargo area, ensuring that the doors can be fully opened.

[0073] The parking space server first compares the overlap area between the obtained preliminary parking space boundary and the no-parking zone with a preset threshold. The preset threshold is the upper limit of the maximum allowed overlap area, which is usually set as a small percentage (e.g., 5%) of the total area of ​​the preliminary parking space boundary. Then, by determining whether the distance between the vehicle's corresponding door and the obstacles around the target virtual parking unit is less than 0.75m, it judges whether these key operation points will be blocked (if the distance is less than 0.75m, it is judged as blocked).

[0074] If the overlap area between the initial parking space boundary and the no-parking zone is less than a preset threshold and the vehicle's key operation points are not obstructed, then it is determined that the target virtual parking unit can meet the parking needs of the first vehicle waiting to park, and step S209 is executed.

[0075] If the overlap area between the initial parking space boundary and the no-parking zone is not less than a preset threshold or the vehicle's key operation points are blocked, then it is determined that the target virtual parking unit cannot meet the parking needs of the first vehicle waiting to park, and step S206 is executed.

[0076] S206. Using the curve boundary re-division method, the boundary between the target virtual parking unit and the adjacent virtual parking unit is re-divided based on the spline curve generated according to the actual vehicle contour and parking requirements.

[0077] Among them, the curved boundary redefinition method refers to the technical method of redefining the parking space boundary using curves instead of straight lines; the actual vehicle profile represents the true external boundary shape of the vehicle.

[0078] The parking space server first proportionally expands the parking space area of ​​the target virtual parking unit to ensure that the overlapping area is not less than a preset threshold. Then, based on the condition that the distance between the corresponding vehicle door and the obstacles around the target virtual parking unit is 0.75m, a spline curve is drawn on the border of the expanded virtual parking unit. The spline curve is a mathematical curve that can smoothly connect multiple control points. Finally, the parking space server generates a non-rectangular boundary line based on the spline curve and uses this boundary line as the boundary between the target virtual parking unit and adjacent virtual parking units.

[0079] In some embodiments, after the server re-divides the boundary of the target virtual parking unit, it checks whether there are vehicles parked in the adjacent units of the target virtual parking unit by querying the server's historical operation database. If a vehicle is detected parked in an adjacent unit, the server obtains the specific parking location of the vehicle by reading sensor data. Then, the system performs spatial overlap analysis on the space formed by the re-dividation of the boundary and the actual parking space of the first adjacent vehicle. If the overlap area is less than a preset threshold, the overlap area is determined to be the shared area of ​​the adjacent vehicle. In the direction perpendicular to the two vehicles in the overlap area, the boundary of the two adjacent virtual parking units is re-divided according to the curve formed by connecting the midpoints of the overlap area in this direction.

[0080] S207. Based on the redefined target virtual parking unit boundary, determine the first parking space boundary of the irregular rectangle from the vacant area of ​​the loading and unloading area.

[0081] S208. The boundary of the first parking space is projected onto the ground using a ground projection device to obtain the first temporary parking space located in the loading and unloading area.

[0082] S209. Send guidance information to guide the first vehicle waiting to park from the parking lot entrance to the first temporary parking space.

[0083] Steps S207 to S209 are similar to steps S104 to S106, and will not be described again here.

[0084] S210. Determine whether the first vehicle waiting to stop has left the first temporary parking space.

[0085] The parking space server determines whether the first vehicle waiting to park has left based on the license plate recognition system at the parking lot entrance and exit.

[0086] If the vehicle leaves, proceed to step S214.

[0087] If the vehicle has not left, proceed to step S211.

[0088] S211. If the first duration is equal to the preset buffer time, calculate the safety index of the intelligent vehicle moving robot moving the first vehicle to be parked from the first temporary parking space to each sampled virtual parking unit.

[0089] Among them, intelligent vehicle moving robots typically have precise positioning, vehicle docking, and autonomous navigation functions. They adopt a wheeled chassis design, allowing them to slide under vehicles, rise and support them, and then autonomously complete the moving task based on the received path and vehicle information.

[0090] The parking space server first determines the current time frame as equal to the preset buffer time based on the remaining time without loading or unloading tasks in the loading / unloading area, according to the real-time detection. Then, it partitions the idle virtual parking units with priority coefficients higher than a specified coefficient according to the priority coefficient (if the priority coefficient is 1-100 points, it is generally divided into zones with intervals of 5 points above the specified coefficient). The specified coefficient is a pre-set priority coefficient, which is generally higher than the priority coefficient of 70% of the virtual parking units, but is not limited here. Next, one idle virtual parking unit is sampled from each zone as the sampled virtual parking unit for that zone. Finally, it determines the safety index of each sampled virtual parking unit for moving the vehicle from the first temporary parking space to each sampled virtual parking unit. The safety index is the safety assessment score for the intelligent car moving robot to move the vehicle from one location to another, based on the path width, turning radius, and obstacle avoidance space. The larger the path width, the higher the score; the larger the turning radius, the higher the score; and the larger the obstacle avoidance space, the higher the score.

[0091] The safety index can be calculated in several ways: In some embodiments, the server's parking guidance system can plan multiple possible paths (generally 1-2 shortest paths) for each sampled virtual parking unit on a high-precision parameter map of the loading and unloading area. Based on the planned paths, the server uses sensors (such as LiDAR and cameras) to perform a full-range scan of the path from the first temporary parking space to each sampled virtual parking unit, acquiring path width, turning radius, and obstacle distribution data. The acquired data is then processed to calculate the minimum width, minimum turning radius, and minimum obstacle avoidance space for each path. These three indicators are then weighted according to preset weights to obtain a comprehensive safety index.

[0092] In some embodiments, the accuracy of data acquisition can be improved by constructing a high-precision three-dimensional digital model: First, a high-precision three-dimensional digital model of the loading and unloading area is constructed. Comprehensive information about the loading and unloading area is obtained through data acquisition technology, including the spatial dimensions of the actual environment, object positions, and ground conditions. Based on the acquired raw data (point cloud data), processing and fusion are performed. First, noise filtering, registration, and merging are performed on the point cloud data to generate a unified environmental geometric model. Then, feature recognition and segmentation are performed to classify the point cloud data into different structural elements such as ground, walls, and columns. Next, image data and the environmental geometric model are fused. Finally, CAD model conversion is performed to identify... The structural elements are converted into a parametric computer-aided design model. Prior information, including architectural floor plans and engineering drawings, is then imported into the model to verify and refine it. Ground material and friction coefficient data are also imported for accurate physical simulation calculations. Finally, the server implements layered environmental modeling, designating fixed facilities (such as building structures, pillars, and fixed equipment) as the bottom-level foundation model, temporary facilities (such as mobile devices and temporary storage) as the intermediate dynamic layer, and other vehicles and moving obstacles as the top-level real-time updating layer. The server then imports detailed parametric models of the target vehicle into the model, including vehicle dimensions and wheelbase.

[0093] In the simulation, the server sets the starting point (first temporary parking space) and the ending point (sampled virtual parking unit), and generates the initial movement path of the intelligent moving robot through a path planning algorithm. Then, the server applies a physics engine to calculate the position, direction, speed, and acceleration changes of the moving robot step by step at small time steps (usually 10-50 milliseconds), simulating the entire process of the intelligent moving robot controlling the vehicle's movement. The time step refers to the time interval between two consecutive calculations in the physics simulation. At the same time, it performs real-time precise calculations of the minimum distance between the vehicle and the surrounding environment and records key path parameters, including effective channel width, actual turning radius, and available avoidance space.

[0094] It is understandable that other methods can be used to calculate the security index, and no restrictions are imposed here.

[0095] S212. Based on the comprehensive index obtained by weighting the safety index and priority coefficient of the sampled virtual parking units, the sampled virtual parking unit with the highest comprehensive index is determined as the target mobilization parking unit.

[0096] Among them, the target parking unit is the designated target location for the intelligent moving robot to move to; the comprehensive index is the overall score calculated by weighting the safety index and the priority coefficient. The corresponding index can be adjusted according to different management strategies (e.g., in the safety priority mode, the safety index is 0.7 and the priority coefficient is 0.3, emphasizing safety considerations), which is not limited here; the comprehensive index threshold is the minimum evaluation index for the intelligent moving robot to perform moving operations. It is generally set based on the parameters of the intelligent moving robot and historical usage data, which is not limited here.

[0097] The parking space server calculates the comprehensive index of the sampled virtual parking units by weighting the safety index and priority coefficient of the sampled virtual parking units according to the set corresponding index. Then, all comprehensive indices are arranged from smallest to largest, and finally the sampled virtual parking unit with the highest comprehensive index is determined as the target parking unit for the intelligent moving robot.

[0098] In some embodiments, the parking space server calculates the comprehensive index of a sampled virtual parking unit by weighting the safety index and priority coefficient of the sampled virtual parking unit according to a set corresponding index. Then, it compares the comprehensive index of the sampled virtual parking unit with a comprehensive index threshold. If the comprehensive index of the sampled virtual parking unit is less than the comprehensive index threshold, another sampled virtual parking unit is selected from the sampling interval where the sampled virtual parking unit is located. This newly selected sampled virtual parking unit replaces the original one and becomes the sampled virtual parking unit in that interval. Next, the safety index and comprehensive index of the new sampled virtual parking unit are recalculated according to the same calculation rules. Finally, all comprehensive indices are arranged in ascending order, and the sampled virtual parking unit with the highest comprehensive index in the list is determined as the target parking unit for the intelligent moving robot.

[0099] S213. Send a moving command to the intelligent moving robot based on the target moving parking space boundary determined by the target moving parking unit.

[0100] Among them, the moving instruction is a detailed operation instruction sent by the server to the robot, which includes the moving target, path and other necessary parameters.

[0101] The parking space server determines the boundary of the target parking space by the outline of the target parking unit, and then retrieves the specific location information of the target parking unit and the path information from the first temporary parking space to the target parking unit in the simulation operation from the virtual parking unit map database and sends them to the intelligent moving robot.

[0102] In some embodiments, after the intelligent vehicle moving robot completes the vehicle moving instruction, the server will send a reminder message and the vehicle's location information after it has been moved to the owner of the first vehicle to be parked by querying the personal information registered in the data.

[0103] S214. Enter the parking record of the first vehicle waiting to be parked into the historical parking database.

[0104] In this embodiment, a non-fixed boundary division technique for parking spaces is adopted, which effectively solves the problem of inflexible allocation of parking space resources. This enables the parking space server to dynamically adjust the location and size of temporary parking spaces based on vehicle size and real-time conditions of loading and unloading areas, thereby maximizing the utilization of available space resources.

[0105] The parking space server in the embodiments of this invention is described below from the perspective of hardware processing. Please refer to [link / reference needed]. Figure 3 This is a schematic diagram of the physical device structure of a parking space server in an embodiment of this application.

[0106] It should be noted that, Figure 3 The structure of the parking space server shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0107] like Figure 3 As shown, the parking space server includes a CPU 301, which can perform various appropriate actions and processes according to a program stored in ROM 302 or a program loaded from storage section 308 into RAM 303, such as performing the methods described in the above embodiments. RAM 303 also stores various programs and data required for system operation. CPU 301, ROM 302, and RAM 303 are interconnected via bus 304. I / O interface 305 is also connected to bus 304.

[0108] The following components are connected to I / O interface 305: input section 306 including audio input devices, push-button switches, etc.; output section 307 including liquid crystal display (LCD) and audio output devices, indicator lights, etc.; storage section 308 including hard disks, etc.; and communication section 309 including network interface cards such as LAN (Local Area Network) cards, modems, etc. Communication section 309 performs communication processing via a network such as the Internet. Drive 310 is also connected to I / O interface 305 as needed. Removable media 311, such as disks, optical disks, magneto-optical disks, semiconductor memories, etc., are installed on drive 310 as needed so that computer programs read from them can be installed into storage section 308 as needed.

[0109] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing computer programs for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 309, and / or installed from removable medium 311. When the computer program is executed by CPU 301, it performs the various functions defined in the present invention.

[0110] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. Each block in a flowchart or block diagram may represent a module, program segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those shown in the drawings.

[0111] Specifically, the parking space server in this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, it implements the intelligent reuse method for parking space in intelligent buildings provided in the above embodiment.

[0112] In another aspect, the present invention also provides a computer-readable storage medium, which may be included in the parking space server described in the above embodiments; or it may exist independently and not assembled into the parking space server. The storage medium carries one or more computer programs that, when executed by a processor of the parking space server, cause the parking space server to implement the intelligent building parking space reuse method provided in the above embodiments.

[0113] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

[0114] As used in the above embodiments, depending on the context, the term "when..." can be interpreted as meaning "if...", "after...", "in response to determining...", or "in response to detecting...". Similarly, depending on the context, the phrase "when determining..." or "if (the stated condition or event) is interpreted as meaning "if determining...", "in response to determining...", "when (the stated condition or event) is detected", or "in response to detecting (the stated condition or event)".

Claims

1. A method for intelligent reuse of parking space in smart buildings, characterized in that, A parking space server deployed in a smart building, the smart building including a parking lot and a loading / unloading area with the same entrance, the method comprising: When the remaining time in the parking lot is less than the preset value and there is no loading or unloading task in the loading and unloading area is the first time, the first vehicle to be parked is identified by the camera at the entrance of the parking lot. The first time is longer than the preset buffer time. The predicted parking duration of the first vehicle to be parked is determined based on the historical parking database; When it is determined that the predicted parking time is less than the first time, the target virtual parking unit is determined from the multiple virtual parking units that are divided into standard parking spaces in the loading and unloading area. The priority coefficient is determined based on the distance of each virtual parking unit from the loading and unloading channel, the distribution of surrounding obstacles, and the historical usage frequency. Based on the target virtual parking unit, the boundary of the first parking space is determined from the vacant area of ​​the loading and unloading area; The boundary of the first parking space is projected onto the ground using a ground projection device to obtain the first temporary parking space located in the loading and unloading area. Send guidance information to direct the first vehicle to be parked from the parking lot entrance to the first temporary parking space.

2. The method according to claim 1, characterized in that, Before the step of identifying the first waiting vehicle via the camera at the parking lot entrance when the remaining time after which there are fewer vacant parking spaces than a preset number and no loading / unloading tasks in the loading / unloading area is the first time, the method further includes: When the remaining time when there are no loading or unloading tasks in the loading and unloading area is less than the preset buffer time, a lifting command is issued to the lifting isolation column at the boundary of the loading and unloading area.

3. The method according to claim 1, characterized in that, The step of determining the predicted parking duration of the first vehicle to be parked based on the historical parking database specifically includes: The entry time of this record is compared with the historical entry times to determine the similarity of time characteristics between different historical records and this record. The similarity of time characteristics is determined based on the same weekday or weekend, similar time period and similar season. The predicted parking duration is calculated by weighting these historical parking durations by assigning different weights to different historical records based on their time similarity.

4. The method according to any one of claims 1 to 3, characterized in that, The step of determining the boundary of the first parking space from the vacant area of ​​the loading and unloading area based on the target virtual parking unit specifically includes: Based on spatial overlap analysis of the preliminary parking space boundary and the no-parking zone, it is determined whether the target virtual parking unit can meet the parking needs of the first vehicle to be parked. The preliminary parking space boundary is determined based on the actual outline of the first vehicle to be parked and the width of the preset buffer zone. The no-parking zone is determined based on the volume and position of obstacles within the target virtual parking unit. The parking needs are that the overlap area between the preliminary parking space boundary and the no-parking zone is less than a preset threshold and the vehicle's key operating points are not obstructed. If the parking needs of the first vehicle to be parked cannot be met, the boundary re-division method is adopted, and the boundary between the target virtual parking unit and the adjacent virtual parking unit is re-divided according to the spline curve generated based on the actual vehicle outline and operation requirements. Based on the redefined boundaries of the target virtual parking units, the first parking space boundary of the irregular rectangle is determined from the vacant area of ​​the loading and unloading area.

5. The method according to claim 4, characterized in that, If the parking needs of the first vehicle to be parked cannot be met, the method further includes the following steps: If the parking needs of the first vehicle to be parked cannot be met, the method of re-dividing the boundaries of the target virtual parking unit and adjacent virtual parking units is adopted using a curve boundary re-division method based on spline curves generated according to the actual vehicle contour and operational requirements. When a first adjacent vehicle is parked in the first adjacent unit of an adjacent virtual parking unit, the shared area of ​​the first adjacent vehicle and the first vehicle waiting to park is determined by spatial overlap analysis of the space formed by the spline curve and the actual parking space of the first adjacent vehicle. The boundary between the target virtual parking unit and the first adjacent unit is determined based on the shared area.

6. The method according to claim 1, characterized in that, After the step of sending guidance information to direct the first vehicle to be parked from the parking lot entrance to the first temporary parking space, the method further includes: If the remaining time is less than the preset buffer time and the first vehicle to be parked has not left, calculate the safety index of the intelligent vehicle moving robot moving the first vehicle to be parked from the first temporary parking space to each sampled virtual parking unit. The sampled virtual parking unit is an idle virtual parking unit within the sampling partition. The sampling partition is obtained by partitioning idle virtual parking units with priority coefficients higher than a specified coefficient according to the priority coefficient. The safety index is calculated based on the path width, turning radius, and obstacle avoidance space sufficiency. Based on the comprehensive index obtained by weighting the safety index and priority coefficient of the sampled virtual parking units, the sampled virtual parking unit with the highest comprehensive index is determined as the target parking unit to be mobilized. Based on the target parking space boundary determined by the target parking unit, a vehicle relocation instruction is sent to the intelligent vehicle relocation robot. The vehicle relocation instruction includes the vehicle position, vehicle characteristic parameters, and target parking space boundary of the first vehicle to be parked.

7. The method according to claim 6, characterized in that, The step of determining the sampled virtual parking unit with the highest comprehensive index as the target parking unit to be mobilized, based on a comprehensive index obtained by weighting the safety index and priority coefficient of the sampled virtual parking units, specifically includes: Based on the comprehensive index obtained by weighting the safety index and priority coefficient of the sampled virtual parking units, the first sampled virtual parking units that are below the minimum acceptable comprehensive index threshold are excluded. Determine the safety index and comprehensive index of a second sampled virtual parking unit located in the same sampling interval as the first sampled virtual parking unit, wherein the second sampled virtual parking unit is different from the first sampled virtual parking unit; The sampled virtual parking unit with the highest comprehensive index is identified as the target parking unit to be mobilized.

8. A parking space server, characterized in that, The parking space server includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code including computer instructions, and the one or more processors call the computer instructions to cause the parking space server to perform the method as described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that, When the instruction is executed on the parking space server, the parking space server performs the method as described in any one of claims 1-7.

10. A computer program product, characterized in that, When the computer program product is run on the parking space server, the parking space server performs the method as described in any one of claims 1-7.

Images