Intelligent park digital twinning system and method based on artificial intelligence

Abstract

The invention provides a smart park digital twinning system and method based on artificial intelligence, and relates to the technical field of digital twinning, and the method comprises the steps: determining a sub-region WA where a target vehicle parks in a smart park; the number NUM0 of remaining parking spaces and the number NUM1 of moving vehicles corresponding to the WA are obtained; obtaining an initial remaining parking space number list A; according to the historical parking information corresponding to each moving vehicle and whether the parking sub-region is pushed, determining the sub-region corresponding to each moving vehicle to obtain a moving vehicle number list B; determining a target remaining parking space number corresponding to each sub-region to obtain a target remaining parking space number list C; determining a target sub-region corresponding to the target vehicle; the situation that the target vehicle cannot be parked due to the fact that no idle parking space exists in the sub-area when the target vehicle runs to the corresponding sub-area can be avoided, and therefore the parking efficiency of users in the smart park is improved.

Description

Technical Field

[0001] The present invention relates to the field of digital twin technology, and in particular to an artificial intelligence-based smart park digital twin system and method. Background Art

[0002] With the acceleration of urbanization and rapid economic development, the number of cars has continued to rise, and urban traffic pressure has increased day by day, especially in large office areas. The parking problem during the morning rush hour has become more and more prominent. In large office areas, a large number of vehicles flock in during the morning rush hour, while parking space resources are limited, resulting in a shortage of parking spaces and great difficulty in parking. The disorderly search for parking spaces in the parking lot will aggravate traffic congestion in the parking lot, increase the risk of collisions, scratches and other accidents between vehicles, and generate a large amount of exhaust emissions, polluting the environment.

[0003] In order to solve the above problems, a screen for real-time display of the parking status of parking spaces is usually set at the vehicle entrance of a large office area to prompt users where there are vacant parking spaces; however, the vehicle entrance of a large office area is far away from the office building, and it takes a long time for the user's vehicle to reach the office building from the time it enters the office area. In addition, there are also several vehicles on the road in the office area, and some of these vehicles may be parked near the same office building as the user's vehicle. When the user's vehicle drives near the office building, the parking status of the parking space has changed significantly, resulting in the user being unable to find a parking space, and the parking efficiency of users in the office area is low. Summary of the invention

[0004] In view of the above technical problems, the technical solution adopted by the present invention is: According to the first aspect of the present application, a method for a digital twin of a smart park based on artificial intelligence is provided, the method comprising the following steps: S100, in response to identifying that the target vehicle arrives at the entrance of the smart park, determining a sub-area WA where the target vehicle is parked in the smart park; S200, obtaining the number of remaining parking spaces NUM0 corresponding to WA; S300, using a mobile vehicle automatic identification model to identify the number NUM1 of mobile vehicles in a moving state in the smart park; S400, if NUM1 ≥ NUM0, then obtain the initial number of remaining parking spaces in each sub-area corresponding to the smart park to obtain an initial number of remaining parking spaces list A = (A1, A2, ..., A i , …, A n ), i=1, 2, …, n; A iis the initial number of remaining parking spaces in the i-th sub-area, n is the number of sub-areas corresponding to the smart park; each sub-area corresponds to a building; WA∈A; S500, according to the historical parking information corresponding to each mobile vehicle and whether the parking sub-area has been pushed, determine the sub-area corresponding to each mobile vehicle, so as to obtain a mobile vehicle quantity list B = (B1, B2, ..., B i , …, B n ); B i is the number of moving vehicles corresponding to the i-th sub-area; S600: Determine the target number of remaining parking spaces corresponding to each sub-area based on A and B, and obtain a list of target number of remaining parking spaces C = (C1, C2, ..., C i , …, C n ); C i is the target number of remaining parking spaces corresponding to the i-th sub-area; C i =A i -B i ; S700: Determine the target sub-area corresponding to the target vehicle according to WA and C.

[0005] According to another aspect of the present application, there is also provided a smart park digital twin system based on artificial intelligence, the system comprising: A parking sub-area determination module, for determining a sub-area WA where the target vehicle is parked in the smart park in response to identifying that the target vehicle has arrived at the entrance of the smart park; The remaining parking space number acquisition module is used to obtain the remaining parking space number NUM0 corresponding to WA; A mobile vehicle identification module is used to identify the number NUM1 of mobile vehicles in a moving state in the smart park using a mobile vehicle automatic identification model; The module for determining the number of initial remaining parking spaces is used to obtain the number of initial remaining parking spaces in each sub-area corresponding to the smart park if NUM1 ≥ NUM0, so as to obtain the list of the number of initial remaining parking spaces A = (A1, A2, ..., A i , …, A n ), i=1, 2, …, n; A i is the initial number of remaining parking spaces in the i-th sub-area, n is the number of sub-areas corresponding to the smart park; each sub-area corresponds to a building; WA∈A; The mobile vehicle quantity determination module is used to determine the sub-area corresponding to each mobile vehicle according to the historical parking information corresponding to each mobile vehicle and whether the parking sub-area has been pushed, so as to obtain a mobile vehicle quantity list B = (B1, B2, ..., B i , …, B n ); B iis the number of moving vehicles corresponding to the i-th sub-area; The target remaining parking space quantity determination module is used to determine the target remaining parking space quantity corresponding to each sub-area according to A and B, and obtain the target remaining parking space quantity list C = (C1, C2, ..., C i , …, C n ); C i is the target number of remaining parking spaces corresponding to the i-th sub-area; C i =A i -B i ; The target sub-area determination module is used to determine the target sub-area corresponding to the target vehicle according to WA and C.

[0006] The present invention has at least the following beneficial effects: The artificial intelligence-based digital twin method for a smart park of the present invention, when identifying that a target vehicle has arrived at the entrance of the smart park, determines the sub-area WA corresponding to the parking of the target vehicle according to the historical parking behavior information of the target vehicle; combines the current number of remaining parking spaces in WA and the number of moving vehicles in the smart park, as well as the historical parking information of each moving vehicle and whether the parking sub-area has been pushed, to predict the number of remaining parking spaces in each sub-area when the target vehicle reaches WA, and then determines the target sub-area corresponding to the target vehicle; thereby, it can avoid the situation where there are no vacant parking spaces in the sub-area when the target vehicle drives to the corresponding sub-area, resulting in the target vehicle being unable to park, thereby improving the parking efficiency of users in the smart park. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0008] Figure 1 A flow chart of the artificial intelligence-based smart park digital twin method provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0009] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0010] It should be noted that, based on the present disclosure, those skilled in the art should understand that an aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects described herein can be used to implement a device and / or practice a method. In addition, other structures and / or functionalities other than one or more of the aspects described herein can be used to implement this device and / or practice this method.

[0011] The following will refer to Figure 1 The flowchart of the digital twin method of a smart park based on artificial intelligence is shown, which introduces a digital twin method of a smart park based on artificial intelligence.

[0012] The artificial intelligence-based smart park digital twin method may include the following steps: S100, in response to identifying that the target vehicle arrives at the entrance of the smart park, determining the sub-area WA where the target vehicle is parked in the smart park.

[0013] In this embodiment, the artificial intelligence-based smart park digital twin system also includes a camera installed at the vehicle entrance of the smart park, which is used to identify the license plate number of the vehicle. The smart park can be any large office area or industrial area. There are several buildings in the smart park, and each building corresponds to a sub-area for parking. Each parking space in the sub-area is equipped with a vehicle license plate number recognition device, which can identify the information of the vehicle parked in each parking space and the parking time.

[0014] Further, step S100 may include the following steps: S110, obtaining the historical sub-areas corresponding to each historical parking of the target vehicle within a preset historical time period, so as to obtain a historical sub-area list LA corresponding to the target vehicle = (LA1, LA2, ..., LA p , …, LA q ), p = 1, 2, …, q; where LA p is the pth historical sub-area corresponding to the target vehicle within the preset historical time period, and q is the number of historical sub-areas corresponding to the target vehicle within the preset historical time period.

[0015] In this embodiment, the target vehicle can be any vehicle. After the license plate number of the target vehicle is identified, the historical sub-area corresponding to each historical parking of the target vehicle within the historical time period can be obtained through the historical database of the digital twin system; the end time of the preset historical time period is the current time, and the duration can be set according to actual needs, such as one month or two months.

[0016] S120, cluster the same historical sub-regions in LA into one cluster to obtain a cluster list D = (D1, D2, ..., D j , …, D m ), j = 1, 2, …, m; where D j is the jth cluster obtained by clustering, and m is the number of clusters obtained by clustering.

[0017] In this embodiment, the same historical sub-regions in LA can be clustered into one cluster by traversal.

[0018] S130, obtaining the number of historical sub-regions in each cluster in D, so as to obtain a list of the number of historical sub-regions corresponding to D, E = (E1, E2, ..., E j , …, E m ); where E j D j The number of historical sub-regions within.

[0019] S140, obtaining the target historical sub-region quantity NE=MAX(E); wherein MAX() is a preset maximum value function.

[0020] S150, if NE / ∑ m j=1 E j >η, the historical sub-area corresponding to NE is determined as WA; wherein η is a preset weight.

[0021] In this embodiment, η is an empirical value, for example, the value range of η is 0.8 to 0.95; if NE / ∑ m j=1 E j >η, it means that the target vehicle is often parked in the sub-area corresponding to NE in the smart park. It can be considered that the building where the target user corresponding to the target vehicle works is the building in the sub-area corresponding to NE; therefore, the historical sub-area corresponding to NE is determined to be WA.

[0022] Furthermore, if NE / ∑ m j=1 E j ≤η, the current processing is jumped out; because at this time it is impossible to accurately determine the sub-area where the target vehicle has been frequently parked in the past; this may be caused by insufficient amount of historical data.

[0023] Furthermore, if the target vehicle enters the smart park for the first time, the target sub-area input by the user can be obtained, that is, the sub-area specified by the user himself.

[0024] S200, obtaining the number NUM0 of remaining parking spaces corresponding to WA.

[0025] In this embodiment, whether there is a vehicle parked in each parking space in each sub-area can be detected by a vehicle identification device on each parking space.

[0026] S300, using a preset mobile vehicle automatic identification model to identify the number NUM1 of mobile vehicles in a moving state in the smart park.

[0027] In this embodiment, a number of cameras are installed in the smart park, which can cover every road in the smart park. The cameras can collect video information in the smart park in real time; then the collected video information is input into a preset mobile vehicle automatic recognition model, which can identify the moving vehicles in the video information, and then obtain the number NUM1 of mobile vehicles in a moving state in the smart park.

[0028] Furthermore, the preset mobile vehicle automatic recognition models include: YOLO, Faster R-CNN and SSD.

[0029] In this embodiment, the YOLO, Faster R-CNN and SSD models have good effects in vehicle detection; the preset mobile vehicle automatic recognition model is a trained model, which can more accurately identify moving vehicles and realize artificial intelligence recognition of moving vehicles; it can be understood that the method steps in this embodiment are applied to the time period of rush hour in the morning, and the moving vehicles in the smart park can be considered as all incoming vehicles, and individual outgoing vehicles can be ignored.

[0030] Furthermore, after step S300 and before step S400, the following steps are also included: S310: If NUM1<NUM0, WA is determined as the target sub-area corresponding to the target vehicle.

[0031] S320, push the WA to the target user corresponding to the target vehicle through the preset digital twin system.

[0032] In this embodiment, if NUM1<NUM0, it means that all moving vehicles in the smart park are parked in WA, and the parking spaces in WA will not be full. Therefore, WA can be determined as the target sub-area corresponding to the target vehicle, and the information of WA can be pushed to the target user through the digital twin system, for example: the WA information is pushed through an APP installed on the target user's mobile phone and communicating with the digital twin system.

[0033] S400, if NUM1 ≥ NUM0, then obtain the initial number of remaining parking spaces in each sub-area corresponding to the smart park to obtain an initial number of remaining parking spaces list A = (A1, A2, ..., A i , …, A n ), i=1, 2, …, n; Ai is the initial number of remaining parking spaces in the i-th sub-area, n is the number of sub-areas corresponding to the smart park; each sub-area corresponds to a building; WA∈A.

[0034] In this embodiment, if NUM1≥NUM0, it means that if all mobile vehicles are parked in WA, the parking spaces in WA may be full, and the target vehicle cannot be parked after arriving at WA; therefore, the initial number of remaining parking spaces in each sub-area corresponding to the smart park can be obtained to obtain an initial remaining number of parking spaces list A; the initial remaining number of parking spaces in each sub-area is the number of remaining parking spaces in each sub-area at the current moment, that is, the moment when the target vehicle arrives at the entrance of the smart park.

[0035] S500, according to the historical parking information corresponding to each mobile vehicle and whether the parking sub-area has been pushed, determine the sub-area corresponding to each mobile vehicle, so as to obtain a mobile vehicle quantity list B = (B1, B2, ..., B i , …, B n ); B i is the number of moving vehicles corresponding to the i-th sub-area.

[0036] Further, step S500 may include the following steps: S510, obtain each moving vehicle to obtain a moving vehicle list YA=(YA1, YA2, ..., YA u ,…,YA v ), u = 1, 2, ..., v; YA u is the u-th moving vehicle, and v is the number of moving vehicles.

[0037] In this embodiment, the identification of the mobile vehicle can be represented by the corresponding license plate number.

[0038] S520, traverse YA, if YA u If the parking sub-area is pushed, YA u Divide into the corresponding pushed parking sub-area; otherwise, obtain YA u The historical sub-areas corresponding to each historical parking within the preset historical time period.

[0039] In this embodiment, it can be understood that mobile vehicles in a moving state also enter the smart park through the entrance of the smart park. Similarly, some vehicle users at the entrance also have the twin system APP installed on their mobile phones and will receive the pushed sub-area information; in addition, there are some mobile vehicle users whose mobile phones do not have the APP installed, so these users will not receive the pushed sub-area information; by querying the background database, it can be obtained which mobile vehicles have pushed the sub-area information.

[0040] It can be understood that for a mobile vehicle in a pushed parking sub-area, the mobile vehicle can be directly divided into the corresponding pushed parking sub-area; for a mobile vehicle in a non-pushed parking sub-area, further determination is required based on historical parking behavior.

[0041] S530, according to YA u The historical sub-area corresponding to each historical parking in the preset historical time period determines YA u The corresponding sub-region.

[0042] In this embodiment, the method in steps S110-S150 can be used to determine YA u The corresponding sub-areas are not described here.

[0043] S540, determining B according to the sub-area corresponding to each moving vehicle in YA.

[0044] Further, step S540 may include the following steps: S541, obtain the shortest path for each mobile vehicle in YA to travel to the corresponding sub-area, so as to obtain the shortest path list HA corresponding to YA = (HA1, HA2, ..., HA u ,…,HA v );HA u for YA u The shortest path to the corresponding sub-area.

[0045] In this embodiment, the coordinates of each mobile vehicle in the smart park at the current moment can be obtained, and the coordinates of each sub-area are also known. Therefore, the shortest path for each mobile vehicle in YA to travel to the corresponding sub-area can be determined in combination with the map information corresponding to the smart park.

[0046] S542, according to the average driving speed of vehicles in the smart park and HA, determine the time taken for each mobile vehicle to travel to the corresponding sub-area, so as to obtain a time consumption list TA = (TA1, TA2, ..., TA u ,…,TA v );TA u for YA u The time it takes to travel to the corresponding sub-area.

[0047] In this embodiment, the average driving speed of vehicles in the smart park can be obtained through a large amount of historical data analysis; the distance of the shortest path can be obtained through map information, and then the time taken for each mobile vehicle to travel to the corresponding sub-area can be obtained.

[0048] S543, obtaining the shortest time DA for the target vehicle to travel to WA.

[0049] S544, determine the target mobile vehicles from the mobile vehicles corresponding to the time consumptions less than DA in TA, so as to obtain a target mobile vehicle list G=(G1, G2, ..., G x , …, G y ), x=1, 2, …, y; G x is the xth target mobile vehicle determined, and y is the number of target mobile vehicles determined.

[0050] In this embodiment, it can be understood that although the mobile vehicles in the smart park enter before the target vehicle, since each sub-area is distributed at various locations in the smart park, the mobile vehicles may reach the corresponding sub-area after the target vehicle. These mobile vehicles will not affect the target vehicle. Therefore, it is necessary to screen out the mobile vehicles that arrive at the corresponding sub-area after the target vehicle.

[0051] S545, traverse G, if G x If the parking sub-area is pushed, G x Divide it into the corresponding pushed parking sub-area; otherwise, obtain G x The historical sub-areas corresponding to each historical parking within the preset historical time period.

[0052] S546, according to G x The historical sub-area corresponding to each historical parking in the preset historical time period is determined by G x The corresponding sub-area S547, determine B according to the sub-area corresponding to each target mobile vehicle in G.

[0053] In this embodiment, the method in steps S545-S547 is the same as the method in steps S520-S540, and is not described in detail here.

[0054] S600: Determine the target number of remaining parking spaces corresponding to each sub-area based on A and B, and obtain a list of target number of remaining parking spaces C = (C1, C2, ..., C i , …, C n ); C i is the target number of remaining parking spaces corresponding to the i-th sub-area; C i =A i -B i .

[0055] In this embodiment, the target remaining parking spaces in each sub-area obtained through the above steps take into account the moving vehicles in the smart park, so that the determination of the target sub-area corresponding to the target vehicle is more accurate.

[0056] S700: Determine the target sub-area corresponding to the target vehicle according to WA and C.

[0057] Further, step S700 may include the following steps: S710: According to C, determine the target number of remaining parking spaces NUM2 corresponding to WA.

[0058] S720, if NUM2>0, WA is determined as the target sub-area corresponding to the target vehicle; otherwise, several sub-areas adjacent to WA are obtained to obtain a list of adjacent sub-areas corresponding to WA H=(H1, H2, ..., H a , …, H b ), a=1, 2, …, b; H a is the ath sub-region adjacent to WA, b is the number of sub-regions adjacent to WA; H a The corresponding number of target remaining parking spaces is greater than 0.

[0059] In this embodiment, if NUM2>0, it means that there are still vacant parking spaces in the target sub-area from the time the target vehicle enters the smart park to the time it drives to the target sub-area, thereby avoiding the situation where the target vehicle cannot find a parking space; and if NUM2≤0, it means that there are no vacant parking spaces in the target sub-area from the time the target vehicle enters the smart park to the time it drives to the target sub-area. At this time, in order to ensure that the target vehicle has a parking space, several sub-areas adjacent to WA and with remaining parking spaces can be obtained to further determine the target sub-area.

[0060] S730: Determine the sub-region in H that is closest to WA as the target sub-region corresponding to the target vehicle.

[0061] In this embodiment, the sub-region in H that is closest to WA is determined as the target sub-region corresponding to the target vehicle, thereby ensuring that the target vehicle has a parking space available.

[0062] In this embodiment, when it is identified that the target vehicle has arrived at the entrance of the smart park, the sub-area WA where the target vehicle is parked is determined based on the historical parking behavior information of the target vehicle; the current number of remaining parking spaces in WA and the number of moving vehicles in the smart park, as well as the historical parking information of each moving vehicle and whether the parking sub-area has been pushed, are combined to predict the number of remaining parking spaces in each sub-area when the target vehicle reaches WA, and then the target sub-area corresponding to the target vehicle is determined; thereby, it is possible to avoid the situation where there are no vacant parking spaces in the corresponding sub-area when the target vehicle drives to the sub-area, resulting in the target vehicle being unable to park, thereby improving the parking efficiency of users in the smart park.

[0063] In an exemplary embodiment, a smart park digital twin system based on artificial intelligence is also provided, the system comprising: The parking sub-area determination module is used to determine the sub-area WA where the target vehicle is parked in the smart park in response to identifying that the target vehicle has arrived at the entrance of the smart park.

[0064] The module for obtaining the number of remaining parking spaces is used to obtain the number of remaining parking spaces NUM0 corresponding to WA.

[0065] The mobile vehicle identification module is used to use a preset mobile vehicle automatic identification model to identify the number NUM1 of mobile vehicles in a moving state in the smart park.

[0066] The module for determining the number of initial remaining parking spaces is used to obtain the number of initial remaining parking spaces in each sub-area corresponding to the smart park if NUM1 ≥ NUM0, so as to obtain the list of the number of initial remaining parking spaces A = (A1, A2, ..., A i , …, A n ), i=1, 2, …, n; A i is the initial number of remaining parking spaces in the i-th sub-area, n is the number of sub-areas corresponding to the smart park; each sub-area corresponds to a building; WA∈A.

[0067] The mobile vehicle quantity determination module is used to determine the sub-area corresponding to each mobile vehicle according to the historical parking information corresponding to each mobile vehicle and whether the parking sub-area has been pushed, so as to obtain a mobile vehicle quantity list B = (B1, B2, ..., B i , …, B n ); B i is the number of moving vehicles corresponding to the i-th sub-area.

[0068] The target remaining parking space quantity determination module is used to determine the target remaining parking space quantity corresponding to each sub-area according to A and B, and obtain the target remaining parking space quantity list C = (C1, C2, ..., C i , …, C n ); C i is the target number of remaining parking spaces corresponding to the i-th sub-area; C i =A i -B i .

[0069] The target sub-area determination module is used to determine the target sub-area corresponding to the target vehicle according to WA and C.

[0070] The methods executed by each module in this embodiment are the same as those in the above embodiments and are not described in detail here.

[0071] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0072] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0073] Although some specific embodiments of the present invention have been described in detail by way of example, it should be understood by those skilled in the art that the above examples are only for illustration, not for limiting the scope of the present invention. It should also be understood by those skilled in the art that various modifications may be made to the embodiments without departing from the scope and spirit of the present invention.

Claims

1. A digital twin method for a smart park based on artificial intelligence, characterized in that: The method comprises the following steps: S100, in response to identifying that the target vehicle arrives at the entrance of the smart park, determining a sub-area WA where the target vehicle is parked in the smart park; S200, obtaining the number of remaining parking spaces NUM0 corresponding to WA; S300, using a preset mobile vehicle automatic identification model to identify the number NUM1 of mobile vehicles in a moving state in the smart park; S400, if NUM1 ≥ NUM0, then obtain the initial number of remaining parking spaces in each sub-area corresponding to the smart park to obtain an initial remaining parking space number list A = (A1, A2, ..., A i , …, A n ), i=1, 2, …, n; A i is the initial number of remaining parking spaces in the i-th sub-area, n is the number of sub-areas corresponding to the smart park; each sub-area corresponds to a building; WA∈A; S500, according to the historical parking information corresponding to each mobile vehicle and whether the parking sub-area has been pushed, determine the sub-area corresponding to each mobile vehicle, so as to obtain a mobile vehicle quantity list B = (B1, B2, ..., B i , …, B n ); B i is the number of moving vehicles corresponding to the i-th sub-area; S600: Determine the target number of remaining parking spaces corresponding to each sub-area based on A and B, and obtain a list of target number of remaining parking spaces C = (C1, C2, ..., C i , …, C n ); C i is the target number of remaining parking spaces corresponding to the i-th sub-area; C i =A i -B i ; S700: Determine the target sub-area corresponding to the target vehicle according to WA and C.

2. The method for the digital twin of a smart park based on artificial intelligence according to claim 1 is characterized in that: Step S100 includes the following steps: S110, obtaining the historical sub-areas corresponding to each historical parking of the target vehicle within a preset historical time period, so as to obtain a historical sub-area list LA corresponding to the target vehicle = (LA1, LA2, ..., LA p , …, LA q ), p = 1, 2, …, q; where LA p is the pth historical sub-area corresponding to the target vehicle in the preset historical time period, and q is the number of historical sub-areas corresponding to the target vehicle in the preset historical time period; S120, cluster the same historical sub-regions in LA into one cluster to obtain a cluster list D = (D1, D2, ..., D j , …, D m ), j = 1, 2, …, m; where D j is the jth cluster obtained by clustering, and m is the number of clusters obtained by clustering; S130, obtaining the number of historical sub-regions in each cluster in D, so as to obtain a list of the number of historical sub-regions corresponding to D, E = (E1, E2, ..., E j ,…,E m ); where E j D j the number of historical sub-regions within; S140, obtaining the target historical sub-region number NE=MAX(E); wherein MAX() is a preset maximum value function; S150, if NE / ∑ m j=1 E j >η, the historical sub-area corresponding to NE is determined as WA; wherein η is a preset weight.

3. The method for the digital twin of a smart park based on artificial intelligence according to claim 1 is characterized in that: Step S500 includes the following steps: S510, obtain each moving vehicle to obtain a moving vehicle list YA=(YA1, YA2, ..., YA u ,…,YA v ), u = 1, 2, ..., v; YA u is the u-th moving vehicle, v is the number of moving vehicles; S520, traverse YA, if YA u If the parking sub-area is pushed, YA u Divide into the corresponding pushed parking sub-area; otherwise, obtain YA u The historical sub-areas corresponding to each historical parking in a preset historical time period; S530, according to YA u The historical sub-area corresponding to each historical parking in the preset historical time period determines YA u The corresponding sub-region; S540, determining B according to the sub-area corresponding to each moving vehicle in YA.

4. The method for the digital twin of a smart park based on artificial intelligence according to claim 3 is characterized in that: Step S540 includes the following steps: S541, obtain the shortest path for each mobile vehicle in YA to travel to the corresponding sub-area, so as to obtain the shortest path list HA corresponding to YA = (HA1, HA2, ..., HA u ,…,HA v );HA u for YA u The shortest path to the corresponding sub-area; S542, according to the average driving speed of vehicles in the smart park and HA, determine the time taken for each mobile vehicle to travel to the corresponding sub-area, so as to obtain a time consumption list TA = (TA1, TA2, ..., TA u ,…,TA v );TA u for YA u The time it takes to travel to the corresponding sub-area; S543, obtaining the shortest time DA taken by the target vehicle to travel to WA; S544, determine the target mobile vehicles from the mobile vehicles corresponding to the time consumptions less than DA in TA, so as to obtain a target mobile vehicle list G=(G1, G2, ..., G x , …, G y ), x=1, 2, …, y; G x is the xth target mobile vehicle determined, and y is the number of target mobile vehicles determined; S545, traverse G, if G x If the parking sub-area is pushed, G x Divide it into the corresponding pushed parking sub-area; otherwise, obtain G x The historical sub-areas corresponding to each historical parking in a preset historical time period; S546, according to G x The historical sub-area corresponding to each historical parking in the preset historical time period is determined by G x The corresponding sub-region; S547, determine B according to the sub-area corresponding to each target mobile vehicle in G.

5. The method for the digital twin of a smart park based on artificial intelligence according to claim 1 is characterized in that: Step S700 includes the following steps: S710, determining the target number of remaining parking spaces NUM2 corresponding to WA according to C; S720, if NUM2>0, WA is determined as the target sub-area corresponding to the target vehicle; otherwise, several sub-areas adjacent to WA are obtained to obtain a list of adjacent sub-areas corresponding to WA H=(H1, H2, ..., H a , …, H b ), a=1, 2, …, b; H a is the ath sub-region adjacent to WA, b is the number of sub-regions adjacent to WA; H a The corresponding number of target remaining parking spaces is greater than 0; S730: Determine the sub-region in H that is closest to WA as the target sub-region corresponding to the target vehicle.

6. The method for the digital twin of a smart park based on artificial intelligence according to claim 1 is characterized in that: After step S300 and before step S400, the following steps are further included: S310, if NUM1<NUM0, determine WA as the target sub-area corresponding to the target vehicle; S320, push the WA to the target user corresponding to the target vehicle through the preset digital twin system.

7. The method for the digital twin of a smart park based on artificial intelligence according to claim 1 is characterized in that: The preset mobile vehicle automatic recognition models include: YOLO, Faster R-CNN and SSD.

8. A digital twin system of a smart park based on artificial intelligence, characterized in that: The system comprises: A parking sub-area determination module, for determining a sub-area WA where the target vehicle is parked in the smart park in response to identifying that the target vehicle has arrived at the entrance of the smart park; The remaining parking space number acquisition module is used to obtain the remaining parking space number NUM0 corresponding to WA; A mobile vehicle identification module is used to identify the number NUM1 of mobile vehicles in a moving state in the smart park using a preset mobile vehicle automatic identification model; The module for determining the number of initial remaining parking spaces is used to obtain the number of initial remaining parking spaces in each sub-area corresponding to the smart park if NUM1 ≥ NUM0, so as to obtain the list of the number of initial remaining parking spaces A = (A1, A2, ..., A i , …, A n ), i=1, 2, …, n; A i is the initial number of remaining parking spaces in the i-th sub-area, n is the number of sub-areas corresponding to the smart park; each sub-area corresponds to a building; WA∈A; The mobile vehicle quantity determination module is used to determine the sub-area corresponding to each mobile vehicle according to the historical parking information corresponding to each mobile vehicle and whether the parking sub-area has been pushed, so as to obtain a mobile vehicle quantity list B = (B1, B2, ..., B i , …, B n ); B i is the number of moving vehicles corresponding to the i-th sub-area; The target remaining parking space quantity determination module is used to determine the target remaining parking space quantity corresponding to each sub-area according to A and B, and obtain the target remaining parking space quantity list C = (C1, C2, ..., C i , …, C n ); C i is the target number of remaining parking spaces corresponding to the i-th sub-area; C i =A i -B i ; The target sub-area determination module is used to determine the target sub-area corresponding to the target vehicle according to WA and C.

Images