Parking space distribution method and device and computer readable storage medium

Abstract

The invention provides a parking space distribution method and device and a computer readable storage medium. The target position of the movable charging device is determined according to the charging demand of each parking area of the parking lot and the idle parking space information of the parking lot; the target position is sent to the corresponding movable charging device, so that the movable charging device moves to the corresponding target position, the layout of a target parking space of the parking lot is dynamically scheduled, and the movable charging device is arranged on the target parking space and can be used for parking and charging of a vehicle; and distributing the target parking space to a to-be-charged vehicle. According to the invention, by adjusting the position of the movable charging device, the layout of the parking and charging parking spaces is dynamically scheduled, so that charging resources are fully utilized, the utilization rate of the charging parking spaces is improved, the problem of low utilization rate of the charging parking spaces caused by fixed charging positions in a fixed charging pile mode is solved, and the phenomenon of serious queuing in a charging peak period is relieved.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, and more specifically, to a parking space allocation method, device, and computer-readable storage medium. Background Technology

[0002] Currently, fixed charging stations are used to charge new energy vehicles. Under the fixed charging station model, the charging space is fixed, and some vehicles remain parked in the charging space even after they are fully charged. This results in low utilization of the charging space and long queuing time for vehicles that need to charge, especially during peak charging hours. Summary of the Invention

[0003] This application proposes a parking space allocation method, device, and computer-readable storage medium. Based on the charging demand of each parking area in the parking lot and the information on available parking spaces, the layout of mobile charging devices is dynamically adjusted to achieve dynamic scheduling of the layout of available parking spaces for charging. This can make full use of charging resources, improve the utilization rate of charging spaces, solve the technical problem of low utilization rate of charging spaces caused by fixed charging locations under the current fixed charging pile mode, and alleviate the serious queuing phenomenon during peak charging periods.

[0004] In a first aspect, embodiments of this application provide a parking space allocation method, the method comprising: determining the target location of a portable charging device based on the charging demand of each parking area of ​​a parking lot and the information on available parking spaces in the parking lot; sending the target location to the corresponding portable charging device so that the portable charging device moves to the corresponding target location; dynamically scheduling the layout of target parking spaces in the parking lot, wherein the target parking space has the portable charging device and can be used for vehicle parking and charging; and allocating the target parking space to a vehicle to be charged.

[0005] Secondly, embodiments of this application provide an automatic parking method, the method comprising: receiving a target parking space allocated by a parking system, the target parking space being determined according to the parking space allocation method of this application; planning an augmented reality navigation path based on the target parking space; and parking a vehicle in the target parking space according to the augmented reality navigation path.

[0006] Thirdly, embodiments of this application provide a parking space allocation device, which includes: a location determination module, used to determine the target location of a portable charging device based on the charging needs of each parking area in the parking lot and the information on available parking spaces in the parking lot; a parking space scheduling module, used to send the target location to the corresponding portable charging device so that the portable charging device moves to the corresponding target location, dynamically scheduling the layout of target parking spaces in the parking lot, wherein the target parking space has the portable charging device, which can be used for vehicle parking and charging; and a parking space allocation module, used to allocate the target parking space to vehicles waiting to be charged.

[0007] Fourthly, embodiments of this application provide an automatic parking device, which includes: an information receiving module for receiving a target parking space allocated by a parking system, wherein the target parking space is determined according to the parking space allocation method of this application; a path planning module for planning an augmented reality navigation path based on the target parking space; and an automatic parking module for parking the vehicle into the target parking space according to the augmented reality navigation path.

[0008] Fifthly, embodiments of this application provide a parking space allocation device, which includes a memory and a processor. The memory stores an application program, which, when invoked by the processor, causes the processor to execute the parking space allocation method of this application.

[0009] Sixthly, embodiments of this application provide a vehicle, the vehicle including: a memory and a processor, the memory storing an application program, the application program being used to cause the processor to execute the automatic parking method of this application when invoked by the processor.

[0010] In a seventh aspect, embodiments of this application provide a computer-readable storage medium storing program code, which, when invoked by a processor, causes the processor to execute the parking space allocation method or automatic parking method of this application.

[0011] Eighthly, embodiments of this application provide a computer program product, which, when invoked by a processor, causes the processor to execute the parking space allocation method or automatic parking method of this application.

[0012] The parking space allocation method provided in this application has the following technical effects: Based on the charging demand of each parking area in the parking lot and the information on available parking spaces in the parking lot, the position of the mobile charging device is dynamically adjusted, thereby realizing the dynamic scheduling of the layout of available parking and charging spaces. This can make full use of charging resources, improve the utilization rate of charging spaces, solve the technical problem of low utilization rate of charging spaces caused by fixed charging locations under the current fixed charging pile mode, and alleviate the serious queuing phenomenon during peak charging periods. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments and drawings obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0014] Figure 1This is a schematic diagram illustrating an application scenario of the method provided in one embodiment of this application; Figure 2 This is a schematic diagram of the structure of a parking system provided in one embodiment of this application; Figure 3 This is a schematic diagram of the structure of a vehicle provided in one embodiment of this application; Figure 4 This is a schematic flowchart of a parking space allocation method provided in an embodiment of this application; Figure 5 This is a schematic diagram of the authorized binary diagram between a vehicle and a parking space provided in an embodiment of this application; Figure 6 This is an embodiment provided by this application. Figure 5 A schematic diagram of the cost matrix corresponding to the weighted bipartite graph shown; Figure 7 This application provides an embodiment of the method for... Figure 6 A schematic diagram of the matrix obtained by subtracting the minimum element of each row from each element of the cost matrix; Figure 8 This application provides an embodiment of the method for... Figure 7 A schematic diagram of the cost matrix obtained by subtracting the smallest element of each column from each element of that column; Figure 9 This application provides an embodiment of the method for... Figure 8 A schematic diagram of the matrix obtained after creating more zero elements from the cost matrix; Figure 10 This application provides an embodiment of the method for... Figure 9 A schematic diagram of the matrix obtained after the first line-drawing operation on the cost matrix; Figure 11 This application provides an embodiment of the method for... Figure 10 A schematic diagram of the matrix obtained after performing the second line-drawing operation on the cost matrix; Figure 12 This is a flowchart illustrating a parking space allocation method provided in another embodiment of this application; Figure 13 This is a schematic flowchart of an automatic parking method provided in an embodiment of this application; Figure 14 This is a structural block diagram of a parking space allocation device provided in one embodiment of this application; Figure 15 This is a structural block diagram of an automatic parking device provided in one embodiment of this application; Figure 16 This is a structural block diagram of the parking space allocation device provided in the embodiments of this application; Figure 17 This is a structural block diagram of the vehicle provided in the embodiments of this application. Detailed Implementation

[0015] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0016] See Figure 1 , Figure 1 This is a schematic diagram illustrating an application scenario of the method provided in one embodiment of this application. The application scenario includes a parking system 1, a vehicle 2, and a cloud server 3. The parking system 1 and the vehicle 2 can achieve wireless communication and data exchange based on the cloud server 3.

[0017] Parking system 1 includes two types of parking spaces: movable parking spaces and fixed parking spaces. Movable parking spaces are those that can be moved, such as mechanical parking spaces. Movable parking spaces may include movable charging devices, which can be moved to different movable parking spaces to create target parking spaces that can simultaneously accommodate vehicle parking and charging. The movable charging devices have built-in navigation systems. The movable charging devices can be designed as Automated Guided Vehicles (AGVs) or rail-mounted mechanical structures. For example, a movable charging device can be designed to include an AGV and a wireless charging floor; the wireless charging floor is transported by the AGV, thus enabling the movement of the movable charging device. Fixed parking spaces refer to parking spaces that are fixed and cannot be moved.

[0018] Vehicle 2 is equipped with sensing devices and a positioning system. The sensing devices are used to perceive environmental information around the vehicle. These devices may include, but are not limited to, at least one of the following: cameras, lidar, millimeter-wave radar, and ultrasonic radar. The positioning system is used to determine the vehicle's real-time location. The positioning system may include, but is not limited to, inertial navigation systems and Global Navigation Satellite Systems (GNSS). Inertial navigation systems may include, but are not limited to, accelerometers and gyroscopes. Global Navigation Satellite Systems may include, but are not limited to, Global Positioning System (GPS), GLONASS, Galileo, BeiDou Navigation Satellite System, Wide Area Augmentation System (WAAS), European Geostationary Navigation Overlay Service (EGNOS), and Multi-Functional Satellite Augmentation System (MSAS). Vehicle 2 may include, but is not limited to, gasoline vehicles or new energy vehicles. New energy vehicles may include electric vehicles, which may include, but are not limited to, pure electric vehicles, hybrid electric vehicles, or fuel cell vehicles.

[0019] Cloud Server 3 can provide basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery network (CDN), and big data and artificial intelligence platforms.

[0020] See Figure 2 , Figure 2 This is a schematic diagram of a parking system provided in one embodiment of this application. The parking system 1 may include a data acquisition module 11, a data preprocessing module 12, a charging demand prediction model 13, a vehicle priority determination module 14, a scheduling decision model 15, a data transmission module 16, a vehicle parking status monitoring module 17, and a status feedback and data update module 18. The specific working process of the above modules in the parking system 1 will be described in detail in the following method embodiments.

[0021] See Figure 3, Figure 3 This is a schematic diagram of the structure of a vehicle provided in one embodiment of this application. Vehicle 2 may include a parking function activation module 21, a multi-source surround-view perception module 22, an augmented reality (AR) path generation module 23, a head-up display (HUD) projection and interaction module 24, an automated valet parking (AVP) control command conversion module 25, an AVP execution module 26, an execution result monitoring module 27, and a charging function activation module 28. The specific working process of the above modules in vehicle 2 will be described in detail in the following method embodiments.

[0022] The parking space allocation method in this application can be applied to parking space allocation devices and parking lot systems (such as parking lot central control systems), and the parking space allocation device can be deployed in the parking lot system. The automatic parking method in this application can be applied to automatic parking devices and vehicles, and the automatic parking device can be deployed in the vehicle. Next, taking parking lot system 1 as the executing entity of the parking space allocation method and vehicle 2 as the executing entity of the automatic parking method as examples, the parking space allocation method and the automatic parking method of this application will be described in detail.

[0023] See Figure 4 , Figure 4 This is a schematic flowchart of a parking space allocation method provided in an embodiment of this application. The parking space allocation method may include steps S110-S130.

[0024] Step S110: Determine the target location of the portable charging device based on the charging needs of each parking area in the parking lot and the information on available parking spaces in the parking lot.

[0025] In some embodiments, before step S110, the data acquisition module 11 can acquire real-time vehicle data streams of the parking lot, the load of each parking area in the parking lot, and historical parking data of the parking lot. Based on the real-time vehicle data streams, the load of each parking area in the parking lot, and the historical parking data, the charging demand prediction model 13 predicts the charging demand of each parking area in the parking lot within a preset time period. The preset time period can be pre-determined based on prior experience; for example, the preset time period can be 30 minutes or 1 hour. This embodiment, based on real-time load prediction, allows portable charging devices to migrate to areas with high charging demand, reducing the idleness of parking spaces with available charging capacity in low-load areas and improving the turnover rate of parking spaces with available charging capacity.

[0026] The real-time vehicle data stream can include data streams of vehicles about to enter, already entered, and about to leave the parking lot. This real-time vehicle data stream can be represented as V={v1, v2, v3, ..., v...}n Data stream v for each vehicle i This may include, but is not limited to: vehicle identification information (Identity Document, ID), vehicle battery status, estimated dwell time (in minutes), current location, total driving range, and charging power. The vehicle battery status can include the remaining SOC (State of Charge, the ratio of remaining battery capacity to fully charged capacity) and the target SOC value (%). Parking gates can identify vehicles and acquire their data streams.

[0027] This application generates a corresponding static parking map for parking lots. The static parking map may include, but is not limited to, the initial fixed location set P={p1, p2, p3, ..., p...} of all parking spaces in the parking lot. n}, the inherent attributes of all parking spaces, and the real-time occupancy status of all parking spaces O={o1, o2, o3,..., o n}(o j =0 indicates that the parking space is vacant. j =1 indicates that the parking space is occupied, etc. Each parking space p j The inherent attributes of the parking space may include, but are not limited to: parking space ID, parking space location (x, y), whether the parking space supports movement (a boolean value of 0 indicates that movement is not supported, and a boolean value of 1 indicates that movement is supported), and maximum power supply (kilowatts). The static map of the parking lot can be obtained by using a data collection vehicle to traverse the path from the parking lot entrance to any parking space, and then overlaying the path data traversed by the data collection vehicle with the parking lot's Amap map to obtain accurate real-time map data.

[0028] Multiple parking areas can be deployed in a parking lot. The load of each parking area refers to the number of parked vehicles in that area, or the ratio of that number to the area's capacity. Based on the load and capacity of each parking area, the availability of parking spaces in each area can be determined. The load of each parking area can be determined based on the real-time occupancy status of all parking spaces in the parking lot. For example, assuming there are four parking areas A, B, C, and D in a parking lot, each with a capacity of 100, if there are 50 parked vehicles in area A, then the load of area A can be 50% or 50%; if there are 70 parked vehicles in area B, then the load of area B can be 70% or 70%; if there are 80 parked vehicles in area C, then the load of area C can be 80% or 80%; if there are 30 parked vehicles in area D, then the load of area D can be 30% or 30%.

[0029] Historical parking data for a parking lot can be obtained based on a static parking map. Static maps of the parking lot at different times can be acquired periodically, for example, every fixed time interval (e.g., 5 minutes), and then stored in a storage area. Based on the stored static maps, historical parking data can be determined. For example, assuming you need to obtain the number of cars parked in each parking area within the previous 30 minutes, you can determine the number of cars parked in each area based on the location and real-time occupancy status of all parking spaces in the static maps within the previous 30 minutes. For example, assuming there are 5 sets of static maps for the previous 30 minutes, you can determine the number of cars parked in each parking area corresponding to each set of static maps based on the location and real-time occupancy status of all parking spaces in each set, obtaining the number of cars parked in each of the 5 sets. Then, calculate the average of the number of cars parked in each of the 5 sets to obtain the total number of cars parked in each parking area within the previous 30 minutes (taking area A as an example, assuming the 5 sets of car parked numbers for A are 51, 49, 50, and 50 respectively, then the total number of cars parked in area A within the previous 30 minutes is 50).

[0030] In some embodiments, after acquiring the real-time vehicle data stream of the parking lot, the load of each parking area in the parking lot, and the historical parking data of the parking lot, the data preprocessing module 12 can preprocess the acquired data; based on the preprocessed data, the charging demand prediction model 13 can predict the charging demand of each parking area in the parking lot within a preset time period in the future. The preprocessing may include removing outliers (e.g., data with a SOC greater than 100%), normalization (e.g., unifying data units), and associating with vehicle demand (e.g., labeling vehicles that owners tend to park near the mall entrance as "near mall entrance"; labeling vehicles that owners tend to park near the parking lot exit as "near parking lot exit"; labeling vehicles with fast charging needs as "fast charging"; and labeling vehicles with extremely low battery levels that need to be charged nearby as "near distance").

[0031] As one implementation method, predicting the charging demand of each parking area within a preset future time period based on the real-time vehicle data stream of the parking lot, the load of each parking area, and the historical parking data of the parking lot may include: inputting the real-time vehicle data stream of the parking lot, the load of each parking area, and the historical parking data into a pre-trained charging demand prediction model 13; and obtaining the charging demand of each parking area within a preset future time period output by the charging demand prediction model 13. The charging demand prediction model 13 may be a deep learning model. A deep learning model or neural network may be pre-selected as the charging demand prediction model. Then, the real-time vehicle data stream of the parking lot, the load of each parking area, and the historical parking data are used as input, and the charging demand of each parking area within a preset future time period is used as output to train the charging demand prediction model until the result of the charging demand prediction model converges and training stops.

[0032] In this application, the charging demand of each parking area in the parking lot during the future preset time period may include, but is not limited to, the approximate proportion of fuel vehicles and new energy vehicles in each parking area of ​​the parking lot during the future preset time period, the number of vehicles with fast charging demand, the number of vehicles with slow charging demand, and the confidence level.

[0033] Optionally, when no vehicles enter the parking lot, or when a new vehicle enters the parking lot, or when a trigger time is reached (e.g., triggered every 5 minutes), the charging demand of each parking area in the parking lot during a preset period can be predicted based on the real-time vehicle data stream of the parking lot, the load of each parking area in the parking lot, and the historical parking data of the parking lot.

[0034] As one implementation method, the scheduling decision model 15 can be used to determine the charging demand of each parking area in the parking lot, the available parking spaces in the parking lot, and the current location of the mobile charging device (denoted as P_mobile(t) = {pm1, pm2, pm3, ..., pm...). n}), determine the target location of the portable charging device (denoted as T_target = {t1, t2, t3,..., t) k In this context, there is a one-to-one correspondence between the portable charging device and the target location.

[0035] The available parking space information can include the location of all available parking spaces and the maximum charging power of all available parking spaces. Based on the parking space occupancy status of all parking spaces in the parking lot, all available parking spaces in the parking lot can be determined.

[0036] As one implementation method, the scheduling decision model 15 can determine the target location of the mobile charging device under the constraints of points ① to ④, based on the charging demand of each parking area in the parking lot, the information on available parking spaces in the parking lot, and the current location of the mobile charging device.

[0037] ① Uniqueness constraint: Each portable charging device can only be assigned to one target location at a time, that is, the location of an available portable parking space.

[0038] ② Location conflict constraint: Each target location can be occupied by at most one mobile charging device.

[0039] ③ Movement distance constraint: The movement distance of the portable charging device is less than or equal to the upper limit of the physical structure of the portable charging device.

[0040] ④ Power supply capacity constraint: The total power of the circuits in the deployment area is less than or equal to the upper limit of the capacitor.

[0041] Step S120: Send the target location to the corresponding mobile charging device so that the mobile charging device moves to the corresponding target location, dynamically scheduling the layout of the target parking spaces in the parking lot. The target parking space has the mobile charging device, which can be used for vehicle parking and charging.

[0042] In one implementation, the data transmission module 16 of the parking system can send the target location to the corresponding mobile charging device via network commands, so that the mobile charging device moves to the target location, thereby dynamically scheduling the layout of target parking spaces in the parking lot. The mobile charging device has a built-in navigation system and autonomous movement capability. In some embodiments, the mobile charging device plans the optimal path based on the Simultaneous Localization and Mapping (SLAM) algorithm according to its current location and target location, and moves to the target location according to the planned optimal path. In other embodiments, the parking system can plan the optimal path for the mobile charging device based on its current location and target location, and send the planned optimal path (key points of the optimal path) to the mobile charging device via network commands. The mobile charging device moves to the target location according to the optimal path based on SLAM.

[0043] Once the portable charging device is moved to the target location, it forms the target parking space together with the movable parking space. At this point, the portable charging device can report its current location (i.e., the target location, or the target parking space) to the parking system. Based on the information reported by the portable charging device (including its location before and after movement, as well as its ID), the parking system updates the new layout of portable charging devices and parking space occupancy in the database system, thereby updating the parking lot's static map.

[0044] Step S130: Assign the target parking space to the vehicle to be charged.

[0045] The vehicles to be charged in this application can include vehicles about to enter the parking lot and vehicles that have already submitted charging requests while in the parking lot. The set of vehicles to be charged can be denoted as V = {v1, v2, v3, ..., v...} n}

[0046] As mentioned earlier, the target parking spaces in this application consist of vacant mobile parking spaces plus mobile charging devices. Therefore, all target parking spaces are vacant spaces that can be used for both parking and charging simultaneously. The set of target parking spaces can be denoted as P_mobile = {p1, p2, p3, ..., p...} n}

[0047] This application employs the Hungarian algorithm to find the optimal matching relationship between the target parking space and the vehicle to be charged; based on the optimal matching relationship, the target parking space is allocated to the vehicle to be charged.

[0048] See Figure 5 , Figure 5 This is a schematic diagram of a weighted bipartite diagram between a vehicle and a parking space provided in an embodiment of this application. This application transforms the optimal matching problem between a vehicle to be charged and a target parking space into... Figure 5 The minimum matching problem in the weighted bipartite graph shown involves determining the weights in the graph between vehicles and parking spaces based on at least one of the following: the distance the portable charging device travels to the target parking space, the distance the vehicle to be charged travels to the target parking space, and the battery state of the vehicle to be charged. Specifically, based on the weighted bipartite graph between vehicles and parking spaces, the Hungarian algorithm can be used to find the minimum matching in the graph, thereby finding the optimal matching relationship between the target parking space and the vehicle to be charged. Based on this optimal matching relationship, a target parking space is assigned to the vehicle to be charged.

[0049] In this application, the Hungarian algorithm can be used to find the optimal matching relationship between the target parking space and the vehicle to be charged based on at least one of the following: the moving distance of the portable charging device to the target parking space, the moving distance of the vehicle to be charged to the target parking space, and the battery state of the vehicle to be charged.

[0050] In one implementation, the vehicle to be charged and the target parking space can be used as the rows and columns of the cost matrix, respectively. The matrix elements of the cost matrix are determined based on at least one of the following: the moving distance from the portable charging device to the target parking space, the moving distance from the vehicle to be charged to the target parking space, and the battery state of the vehicle to be charged. The optimal matching relationship between the portable charging device and the vehicle to be charged is found based on the cost matrix using the Hungarian algorithm.

[0051] The cost matrix is ​​an m×m matrix, which can be represented as C. The matrix elements are represented as C[i][j], where C[i][j] represents the cost of allocating a target parking space (worker) to a vehicle (task) to be charged. C[i][j] can be determined based on at least one of the following: the distance the portable charging device travels to the target parking space, the distance the vehicle to be charged travels to the target parking space, and the battery state of the vehicle to be charged.

[0052] Because the minimum matching of a weighted bipartite graph requires that the number of rows and columns of the adjacency matrix be the same when using the Hungarian algorithm, this application can determine whether the number of vehicles to be charged is the same as the number of target parking spaces before constructing the cost matrix (i.e., the adjacency matrix).

[0053] If the number of vehicles waiting to be charged is equal to the number of target parking spaces, then the scheduling decision model 15 can directly allocate target parking spaces to the vehicles waiting to be charged, and there is a one-to-one correspondence between the vehicles waiting to be charged and the target parking spaces.

[0054] If the number of vehicles waiting to be charged is less than the number of target parking spaces, the scheduling decision model 15 can select the M target parking spaces closest to the vehicles waiting to be charged based on the location of the target parking spaces, where M is equal to the number of vehicles waiting to be charged; and then allocate the M target parking spaces to the vehicles waiting to be charged.

[0055] If the number of vehicles waiting to be charged is greater than the number of target parking spaces, the vehicle priority determination module 14 can determine the priority of the vehicles waiting to be charged based on the battery status, target power, and load of each parking area in the parking lot. Based on the priority of the vehicles waiting to be charged, the N vehicles with the highest priority are selected, where N is equal to the number of target parking spaces. The target parking spaces are then allocated to the selected N vehicles waiting to be charged through the scheduling decision model 15.

[0056] In one implementation, the vehicle priority determination module 14 can determine the priority of the vehicle to be charged according to the expression "Priority of the vehicle to be charged = (1-SOC)×0.4 + Target power×0.3 + Parking area load (proportion)×0.3", based on the battery status, target power, and load of each parking area in the parking lot. Then, it outputs a priority arrangement matrix, which may include the vehicle ID, vehicle type, vehicle priority, and recommended parking area of ​​the vehicle to be charged.

[0057] In some embodiments, the shortest waiting time can be used as the optimization objective, and the Hungarian algorithm can be employed to allocate target parking spaces to vehicles awaiting charging. Specifically, the vehicle awaiting charging and the target parking space can be first used as the row and column of a cost matrix, respectively. The matrix elements are determined based on the travel distance from the portable charging device to the target parking space and the travel distance from the vehicle awaiting charging to the target parking space, thus constructing a cost matrix. Then, the Hungarian algorithm is used to find the optimal matching relationship between the target parking space and the vehicle awaiting charging based on the cost matrix. This embodiment uses the shortest waiting time as the optimization objective to achieve the optimal matching of parking spaces and vehicles, which can achieve the technical effect of charging vehicles as quickly as possible and shortening vehicle waiting time.

[0058] The determination of matrix elements based on the moving distance of the portable charging device to the target parking space and the moving distance of the vehicle to be charged to the target parking space may include: determining matrix elements based on the sum of the moving distance of the portable charging device to the target parking space and the moving distance of the vehicle to be charged to the target parking space.

[0059] See Figure 6 , Figure 6 This is an embodiment provided by this application. Figure 5 The diagram shows a cost matrix corresponding to the weighted bipartite graph. Figure 6 The matrix elements in the cost matrix shown are the sum of the distance the mobile charging device moves to the target parking space and the distance the vehicle to be charged moves to the target parking space. Taking the matrix element "5" in the first row and first column as an example, the matrix element "5" represents the sum of the distance the mobile charging device moves from its previous position (its position before scheduling) to the target parking space P1 (i.e., the target position of the mobile charging device) and the distance the vehicle V1 moves from its current position to the target parking space P1.

[0060] See Figures 6 to 11 Using the Hungarian algorithm and based on the cost matrix, finding the optimal match between the target parking space and the vehicle to be charged may include the following steps S1-S5.

[0061] Step S1: Subtract the smallest element in each row of the cost matrix from each element. For example, subtract the smallest element in each row from the smallest element in each row of the cost matrix. Figure 6 Subtracting the minimum element of each row from each element of the cost matrix shown yields... Figure 7 The matrix shown.

[0062] Step S2: Subtract the smallest element of each column from each element in that column. For example, subtract the smallest element of that column from each element in the column. Figure 7 Subtracting the minimum element of each column from each element of the cost matrix shown yields... Figure 8 The matrix shown.

[0063] Step S3: Repeat. Step S3 includes steps ① to ③.

[0064] ① Find the fewest lines that cover all zero elements.

[0065] ② Determine whether to stop the loop. Specifically, determine whether the number of lines is less than the number of rows / columns of the cost matrix; if the number of lines is less than the number of rows / columns of the cost matrix, continue looping ③①② until the number of lines equals the number of rows / columns of the cost matrix; if the number of lines equals the number of rows / columns of the cost matrix, stop the loop and proceed to step S4.

[0066] ③ Create more 0 elements: Determine the smallest element among the elements not covered by a line as k, subtract k from each element not covered by a line, and add k to the elements at the intersection of lines.

[0067] For example, Figure 8 The matrix shown can be covered by at least two straight lines to cover all the zero elements, while Figure 8 If the number of lines in the matrix (2) is less than the number of rows in the cost matrix (3), continue the loop. If the smallest element not covered by a line is 1, then decrement 1 from each element not covered by a line and increment 1 from the elements at line intersections. Figure 9 The matrix shown can be covered by at least 3 straight lines to cover all the 0 elements, while Figure 9 The number of straight lines in the matrix is ​​3, which equals the number of rows in the cost matrix, so the loop stops.

[0068] Step S4: When the cycle stops, find the optimal match, and then you can perform "independent 0 selection".

[0069] Step S5: "Selection of Independent 0". For example, Figure 9 The matrix shown has only one 0 element in the second row. You can select (V2, P2) and cross out row V2 and column P2; for example... Figure 10 As shown, after crossing out row V2 and column P2, the third row contains only one 0 element. You can select (V3, P1) and cross out row V3 and column P1; (as shown) Figure 11As shown, after crossing out row V3 and column P1, only (V1, P3) remains. Therefore, we select (V1, P3). Thus, the optimal matching relationship between the vehicle to be charged and the target parking space is (V1, P3), (V2, P2), and (V3, P1). Therefore, we can assign the target parking space P3 to the vehicle to be charged V1, the target parking space P2 to the vehicle to be charged V2, and the target parking space P1 to the vehicle to be charged V3.

[0070] In other embodiments, the optimal charging power can be used as the optimization objective, and the Hungarian algorithm can be employed to allocate target parking spaces to vehicles to be charged. Specifically, the vehicles to be charged and the target parking spaces can be first used as rows and columns of a cost matrix, respectively. The matrix elements are determined based on the battery state of the vehicles to be charged to construct the cost matrix. Then, the Hungarian algorithm is used to find the optimal matching relationship between the target parking spaces and the vehicles to be charged based on the cost matrix (see [link to Hungarian algorithm steps]). Figures 6-11 (And the related descriptions mentioned above will not be repeated here). This embodiment uses the optimal charging power as the optimization target to achieve optimal matching of parking spaces and vehicles, which can achieve the technical effect of rationally allocating charging resources and avoiding high-range vehicles occupying fast charging resources.

[0071] The process of determining matrix elements based on the battery status of the vehicle to be charged may include: determining the target charging power of the vehicle to be charged based on the battery status of the vehicle to be charged; obtaining the charging power of the portable charging device in the target parking space as the charging power of the target parking space; and determining matrix elements based on the target charging power of the vehicle to be charged and the charging power of the target parking space.

[0072] The battery state of a vehicle to be charged can include its remaining SOC and target SOC. Based on the remaining SOC, target SOC, and expected dwell time, the target charging power can be determined. For example, target charging power = (target SOC - remaining SOC) × battery capacity / expected dwell time.

[0073] Different portable charging devices can be set with different charging power to provide different charging power for vehicles with different charging needs, thereby improving the user experience. For example, portable charging devices with a charging power of 3-15 kW can charge vehicles that require slow charging, while portable charging devices with a charging power of 30-200 kW can charge vehicles that require fast charging.

[0074] Determining matrix elements based on the target charging power of the vehicle to be charged and the charging power of the target parking space may include: calculating the difference between the target charging power of the vehicle to be charged and the charging power of the target parking space, and using this difference as a matrix element.

[0075] In some embodiments, the optimal charging power can be used as the optimization objective, and the Hungarian algorithm can be employed to allocate target parking spaces to vehicles to be charged. Specifically, the vehicles to be charged and the target parking spaces can be first used as rows and columns of a cost matrix, respectively. The matrix elements are determined based on the travel distance from the portable charging device to the target parking space, the travel distance from the vehicles to be charged to the target parking space, and the battery state of the vehicles to be charged, thus constructing a cost matrix. Then, the Hungarian algorithm is used to find the optimal matching relationship between the target parking spaces and the vehicles to be charged based on the cost matrix (see [link to Hungarian algorithm steps]). Figures 6 to 11 (And the related descriptions mentioned above will not be repeated here). This embodiment aims to optimize the shortest waiting time and the optimal charging power by matching vehicles and parking spaces in the best possible way. This achieves the technical effect of reasonably allocating charging resources while also reducing vehicle waiting time.

[0076] The determination of matrix elements based on the moving distance of the portable charging device to the target parking space, the moving distance of the vehicle to be charged to the target parking space, and the battery status of the vehicle to be charged may include: determining the target charging power of the vehicle to be charged based on the battery status of the vehicle to be charged; obtaining the charging power of the portable charging device in the target parking space as the charging power of the target parking space; and determining matrix elements based on the moving distance of the portable charging device to the target parking space, the moving distance of the vehicle to be charged to the target parking space, the target charging power of the vehicle to be charged, and the charging power of the target parking space.

[0077] Determining matrix elements based on the moving distance of the portable charging device to the target parking space, the moving distance of the vehicle to be charged to the target parking space, the target charging power of the vehicle to be charged, and the charging power of the target parking space may include: calculating the sum of the moving distance of the portable charging device to the target parking space and the moving distance of the vehicle to be charged to the target parking space; calculating the difference between the target charging power of the vehicle to be charged and the charging power of the target parking space; performing a weighted average of the calculated sum and difference, and using the calculation result as a matrix element (for example, matrix element = difference × first weight + sum × first weight, where the first weight and the second weight can be pre-calibrated based on prior experience).

[0078] Those skilled in the art will understand that the embodiments of this application list a scheme for determining the matrix elements of a cost matrix based on at least one of the following: the moving distance of the portable charging device to the target parking space, the moving distance of the vehicle to be charged to the target parking space, and the battery state of the vehicle to be charged, with the shortest waiting time and the best charging power as optimization objectives. However, those skilled in the art can extend the method of determining the matrix elements based on different optimization objectives when implementing the method of this application. For example, the matrix elements of the cost matrix can be determined by associating the parking preferences of car owners. For instance, some car owners prefer to park directly at the entrance of a shopping mall, while others prefer to park closer to the parking lot exit; in this case, the parking preferences of car owners can be used as a co-parameter of the optimization objective.

[0079] Based on the Hungarian algorithm, the optimal matching relationship between the vehicle to be charged and the target parking space can be found. The optimal matching relationship is a one-to-one correspondence, that is, after the optimal matching of the vehicle and the parking space by the Hungarian algorithm, there is a one-to-one correspondence between the vehicle to be charged and the target parking space.

[0080] In some embodiments, after allocating the target parking space to the vehicle to be charged, based on the one-to-one correspondence between the vehicle to be charged and the target parking space, the allocated target parking space can be sent to the corresponding vehicle to be charged, so that the vehicle to be charged can plan an augmented reality navigation path according to the corresponding target parking space and park in the corresponding target parking space according to the augmented reality navigation path.

[0081] Steps S110-S130 have the following technical effects: Based on the charging demand of each parking area in the parking lot and the information on available parking spaces, the position of the mobile charging device is dynamically adjusted to achieve dynamic scheduling of the layout of available parking spaces for charging. For example, based on real-time load prediction, the mobile charging device can be moved to areas with high charging demand, reducing the idleness of available parking spaces for charging in low-load areas, improving the turnover rate of available parking spaces for charging, making full use of charging resources, improving the utilization rate of charging spaces, solving the technical problem of low utilization rate of charging spaces caused by fixed charging locations under the current fixed charging pile mode, and alleviating the serious queuing during peak charging hours and the long time it takes for users to find charging spaces.

[0082] See Figure 12 , Figure 12 This is a flowchart illustrating a parking space allocation method provided in another embodiment of this application. The parking space allocation method may include steps S210 to S260.

[0083] Step S210: Determine the target location of the portable charging device based on the charging needs of each parking area in the parking lot and the information on available parking spaces in the parking lot.

[0084] Step S220: Send the target location to the corresponding mobile charging device so that the mobile charging device moves to the corresponding target location, dynamically scheduling the layout of the target parking spaces in the parking lot. The target parking space has the mobile charging device, which can be used for vehicle parking and charging.

[0085] Step S230: Assign the target parking space to the vehicle to be charged.

[0086] Step S240: Send the assigned target parking space to the corresponding vehicle to be charged, so that the vehicle to be charged can plan an augmented reality navigation path according to the corresponding target parking space and park in the corresponding target parking space according to the augmented reality navigation path.

[0087] By traversing the path from the parking lot entrance to any parking space using a data collection vehicle, the path data is overlaid with the parking lot's Amap (Gaode Map) data to obtain accurate real-time map data of the parking lot. Based on cloud sharing, vehicles waiting to be charged can access the parking lot's real-time map data.

[0088] The vehicle waiting to be charged can plan a path based on the location of the target parking space and the real-time location of the vehicle (multiple paths are possible). Through the HUD interface protocol, the key points of the planned path are converted into AR overlay targets, dynamically annotating the charging power and occupancy status of parking spaces near the key points of the optimal path (color coding: green = vacant, red = occupied). Finally, an AR-HUD data stream conforming to the ISO13209 standard is output. This AR-HUD data stream is then matched with the real-time map data of the parking lot (selecting the optimal path from multiple paths) to obtain the optimal augmented reality navigation path (in map display format).

[0089] After determining the optimal augmented reality navigation path (displayed on a map), the vehicle to be charged can activate the AVP (Augmented Reality Navigation) function. This path is pushed via an AR data stream and, combined with vehicle sensor data (such as LiDAR and camera data), uses the vehicle's initial position upon entering the parking lot as the starting point and the target parking space as the endpoint. The coordinates of the augmented reality navigation path are mapped into the AVP algorithm module's system. The vehicle to be charged then uses the location information to initiate parking, sending control commands for the accelerator, steering, and brake pedals to the AVP state machine to execute the parking operation and park the vehicle in the target parking space.

[0090] Once a vehicle is parked in the target parking space, it can report its current location to the parking system. If the vehicle is parked in the target parking space assigned by the parking system, the parking system can notify the user to use the portable charging device in that target parking space to charge the vehicle.

[0091] In some embodiments, due to uncontrollable factors, such as the owner believing the vehicle's current battery level is sufficient and charging is unnecessary, or the owner not wanting to park in their preferred parking space, the owner may not want to park in the target parking space assigned by the parking system. In such cases, the owner can choose a parking space and park the vehicle there. After parking, the vehicle can send a rejection instruction (instructing the owner to refuse parking in the target parking space assigned by the parking system) and the vehicle's current location back to the parking system. Based on the rejection instruction and the vehicle's current location, the parking system can determine that the vehicle is not parked in the assigned target parking space.

[0092] Step S250: If a vehicle to be charged is not parked in the assigned target parking space, then obtain the parking location of the target vehicle, which is a vehicle to be charged that is not parked in the assigned target parking space.

[0093] If a vehicle awaiting charging is not parked in its assigned target parking space, the parking system can obtain the parking location of the target space and, based on that location, determine if a portable charging device is available in that space. If a portable charging device is available, the system does not need to send the vehicle's location information to an available device; it can simply notify the user to use that device. If no portable charging device is available, the system can check for available ones.

[0094] If there are no available portable charging stations (for example, if the number of vehicles waiting to be charged is greater than the number of target parking spaces, other vehicles waiting to be charged that have not been assigned a target parking space may be parked in the target parking space, resulting in no available portable charging stations), then notify the vehicle that there are currently no available charging spaces.

[0095] If a portable charging station is available, it can be determined whether the target vehicle's parking location meets the conditions for the portable charging station to move to. If the target vehicle's parking location does not meet the conditions for the portable charging station to move to, the available parking space is sent to the vehicle so that the owner can freely choose whether to drive to the available parking space. If the target vehicle's parking location meets the conditions for the portable charging station to move to, the target vehicle's parking location is sent to the available portable charging station so that the portable charging station can move to the target vehicle's parking location.

[0096] The process of determining whether the parking location of the target vehicle meets the conditions for the movement of an available portable charging device may include: determining whether the total power of the circuit in the parking area where the target vehicle's parking location is located is lower than the upper limit of the capacitor; determining whether the distance that the available portable charging device needs to move to the parking location of the target vehicle is less than or equal to the upper limit of the physical movement of the portable charging device; if the total power of the circuit in the parking area where the target vehicle's parking location is located is lower than the upper limit of the capacitor, and the distance that the available portable charging device needs to move to the parking location of the target vehicle is less than or equal to the upper limit of the physical movement of the portable charging device, then the parking location of the target vehicle is determined to meet the conditions for the movement of an available portable charging device; otherwise, the parking location of the target vehicle is determined not to meet the conditions for the movement of an available portable charging device.

[0097] Step S260: If the parking location of the target vehicle meets the moving conditions of the idle portable charging device, then the parking location of the target vehicle is sent to the idle portable charging device so that the idle portable charging device can move to the parking location of the target vehicle.

[0098] Once an available portable charging device is moved to the parking space of the target vehicle, it can send a notification to the parking system that it has arrived. Once the parking system is aware that the available portable charging device has arrived, it can notify the user to use the portable charging device in the target parking space to charge the vehicle.

[0099] Compared to steps S110-S130, steps S210-S260 have the following additional technical effects: when a user does not want to park in the assigned parking space and chooses a movable parking space, the movable charging module is controlled to move to the parking space chosen by the user, which can fully meet the user's parking and charging needs and improve the user experience.

[0100] See Figure 13 , Figure 13 This is a schematic flowchart of an automatic parking method provided in an embodiment of this application. The automatic parking method may include steps S310 to S330.

[0101] Step S310: Receive the target parking space allocated by the parking system. The target parking space is determined according to the parking space allocation method described above.

[0102] Step S320: Based on the target parking space, plan an augmented reality navigation route.

[0103] By traversing the path from the parking lot entrance to any parking space using a data collection vehicle, the path data is overlaid with the parking lot's Amap (Gaode Map) data to obtain accurate real-time map data of the parking lot. Based on cloud sharing, vehicles waiting to be charged can access the parking lot's real-time map data.

[0104] The vehicle waiting to be charged can plan a route (multiple routes) based on the location of the target parking space and the real-time location of the vehicle. Through the HUD interface protocol, the key points of the planned route are converted into AR overlay targets, and the charging power and occupancy status of parking spaces near the key points of the optimal route are dynamically labeled (color-coded: green = vacant, red = occupied). Finally, an AR-HUD data stream conforming to the ISO13209 standard is output. This AR-HUD data stream is then matched with the real-time map data of the parking lot (selecting the optimal route from multiple options) to obtain the optimal augmented reality navigation route (in map display format).

[0105] Step S330: Park the vehicle in the target parking space according to the augmented reality navigation path.

[0106] After determining the optimal augmented reality navigation path (displayed on a map), the vehicle to be charged can activate the AVP (Augmented Reality Navigation) function. This path is pushed via an AR data stream and, combined with vehicle sensor data (such as LiDAR and camera data), uses the vehicle's initial position upon entering the parking lot as the starting point and the target parking space as the endpoint. The coordinates of the augmented reality navigation path are mapped into the AVP algorithm module's system. The vehicle to be charged then uses the location information to initiate parking, sending control commands for the accelerator, steering, and brake pedals to the AVP state machine to execute the parking operation and park the vehicle in the target parking space.

[0107] For example, see Figure 3Taking vehicle 2 as an example, after receiving the target parking space, vehicle 2 can activate the automatic parking function through the parking function activation module 21. The multi-source surround-view perception module 22 acquires onboard sensor data, parking lot data, and real-time status information of vehicle 2 (e.g., vehicle speed, acceleration, heading angle, pose information, etc.). Based on the onboard sensor data, parking lot data, and real-time status information of vehicle 2, a real-time 3D semantic map of the parking lot and the real-time pose of the vehicle are determined. The AR path generation module 23 determines the dynamic AR path and path source data based on the real-time 3D semantic map of the parking lot, the real-time pose of the vehicle, the location of the target parking space, and obstacle avoidance constraints. The HUD projection and interaction module 24 determines the HUD virtual and real image and path execution instructions based on the AR path, the real-time status information of vehicle 2, and user commands (input by the vehicle owner). The AVP control command conversion module 25 determines the AVP control command set (steering / vehicle speed) based on the path execution instructions and vehicle parameters. The AVP execution module 26 determines the motion state of vehicle 2 based on the AVP control command set and sensor feedback information. The execution result monitoring module 27 determines whether vehicle 2 has successfully docked with the portable charging device. If vehicle 2 successfully docks with the portable charging device, it notifies the AVP control command conversion module 25 to control vehicle 2 to stop. If vehicle 2 fails to dock with the portable charging device, it returns to the AR path generation module 23 until vehicle 2 successfully docks with the portable charging device. The charging function activation module 28 activates the charging function of vehicle 2 when it successfully docks with the portable charging device, and begins charging vehicle 2 using the portable charging device. This application demonstrates a breakthrough in system collaboration, enabling charging management, AR, and AVP to share a unified data protocol, supporting full-link automated integration of AR-AVP, avoiding inter-system communication delays and path execution delays, and optimizing user operation efficiency. Furthermore, AR navigation avoids manual pathfinding and reduces errors in online mapping based on high-precision positioning, ensuring improved accuracy of parking path tracking in scenarios with weak GPS signals in underground parking garages and in complex and narrow parking lot environments.

[0108] Steps S310 to S330, compared to steps S110 to S120, have the following additional technical effects: This application integrates augmented reality navigation and automatic valet parking to park the vehicle in the target parking space. AR navigation avoids manual navigation and reduces errors in online mapping based on high-precision positioning, ensuring improved accuracy of the parking path in scenarios with weak GPS signals in underground parking garages and in complex, narrow parking lots. Furthermore, this application achieves breakthroughs in system collaboration, enabling charging management, AR, and AVP to share a unified data protocol, supporting full-link automated integration of AR-AVP, avoiding inter-system communication delays and path execution delays, and optimizing user operation efficiency.

[0109] See Figure 14 , Figure 14 This is a structural block diagram of a parking space allocation device provided in an embodiment of this application. The parking space allocation device 100 includes a location determination module 110, a parking space scheduling module 120, and a parking space allocation module 130. The location determination module 110 is used to determine the target location of a portable charging device based on the charging demand of each parking area in the parking lot and the available parking space information. The parking space scheduling module 120 is used to send the target location to the corresponding portable charging device, so that the portable charging device moves to the corresponding target location, dynamically scheduling the layout of target parking spaces in the parking lot. The target parking space has the portable charging device, which can be used for vehicle parking and charging. The parking space allocation module 130 is used to allocate the target parking space to vehicles waiting to be charged. For specific details of the operations performed by the location determination module 110, the parking space scheduling module 120, and the parking space allocation module 130, please refer to the embodiment of the parking space allocation method of this application.

[0110] See Figure 15 , Figure 15 This is a structural block diagram of an automatic parking device provided in an embodiment of this application. The automatic parking device 200 includes an information receiving module 210, a path planning module 220, and an automatic parking module 230. The automatic parking device 200 is used to implement the above-described automatic parking method. The automatic parking device 200 can be deployed in a vehicle. The information receiving module 210 is used to receive a target parking space allocated by the parking lot system, the target parking space being determined according to the parking space allocation method. The path planning module 220 is used to plan an augmented reality navigation path based on the target parking space. The automatic parking module 230 is used to park the vehicle into the target parking space according to the augmented reality navigation path. For specific details regarding the operations performed by the location determination module 110, the parking space scheduling module 120, and the parking space allocation module 130, please refer to the embodiment of automatic parking in this application.

[0111] Those skilled in the art will clearly understand that the parking space allocation device and automatic parking device provided in the embodiments of this application can respectively implement the parking space allocation method and automatic parking method provided in the embodiments of this application. The specific working process of the described devices and modules can be found in the corresponding processes of the corresponding methods in the embodiments of this application, and will not be repeated here.

[0112] In the embodiments provided in this application, the coupling, direct coupling, or communication connection between the modules shown or discussed may be indirect coupling or communication coupling through some interfaces, devices, or modules, and may be electrical, mechanical, or other forms. The embodiments of this application do not impose specific limitations on this.

[0113] Furthermore, the functional modules in the embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0114] See Figure 16 , Figure 16 This is a structural block diagram of the parking space allocation device provided in this application embodiment. The parking space allocation device 300 can be deployed in a parking lot system, or the parking space allocation device 300 can be a server. The server can include, but is not limited to, a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server. The parking space allocation device 300 may include a memory 310 and a processor 320. The memory 310 stores an application program, which is configured to cause the processor 320 to execute the parking space allocation method provided in this application embodiment when invoked by the processor 320.

[0115] The memory 310 may include random access memory (RAM) or read-only memory (ROM). The memory 310 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 310 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function, instructions for implementing the various method embodiments described above, etc. The data storage area may store data created by the parking space allocation device 300 during use.

[0116] Processor 320 may include one or more processing cores. Processor 320 connects to various parts within the parking space allocation device 300 using various interfaces and lines, and is used to run or execute instructions, programs, code sets, or instruction sets stored in memory 310, as well as to call and execute data stored in memory 310, performing various functions and processing data of the parking space allocation device 300. Processor 320 may be implemented using at least one of the following hardware forms: Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA). Processor 320 may integrate one or more of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and Modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the displayed content; and the modem handles wireless communication. It is understood that the modem may also not be integrated into processor 320, but implemented separately through a communication chip.

[0117] See Figure 17 , Figure 17 This is a structural block diagram of a vehicle provided in an embodiment of this application. The vehicle 400 may include, but is not limited to, gasoline vehicles or new energy vehicles. New energy vehicles may include electric vehicles, which may include, but are not limited to, pure electric vehicles, hybrid electric vehicles, or fuel cell vehicles. The vehicle 400 may include a memory 410 and a processor 420. The memory 410 stores an application program configured to cause the processor 420 to execute the automatic parking method provided in this embodiment of the application when invoked by the processor 420.

[0118] The memory 410 may include RAM or ROM. The memory 410 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 410 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function, instructions for implementing the various method embodiments described above, etc. The data storage area may store data created by the vehicle 400 during use.

[0119] Processor 420 may include one or more processing cores. Processor 420 connects to various parts within the vehicle 400 using various interfaces and lines, and is used to run or execute instructions, programs, code sets, or instruction sets stored in memory 410, as well as to call and execute data stored in memory 410, performing various functions and processing data of the vehicle 400. Processor 420 may be implemented using at least one hardware form of DSP, FPGA, or PLA. Processor 420 may integrate one or more of CPU, GPU, and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing displayed content; and the modem handles wireless communication. It is understood that the modem may also not be integrated into processor 420, but implemented separately through a communication chip.

[0120] This application also provides a computer-readable storage medium. The computer-readable storage medium stores program code configured to, when invoked by a processor, cause the processor to execute the parking space allocation method or automatic parking method provided in this application. The computer-readable storage medium may include, but is not limited to, flash memory, electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), hard disk, or ROM. In some embodiments, the computer-readable storage medium includes a non-volatile computer-readable storage medium (Non-TCRSM). The computer-readable storage medium has storage space for program code that performs any of the method steps described above. This program code can be read from or written to one or more computer program products. The program code may be compressed in an appropriate form.

[0121] This application also provides a computer program product, which includes a computer program that, when invoked by a processor, causes the processor to execute the parking space allocation method or automatic parking method provided in the embodiments of this application.

[0122] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. 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 spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A parking space allocation method, characterized in that, include: Based on the charging needs of each parking area and the availability of parking spaces, the target location of the portable charging device is determined. The target location is sent to the corresponding mobile charging device so that the mobile charging device moves to the corresponding target location, dynamically scheduling the layout of the target parking spaces in the parking lot. The target parking space has the mobile charging device, which can be used for vehicle parking and charging. The target parking space is assigned to the vehicle to be charged.

2. The method according to claim 1, characterized in that, The step of allocating the target parking space to the vehicle to be charged includes: The Hungarian algorithm is used to find the optimal matching relationship between the target parking space and the vehicle to be charged; Based on the optimal matching relationship, the target parking space is assigned to the vehicle to be charged.

3. The method according to claim 2, characterized in that, The step of using the Hungarian algorithm to find the optimal matching relationship between the target parking space and the vehicle to be charged includes: The vehicle to be charged and the target parking space are respectively used as the row and column of the cost matrix. The matrix elements are determined based on at least one of the following: the moving distance of the portable charging device to the target parking space, the moving distance of the vehicle to be charged to the target parking space, and the battery state of the vehicle to be charged. The Hungarian algorithm is used to find the optimal matching relationship between the target parking space and the vehicle to be charged based on the cost matrix.

4. The method according to claim 3, characterized in that, The step of determining matrix elements based on the moving distance of the portable charging device to the target parking space and the moving distance of the vehicle to be charged to the target parking space includes: The matrix elements are determined based on the sum of the moving distance of the portable charging device from the target parking space and the moving distance of the vehicle to be charged from the target parking space.

5. The method according to claim 3, characterized in that, The steps for determining matrix elements based on the battery state of the vehicle to be charged include: The target charging power of the vehicle to be charged is determined based on the battery status of the vehicle to be charged. The charging power of the portable charging device in the target parking space is obtained and used as the charging power of the target parking space. The matrix elements are determined based on the target charging power of the vehicle to be charged and the charging power of the target parking space.

6. The method according to claim 3, characterized in that, The step of determining matrix elements based on the moving distance of the portable charging device to the target parking space, the moving distance of the vehicle to be charged to the target parking space, and the battery state of the vehicle to be charged includes: The target charging power of the vehicle to be charged is determined based on the battery status of the vehicle to be charged. The charging power of the portable charging device in the target parking space is obtained and used as the charging power of the target parking space. The matrix elements are determined based on the moving distance of the portable charging device to the target parking space, the moving distance of the vehicle to be charged to the target parking space, the target charging power of the vehicle to be charged, and the charging power of the target parking space.

7. The method according to claim 1, characterized in that, After allocating the target parking space to the vehicle to be charged, the method further includes: The assigned target parking space is sent to the corresponding vehicle to be charged, so that the vehicle to be charged can plan an augmented reality navigation path according to the corresponding target parking space and park in the corresponding target parking space according to the augmented reality navigation path.

8. A parking space allocation device, characterized in that, include: The location determination module is used to determine the target location of the portable charging device based on the charging needs of each parking area in the parking lot and the available parking spaces in the parking lot. The parking space scheduling module is used to send the target location to the corresponding mobile charging device so that the mobile charging device moves to the corresponding target location, dynamically scheduling the layout of the target parking spaces in the parking lot. The target parking space has the mobile charging device, which can be used for vehicle parking and charging. The parking space allocation module is used to allocate the target parking space to the vehicle to be charged.

9. A parking space allocation device, characterized in that, include: A memory and a processor, wherein the memory stores an application program that, when invoked by the processor, causes the processor to perform the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores program code that, when invoked by a processor, causes the processor to perform the method as described in any one of claims 1-7.

Images