Vehicle parking method and vehicle searching method

Abstract

The invention relates to the technical field of vehicles, and provides a vehicle parking method and a vehicle searching method, and the vehicle parking method comprises the steps: obtaining sensing data of a parking lot area through a sensing device; and generating a real-time area map of the parking lot area based on the sensing data, wherein the real-time area map dynamically stores area object data and corresponding object state data in the parking lot area. And when a parking instruction of the target vehicle is received and it is detected that the target vehicle is driven into the parking lot area, the vehicle position of the target vehicle and the parking space position of the target parking space are determined according to the area object data and the corresponding object state data. The parking route of the target vehicle is generated based on the vehicle position, the parking space position and the real-time area map, the first control instruction is generated based on the parking route, the parking route and the first control instruction are sent to the target vehicle, and the target vehicle is controlled to drive to the target parking space according to the parking route. And the parking experience of the driver is improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a vehicle parking method and a vehicle finding method. Background Art

[0002] As cities develop, the number of vehicles continues to increase, while the number and space of parking lots are limited. This leads to parking difficulties, especially in busy commercial areas, hospitals, schools, and other places, where parking spaces are often in short supply. In many parking lots, improper management and operation can easily lead to overcrowding, waste of resources, and environmental pollution. Furthermore, in large parking lots, drivers often have difficulty quickly finding their vehicles due to the large number of spaces and unclear signage, especially in large parking lots or underground parking lots. These situations waste drivers' time and affect their parking and car-finding experience. Summary of the Invention

[0003] In view of this, the present application provides a vehicle parking method and a vehicle finding method to solve the problem in the related art that the efficiency of parking or finding a vehicle in a parking lot is low, resulting in a poor user experience.

[0004] A first aspect of an embodiment of the present application provides a vehicle parking method, the vehicle parking method comprising: acquiring sensing data of a parking area through a sensing device; generating a real-time area map of the parking area based on the sensing data, the real-time area map dynamically storing area object data and corresponding object status data within the parking area, the area object data including at least data of a driver, a vehicle, and a parking space, and the object status data including at least object positions and correspondences between objects; upon receiving a parking instruction of a target vehicle and detecting that the target vehicle enters the parking area, determining the vehicle position of the target vehicle in the real-time area map and the parking space position of a target parking space in the parking area in the real-time area map based on the area object data and the corresponding object status data; generating a parking route for the target vehicle based on the vehicle position, the parking space position, and the real-time area map; generating a first control instruction based on the parking route, and sending the parking route and the first control instruction to the target vehicle to control the target vehicle to travel to the target parking space according to the parking route.

[0005] A second aspect of an embodiment of the present application provides a vehicle search method, the vehicle search method comprising: upon receiving a vehicle search instruction from a driver for a target vehicle, obtaining a real-time area map of a parking lot area and area object data and corresponding object status data dynamically stored in the real-time area map; determining a parking space position and a preset pick-up position of the target vehicle corresponding to the target vehicle parking space based on the vehicle search instruction and the area object data and corresponding object status data; generating a vehicle search route for the target vehicle based on the parking space position, the preset pick-up position and the real-time area map; generating a second control instruction based on the vehicle search route, and sending the vehicle search route and the second control instruction to the target vehicle to control the target vehicle to travel to the preset pick-up position according to the vehicle search route.

[0006] A third aspect of an embodiment of the present application provides a computer device, comprising a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, wherein the processor implements the above-mentioned vehicle parking method or the above-mentioned vehicle searching method when executing the computer-readable instructions.

[0007] A fourth aspect of an embodiment of the present application provides a computer-readable storage medium, which stores computer-readable instructions. When the computer-readable instructions are executed by a processor, the above-mentioned vehicle parking method or the above-mentioned vehicle searching method is implemented.

[0008] The vehicle parking method provided in the first aspect of the embodiment of the present application obtains sensing data of the parking area through the sensing equipment in the parking area. A real-time area map of the parking area is generated based on the sensing data. The real-time area map dynamically stores area object data and corresponding object status data in the parking area. The area object data includes but is not limited to data of the driver, vehicle, and parking space. The object status data includes but is not limited to object positions and the correspondence between objects. When a parking instruction of a target vehicle is received and the target vehicle is detected to enter the parking area, the vehicle position of the target vehicle in the real-time area map and the parking space position of the target parking space in the parking area can be determined based on the area object data and corresponding object status data in the real-time area map. Based on the vehicle position, parking space position and real-time area map, a parking route for the target vehicle can be generated, a first control instruction can be generated based on the parking route, and the parking route and the first control instruction can be sent to the target vehicle to control the target vehicle to drive to the target parking space according to the parking route. When the target vehicle enters the parking lot area, the computer equipment corresponding to the parking lot management system takes over the target vehicle, determines the target parking space and controls the target vehicle to drive to the target parking space, which can reduce the precious time and resources wasted by users or drivers when looking for parking spaces, improve the driver's parking experience, and make more effective use of the limited parking space, thereby improving the utilization rate of the parking lot area and creating greater utilization benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0010] Figure 1 This is an application scenario diagram of the vehicle parking method or vehicle finding method provided in an embodiment of the present application.

[0011] Figure 2 This is a flowchart of the implementation of the vehicle parking method provided in an embodiment of the present application.

[0012] Figure 3 This is a flow chart for implementing the vehicle search method provided in an embodiment of the present application.

[0013] Figure 4 This is a flowchart of the implementation of the vehicle parking device provided in an embodiment of the present application.

[0014] Figure 5 This is a flowchart of the implementation of the vehicle search device provided in the embodiment of the present application.

[0015] Figure 6 It is a structural diagram of the computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0016] It should be noted that the terms "first" and "second" in the description, claims and drawings of this application are used to distinguish similar objects, rather than to describe a specific order or sequence.

[0017] It should also be noted that the method disclosed in the embodiments of the present application or the method shown in the flowchart includes one or more steps for implementing the method. Without departing from the scope of the claims, the execution order of multiple steps can be interchanged with each other, and some steps can also be deleted.

[0018] The following will describe some embodiments with reference to the accompanying drawings. In the absence of conflict, the following embodiments and features therein may be combined with each other.

[0019] The vehicle parking method and vehicle search method provided in the embodiments of the present application can be applied to a parking lot management system of a pre-designed parking lot area. The parking lot management system can be integrated into computer equipment by means of technical means such as database integration and API interface docking to achieve unified management and operation of vehicles, parking spaces, etc. in the parking lot area.

[0020] See also Figure 1 , Figure 1 The figure shows an application scenario of the vehicle parking method provided by the embodiment of the present application. Figure 1 As shown, the computer device 100, the terminal device 300, and the vehicle 200 are communicatively connected. In some embodiments, the computer device 100 is communicatively connected to the sensing devices in the parking area. The computer device 100 can control the sensing devices to detect and acquire sensory data from the parking area. Based on the sensory data from the parking area, the computer device 100 can generate a real-time regional map of the parking area. The real-time regional map dynamically stores regional object data and corresponding object status data within the parking area. The regional object data includes, but is not limited to, data on drivers, vehicles, and parking spaces. The object status data includes, but is not limited to, object locations and corresponding relationships between objects.

[0021] In some embodiments, a user can trigger a parking instruction for the target vehicle 200 via the terminal device 300 or the target vehicle 200, and the terminal device 300 or the target vehicle 200 sends the parking instruction to the computer device 100. When the computer device 100 receives the parking instruction for the target vehicle 200 and detects that the target vehicle 200 has entered the parking area, it can determine the vehicle position of the target vehicle 200 in the real-time regional map and the parking space position of the target parking space in the parking area in the real-time regional map based on the regional object data and the corresponding object state data. Based on the vehicle position, the parking space position, and the real-time regional map, the computer device 100 can generate a parking route for the target vehicle 200, generate a first control instruction based on the parking route, and send the parking route and the first control instruction to the target vehicle 200 to control the target vehicle 200 to drive to the target parking space according to the parking route.

[0022] In some embodiments, a user can trigger a vehicle search command for the target vehicle 200 via the terminal device 300 or the target vehicle 200. The terminal device 300 or the target vehicle 200 then sends the vehicle search command to the computer device 100. Upon receiving the vehicle search command, the computer device 100 obtains a real-time area map of the parking area, as well as dynamically stored area object data and corresponding object status data within the real-time area map. Based on the vehicle search command, the area object data, and the corresponding object status data, the computer device 100 can determine the parking space location and the preset pickup location of the target vehicle 200 corresponding to the target parking space. Based on the parking space location, the preset pickup location, and the real-time area map, the computer device 100 generates a vehicle search route for the target vehicle 200. The computer device 100 then generates a second control command based on the vehicle search route and sends the vehicle search route and the second control command to the target vehicle 200, controlling the target vehicle 200 to travel to the preset pickup location according to the vehicle search route.

[0023] In some embodiments, the terminal device 300 may be installed with an application for monitoring, controlling, and managing the target vehicle 200 and providing users with services related to the target vehicle 200. This application may establish a connection with the parking lot management system via a network, communication protocols, data exchange, or other means. The parking lot management system may provide parking services, vehicle pickup services, reservation services, and the like. Through this application, users may select parking services, vehicle pickup services, reservation services, and the like, and may trigger parking commands or vehicle search commands, authorizing the parking lot management system to take over control of the target vehicle 200 and control the parking or search for the target vehicle 200.

[0024] In some embodiments, the application may also be installed on the target vehicle 200 , so that the user may trigger a parking instruction or a vehicle search instruction, etc. through the target vehicle 200 .

[0025] In some embodiments, communication connections include, but are not limited to, wired connections and wireless connections. Computer device 100 may be a computer, a standalone server, or a server cluster consisting of multiple servers. Terminal device 300 may include, but is not limited to, one or more of a mobile phone, tablet computer, wearable device, and the like.

[0026] See also Figure 2 As shown in FIG, it is a flow chart of the implementation of the vehicle parking method provided in the embodiment of the present application, and the method is applied in Figure 1 The computer device 100 in FIG. 1 is used as an example to illustrate the method, which includes the following steps.

[0027] S11: Acquire sensing data of the parking area through a sensing device.

[0028] In some embodiments, the computer device is communicatively connected to the sensing device, the sensing device collects sensing data of the parking lot area, and can transmit the sensing data of the parking lot area to the computer device via a communication link with the computer device.

[0029] In some embodiments, sensing devices include, but are not limited to, cameras, millimeter-wave radars, optical radars, and ultrasonic sensors. To comprehensively cover and collect sensory data within the parking lot, embodiments of this application design and deploy the sensing devices necessary to create a real-time area map based on the structure and scope of the parking lot. These sensing devices are distributed throughout the parking lot, ensuring comprehensive monitoring and data collection, capturing detailed information within the parking lot.

[0030] S12: Generate a real-time area map of the parking area based on the sensing data. The real-time area map dynamically stores area object data and corresponding object status data in the parking area.

[0031] In some embodiments, the real-time area map may be a topological map, a semantic map, or the like. Area object data includes at least driver, vehicle, and parking space data, and object status data includes at least object locations and correspondences between objects, such as the vehicle's location, the parking space's location, and the correspondences between parking spaces and vehicles. Because the status of area objects such as vehicles, drivers, and parking spaces within a parking area changes dynamically, the map data stored in the real-time area map must be regularly updated to maintain its accuracy and real-time performance. This ensures that the real-time area map maintains dynamic area object data and corresponding object status data for the parking area.

[0032] In some embodiments, the computer device can continuously collect sensing data through the sensing device and repeat the above steps S11-S12 to achieve real-time updating of the real-time area map, thereby updating the area object data and corresponding object status data in the parking area stored in the real-time area map.

[0033] In some embodiments, objects in the parking lot area and corresponding object statuses may be displayed in the real-time area map.

[0034] In some embodiments, when generating a real-time area map of a parking lot based on sensory data, the computer device may utilize a vision-based map construction method, using computer vision technologies such as feature extraction and Simultaneous Localization and Mapping (SLAM) technology, to generate a real-time area map of the parking lot based on the sensory data; or utilize a neural network model to generate a real-time area map of the parking lot based on the sensory data. The present embodiments do not limit the method for constructing the real-time area map.

[0035] In some embodiments of the present application, a real-time area map of a parking area is generated based on sensory data, including: preprocessing the sensory data to obtain preprocessed sensory data; and analyzing the preprocessed sensory data using a preset map construction model to generate a real-time area map.

[0036] In some embodiments, preprocessing the sensory data includes, but is not limited to, time-aligning the sensory data to match sensory data at different times, determining correspondences between sensory data, and performing noise filtering on the sensory data. The computer device preprocesses the sensory data and, based on the preprocessed sensory data, generates a real-time regional map using a preset map construction model, thereby ensuring the accuracy and reliability of the map data.

[0037] In some embodiments, the preset map construction model can be a deep learning network model, such as a convolutional neural network model, a recurrent neural network model, a generative adversarial network model, a hybrid model, etc. In the process of using the preset map construction model to analyze the preprocessed sensory data and generate a real-time regional map, the computer device can fuse the sensory data from different sensing devices to obtain more comprehensive and accurate environmental perception information. For example, the computer device can use a fusion algorithm such as weighted averaging or Kalman filtering to fuse the sensory data from different sensing devices into a unified data stream. The computer device can then extract useful features from the fused data, such as spatial features and texture features, and use these features as input to the preset map construction model. The preset map construction model processes and analyzes the input feature data to generate a real-time regional map of the parking area.

[0038] In some embodiments, the computer device may perform post-processing and visualization operations on the real-time area map generated using a preset map construction model, such as smoothing, color rendering, etc., to obtain a more intuitive and easy-to-understand real-time area map.

[0039] In some embodiments of the present application, before analyzing the preprocessed sensing data using a preset map construction model to generate a real-time regional map, the method further includes: obtaining a training sample set, the training sample set including multiple groups of data samples collected by different sensing devices; and using the training sample set to perform model training on the initial map construction model to obtain a preset map construction model.

[0040] In some embodiments, the training sample set includes multiple sets of data samples collected by different sensing devices. When the computer device uses the training sample set to train the initial map construction model, it can perform data preprocessing, data fusion, and feature extraction on the training sample set to obtain sample features. The sample features are then used as input to train the initial map construction model. During the training process, the parameters of the initial map construction model are adjusted to improve the model's accuracy and generalization capabilities. Furthermore, the computer device can use appropriate evaluation metrics and methods, such as calculating the model's accuracy and recall rate, to evaluate and optimize the trained map construction model to determine its performance and accuracy.

[0041] In some embodiments, the initial map construction model includes but is not limited to a convolutional neural network model, a recurrent neural network model, and the like.

[0042] S13: When a parking instruction of a target vehicle is received and the target vehicle is detected to enter the parking area, the vehicle position of the target vehicle in the real-time area map and the parking space position of the target parking space in the parking area in the real-time area map are determined based on the area object data and the corresponding object status data.

[0043] In some embodiments, an application for controlling and managing the target vehicle is installed in the terminal device or target vehicle. This application is integrated with the parking lot management system and can provide users with parking services, vehicle search services, reservation services, queuing services, etc. Users can trigger a parking instruction for the target vehicle through this application in the terminal device or target vehicle to request parking services. In response to the user's operation, the terminal device or target vehicle can send the parking instruction to a computer device corresponding to the parking lot management system. In response to the parking instruction from the target vehicle, the computer device, upon detecting that the target vehicle enters the parking lot area, obtains regional object data and corresponding object status data within the current parking lot area based on the current real-time regional map. Based on the regional object data and corresponding object status data, the computer device determines the vehicle position of the target vehicle in the real-time regional map and the parking space position of the target parking space in the parking lot area.

[0044] In some embodiments, the target parking space includes a vacant parking space in the current parking lot area.

[0045] In some embodiments, the parking instruction includes but is not limited to a vehicle takeover instruction or a vehicle authorization instruction. The computer device can only perform operations such as controlling the target vehicle if the user authorizes taking over the target vehicle.

[0046] In some embodiments, a user can reserve parking in a parking area through an application corresponding to a target vehicle. When the computer device receives parking service requests from multiple vehicles, it can queue the vehicles according to a preset queuing strategy, such as the order in which the parking service requests were received. After each vehicle enters the parking area, the computer device can take over each vehicle in turn, determine the parking space corresponding to each vehicle, and control each vehicle to move to the corresponding parking space.

[0047] In some embodiments, a user can access a real-time area map of a parking area via a terminal device or a target vehicle. The real-time area map can display various area objects in the parking area and their corresponding object statuses. For example, the real-time area map can display a parking space that is vacant. The user can select a target parking space for the target vehicle based on the real-time area map of the parking area. In response to the user's selection, the terminal device can transmit information including the target parking space to a computer device. The computer device can then obtain the corresponding parking space location based on the target parking space selected by the user.

[0048] In some embodiments of the present application, a computer device determines the parking space position of a target parking space in a parking lot area in a real-time area map, including: determining the parking space status data corresponding to all parking spaces in the parking lot area based on the area object data and the corresponding object status data; determining the usage status of the parking space based on the parking space status data; determining all idle parking spaces in the parking lot area based on the usage status of all parking spaces; determining the target parking space from all idle parking spaces according to a preset strategy; and determining the parking space position of the target parking space in the real-time area map based on the parking space status data.

[0049] In some embodiments, area object data includes data on objects such as vehicles, parking spaces, and drivers. Object status data includes, but is not limited to, the location of objects such as vehicles, parking spaces, and drivers, the usage status of parking spaces, and the correspondence between vehicles and parking spaces. Preset strategies may include, for example, a distance-priority strategy and a path-priority strategy.

[0050] In some embodiments, when determining the parking space location of a target parking space in a real-time area map within a parking lot area, the computer device may obtain a current real-time area map of the parking lot area and obtain current area object data and corresponding object status data based on the real-time area map. Based on the area object data and corresponding object status data for the parking lot area, parking space status data for all parking spaces within the parking lot area may be determined. Based on the parking space status data for all parking spaces, the usage status of each parking space may be determined, such as whether a vehicle is parked in the space, the space is idle, or the space is reserved. Based on the usage status of each parking space, the computer device may determine idle parking spaces within the parking lot area, i.e., idle parking spaces. The target parking space may be determined from all idle parking spaces according to a preset strategy. For example, based on a distance-priority strategy, the target parking space may be determined from all idle parking spaces. Alternatively, based on a path-priority strategy, the target parking space may be determined from all idle parking spaces with the shortest path time to the target vehicle's location. After determining the target parking space, the computer device can obtain parking space status data corresponding to the target parking space, and determine the parking space position of the target parking space in the real-time area map based on the parking space status data corresponding to the target parking space.

[0051] S14: Generate a parking route for the target vehicle based on the vehicle position, parking space position, and real-time area map.

[0052] In some embodiments, a computer device may utilize a neural network model to process and analyze the target vehicle's location, parking space location, and real-time area map, and output a parking route for the target vehicle. The parking route may comprise a list of waypoints. The neural network model may, for example, be a convolutional neural network model, a recurrent neural network model, or a generative adversarial network model.

[0053] In other embodiments, the computer device may also employ some path planning algorithms, such as genetic algorithms, to plan the parking route of the target vehicle based on the vehicle location, parking space location, and a real-time area map, or may call a public map application interface and utilize the path planning function of the map application to plan the parking route of the target vehicle. This application does not limit the method for generating the parking route of the target vehicle.

[0054] In some embodiments of the present application, a parking route for a target vehicle is generated based on the vehicle position, parking space position, and real-time area map, including: outputting the parking route for the target vehicle using a preset route planning model based on the vehicle position, parking space position, and real-time area map.

[0055] In some embodiments, the preset route planning model may be a neural network model, such as a convolutional neural network model, a recurrent neural network model, and the like.

[0056] In the process of outputting a parking route for the target vehicle using a preset route planning model based on the vehicle position, parking space location, and real-time area map, the computer device may pre-process the vehicle position, parking space location, and real-time area map, such as obtaining standardized coordinates of the vehicle position and parking space location in the real-time area map and converting the real-time area map into a processable format. The computer device processes and analyzes the pre-processed vehicle position, parking space location, and real-time area map using the preset route planning model to output a predicted parking route for the target vehicle.

[0057] In some embodiments of the present application, before analyzing the vehicle position, parking space position, and real-time area map using a preset route planning model and outputting the parking route of the target vehicle, the method further includes: obtaining model training samples, the model training samples including multiple sets of different vehicle initial positions, vehicle destination positions, and real-time area maps; and using the model training samples to perform model training on the initial route planning model to obtain a preset route planning model.

[0058] In some embodiments, the computer device can obtain multiple sets of different vehicle initial positions, vehicle destination positions, and real-time area maps as model training samples for the preset route planning model. Select a suitable initial route planning model, such as a convolutional neural network model, a recurrent neural network model, etc., to ensure that the model can receive the vehicle initial position, vehicle destination position, and real-time area map as input, and output a trajectory route. The computer device can then use the model training samples to train the initial route planning model, and can optimize the model parameters by minimizing the loss function so that the initial route planning model can output a more accurate and reasonable trajectory route. The computer device can divide the obtained model training samples into training samples and verification samples, use the training samples to train the initial route planning model, use the verification samples to evaluate the performance of the model, and adjust the network structure or hyperparameters as needed to improve the accuracy and robustness of the model, and finally obtain the trained initial route planning model as the preset route planning model.

[0059] S15: Generate a first control instruction based on the parking route, and send the parking route and the first control instruction to the target vehicle to control the target vehicle to drive to the target parking space according to the parking route.

[0060] In some embodiments, the computer device may utilize a model predictive control method to convert the parking route into a first control instruction, where the first control instruction may include control of acceleration, speed, steering wheel, vehicle orientation, and the like.

[0061] In some embodiments, a vehicle control module is installed in the target vehicle. The vehicle control module is configured to receive the parking route and the first control instruction sent by the computer device, read the vehicle status of the target vehicle, and return the vehicle status of the target vehicle to the computer device. In response to the first control instruction, the target vehicle can be controlled to drive to the target parking space according to the parking route.

[0062] In some embodiments of the present application, if it is determined that the target parking space has changed based on the area object data and the corresponding object status data, the updated parking space position corresponding to the updated target parking space and the current position of the target vehicle are obtained; based on the current position, the updated parking space position and the real-time area map, the parking route of the target vehicle is regenerated.

[0063] In some embodiments, while the target vehicle is traveling along the parking route, it may need to temporarily change the target parking space due to circumstances such as the currently determined target parking space being occupied. In this case, the computer device may repeatedly perform steps S11 to S12, obtaining a real-time area map of the parking area, obtaining real-time object data and corresponding object status data for the parking area based on the real-time area map, updating the target parking space based on the area object data and corresponding object status data, re-determining the parking space position of the updated target parking space, and obtaining the current position of the target vehicle. The computer device may regenerate the parking route for the target vehicle based on the current position of the target vehicle, the updated parking space position, and the real-time area map, generate an updated first control instruction based on the updated parking route, and transmit the updated parking route and the first control instruction to the target vehicle, thereby controlling the target vehicle to travel to the updated target parking space according to the updated parking route.

[0064] In some embodiments of the present application, after controlling the target vehicle to travel to the target parking space according to the parking route, the method further includes: updating the regional object data and corresponding object status data in the parking lot area based on the correspondence between the target vehicle and the target parking space.

[0065] In some embodiments, after controlling the target vehicle to drive to the target parking space according to the parking route, a correspondence is established between the target vehicle and the target parking space. The computer device can update the regional object data and corresponding object status data in the parking lot area based on the correspondence between the target vehicle and the target parking space, such as updating the vehicle status data of the target vehicle and updating the usage status of the target parking space.

[0066] The vehicle parking method provided in the embodiment of the present application obtains sensing data of the parking area through the sensing equipment in the parking area. A real-time area map of the parking area is generated based on the sensing data. The real-time area map dynamically stores area object data and corresponding object status data in the parking area. The area object data includes but is not limited to data of the driver, vehicle, and parking space. The object status data includes but is not limited to object positions and correspondences between objects. When a parking instruction of a target vehicle is received and the target vehicle is detected to enter the parking area, the vehicle position of the target vehicle in the real-time area map and the parking space position of the target parking space in the parking area in the real-time area map can be determined based on the area object data and corresponding object status data in the real-time area map. Based on the vehicle position, parking space position and real-time area map, a parking route for the target vehicle can be generated, a first control instruction can be generated based on the parking route, and the parking route and the first control instruction can be sent to the target vehicle to control the target vehicle to drive to the target parking space according to the parking route. When the target vehicle enters the parking lot area, the computer equipment corresponding to the parking lot management system takes over the target vehicle, determines the target parking space and controls the target vehicle to drive to the target parking space, which can reduce the precious time and resources wasted by users or drivers when looking for parking spaces, improve the driver's parking experience, and make more effective use of the limited parking space, thereby improving the utilization rate of the parking lot area and creating greater utilization benefits.

[0067] See also Figure 3 , Figure 3 The flowchart of the vehicle search method provided by the embodiment of the present application is shown. The method is applied to a computer device. The embodiment of the present application is applied to the method as follows: Figure 1 Taking the computer device 100 in FIG. 1 as an example, the method includes the following steps.

[0068] S21: upon receiving a vehicle search instruction from the driver for a target vehicle, obtaining a real-time area map of the parking lot area and area object data and corresponding object status data dynamically stored in the real-time area map.

[0069] In some embodiments, the real-time area map of the parking area can be generated based on steps S11 to S12 and the corresponding embodiment content. The real-time area map dynamically stores area object data and corresponding object status data.

[0070] In some embodiments, the terminal device or target vehicle is installed with an application for controlling and managing the target vehicle. This application is integrated with the parking lot management system and can provide users with parking services, vehicle search services, reservation services, queuing services, and other services. Users can use this application on the terminal device or target vehicle to trigger a vehicle search command for the target vehicle, requesting the vehicle search service. In response to the user's operation, the terminal device or target vehicle can send the vehicle search command to a computer device corresponding to the parking lot management system. In response to the vehicle search command, the computer device obtains a real-time area map of the parking lot area, as well as the area object data and corresponding object status data dynamically stored in the real-time area map.

[0071] S22: Based on the vehicle search instruction, the area object data and the corresponding object status data, determine the parking space position of the target vehicle corresponding to the target vehicle parking space and the preset pick-up position.

[0072] In some embodiments, the vehicle search instruction may include vehicle information of the target vehicle, such as the license plate number and vehicle identification, as well as information such as a preset vehicle pickup location. The area object data may include object identifications of objects such as vehicles, parking spaces, and drivers, and the object status data may include the locations of objects such as vehicles, parking spaces, and drivers, as well as the corresponding relationships between the objects. Thus, based on the vehicle search instruction, the area object data, and the corresponding object status data, the computer device determines the parking space location of the target vehicle corresponding to the target vehicle parking space and the preset vehicle pickup location.

[0073] In some embodiments of the present application, based on the vehicle search instruction and the regional object data and the corresponding object status data, the parking space position of the target vehicle corresponding to the target vehicle parking space and the preset pick-up location are determined, including: parsing the vehicle search instruction, obtaining the preset pick-up location, and the preset pick-up location is located in the parking lot area; according to the regional object data and the corresponding object status data, the preset pick-up location of the preset pick-up location in the real-time regional map is determined; according to the regional object data and the corresponding object status data, the target vehicle and the corresponding target vehicle status are determined; according to the target vehicle and the corresponding target vehicle status, the target parking space corresponding to the target vehicle and the parking space position of the target parking space in the real-time regional map are determined.

[0074] In some embodiments, a user can use an application corresponding to a target vehicle to set a location in the parking area as a preset pickup location. Based on the user's operation, the terminal device hosting the application or the target vehicle can generate a vehicle search instruction based on the preset pickup location and send the vehicle search instruction to a computer device. The computer device parses the vehicle search instruction, obtains the preset pickup location, and determines the preset pickup location on a real-time regional map based on the regional object data and corresponding object status data.

[0075] In some embodiments, the computer device parses the vehicle search command to obtain vehicle information such as the target vehicle's vehicle identification, and can identify the target vehicle based on the vehicle identification. Furthermore, based on regional object data and corresponding object status data in the real-time regional map, the target vehicle and its corresponding target vehicle status can be identified. Based on the target vehicle and its corresponding target vehicle status, the target parking space corresponding to the target vehicle and the parking space location of the target parking space in the real-time regional map can be determined.

[0076] In some embodiments, the computer device can pre-set the pick-up location, and the driver can go to the pick-up location and wait to pick up the car.

[0077] S23: Generate a vehicle search route for the target vehicle based on the parking space location, the preset vehicle pickup location, and the real-time area map.

[0078] In some embodiments, a computer device may utilize a neural network model to process and analyze the target vehicle's parking space location, pre-set pickup location, and real-time area map, and output a route for the target vehicle. The route may comprise a list of waypoints. The neural network model may be, for example, a convolutional neural network model, a recurrent neural network model, or a generative adversarial network model.

[0079] In other embodiments, the computer device may also employ some path planning algorithms, such as genetic algorithms, to plan the target vehicle's route based on the parking space location, the preset pickup location, and a real-time regional map, or may call a public map application interface and utilize the path planning function of the map application to plan the target vehicle's route. This application does not limit the method for generating the target vehicle's route.

[0080] In some embodiments of the present application, a vehicle-searching route for a target vehicle is generated based on a parking space location, a preset vehicle pick-up location, and a real-time area map, including: outputting a vehicle-searching route for the target vehicle using a preset route planning model based on the parking space location, the preset vehicle pick-up location, and the real-time area map.

[0081] In some embodiments, the preset route planning model may be a neural network model, such as a convolutional neural network model, a recurrent neural network model, and the like.

[0082] In the process of outputting a target vehicle's route using a preset route planning model based on the parking space location, the preset pick-up location, and the real-time area map, the computer device may pre-process the parking space location, the preset pick-up location, and the real-time area map, such as obtaining standardized coordinates of the preset pick-up location and the parking space location in the real-time area map and converting the real-time area map into a processable format. The computer device processes and analyzes the pre-processed parking space location, the preset pick-up location, and the real-time area map using the preset route planning model to output a predicted target vehicle's route.

[0083] In some embodiments, the specific implementation method of generating the target vehicle's vehicle-searching route based on the parking space location, the preset pick-up location and the real-time area map can refer to the implementation method of generating the target vehicle's parking route based on the vehicle location, the parking space location and the real-time area map in step S14.

[0084] S24: Generate a second control instruction based on the vehicle search route, and send the vehicle search route and the second control instruction to the target vehicle, controlling the target vehicle to drive to a preset vehicle pickup location according to the vehicle search route.

[0085] In some embodiments, the computer device may utilize a model predictive control method to convert the vehicle-finding route into a second control instruction, where the second control instruction may include control of acceleration, speed, steering wheel, vehicle orientation, and the like.

[0086] In some embodiments, the target vehicle is equipped with a vehicle control module, which is configured to receive the vehicle search route and the second control command sent by the computer device, read the vehicle status of the target vehicle, and return the target vehicle status to the computer device. In response to the second control command, the target vehicle can be controlled to drive to a preset vehicle pickup location according to the vehicle search route.

[0087] In some embodiments of the present application, if the preset pick-up location is determined to have changed based on the regional object data and the corresponding object status data, the updated pick-up location and the current location of the target vehicle are obtained; based on the current location, the updated pick-up location and the real-time regional map, the vehicle search route of the target vehicle is regenerated.

[0088] In some embodiments, as the target vehicle travels along the vehicle search route, the preset vehicle pickup location may change. In this case, the computer device can reacquire a real-time regional map of the parking area and obtain real-time object data and corresponding object status data of the parking area based on the real-time regional map. Based on the regional object data and corresponding object status data, an updated vehicle pickup location can be determined and the current location of the target vehicle can be obtained. The computer device can regenerate the vehicle search route for the target vehicle based on the current location of the target vehicle, the updated vehicle pickup location, and the real-time regional map, generate an updated second control instruction based on the updated vehicle search route, send the updated vehicle search route and the second control instruction to the target vehicle, and control the target vehicle to travel to the updated vehicle pickup location according to the updated vehicle search route.

[0089] In some embodiments of the present application, after controlling the target vehicle to drive to a preset pick-up location according to the vehicle search route, the computer device can update the regional object data and corresponding object status data in the parking area, such as updating the usage status of the target parking space.

[0090] The vehicle search method provided in an embodiment of the present application, upon receiving a vehicle search instruction from a target vehicle, obtains a real-time regional map of the parking area and the regional object data and corresponding object status data dynamically stored in the real-time regional map. Based on the vehicle search instruction, regional object data, and corresponding object status data, the parking space position and preset pick-up location of the target vehicle corresponding to the target parking space can be determined. Based on the parking space position, the preset pick-up location, and the real-time regional map, a vehicle search route for the target vehicle is generated. A second control instruction is generated based on the vehicle search route, and the vehicle search route and the second control instruction can be sent to the target vehicle to control the target vehicle to travel to the preset pick-up location according to the vehicle search route. When a user or driver needs to pick up a vehicle from the parking area, they only need to trigger the vehicle search instruction. The parking lot management system responds to the vehicle search instruction, takes over the target vehicle, and controls the target vehicle to travel to the preset pick-up location. This can reduce the precious time and resources wasted by the user or driver in searching for the vehicle's parking space location, thereby improving the driver's vehicle search experience.

[0091] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0092] In one embodiment of the present application, a vehicle parking device 400 is provided, which is applied to a computer device. The functions that can be realized by the vehicle parking device 400 correspond to the vehicle parking method in the above embodiment. Figure 4As shown, the vehicle parking device 400 includes an acquisition module 401 , a map generation module 402 , a determination module 403 , a route generation module 404 and a control module 405 . Each functional module is described in detail as follows: an acquisition module 401 is used to acquire sensing data of the parking area through a sensing device; a map generation module 402 is used to generate a real-time regional map of the parking area based on the sensing data, and the real-time regional map dynamically stores regional object data and corresponding object status data in the parking area, wherein the regional object data at least includes data of the driver, vehicle and parking space, and the object status data at least includes object positions and correspondences between objects; a determination module 403 is used to determine the vehicle position of the target vehicle in the real-time regional map and the parking space position of the target parking space in the parking area in the real-time regional map based on the regional object data and the corresponding object status data when receiving a parking instruction of the target vehicle and detecting that the target vehicle enters the parking area; a route generation module 404 is used to generate a parking route for the target vehicle based on the vehicle position, the parking space position and the real-time regional map; a control module 405 is used to generate a first control instruction based on the parking route, and send the parking route and the first control instruction to the target vehicle to control the target vehicle to drive to the target parking space according to the parking route.

[0093] The specific definition of vehicle parking device 400 can be found in the definition of the vehicle parking method above and will not be repeated here. Each module in the aforementioned vehicle parking device 400 may be implemented in whole or in part via software, hardware, or a combination thereof. Each module may be embedded in or independent of a processor in a computer device in hardware form, or may be stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0094] In one embodiment of the present application, a vehicle search device 500 is provided, which is applied to a computer device. The functions that can be realized by the vehicle search device 500 correspond to the vehicle search method in the above embodiment. Figure 5As shown, the vehicle search device 500 includes an acquisition module 501, a determination module 502, a generation module 503, and a control module 504. The functional modules are described in detail as follows: the acquisition module 501 is configured to, upon receiving a vehicle search instruction from a driver for a target vehicle, acquire a real-time regional map of the parking area and the regional object data and corresponding object status data dynamically stored in the real-time regional map; the determination module 502 is configured to determine the parking space position and the preset pickup position of the target vehicle corresponding to the target vehicle parking space based on the vehicle search instruction, the regional object data, and the corresponding object status data; the generation module 503 is configured to generate a vehicle search route for the target vehicle based on the parking space position, the preset pickup position, and the real-time regional map; and the control module 504 is configured to generate a second control instruction based on the vehicle search route, and transmit the vehicle search route and the second control instruction to the target vehicle, thereby controlling the target vehicle to travel to the preset pickup position according to the vehicle search route.

[0095] The specific limitations of the vehicle finding device 500 can be found in the limitations of the vehicle finding method described above and will not be further elaborated here. Each module in the vehicle finding device 500 may be implemented in whole or in part via software, hardware, or a combination thereof. Each module may be embedded in or independent of a processor within a computer device in hardware form, or may be stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0096] See also Figure 6 FIG2 is a schematic diagram of the structure of a computer device provided in an embodiment of the present application. The network where the computer device 100 is located includes but is not limited to the Internet, a wide area network, a metropolitan area network, a local area network, a virtual private network (VPN), etc.

[0097] like Figure 6 As shown, the computer device 100 includes a communication module 101, a memory 102, a processor 103, an input / output (I / O) interface 104, and a bus 105. The processor 103 is coupled to the communication module 101, the memory 102, and the I / O interface 104 through the bus 105.

[0098] The communication module 101 can be a wireless communication module or a mobile communication module. The wireless communication module can provide wireless communication solutions including wireless local area networks (WLAN) (e.g., wireless fidelity (Wi-Fi) network), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared technology (IR), etc. applied to the computer device 100. The mobile communication module can provide wireless communication solutions including 2G / 3G / 4G / 5G, etc. applied to the computer device 100.

[0099] The memory 102 may include one or more random access memories (RAMs) and one or more non-volatile memories (NVMs). The RAM can be directly read and written by the processor 103 and can be used to store executable programs (e.g., machine instructions) of the operating system or other running programs, as well as user and application data. The RAM may include static random-access memory (SRAM), dynamic random-access memory (DRAM), synchronous dynamic random-access memory (SDRAM), double data rate synchronous dynamic random-access memory (DDR SDRAM, for example, the fifth generation of DDR SDRAM is generally referred to as DDR5 SDRAM), etc.

[0100] The non-volatile memory can also store executable programs and user and application data, etc., which can be pre-loaded into the random access memory for direct reading and writing by the processor 103. The non-volatile memory can include disk storage devices and flash memory.

[0101] The memory 102 is configured to store one or more computer programs. The one or more computer programs are configured to be executed by the processor 103. The one or more computer programs include a plurality of instructions. When executed by the processor 103, the plurality of instructions can implement a vehicle parking method or a vehicle finding method executed on the computer device 100.

[0102] In other embodiments, the computer device 100 further includes an external memory interface for connecting to an external memory to expand the storage capacity of the computer device 100 .

[0103] The processor 103 may include one or more processing units. For example, the processor 103 may include an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU). The different processing units may be independent devices or integrated into one or more processors.

[0104] The processor 103 provides computing and control capabilities. For example, the processor 103 is used to execute a computer program stored in the memory 102 to implement the above-mentioned vehicle parking method or vehicle finding method.

[0105] The I / O interface 104 is used to provide a channel for user input or output. For example, the I / O interface 104 can be used to connect various input and output devices, such as a mouse, keyboard, touch device, display screen, etc., so that the user can enter information or visualize information.

[0106] The bus 105 is at least used to provide a channel for mutual communication among the communication module 101 , the memory 102 , the processor 103 , and the I / O interface 104 in the computer device 100 .

[0107] It should be understood that the structures illustrated in the embodiments of the present application do not constitute a specific limitation on the computer device 100. In other embodiments of the present application, the computer device 100 may include more or fewer components than shown, or may combine or separate certain components, or arrange the components differently. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0108] An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. The computer program includes program instructions. The method implemented when the program instructions are executed can refer to the vehicle parking method or vehicle search method in the above-mentioned embodiments of the present application.

[0109] The computer-readable storage medium may be an internal memory of the computer device described in the above embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. equipped with the computer device.

[0110] Furthermore, the computer-readable storage medium may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, etc.; the data storage area may store data created according to the use of the computer device, etc.

[0111] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit the present application. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. A vehicle parking method, applied to a computer device, characterized in that: The vehicle parking method comprises: Acquire sensing data of the parking area through sensing devices; generating a real-time area map of the parking area based on the sensing data, the real-time area map dynamically storing area object data and corresponding object status data within the parking area, the area object data including at least data of a driver, a vehicle, and a parking space, and the object status data including at least object positions and corresponding relationships between objects; Upon receiving a parking instruction from a target vehicle and detecting that the target vehicle enters the parking area, determining a vehicle position of the target vehicle in the real-time area map and a parking space position of a target parking space in the parking area in the real-time area map based on the area object data and the corresponding object state data; generating a parking route for the target vehicle based on the vehicle position, the parking space position, and the real-time area map; A first control instruction is generated based on the parking route, and the parking route and the first control instruction are sent to the target vehicle to control the target vehicle to travel to the target parking space according to the parking route.

2. The vehicle parking method according to claim 1, wherein: Determining the parking space position of the target parking space in the parking lot area on the real-time area map includes: determining parking space status data corresponding to all parking spaces in the parking lot area based on the area object data and the corresponding object status data; determining a usage status of the parking space according to the parking space status data; Determining all idle parking spaces in the parking lot area according to the usage status of all parking spaces; Determining the target parking space from all the idle parking spaces according to a preset strategy; The parking space position of the target parking space in the real-time area map is determined according to the parking space status data.

3. The vehicle parking method according to claim 1, wherein: Generating a real-time area map of the parking area based on the sensing data includes: Preprocessing the sensing data to obtain preprocessed sensing data; The pre-processed sensing data is analyzed using a preset map construction model to generate the real-time area map.

4. The vehicle parking method according to claim 3, wherein: Before analyzing the pre-processed sensing data using a preset map construction model to generate the real-time area map, the vehicle parking method further includes: Acquire a training sample set, where the training sample set includes multiple groups of data samples collected by different sensing devices; The initial map construction model is trained using the training sample set to obtain the preset map construction model.

5. The vehicle parking method according to claim 1, wherein: The generating of the parking route of the target vehicle based on the vehicle position, the parking space position and the real-time area map includes: Based on the vehicle position, the parking space position and the real-time area map, a preset route planning model is used to output a parking route for the target vehicle.

6. The vehicle parking method according to claim 5, wherein: Before analyzing the vehicle position, the parking space position, and the real-time area map using a preset route planning model and outputting a parking route for the target vehicle, the vehicle parking method further includes: Obtaining model training samples, wherein the model training samples include multiple sets of different vehicle initial positions, vehicle destination positions, and real-time area maps; The model training samples are used to perform model training on the initial route planning model to obtain the preset route planning model.

7. The vehicle parking method according to claim 1, wherein: The vehicle parking method further includes: If it is determined according to the area object data and the corresponding object state data that the target parking space has changed, obtaining an updated parking space position corresponding to the updated target parking space and the current position of the target vehicle; A parking route for the target vehicle is regenerated based on the current position, the updated parking space position, and the real-time area map.

8. The vehicle parking method according to claim 1, wherein: After controlling the target vehicle to travel to the target parking space according to the parking route, the vehicle parking method further includes: Based on the correspondence between the target vehicle and the target parking space, the area object data and the corresponding object status data in the parking lot area are updated.

9. A vehicle search method, applied to a computer device, characterized in that: The vehicle search method comprises: Upon receiving a vehicle search instruction from a driver for a target vehicle, obtaining a real-time area map of the parking area and area object data and corresponding object status data dynamically stored in the real-time area map; Determining a parking space position of the target vehicle corresponding to the target vehicle parking space and a preset pick-up position based on the vehicle search instruction, the area object data, and the corresponding object status data; Generate a vehicle search route for the target vehicle based on the parking space location, the preset vehicle pickup location, and the real-time area map; A second control instruction is generated based on the vehicle search route, and the vehicle search route and the second control instruction are sent to the target vehicle to control the target vehicle to travel to the preset vehicle pickup location according to the vehicle search route.

10. The vehicle search method according to claim 9, wherein: The determining, based on the vehicle search instruction, the area object data, and the corresponding object status data, of a parking space position of the target vehicle corresponding to the target vehicle parking space and a preset pick-up position includes: Parsing the car search instruction to obtain a preset car pick-up location, where the preset car pick-up location is located in the parking lot area; determining the preset pick-up location of the preset pick-up location in the real-time regional map based on the regional object data and the corresponding object status data; determining the target vehicle and the corresponding target vehicle state based on the area object data and the corresponding object state data; According to the target vehicle and the corresponding target vehicle state, a target parking space corresponding to the target vehicle and the parking space position of the target parking space in the real-time area map are determined.

Images