Parking guidance method and device, equipment and storage medium

Abstract

The embodiment of the invention provides a parking guidance method and device, equipment and a storage medium. Vehicle information of a vehicle driving into a parking lot and driver information of a driver of the vehicle are identified through a camera; according to the vehicle information and the driver information, matching a historical information set corresponding to the vehicle and the driver; based on the vehicle information, the historical information set and the parking space information of the parking lot, using a parking guidance model to obtain a target parking space and a corresponding target parking route; the parking guidance model is obtained by training according to historical parking information corresponding to the driver, and the historical parking information comprises parking habit information and parking proficiency information of the driver; and according to the target parking route, guiding the driver to park the vehicle in the target parking space. According to the embodiment of the invention, the parking space most suitable for the driver can be recommended by automatically identifying the entering and exiting of the vehicle and the driver and utilizing the parking guidance model obtained by training the historical parking information corresponding to the driver.

Description

Technical Field

[0001] The present application relates to the field of intelligent transportation technology, and in particular to a parking guidance method and device, an electronic device and a storage medium. Background Art

[0002] In recent years, the rapid development of computer vision technology and artificial intelligence has brought new opportunities to the field of parking management. Based on intelligent monitoring and recognition technology, the accuracy and real-time performance of parking space detection have been significantly improved. At the same time, data analysis can also provide drivers with more intelligent parking guidance services.

[0003] However, the existing parking management system based on monitoring and recognition still has some shortcomings. For example, the current parking guidance mainly relies on automatically detecting the vacancy status and location information of parking spaces, and providing route guidance through the system. This model lacks the ability to comprehensively analyze the driver's parking destination, parking proficiency and parking habits, which greatly reduces the efficiency of parking guidance and user experience satisfaction. In addition, how to efficiently integrate monitoring data and apply it to big data technology and machine learning to achieve intelligent matching and recommendation of parking spaces is also a problem that needs to be solved urgently. Summary of the invention

[0004] The embodiments of the present application provide a parking guidance method to solve or at least partially solve the above technical problems.

[0005] Correspondingly, the embodiment of the present application also provides a parking guidance device, an electronic device and a storage medium to ensure the implementation and application of the above method.

[0006] In order to solve the above problems, the embodiment of the present application discloses a parking guidance method, which includes:

[0007] Identifying vehicle information of a vehicle entering the parking lot and driver information of a driver of the vehicle through a camera;

[0008] Matching a set of historical information corresponding to the vehicle and the driver according to the vehicle information and the driver information;

[0009] Based on the vehicle information, the historical information set and the parking space information of the parking lot, a parking guidance model is used to obtain a target parking space and a corresponding target parking route; the parking guidance model is trained according to the historical parking information corresponding to the driver, and the historical parking information includes the parking habit information and parking proficiency information of the driver;

[0010] According to the target parking route, the driver is guided to park the vehicle in the target parking space.

[0011] In an optional embodiment of the present application, the vehicle information includes at least vehicle size, and the method of obtaining a target parking space and a corresponding target parking route by using a parking guidance model based on the vehicle information, the historical information set, and the parking space information of the parking lot includes:

[0012] Obtain the currently available parking spaces in the parking lot;

[0013] Using the camera, identifying the actual parking space size of the vacant parking space;

[0014] According to the vehicle size, matching the actual parking space size with a target vacant parking space that meets parking conditions;

[0015] Based on the historical information set and the parking space information of the parking lot, the target vacant parking space is analyzed using the parking guidance model to obtain the target parking space and the corresponding target parking route.

[0016] In an optional embodiment of the present application, the historical information set includes at least historical parking information corresponding to the driver, and the target vacant parking space is analyzed using the parking guidance model based on the historical information set and the parking space information of the parking lot, including:

[0017] analyzing the parking proficiency of the driver according to the parking proficiency information in the historical parking information corresponding to the driver;

[0018] Based on the parking proficiency, the target vacant parking space is analyzed using the parking guidance model to obtain a first analysis result.

[0019] In an optional embodiment of the present application, after analyzing the target vacant parking space based on the parking proficiency using the parking guidance model, the method further includes:

[0020] analyzing the parking habits of the driver according to the parking habit information in the historical parking information corresponding to the driver;

[0021] Based on the parking habit, the target vacant parking space is analyzed using the parking guidance model to obtain a second analysis result.

[0022] In an optional embodiment of the present application, after analyzing the target vacant parking space based on the parking habit using the parking guidance model, the method further includes:

[0023] Based on the parking space information, using the parking guidance model, analyzing the target vacant parking space to obtain a third analysis result, wherein the third analysis result at least includes a parking route corresponding to the target vacant parking space;

[0024] The target parking space and the corresponding target parking route are determined from the target vacant parking space and the parking route corresponding to the target vacant parking space according to the first analysis result, the second analysis result and the third analysis result.

[0025] In an optional embodiment of the present application, the training method of the parking guidance model includes:

[0026] Acquire historical parking information corresponding to the driver, where the historical parking information corresponding to the driver is obtained by identifying the parking behavior of the driver each time entering the parking lot based on the camera;

[0027] The parking guidance model is trained using the historical parking information corresponding to the driver to obtain the parking guidance model suitable for the driver.

[0028] In an optional embodiment of the present application, after instructing the driver to park the vehicle in the target parking space, the method further includes:

[0029] Acquiring the parking behavior of the driver when entering the parking lot through the camera;

[0030] According to the parking behavior of the driver when entering the parking lot, identifying the parking information corresponding to the driver;

[0031] The parking guidance model suitable for the driver is trained using the current parking information.

[0032] In an optional embodiment of the present application, guiding the driver to park the vehicle in the target parking space according to the target parking route includes:

[0033] When the vehicle does not travel according to the target parking route, obtaining a current travel route of the vehicle;

[0034] The target parking space and the corresponding target parking route are updated using the parking guidance model according to the current driving route, the vehicle information, the historical information set, and the parking space information of the parking lot.

[0035] In an optional embodiment of the present application, the identifying, by means of a camera, vehicle information of a vehicle entering a parking lot and driver information of a driver of the vehicle includes:

[0036] When the driver drives the vehicle into the parking lot, the camera captures an image, wherein the image includes the vehicle and the driver;

[0037] The vehicle information of the vehicle in the recognition image and the identity information of the driver are identified, wherein the vehicle information includes at least: a license plate number, a vehicle model, and a vehicle size.

[0038] In an optional embodiment of the present application, the parking proficiency information includes at least the time taken to turn left, the time taken to turn right, and the reversing adjustment situation;

[0039] The parking habit information includes at least: the number of historical left-side parking times, the number of historical right-side parking times, the time taken to reverse into a garage, the number of turns required for parking, the number of reverses required for parking, and parking space preference information.

[0040] The present application also discloses a parking guidance device, which includes:

[0041] An information recognition module, used to recognize vehicle information of a vehicle entering the parking lot and driver information of a driver of the vehicle through a camera;

[0042] An information matching module, used for matching the historical information set corresponding to the vehicle and the driver according to the vehicle information and the driver information;

[0043] an information screening module, configured to obtain a target parking space and a corresponding target parking route using a parking guidance model based on the vehicle information, the historical information set and the parking space information of the parking lot; the parking guidance model is trained based on the historical parking information corresponding to the driver, and the historical parking information includes the parking habit information and parking proficiency information of the driver;

[0044] The parking guidance module is used to guide the driver to park the vehicle in the target parking space according to the target parking route.

[0045] An embodiment of the present application also discloses an electronic device, including: a processor; and a memory, on which executable code is stored. When the executable code is executed, the processor executes the parking guidance method as described in one or more of the embodiments of the present application.

[0046] The embodiments of the present application also disclose one or more machine-readable media on which executable codes are stored. When the executable codes are executed, the processor executes the parking guidance method as described in one or more of the embodiments of the present application.

[0047] Compared with the prior art, the embodiments of the present application have the following advantages:

[0048] In an embodiment of the present application, a camera is used to identify the vehicle information of a vehicle entering a parking lot and the driver information of the driver of the vehicle; based on the vehicle information and the driver information, a historical information set corresponding to the vehicle and the driver is matched; based on the vehicle information, the historical information set and the parking space information of the parking lot, a parking guidance model is used to obtain a target parking space and a corresponding target parking route; the parking guidance model is trained based on the historical parking information corresponding to the driver, and the historical parking information includes the driver's parking habit information and parking proficiency information; according to the target parking route, the driver is guided to park the vehicle in the target parking space. The embodiment of the present application can recommend the parking space that is most suitable for the driver by automatically identifying the entry and exit of the vehicle and the driver, combining the vehicle information, the historical information set and the parking space information of the parking lot, and using the parking guidance model trained based on the historical parking information corresponding to the driver.

[0049] In addition, the embodiment of the present application will also analyze the historical information set of vehicles and drivers collected by the camera, perform personalized parking route planning based on each driver's different parking habit information and parking proficiency information, and recommend target parking spaces, thereby reducing the driver's parking difficulty and making the parking process smoother and safer.

[0050] At the same time, the embodiments of the present application can effectively reduce the ineffective driving of drivers in the process of looking for parking spaces through precise parking guidance, intelligent allocation of reasonable parking spaces, and optimized parking management. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 is a flowchart of steps of an embodiment of a parking guidance method of the present application;

[0052] Figure 2 is a schematic diagram of the system structure of an embodiment of a parking guidance method of the present application;

[0053] Figure 3 It is a flowchart of an embodiment of a parking guidance method of the present application;

[0054] Figure 4 is a structural block diagram of an embodiment of a parking guidance device of the present application;

[0055] Figure 5 It is a schematic diagram of the structure of a device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0056] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0057] Reference Figure 1 , is a flowchart of a parking guidance method embodiment of the present application, comprising the following steps:

[0058] Step 101: Identify vehicle information of a vehicle entering a parking lot and driver information of the driver of the vehicle through a camera.

[0059] A parking guidance method in an embodiment of the present application can be applied to an intelligent monitoring parking guidance system. The intelligent monitoring parking guidance system stores parking space information of several parking lots, and the parking space information at least includes information such as the parking space location, lane location, and parking lot entrance and exit location. Cameras can be installed in several parking lots. The cameras can be installed at the parking lot entrance and exit, on both sides of the lane, near the parking space, etc., and the embodiment of the present application does not impose any restrictions on this. The intelligent monitoring parking guidance system obtains images through the camera, analyzes the images, and stores the data obtained from the analysis.

[0060] The intelligent monitoring parking guidance system may also store historical parking information corresponding to different drivers obtained by analyzing images taken by the camera, and the historical parking information reflects data about the driver's historical parking behavior.

[0061] The intelligent monitoring parking guidance system can also obtain information about different vehicles driven by the driver through a camera, and associate the information about different vehicles driven by the driver with the historical parking information corresponding to the driver as a historical information set, and store it in the intelligent monitoring parking guidance system in association with the driver information. The driver information is the identity information of the driver. When it is necessary to obtain a historical information set, the corresponding historical information set can be matched and obtained based on the driver information and the information about the vehicle driven by the driver.

[0062] A parking guidance model is deployed on the intelligent monitoring parking guidance system to recommend the most suitable target parking spaces and corresponding target parking routes for different drivers and different vehicles, so that the intelligent monitoring parking guidance system can provide parking guidance for the drivers.

[0063] In step 101, when the driver drives the vehicle into the parking lot, the camera automatically acquires an image, and recognizes the vehicle information and the driver information of the driver of the vehicle through the image. In an optional embodiment, the driver information is the identity information of the driver, and the vehicle information includes at least: license plate number, vehicle model and vehicle size.

[0064] Step 102: Match the historical information set corresponding to the vehicle and the driver according to the vehicle information and the driver information.

[0065] In step 102, the historical information set corresponding to the vehicle and the driver is matched according to the vehicle information and the driver information.

[0066] Since in this embodiment, the intelligent monitoring parking guidance system stores a historical information set of different vehicle information driven by the driver and the historical parking information corresponding to the driver, and the historical information set is stored in association with the driver information, the vehicle information and driver information obtained through step 101 can be matched to the historical information set corresponding to the driver and the vehicle driven by the driver at that time.

[0067] Step 103: Based on the vehicle information, the historical information set and the parking space information of the parking lot, a parking guidance model is used to obtain a target parking space and a corresponding target parking route; the parking guidance model is trained according to the historical parking information corresponding to the driver, and the historical parking information includes the parking habit information and parking proficiency information of the driver.

[0068] In this embodiment, the parking guidance model is a parking guidance prediction model that is pre-trained based on the historical parking information corresponding to different drivers stored in the intelligent monitoring parking guidance system and is applicable to different drivers. Based on the vehicle information, the historical information set corresponding to the driver and the vehicle driven by the driver at that time, and the parking space information of the current parking lot, the parking guidance model can be used to obtain the target parking space and the corresponding target parking route that are most suitable for the driver and the vehicle.

[0069] In step 103, based on the vehicle information, historical information set and parking space information of the current parking lot obtained in the above steps, a parking guidance model is used to obtain a target parking space and a corresponding target parking route; the parking guidance model is trained according to the driver's corresponding historical parking information, and the historical parking information includes the driver's parking habit information and parking proficiency information.

[0070] Since the parking guidance model is trained based on historical parking information corresponding to different drivers, and these historical parking information include each driver's parking habit information and parking proficiency information, the parking guidance model can recommend the most suitable target parking space and corresponding target parking route for each driver based on each driver's personal parking habits and parking proficiency.

[0071] Step 104: Instruct the driver to park the vehicle in the target parking space according to the target parking route.

[0072] In step 104, after obtaining the target parking space and the corresponding target parking route, the intelligent monitoring parking guidance system will guide the driver to park the vehicle in the target parking space according to the target parking route.

[0073] In one embodiment, the intelligent monitoring parking guidance system can use voice broadcast or screen visualization to provide parking guidance. The embodiment of the present application does not impose any limitation on the specific method of providing parking guidance.

[0074] In the embodiment of the present application, the vehicle information of the vehicle entering the parking lot and the driver information of the driver of the vehicle are identified through a camera; the historical information set corresponding to the vehicle and the driver is matched according to the vehicle information and the driver information; based on the vehicle information, the historical information set and the parking space information of the parking lot, a parking guidance model is used to obtain the target parking space and the corresponding target parking route; the parking guidance model is trained according to the historical parking information corresponding to the driver, and the historical parking information includes the driver's parking habit information and parking proficiency information; according to the target parking route, the driver is guided to park the vehicle in the target parking space. The embodiment of the present application can recommend the parking space that is most suitable for the driver by automatically identifying the entry and exit of the vehicle and the driver, combining the vehicle information, the historical information set and the parking space information of the parking lot, and using the parking guidance model trained according to the historical parking information corresponding to the driver.

[0075] In addition, the embodiment of the present application will also analyze the historical information set of vehicles and drivers collected by the camera, perform personalized parking route planning based on each driver's different parking habit information and parking proficiency information, and recommend target parking spaces, thereby reducing the driver's parking difficulty and making the parking process smoother and safer.

[0076] At the same time, the embodiments of the present application can effectively reduce the ineffective driving of drivers in the process of looking for parking spaces through precise parking guidance, intelligent allocation of reasonable parking spaces, and optimized parking management.

[0077] In an optional embodiment of the present application, the vehicle information includes at least vehicle size, and the method of obtaining a target parking space and a corresponding target parking route by using a parking guidance model based on the vehicle information, the historical information set, and the parking space information of the parking lot includes:

[0078] Obtain the currently available parking spaces in the parking lot;

[0079] Using the camera, identifying the actual parking space size of the vacant parking space;

[0080] According to the vehicle size, matching the actual parking space size with a target vacant parking space that meets parking conditions;

[0081] Based on the historical information set and the parking space information of the parking lot, the target vacant parking space is analyzed using the parking guidance model to obtain the target parking space and the corresponding target parking route.

[0082] In this embodiment, before using the parking guidance model to obtain the target parking space and the corresponding target parking route, the target vacant parking space in the parking lot that matches the size of the current vehicle can be screened out according to the vehicle size, and then the parking guidance model is used to obtain the target parking space and the corresponding target parking route for the target vacant parking space.

[0083] In this embodiment, a camera may be used to identify and obtain the vacant parking spaces in the current parking lot, and the camera may be used to further identify the actual parking space size of the vacant parking spaces, such as identifying the length and width of the actual parking spaces. In one example, in some parking lots, some vacant parking spaces require side parking to complete the parking of the vehicle. However, since the front and rear parking spaces may be parked with longer vehicles or have obstacles, the actual available parking space length is relatively small. Therefore, it is necessary to obtain the actual parking space size of the vacant parking spaces.

[0084] Afterwards, the target vacant parking spaces whose actual parking space sizes meet the parking conditions can be matched according to the vehicle size. Some vacant parking spaces whose actual parking space sizes do not meet the parking conditions will be excluded. In one example, the target vacant parking spaces can be matched and screened according to whether the length and width of the actual parking space meet the parking conditions of the current vehicle.

[0085] After all target vacant parking spaces are obtained, the target vacant parking spaces are analyzed based on the historical information set and the parking space information of the parking lot using the parking guidance model to obtain the target parking spaces and the corresponding target parking routes. That is, from the target vacant parking spaces, the target parking spaces and the corresponding target parking routes are selected using the parking guidance model based on the historical information set and the parking space information of the parking lot.

[0086] The embodiment of the present application matches the target vacant parking space with the actual parking space size that meets the parking conditions according to the vehicle size, then selects the target parking space from the target vacant parking spaces, and obtains the corresponding target parking route, which can avoid the situation where the target vacant parking space recommended to the driver is vacant but actually cannot park the vehicle.

[0087] In an optional embodiment of the present application, the historical information set includes at least historical parking information corresponding to the driver, and the target vacant parking space is analyzed using the parking guidance model based on the historical information set and the parking space information of the parking lot, including:

[0088] analyzing the parking proficiency of the driver according to the parking proficiency information in the historical parking information corresponding to the driver;

[0089] Based on the parking proficiency, the target vacant parking space is analyzed using the parking guidance model to obtain a first analysis result.

[0090] In the embodiment of the present application, the parking guidance model needs to be analyzed and iterated according to the parking proficiency information.

[0091] Since the historical information set includes at least the historical parking information corresponding to the driver, and the historical parking information corresponding to the driver includes the parking habit information and parking proficiency information of the driver, the parking proficiency information in the historical parking information corresponding to the driver can be filtered out from the historical information set, and the parking proficiency of the driver can be analyzed based on the parking proficiency information in the historical parking information corresponding to the driver.

[0092] In one example, the parking proficiency information includes at least the time taken to turn left, the time taken to turn right, and the backing adjustment. By analyzing the time taken to turn left and right in the driver's historical parking behavior, the driving speed during parking, and the backing adjustment of whether backing adjustment is required after entering the parking space, the driver's technical proficiency in turning left and right can be analyzed to obtain the driver's parking proficiency.

[0093] The driver's parking proficiency can be presented in the form of a proficiency score, a proficiency level, etc. The embodiment of the present application does not impose any restrictions on the form of presentation of the driver's parking proficiency.

[0094] Based on the parking proficiency, the parking guidance model is used to analyze the target free parking spaces to obtain the first analysis result. The first analysis result indicates the parking difficulty corresponding to the current target free parking spaces respectively obtained according to the parking proficiency evaluation of the driver. Since the parking proficiency of different drivers is different, some parking spaces require lower parking proficiency, and the parking difficulty is higher; while some parking spaces require higher parking proficiency, and the parking difficulty is lower. Therefore, it is necessary to use the parking guidance model to obtain the parking difficulty corresponding to the current target free parking spaces respectively according to the parking proficiency evaluation of the driver as the first analysis result.

[0095] The embodiment of the present application uses a parking guidance model to analyze the target vacant parking space based on parking proficiency to obtain a first analysis result, which can avoid making parking space recommendations based solely on the current vacant parking space type, reduce the different parking difficulties caused by differences in parking proficiency among different drivers, and avoid the risk of scratches caused by insufficient parking proficiency of the driver.

[0096] In an optional embodiment of the present application, after analyzing the target vacant parking space based on the parking proficiency using the parking guidance model, the method further includes:

[0097] analyzing the parking habits of the driver according to the parking habit information in the historical parking information corresponding to the driver;

[0098] Based on the parking habit, the target vacant parking space is analyzed using the parking guidance model to obtain a second analysis result.

[0099] In this embodiment, after using the parking guidance model to perform analysis and iteration according to the parking proficiency information, it is also necessary to use the parking guidance model to perform analysis and iteration according to the parking habit information.

[0100] Since the historical information set includes at least the historical parking information corresponding to the driver, and the historical parking information corresponding to the driver includes the driver's parking habit information and parking proficiency information, the parking habit information in the historical parking information corresponding to the driver can be filtered out from the historical information set, and the driver's parking habits can be analyzed based on the parking habit information in the historical parking information corresponding to the driver.

[0101] In one example, the parking habit information includes at least: the number of historical left-side parking times, the number of historical right-side parking times, the time taken to reverse into a garage, the number of turns required for parking, the number of reverses required for parking, and parking space preference information.

[0102] In this example, the driver's steering preference can be analyzed based on the historical number of left-side parking and the historical number of right-side parking, so as to match the turning and angle data required for parking in the target vacant parking space in the parking lot. For example, if the driver's habitual preference is more inclined to park in a narrow parking lot, then the inclined parking space is more suitable for the driver to park the vehicle, and the parking space that requires a right-angle turn to enter or leave is not suitable for the driver to park the vehicle.

[0103] Furthermore, based on the historical number of left parking, the historical number of right parking, the time taken to reverse into the garage, the number of turns required for parking, and the number of reverses required for parking, the driver's position perception ability of the left, right, front, and back of the vehicle when parking can be analyzed; based on the parking space preference information, it can be analyzed which type of parking space the driver prefers to park in when driving the current vehicle. The above parking habit information and related parking habit analysis are only for example, and those skilled in the art can set more parking habit information and related parking habit analysis according to actual needs.

[0104] Based on the parking habits, the parking guidance model is used to analyze the target vacant parking spaces to obtain the second analysis result. The first analysis result represents the driver's habits and preference levels corresponding to the current target vacant parking spaces respectively obtained according to the parking habits of the driver. Since different drivers have different parking habits and selection preferences for various parking spaces, it is necessary to use the parking guidance model to obtain the driver's habits and preference levels corresponding to the current target vacant parking spaces respectively according to the parking habits of the driver as the second analysis result.

[0105] The embodiment of the present application uses a parking guidance model to analyze the target vacant parking space based on parking habits to obtain a second analysis result, which can make the recommended target parking space and the corresponding target parking route more in line with the driver's personal parking habits and preferences for parking space selection.

[0106] In an optional embodiment of the present application, after analyzing the target vacant parking space based on the parking habit using the parking guidance model, the method further includes:

[0107] Based on the parking space information, using the parking guidance model, analyzing the target vacant parking space to obtain a third analysis result, wherein the third analysis result at least includes a parking route corresponding to the target vacant parking space;

[0108] The target parking space and the corresponding target parking route are determined from the target vacant parking space and the parking route corresponding to the target vacant parking space according to the first analysis result, the second analysis result and the third analysis result.

[0109] In this embodiment, after using the parking guidance model to perform analysis and iteration according to the parking habit information, it is also necessary to use the parking guidance model to perform analysis and iteration according to the parking space information of the parking lot.

[0110] The parking space information of the parking lot may at least include information such as the parking space location, lane location, and parking lot entrance and exit location. Based on the parking space information, the target vacant parking space is analyzed using the parking guidance model to obtain a third analysis result, which at least includes a parking route corresponding to the target vacant parking space, wherein each target vacant parking space may correspond to one or more parking routes.

[0111] In one example, the third analysis result may also include the distance and time it takes the driver to walk to each target vacant parking space in the parking lot, the overall predicted parking time, etc.

[0112] According to the first analysis result, the second analysis result and the third analysis result, the target parking space and the corresponding target parking route are determined from the target vacant parking space and the parking routes corresponding to the target vacant parking space. The parking guidance model integrates the first analysis result, the second analysis result and the third analysis result obtained through the above analysis iteration steps, and can select the best target parking space and the corresponding target parking route from the target vacant parking space and the parking routes corresponding to the target vacant parking space. The best target parking space and the corresponding target parking route meet the different parking habit information and parking proficiency information of each driver, and can reasonably allocate vacant parking spaces for the parking lot.

[0113] The embodiment of the present application performs personalized parking route planning based on each driver's different parking habit information and parking proficiency information, combined with the parking space information of the parking lot, and recommends target parking spaces, thereby reducing the driver's parking difficulty and making the parking process smoother and safer.

[0114] In an optional embodiment of the present application, the training method of the parking guidance model includes:

[0115] Acquire historical parking information corresponding to the driver, where the historical parking information corresponding to the driver is obtained by identifying the parking behavior of the driver each time entering the parking lot based on the camera;

[0116] The parking guidance model is trained using the historical parking information corresponding to the driver to obtain the parking guidance model suitable for the driver.

[0117] In the embodiment of the present application, the parking guidance model needs to be trained in advance. In this embodiment, the historical parking information corresponding to the driver is obtained from the intelligent monitoring parking guidance system. The historical parking information corresponding to the driver is obtained by identifying the parking behavior of the driver each time he enters the parking lot based on the camera. That is, every time the driver drives the vehicle into the parking lot, the camera will capture and identify the vehicle, driver and other information, and record the driver's parking behavior at that time, upload the data to the system, and the system will analyze the driver's parking behavior at that time to obtain the parking information at that time, and then store it in association with the driver's information.

[0118] The parking guidance model is trained using the historical parking information corresponding to the driver to obtain a parking guidance model suitable for the driver. The historical parking information corresponding to different drivers collected is used as a feature to establish a parking guidance model, which can recommend the best target parking space and corresponding target parking route suitable for different drivers, and is therefore suitable for different drivers.

[0119] The embodiment of the present application trains the parking guidance model by using historical parking information corresponding to different drivers, so as to obtain the parking guidance model suitable for different drivers, so that the recommended target parking space and the corresponding target parking route are more in line with the different parking habit information and parking proficiency information of different drivers.

[0120] In an optional embodiment of the present application, after instructing the driver to park the vehicle in the target parking space, the method further includes:

[0121] Acquiring the parking behavior of the driver when entering the parking lot through the camera;

[0122] According to the parking behavior of the driver when entering the parking lot, identifying the parking information corresponding to the driver;

[0123] The parking guidance model suitable for the driver is trained using the current parking information.

[0124] In the embodiment of the present application, the intelligent monitoring parking guidance system needs to obtain the parking behavior of the driver entering the parking lot through a camera, and identify the driver's corresponding parking information according to the parking behavior of the driver entering the parking lot. In one example, the parking information at least includes parking habit information and parking proficiency information corresponding to the historical parking information.

[0125] After completing the parking guidance for the current time, this embodiment can use the parking information for the current time to train a parking guidance model suitable for the driver, adjust, continuously optimize and iterate the parking guidance model, so that it can more and more accurately calculate the best parking plan for different drivers in the parking lot.

[0126] When providing parking guidance, the embodiment of the present application also collects the current parking information and uses the current parking information to train a parking guidance model suitable for the driver, so that the parking guidance model can more and more accurately calculate the optimal parking plan for different drivers in the parking lot.

[0127] In an optional embodiment of the present application, guiding the driver to park the vehicle in the target parking space according to the target parking route includes:

[0128] When the vehicle does not travel according to the target parking route, obtaining a current travel route of the vehicle;

[0129] The target parking space and the corresponding target parking route are updated using the parking guidance model according to the current driving route, the vehicle information, the historical information set, and the parking space information of the parking lot.

[0130] In this embodiment, if during the process of providing parking guidance according to the target parking route, the parking guidance does not match the actual situation on site or the driver finds a more suitable parking space, the current driving route of the vehicle is obtained if the vehicle does not follow the target parking route.

[0131] According to the current driving route, combined with vehicle information, historical information collection and parking space information of the parking lot, the parking guidance model is used to update the target parking space and the corresponding target parking route, and recommend the best target parking space and the corresponding target parking route that match the current driving route to the driver.

[0132] In the case where the vehicle does not travel according to the target parking route, the embodiment of the present application can re-recommend a matching target parking space and a corresponding target parking route based on the current driving route, and can quickly locate and recommend a more suitable parking space based on the driver's parking destination area, thereby improving parking efficiency.

[0133] In an optional embodiment of the present application, the identifying, by means of a camera, vehicle information of a vehicle entering a parking lot and driver information of a driver of the vehicle includes:

[0134] When the driver drives the vehicle into the parking lot, the camera captures an image, wherein the image includes the vehicle and the driver;

[0135] The vehicle information of the vehicle in the recognition image and the identity information of the driver are identified, wherein the vehicle information includes at least: a license plate number, a vehicle model, and a vehicle size.

[0136] In this embodiment, when the driver drives the vehicle into the parking lot, the camera captures an image including the vehicle and the driver. The vehicle information and the driver's identity information in the image are identified, and the vehicle information at least includes: license plate number, vehicle model and vehicle size.

[0137] Furthermore, since the intelligent monitoring parking guidance system stores a historical information set of different vehicle information driven by the driver in the past and the historical parking information corresponding to the driver, and the historical information set is stored in association with the driver information, the historical information set corresponding to the driver and the vehicle driven by the driver at that time can be matched through the vehicle information and the driver information.

[0138] The embodiment of the present application utilizes monitoring recognition technology to automatically identify the entry and exit of vehicles and drivers, thereby matching the driver and the historical information set corresponding to the vehicle driven by the driver at that time based on the recognized information for use in subsequent parking plan recommendations.

[0139] In an optional embodiment of the present application, the parking proficiency information includes at least the time taken to turn left, the time taken to turn right, and the reversing adjustment situation;

[0140] The parking habit information includes at least: the number of historical left-side parking times, the number of historical right-side parking times, the time taken to reverse into a garage, the number of turns required for parking, the number of reverses required for parking, and parking space preference information.

[0141] In this embodiment, the parking proficiency information includes at least the time taken to turn left, the time taken to turn right, and the backing adjustment. The driver's technical proficiency in turning left and right can be analyzed by analyzing the time taken to turn left and right in the driver's historical parking behavior, the driving speed during the parking process, and the backing adjustment of whether backing adjustment is required after entering the parking space, thereby obtaining the driver's parking proficiency.

[0142] The parking habit information includes at least: the number of historical left-side parking times, the number of historical right-side parking times, the time taken to reverse into a garage, the number of turns required for parking, the number of reverse turns required for parking, and parking space preference information.

[0143] In one example, the driver's steering preference can be analyzed based on the historical number of left-side parking and the historical number of right-side parking, so as to match the turning and angle data required for parking in the target vacant parking space in the parking lot. For example, if the driver's habitual preference is more inclined to park in a narrow parking lot, then an inclined parking space is more suitable for the driver to park the vehicle, and a parking space that requires a right-angle turn to enter or leave is not suitable for the driver to park the vehicle.

[0144] Furthermore, based on the historical number of left-side parking attempts, the historical number of right-side parking attempts, the time taken to reverse into a garage, the number of turns required for parking, and the number of reverse attempts required for parking, the driver's position perception ability of the vehicle in the four directions of left, right, front and back when parking can be analyzed; based on the parking space preference information, it can be analyzed which type of parking space the driver prefers to park in when driving the current vehicle.

[0145] The embodiment of the present application can use a parking guidance model to analyze and iterate the parking proficiency and parking habits of the driver according to the parking proficiency information and parking habit information, so that the recommended target parking space and the corresponding target parking route are more in line with the different parking habit information and parking proficiency information of different drivers.

[0146] In an embodiment of the present application, a camera is used to identify the vehicle information of a vehicle entering a parking lot and the driver information of the driver of the vehicle; based on the vehicle information and the driver information, a historical information set corresponding to the vehicle and the driver is matched; based on the vehicle information, the historical information set and the parking space information of the parking lot, a parking guidance model is used to obtain a target parking space and a corresponding target parking route; the parking guidance model is trained based on the historical parking information corresponding to the driver, and the historical parking information includes the driver's parking habit information and parking proficiency information; according to the target parking route, the driver is guided to park the vehicle in the target parking space. The embodiment of the present application can recommend the parking space that is most suitable for the driver by automatically identifying the entry and exit of the vehicle and the driver, combining the vehicle information, the historical information set and the parking space information of the parking lot, and using the parking guidance model trained based on the historical parking information corresponding to the driver.

[0147] In addition, the embodiment of the present application will also analyze the historical information set of vehicles and drivers collected by the camera, perform personalized parking route planning based on each driver's different parking habit information and parking proficiency information, and recommend target parking spaces, thereby reducing the driver's parking difficulty and making the parking process smoother and safer.

[0148] At the same time, the embodiments of the present application can effectively reduce the ineffective driving of drivers in the process of looking for parking spaces through precise parking guidance, intelligent allocation of reasonable parking spaces, and optimized parking management.

[0149] Reference Figure 2 , is a system structure diagram of an embodiment of a parking guidance method of the present application.

[0150] like Figure 2 As shown, when the driver drives the vehicle into the parking lot, the monitoring camera can intelligently identify the driver information and vehicle information, and use the parking guidance model based on the vehicle information, the driver's corresponding historical parking information, the parking lot information and the vehicle's current driving information to obtain the best target parking space and the corresponding target parking route and push them to the driver, thereby guiding the driver to park the vehicle in the target parking space according to the target parking route.

[0151] In one embodiment, the current driving information of the vehicle may include the current driving speed of the vehicle.

[0152] Reference Figure 3 , is a flow chart of an embodiment of a parking guidance method of the present application.

[0153] Figure 3 A complete flow chart of a parking guidance method according to an embodiment of the present application is shown below. Figure 3, as an example, a parking guidance method of an embodiment of the present application is explained in detail.

[0154] Step 1: The driver drives into the parking lot, and the camera of the intelligent monitoring system captures and identifies the vehicle information and driver information, and uploads the data to the system.

[0155] Step 2: After the system collects the driver information and vehicle information, it analyzes the vehicle's driving data and the driver's parking information, such as the size of the driving vehicle, historical parking spaces, parking space type, steering preference, driving speed, parking time, the distance and time the driver walks to the parking space in the parking lot, and the availability of parking spaces in each area.

[0156] Step 3: Establish a parking guidance model. The collected data information is clustered and merged as features to establish a parking guidance prediction model suitable for different drivers. The model is trained using a machine learning algorithm so that it can more and more accurately predict the best parking plan for different drivers in the parking lot.

[0157] Step 4: The intelligent monitoring parking guidance system is implemented in the parking lot. According to the vehicles driven by different drivers, the best parking routes and parking spaces are pushed, and the drivers can park according to the parking guidance or the actual situation on site. The specific process is described as follows:

[0158] S1. The driver drives into the parking lot, and the intelligent monitoring camera captures and identifies the vehicle information and driver information.

[0159] S2. Upload the identified data to the intelligent monitoring parking guidance system. The intelligent monitoring parking guidance system matches the vehicle information and driver information with the historical information set corresponding to the vehicle and the driver. Based on the vehicle information, historical information set and parking space information of the parking lot, the parking guidance model is combined to analyze the best parking space and route, and push it to the driver. The specific implementation is as follows:

[0160] S201, the intelligent monitoring camera captures and identifies the body size of the driving vehicle, identifies the actual length and width of the vacant parking space in the parking lot, and performs matching association. If the actual length and width of the parking space do not meet the parking conditions, the parking space is excluded first.

[0161] S202, performing analysis iterations through the parking guidance prediction model:

[0162] S2021. The driver's proficiency in left and right turn techniques can be analyzed and iterated based on the turning time, driving speed, and whether reverse adjustment is required for left and right turns.

[0163] S2022. The driver's steering preference can be analyzed and iterated based on the number of left turns and right turns in historical parking.

[0164] S2023. The driver's ability to perceive the position of the vehicle in the four directions of left, right, front and back when parking can be analyzed and iterated through the historical parking time, number of turns, and number of reversing times for left-side parking, right-side parking, and reversing into a garage.

[0165] S2024. Analyze parking habits and parking space preferences, such as being accustomed to backing into a parking space on the left side or parking sideways on the right side.

[0166] S2025. The parking efficiency of each type of parking space can be analyzed and iterated through the driving speed during the parking process and the parking time data.

[0167] S203, finally, the driving speed during the parking process, the parking time, and the distance and time the driver walks to the parking space in the parking lot are comprehensively analyzed to recommend the best parking space and route.

[0168] S3. The driver parks according to the route and parking space indicated by the parking instructions. If the parking instructions do not match the actual situation on site, or the driver sees a more suitable parking space, he or she may adjust and change to select the most suitable parking plan for himself or herself.

[0169] Step 5: Every time a vehicle enters or exits the parking lot, the smart surveillance camera will capture and identify data related to vehicle driving and parking. The smart monitoring parking guidance system associated with the surveillance camera will collect the data and adjust, continuously optimize and iterate the parking guidance model and machine learning algorithm.

[0170] Based on the above examples, the parking guidance model can mainly analyze the driver's parking skills and familiarity, match the specific conditions of the parking spaces in the parking lot (turns, paths, left parking, right parking, etc.), avoid relying solely on historical parking analysis, and fail to recommend more suitable parking spaces after new renovations, thereby improving the driver's parking guidance experience.

[0171] In the embodiment of the present application, the vehicle information of the vehicle entering the parking lot and the driver information of the driver of the vehicle are identified through a camera; the historical information set corresponding to the vehicle and the driver is matched according to the vehicle information and the driver information; based on the vehicle information, the historical information set and the parking space information of the parking lot, a parking guidance model is used to obtain the target parking space and the corresponding target parking route; the parking guidance model is trained according to the historical parking information corresponding to the driver, and the historical parking information includes the driver's parking habit information and parking proficiency information; according to the target parking route, the driver is guided to park the vehicle in the target parking space. The embodiment of the present application can recommend the parking space that is most suitable for the driver by automatically identifying the entry and exit of the vehicle and the driver, combining the vehicle information, the historical information set and the parking space information of the parking lot, and using the parking guidance model trained according to the historical parking information corresponding to the driver.

[0172] In addition, the embodiment of the present application will also analyze the historical information set of vehicles and drivers collected by the camera, perform personalized parking route planning based on each driver's different parking habit information and parking proficiency information, and recommend target parking spaces, thereby reducing the driver's parking difficulty and making the parking process smoother and safer.

[0173] At the same time, the embodiments of the present application can effectively reduce the ineffective driving of drivers in the process of looking for parking spaces through precise parking guidance, intelligent allocation of reasonable parking spaces, and optimized parking management.

[0174] It should be noted that, for the method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present application are not limited by the described order of actions, because according to the embodiments of the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present application.

[0175] On the basis of the above-mentioned embodiment, this embodiment further provides a parking guidance device, which is applied to electronic devices such as terminal devices and servers.

[0176] Reference Figure 4 , shows a structural block diagram of an embodiment of a parking guidance device of the present application, which may specifically include the following modules:

[0177] The information recognition module 401 is used to recognize the vehicle information of the vehicle entering the parking lot and the driver information of the driver of the vehicle through a camera;

[0178] An information matching module 402, configured to match a historical information set corresponding to the vehicle and the driver according to the vehicle information and the driver information;

[0179] The information screening module 403 is used to obtain a target parking space and a corresponding target parking route using a parking guidance model based on the vehicle information, the historical information set and the parking space information of the parking lot; the parking guidance model is trained according to the historical parking information corresponding to the driver, and the historical parking information includes the parking habit information and parking proficiency information of the driver;

[0180] The parking guidance module 404 is used to guide the driver to park the vehicle in the target parking space according to the target parking route.

[0181] In an optional embodiment of the present application, the vehicle information at least includes vehicle size, and the information screening module 403 includes:

[0182] The free parking space detection submodule is used to obtain the free parking spaces in the current parking lot;

[0183] A parking space size recognition submodule, used to recognize the actual parking space size of the vacant parking space through the camera;

[0184] A size matching submodule, used for matching the target vacant parking space whose actual parking space size satisfies the parking conditions according to the vehicle size;

[0185] The parking space analysis submodule is used to analyze the target vacant parking space based on the historical information set and the parking space information of the parking lot using the parking guidance model to obtain the target parking space and the corresponding target parking route.

[0186] In an optional embodiment of the present application, the historical information set includes at least historical parking information corresponding to the driver, and the parking space analysis submodule is further used to:

[0187] analyzing the parking proficiency of the driver according to the parking proficiency information in the historical parking information corresponding to the driver;

[0188] Based on the parking proficiency, the target vacant parking space is analyzed using the parking guidance model to obtain a first analysis result.

[0189] In an optional embodiment of the present application, the parking space analysis submodule is further used to:

[0190] analyzing the parking habits of the driver according to the parking habit information in the historical parking information corresponding to the driver;

[0191] Based on the parking habit, the target vacant parking space is analyzed using the parking guidance model to obtain a second analysis result.

[0192] In an optional embodiment of the present application, the parking space analysis submodule is further used to:

[0193] Based on the parking space information, using the parking guidance model, analyzing the target vacant parking space to obtain a third analysis result, wherein the third analysis result at least includes a parking route corresponding to the target vacant parking space;

[0194] The target parking space and the corresponding target parking route are determined from the target vacant parking space and the parking route corresponding to the target vacant parking space according to the first analysis result, the second analysis result and the third analysis result.

[0195] In an optional embodiment of the present application, the device further includes:

[0196] A historical parking information acquisition module, used to acquire the historical parking information corresponding to the driver, wherein the historical parking information corresponding to the driver is obtained by identifying the parking behavior of the driver each time entering the parking lot based on the camera;

[0197] The model training module is used to train the parking guidance model using the historical parking information corresponding to the driver to obtain the parking guidance model suitable for the driver.

[0198] In an optional embodiment of the present application, the device further includes:

[0199] The current parking record module is used to obtain the parking behavior of the driver entering the parking lot through the camera;

[0200] The current information recognition module is used to identify the current parking information corresponding to the driver according to the parking behavior of the driver entering the parking lot at that time;

[0201] The optimization training module is used to train the parking guidance model suitable for the driver using the current parking information.

[0202] In an optional embodiment of the present application, the parking guidance module 404 includes:

[0203] A current route acquisition submodule, used for acquiring the current driving route of the vehicle when the vehicle does not drive according to the target parking route;

[0204] The recommendation information updating submodule is used to update the target parking space and the corresponding target parking route using the parking guidance model according to the current driving route, the vehicle information, the historical information set and the parking space information of the parking lot.

[0205] In an optional embodiment of the present application, the information identification module 401 includes:

[0206] An image capturing submodule, configured to capture an image through the camera when the driver drives the vehicle into the parking lot, wherein the image includes the vehicle and the driver;

[0207] The image recognition submodule is used to recognize the vehicle information of the vehicle in the image and the identity information of the driver, wherein the vehicle information includes at least: a license plate number, a vehicle model and a vehicle size.

[0208] In an optional embodiment of the present application, the parking proficiency information includes at least the time taken to turn left, the time taken to turn right, and the reversing adjustment situation;

[0209] The parking habit information includes at least: the number of historical left-side parking times, the number of historical right-side parking times, the time taken to reverse into a garage, the number of turns required for parking, the number of reverses required for parking, and parking space preference information.

[0210] In an embodiment of the present application, a camera is used to identify the vehicle information of a vehicle entering a parking lot and the driver information of the driver of the vehicle; based on the vehicle information and the driver information, a historical information set corresponding to the vehicle and the driver is matched; based on the vehicle information, the historical information set and the parking space information of the parking lot, a parking guidance model is used to obtain a target parking space and a corresponding target parking route; the parking guidance model is trained based on the historical parking information corresponding to the driver, and the historical parking information includes the driver's parking habit information and parking proficiency information; according to the target parking route, the driver is guided to park the vehicle in the target parking space. The embodiment of the present application can recommend the parking space that is most suitable for the driver by automatically identifying the entry and exit of the vehicle and the driver, combining the vehicle information, the historical information set and the parking space information of the parking lot, and using the parking guidance model trained based on the historical parking information corresponding to the driver.

[0211] In addition, the embodiment of the present application will also analyze the historical information set of vehicles and drivers collected by the camera, perform personalized parking route planning based on each driver's different parking habit information and parking proficiency information, and recommend target parking spaces, thereby reducing the driver's parking difficulty and making the parking process smoother and safer.

[0212] At the same time, the embodiments of the present application can effectively reduce the ineffective driving of drivers in the process of looking for parking spaces through precise parking guidance, intelligent allocation of reasonable parking spaces, and optimized parking management.

[0213] The embodiment of the present application also provides a non-volatile readable storage medium, which stores one or more modules (programs). When the one or more modules are applied to a device, the device can execute instructions (instructions) of each method step in the embodiment of the present application.

[0214] The present application embodiment provides one or more machine-readable media on which instructions are stored, and when executed by one or more processors, an electronic device executes one or more of the methods described in the above embodiments. In the present application embodiment, the electronic device includes various types of devices such as terminal devices and servers (clusters).

[0215] The embodiments of the present disclosure may be implemented as a device configured as desired using any appropriate hardware, firmware, software, or any combination thereof, and the device may include electronic devices such as terminal devices and servers (clusters). Figure 5 An exemplary apparatus 500 that can be used to implement various embodiments described in this application is schematically shown.

[0216] For one embodiment, Figure 5 An exemplary apparatus 500 is shown having one or more processors 502, a control module (chip set) 504 coupled to at least one of the processor(s) 502, a memory 506 coupled to the control module 504, a non-volatile memory (NVM) / storage device 508 coupled to the control module 504, one or more input / output devices 510 coupled to the control module 504, and a network interface 512 coupled to the control module 504.

[0217] The processor 502 may include one or more single-core or multi-core processors, and the processor 502 may include any combination of general-purpose processors or special-purpose processors (such as graphics processors, application processors, baseband processors, etc.). In some embodiments, the device 500 can be used as a terminal device, server (cluster), etc. described in the embodiments of the present application.

[0218] In some embodiments, the apparatus 500 may include one or more computer-readable media (e.g., memory 506 or NVM / storage device 508) having instructions 514 and one or more processors 502 configured in conjunction with the one or more computer-readable media to execute the instructions 514 to implement a module to perform the actions described in the present disclosure.

[0219] For one embodiment, control module 504 may include any suitable interface controller to provide any suitable interface to at least one of processor(s) 502 and / or any suitable device or component in communication with control module 504 .

[0220] The control module 504 may include a memory controller module to provide an interface to the memory 506. The memory controller module may be a hardware module, a software module, and / or a firmware module.

[0221] The memory 506 may be used, for example, to load and store data and / or instructions 514 for the device 500. For one embodiment, the memory 506 may include any suitable volatile memory, such as a suitable DRAM. In some embodiments, the memory 506 may include double data rate type four synchronous dynamic random access memory (DDR4 SDRAM).

[0222] For one embodiment, control module 504 may include one or more input / output controllers to provide an interface to NVM / storage device 508 and input / output device(s) 510 .

[0223] For example, NVM / storage 508 may be used to store data and / or instructions 514. NVM / storage 508 may include any suitable non-volatile memory (e.g., flash memory) and / or may include any suitable non-volatile storage device(s) (e.g., one or more hard disk drives (HDDs), one or more compact disk (CD) drives, and / or one or more digital versatile disk (DVD) drives).

[0224] NVM / storage device 508 may include storage resources that are physically part of the device on which apparatus 500 is installed, or it may be accessible to the device without being part of the device. For example, NVM / storage device 508 may be accessed via input / output device(s) 510 over a network.

[0225] (One or more) input / output devices 510 may provide an interface for the apparatus 500 to communicate with any other appropriate device, and the input / output device 510 may include a communication component, an audio component, a sensor component, etc. The network interface 512 may provide an interface for the apparatus 500 to communicate through one or more networks, and the apparatus 500 may wirelessly communicate with one or more components of a wireless network according to any of one or more wireless network standards and / or protocols, for example, accessing a wireless network based on a communication standard, such as WiFi, 2G, 3G, 4G, 5G, etc., or a combination thereof for wireless communication.

[0226] For one embodiment, at least one of the processor(s) 502 may be packaged together with the logic of one or more controllers (e.g., a memory controller module) of the control module 504. For one embodiment, at least one of the processor(s) 502 may be packaged together with the logic of one or more controllers of the control module 504 to form a system-in-package (SiP). For one embodiment, at least one of the processor(s) 502 may be integrated on the same die with the logic of one or more controllers of the control module 504. For one embodiment, at least one of the processor(s) 502 may be integrated on the same die with the logic of one or more controllers of the control module 504 to form a system-on-chip (SoC).

[0227] In various embodiments, the apparatus 500 may be, but is not limited to, a terminal device such as a server, a desktop computing device, or a mobile computing device (e.g., a laptop computing device, a handheld computing device, a tablet computer, a netbook, etc.). In various embodiments, the apparatus 500 may have more or fewer components and / or a different architecture. For example, in some embodiments, the apparatus 500 includes one or more cameras, a keyboard, a liquid crystal display (LCD) screen (including a touch screen display), a non-volatile memory port, multiple antennas, a graphics chip, an application-specific integrated circuit (ASIC), and a speaker.

[0228] Among them, the main control chip can be used as a processor or control module in the detection device, sensor data, location information, etc. are stored in a memory or NVM / storage device, the sensor group can be used as an input / output device, and the communication interface may include a network interface.

[0229] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0230] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0231] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable parking guidance terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable parking guidance terminal device generate instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0232] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable parking guidance terminal device to operate in a specific manner, so that the instructions stored in the computer readable memory produce a product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0233] These computer program instructions can also be loaded onto a computer or other programmable parking guidance terminal device, so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable terminal device provide for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0234] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present application.

[0235] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0236] The above is a detailed introduction to a parking guidance method and device, an electronic device and a storage medium provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A parking guidance method, characterized in that: The method comprises: Identifying vehicle information of a vehicle entering the parking lot and driver information of a driver of the vehicle through a camera; Matching a set of historical information corresponding to the vehicle and the driver according to the vehicle information and the driver information; Based on the vehicle information, the historical information set and the parking space information of the parking lot, a parking guidance model is used to obtain a target parking space and a corresponding target parking route; the parking guidance model is trained according to the historical parking information corresponding to the driver, and the historical parking information includes the parking habit information and parking proficiency information of the driver; According to the target parking route, the driver is guided to park the vehicle in the target parking space.

2. The method according to claim 1, characterized in that The vehicle information includes at least vehicle size, and obtaining a target parking space and a corresponding target parking route using a parking guidance model based on the vehicle information, the historical information set, and the parking space information of the parking lot includes: Obtain the currently available parking spaces in the parking lot; Using the camera, identifying the actual parking space size of the vacant parking space; According to the vehicle size, matching the actual parking space size with a target vacant parking space that meets parking conditions; Based on the historical information set and the parking space information of the parking lot, the target vacant parking space is analyzed using the parking guidance model to obtain the target parking space and the corresponding target parking route.

3. The method according to claim 2, characterized in that The historical information set includes at least historical parking information corresponding to the driver, and the target vacant parking space is analyzed based on the historical information set and the parking space information of the parking lot using the parking guidance model, including: analyzing the parking proficiency of the driver according to the parking proficiency information in the historical parking information corresponding to the driver; Based on the parking proficiency, the target vacant parking space is analyzed using the parking guidance model to obtain a first analysis result.

4. The method according to claim 3, characterized in that: After analyzing the target vacant parking space based on the parking proficiency using the parking guidance model, the method further includes: analyzing the parking habits of the driver according to the parking habit information in the historical parking information corresponding to the driver; Based on the parking habit, the target vacant parking space is analyzed using the parking guidance model to obtain a second analysis result.

5. The method according to claim 4, characterized in that After analyzing the target vacant parking space based on the parking habit and using the parking guidance model, the method further includes: Based on the parking space information, using the parking guidance model, analyzing the target vacant parking space to obtain a third analysis result, wherein the third analysis result at least includes a parking route corresponding to the target vacant parking space; The target parking space and the corresponding target parking route are determined from the target vacant parking space and the parking route corresponding to the target vacant parking space according to the first analysis result, the second analysis result and the third analysis result.

6. The method according to claim 1, characterized in that The training method of the parking guidance model comprises: Acquire historical parking information corresponding to the driver, where the historical parking information corresponding to the driver is obtained by identifying the parking behavior of the driver each time entering the parking lot based on the camera; The parking guidance model is trained using the historical parking information corresponding to the driver to obtain the parking guidance model suitable for the driver.

7. The method according to claim 6, characterized in that After instructing the driver to park the vehicle in the target parking space, the method further includes: Acquiring the parking behavior of the driver when entering the parking lot through the camera; According to the parking behavior of the driver when entering the parking lot, identifying the parking information corresponding to the driver; The parking guidance model suitable for the driver is trained using the current parking information.

8. The method according to claim 1, characterized in that The step of guiding the driver to park the vehicle in the target parking space according to the target parking route includes: When the vehicle does not travel according to the target parking route, obtaining a current travel route of the vehicle; The target parking space and the corresponding target parking route are updated using the parking guidance model according to the current driving route, the vehicle information, the historical information set, and the parking space information of the parking lot.

9. The method according to claim 1, characterized in that: The method of identifying the vehicle information of the vehicle entering the parking lot and the driver information of the driver of the vehicle by using a camera includes: When the driver drives the vehicle into the parking lot, the camera captures an image, wherein the image includes the vehicle and the driver; The vehicle information of the vehicle in the recognition image and the identity information of the driver are identified, wherein the vehicle information includes at least: a license plate number, a vehicle model, and a vehicle size.

10. The method according to claim 4, characterized in that The parking proficiency information at least includes the time taken to turn left, the time taken to turn right, and the reversing adjustment situation; The parking habit information includes at least: the number of historical left-side parking times, the number of historical right-side parking times, the time taken to reverse into a garage, the number of turns required for parking, the number of reverses required for parking, and parking space preference information.

11. A parking guidance device, characterized in that: The device comprises: An information recognition module, used to recognize vehicle information of a vehicle entering the parking lot and driver information of a driver of the vehicle through a camera; An information matching module, used for matching the historical information set corresponding to the vehicle and the driver according to the vehicle information and the driver information; an information screening module, configured to obtain a target parking space and a corresponding target parking route using a parking guidance model based on the vehicle information, the historical information set and the parking space information of the parking lot; the parking guidance model is trained based on the historical parking information corresponding to the driver, and the historical parking information includes the parking habit information and parking proficiency information of the driver; The parking guidance module is used to guide the driver to park the vehicle in the target parking space according to the target parking route.

12. An electronic device, characterized in that: include: processor; and A memory having executable codes stored thereon, which, when executed, causes the processor to execute the parking guidance method as claimed in one or more of claims 1-10.

13. One or more machine-readable media having executable codes stored thereon, which, when executed, cause a processor to perform the parking guidance method according to one or more of claims 1-10.

Images