Adaptive threshold determination method and vehicle control method

Abstract

The embodiment of the invention discloses a self-adaptive threshold determination method and a vehicle control method, and the method is characterized in that the self-adaptive threshold method comprises the steps: determining a self-adaptive threshold model according to the Bluetooth signal values in a plurality of historical orders corresponding to a parking spot and the distances between the corresponding parked vehicles and the parking spot, and determining a Bluetooth signal threshold value of the corresponding parking point according to the adaptive threshold value model and the parking distance, and determining an enabling signal value according to the Bluetooth signal threshold value so as to trigger the vehicle to complete the vehicle returning process at the corresponding parking point through the enabling signal value. Therefore, the enabling signal value of the corresponding parking point is determined according to the Bluetooth signal values and the corresponding distance when the vehicle is parked, the influence of Bluetooth signal changes on vehicle returning judgment of a user can be reduced, and the vehicle returning passing rate and stability of the user at the parking point are improved.

Description

Technical Field

[0001] The present invention relates to the field of vehicle technology, and in particular to an adaptive threshold determination method and a vehicle control method. Background Art

[0002] Real-time monitoring of orderly vehicle return operations (including returning the vehicle at a designated location, neatly parking, etc.) through orderly products (such as Bluetooth road studs) can help users park quickly or report information to the user's terminal device (such as a mobile phone) when the user's operation is abnormal, and prompt the user to operate in a standardized manner, thereby achieving orderly parking of the vehicle. Taking the process of achieving orderly vehicle operation using Bluetooth road studs as an example, the central control of the vehicle body interacts with the peripherals that standardize the layout of parking spots, and the acquired Bluetooth signal value data is uploaded to the cloud. By comparing the Bluetooth signal value with the background preset threshold, it is determined based on the comparison result whether the user has parked the vehicle in an orderly manner at a designated location.

[0003] However, in the actual application of ordered products such as Bluetooth road studs, the mapping relationship between the Bluetooth signal value read interactively by the vehicle and the peripheral (i.e., Bluetooth road stud) and the physical distance will change continuously due to environmental factors (time, geographic location, temperature, humidity, etc.). The above method of using a single fixed threshold to realize vehicle return will cause users to have different perceptions of the vehicle in different scenarios, making it impossible to return the vehicle quickly or the user return pass rate will be unstable, which will lead to a bad return experience. Summary of the invention

[0004] In view of this, an embodiment of the present invention aims to provide an adaptive threshold determination method and a vehicle control method to reduce the impact of Bluetooth signal changes on the user's vehicle return judgment, thereby improving the user's vehicle return pass rate and stability.

[0005] In a first aspect, an embodiment of the present invention is to provide a method for determining an adaptive threshold, the method comprising:

[0006] Acquire training data, the training data including vehicle positions of each parked vehicle in a plurality of historical orders corresponding to the parking spot and Bluetooth signal values ​​corresponding to each parked vehicle;

[0007] Determining the distance between the corresponding parked vehicle and the parking point according to the position of each vehicle;

[0008] Determine an adaptive threshold model according to each of the Bluetooth signal values ​​and each of the corresponding distances;

[0009] Determine a Bluetooth signal threshold of a corresponding parking spot according to the adaptive threshold model and a parking distance, wherein the parking distance is determined according to the distance between each parked vehicle in the corresponding parking spot and the parking spot;

[0010] An enabling signal value is determined according to the Bluetooth signal threshold, and the enabling signal value is used to represent a Bluetooth signal value that triggers the vehicle to complete a vehicle return process at a corresponding parking point.

[0011] Further, the determining of the adaptive threshold model according to each of the Bluetooth signal values ​​and the corresponding each of the distances comprises:

[0012] Determine a reference distance corresponding to each Bluetooth signal value according to at least one distance corresponding to the same Bluetooth signal value;

[0013] Regression processing is performed on each of the Bluetooth signal values ​​and the corresponding reference distance to determine the adaptive threshold model.

[0014] Further, the determining the distance between the corresponding parked vehicle and the parking point according to the position of each vehicle includes:

[0015] Determine a position reference line corresponding to a parking point according to the position of each vehicle;

[0016] The distance between the corresponding parked vehicle and the parking point is determined according to the distance between each vehicle position and the position reference line, and the distance is the vertical distance from the vehicle position to the position reference line.

[0017] Further, determining the reference distance corresponding to each Bluetooth signal value according to at least one distance corresponding to the same Bluetooth signal value includes:

[0018] Determine at least one distance corresponding to the same Bluetooth signal value;

[0019] An average value is taken for each of the distance values ​​to determine the average value as a reference distance corresponding to the Bluetooth signal value.

[0020] Further, determining the parking distance according to the distance between each parked vehicle in the corresponding parking spot and the parking spot includes:

[0021] Determine the distance between each parked vehicle at the parking spot and the position reference line within a preset time period as a historical distance;

[0022] An average value or a percentile value is taken for each of the historical distances to determine a parking distance of a corresponding parking point.

[0023] Further, determining the enabling signal value according to the Bluetooth signal threshold comprises:

[0024] Comparing the Bluetooth signal threshold with a preset threshold corresponding to a historical vehicle return record;

[0025] In response to the Bluetooth signal threshold being less than or equal to the preset threshold, determining the Bluetooth signal threshold as an enabling signal value;

[0026] In response to the preset threshold being less than the Bluetooth signal threshold, determining the preset threshold as an enable signal value.

[0027] Further, the determining of the position reference line of the corresponding parking point according to the position of each vehicle includes:

[0028] Fitting is performed on the positions of the vehicles to determine a position reference line corresponding to the parking point.

[0029] In a second aspect, an embodiment of the present invention is intended to provide a vehicle control method, the method comprising:

[0030] Obtaining a return request of a to-be-returned vehicle, wherein the return request includes a Bluetooth real-time signal value, a vehicle location, and a target parking point;

[0031] Comparing the Bluetooth real-time signal value with the enable signal value of the target parking point, the enable signal value being used to represent the Bluetooth signal value that triggers the vehicle to complete the vehicle return process at the corresponding parking point;

[0032] In response to the Bluetooth real-time signal value reaching the enabling signal value, executing a vehicle return process of the vehicle to be returned;

[0033] Among them, the enable signal value is determined according to a predetermined adaptive threshold model and the parking distance of the target parking point, the adaptive threshold model is used to characterize the corresponding relationship between the parking distance of the target parking point and each Bluetooth signal threshold, and the parking distance is determined according to the distance between each parked vehicle and the target parking point in multiple historical orders corresponding to the target parking point.

[0034] In a third aspect, an embodiment of the present invention is intended to provide an adaptive threshold determination device, the device comprising:

[0035] A data acquisition module, used to acquire training data, wherein the training data includes a vehicle position of each parked vehicle in a plurality of historical orders corresponding to a parking spot and a Bluetooth signal value corresponding to each of the vehicles;

[0036] A distance determination module, used to determine the distance between the corresponding parked vehicle and the parking point according to the position of each vehicle;

[0037] A model determination module, used to determine an adaptive threshold model according to each of the Bluetooth signal values ​​and the corresponding each of the distances;

[0038] A threshold determination module, configured to determine a Bluetooth signal threshold of a corresponding parking spot according to the adaptive threshold model and a parking distance, wherein the parking distance is determined according to a distance between each parked vehicle in the corresponding parking spot and the parking spot;

[0039] The vehicle return trigger module is used to determine the enable signal value according to the Bluetooth signal threshold, and the enable signal value is used to represent the Bluetooth signal value that triggers the vehicle to complete the vehicle return process at the corresponding parking point.

[0040] In a fourth aspect, an embodiment of the present invention is intended to provide a vehicle control device, the device comprising:

[0041] An information acquisition unit, used to acquire a return request of a to-be-returned vehicle, wherein the return request includes a Bluetooth real-time signal value, a vehicle location, and a target parking point;

[0042] A process processing unit is used to compare the Bluetooth real-time signal value with the enable signal value of the target parking point, and in response to the Bluetooth real-time signal value reaching the enable signal value, run the vehicle return process of the to-be-returned vehicle, wherein the enable signal value is determined according to a predetermined adaptive threshold model and the parking distance of the target parking point, the adaptive threshold model is used to characterize the corresponding relationship between the parking distance of the target parking point and each Bluetooth signal threshold, and the parking distance is determined according to the distance between each parked vehicle and the target parking point in multiple historical orders corresponding to the target parking point.

[0043] In a fifth aspect, an embodiment of the present invention aims to provide a computer program product, wherein the computer program product comprises a computer program / instructions, and when the computer program / instructions are executed by a processor, the method as described in any one of the above items is implemented.

[0044] In a sixth aspect, an embodiment of the present invention aims to provide an electronic device, comprising a memory and a processor, wherein the memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement a method as described in any one of the above items.

[0045] In a seventh aspect, an embodiment of the present invention aims to provide a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method steps as described in any one of the above items are implemented.

[0046] The technical solution of the embodiment of the present invention determines an adaptive threshold model through the Bluetooth signal values ​​of the vehicles in the multiple historical orders corresponding to the parking point when they are parked in a standardized manner and the distances between the corresponding parked vehicles and the parking point, and determines the Bluetooth signal threshold of the corresponding parking point according to the adaptive threshold model and the parking distance, and determines the enabling signal value according to the Bluetooth signal threshold, so as to trigger the vehicle to complete the return process at the corresponding parking point through the enabling signal value. Thus, the enabling signal value of the corresponding parking point is determined by the Bluetooth signal values ​​of the vehicles when they are parked and the corresponding distances, so that the Bluetooth signal threshold and enabling signal value of each parking point can take into account the influence of the Bluetooth signal change on the judgment of the distance between the parked vehicle and the parking point, thereby reducing the influence of the Bluetooth signal change on the judgment of the user's return of the vehicle, and improving the pass rate and stability of the user's return of the vehicle at the parking point. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The above and other objects, features and advantages of the present invention will become more apparent through the following description of the embodiments of the present invention with reference to the accompanying drawings, in which:

[0048] Figure 1 It is a schematic diagram of a vehicle return in the prior art;

[0049] Figure 2 is a flow chart of a method for determining an adaptive threshold value according to an embodiment of the present invention;

[0050] Figure 3 is a flow chart of determining the distance between two objects according to an embodiment of the present invention;

[0051] Figure 4 is a schematic diagram of determining a position reference line in an embodiment of the present invention;

[0052] Figure 5 is a schematic diagram of the distance in an embodiment of the present invention;

[0053] Figure 6 is a flow chart of determining an adaptive threshold model according to an embodiment of the present invention;

[0054] Figure 7 is a flow chart of determining a reference distance according to an embodiment of the present invention;

[0055] Figure 8 is a schematic diagram of determining an adaptive threshold model according to an embodiment of the present invention;

[0056] Fig. 9 is a flow chart for determining a stopping distance in an embodiment of the present invention;

[0057] Fig.10 is a flow chart of determining an enable signal value according to an embodiment of the present invention;

[0058] Fig.11is a flow chart of a vehicle control method according to an embodiment of the present invention;

[0059] Fig.12 is a schematic diagram of an adaptive threshold determination device according to an embodiment of the present invention;

[0060] Fig.13 is a schematic diagram of a vehicle control device according to an embodiment of the present invention;

[0061] Fig.14 is a schematic diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0062] The present application is described below based on embodiments, but the present application is not limited to these embodiments. In the detailed description of the present application below, some specific details are described in detail. It is possible for those skilled in the art to fully understand the present application without the description of these details. In order to avoid confusing the essence of the present application, known methods, processes, flows, components and circuits are not described in detail.

[0063] In addition, persons of ordinary skill in the art will appreciate that the drawings provided herein are for illustration purposes and are not necessarily drawn to scale.

[0064] Unless the context clearly requires otherwise, the words "include", "comprising" and similar words throughout the application should be interpreted as including rather than exclusive or exhaustive; that is, the meaning is "including but not limited to".

[0065] In the description of this application, it should be understood that the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of this application, unless otherwise specified, the meaning of "plurality" is two or more.

[0066] The solutions described in this specification and in the examples, if they involve the processing of personal information, will be processed on the premise of having a legal basis (such as obtaining the consent of the subject of personal information, or being necessary for the performance of a contract, etc.), and will only be processed within the scope of regulations or agreements. If a user refuses to process personal information other than the necessary information for basic functions, it will not affect the user's use of basic functions.

[0067] In order to standardize user parking and achieve orderly parking of vehicles, the position of vehicles is often monitored through orderly products, and when the vehicle position is detected to be in the parking area corresponding to the specified parking point, the vehicle is helped to complete fixed-point and orderly parking, thereby avoiding the adverse effects of random parking of vehicles on the urban road environment, such as chaos and congestion.

[0068] Taking shared two-wheeled vehicles as an example, the existing technology usually uses Bluetooth road studs, an orderly product, to achieve reasonable parking of vehicles. Figure 1 As shown, the vehicle control panel automatically scans the Bluetooth road studs S arranged in the parking area A corresponding to the parking spot, and uploads the Bluetooth data generated by the Bluetooth road stud S0 scanned and closest to the vehicle to the cloud C, which compares the Bluetooth data with the data threshold set in the background. If the comparison result conforms to the business logic, it is determined that the user has parked the vehicle in a fixed point and in an orderly manner, and this is used as the basis for the user's application for vehicle return settlement. For example, when the Bluetooth data represents the Bluetooth signal strength, the vehicle control panel will send the maximum value of the Bluetooth signal value to the cloud, so that the cloud can compare the Bluetooth signal value with the preset signal threshold, and when the Bluetooth signal value is greater than the preset signal threshold, it is determined that the vehicle has been parked in the parking area, and the user is allowed and guided to continue to complete the vehicle return operation.

[0069] However, in actual use, since the mapping relationship between the Bluetooth signal value and the physical distance read by the vehicle through interaction with the Bluetooth road stud will constantly change, this will cause huge fluctuations in the actual use of Bluetooth road studs to realize the return of the car. Specifically, under different time, geographical location, temperature and humidity and other return environments, the corresponding optimal signal value for return (i.e., signal threshold) is changing. Therefore, the method of using a fixed and unified preset threshold to judge the return of the car in the prior art cannot adapt well to the fluctuation of environmental factors, making the user's return operation at different times or locations more uncertain, which easily causes the user to have different perceptions of the return experience. For example, sometimes the return can be completed quickly at the same location, but sometimes it cannot be returned. This leads to different user perceptions and a poor return experience. At the same time, it will cause some car orders that are not parked in a standardized manner to flow into the bottom-up return funnel, which puts pressure on the city's regulatory level and leads to random returns.

[0070] In view of this, the embodiments of the present invention aim to provide an adaptive threshold determination method and a vehicle control method to reduce the impact of Bluetooth signal changes on the user's vehicle return judgment and improve the user's vehicle return pass rate and stability.

[0071] It should be understood that the method in this embodiment can be applied not only to shared two-wheeled vehicles (including shared bicycles, shared electric motorcycles, etc.), but also to other objects that need to be placed in an orderly manner and have Bluetooth communication functions (such as motor vehicles, transport robots, etc.). The objects and scenarios of use of this solution are not limited here.

[0072] Figure 2 FIG. 1 is a flow chart of a method for determining an adaptive threshold value according to an embodiment of the present invention. Figure 2 As shown, the adaptive threshold determination method in this embodiment includes the following steps.

[0073] In step S100, training data is obtained, wherein the training data includes the vehicle position of each parked vehicle in a plurality of historical orders corresponding to the parking spot and the Bluetooth signal value corresponding to each parked vehicle.

[0074] In this embodiment, the training data is determined based on the vehicle return information in multiple historical orders corresponding to the parking spot, and one order corresponds to one parked vehicle. The vehicle return information includes the vehicle position of the parked vehicle in the corresponding order and the corresponding Bluetooth signal value. The vehicle position is the vehicle parking position after the vehicle is parked in a standardized manner. The vehicle parking position can be the parking position of the vehicle after the user successfully completes the vehicle return operation, or it can be the parking position of the vehicle after manual intervention and correction. When the vehicle is located at the vehicle position, the Bluetooth signal strength value received from the nearest Bluetooth road stud in the parking spot is the Bluetooth signal value corresponding to the vehicle. The Bluetooth signal value is the maximum Bluetooth signal strength, corresponding to the Bluetooth signal with the maximum signal strength that the vehicle can receive when it is located at the vehicle position. The closer the vehicle is to the parking spot, the larger the corresponding Bluetooth signal value.

[0075] Optionally, in order to facilitate the distinction between different parking spots, orders and parked vehicles, the vehicle return information in this embodiment also includes a parking spot identification, an order identification and a vehicle identification, so as to distinguish the vehicle return information corresponding to each parking spot, each order and each parked vehicle through different identifications, which is conducive to improving the efficiency of determining the training data, and thereby improving the efficiency of determining the adaptive threshold.

[0076] Furthermore, in order to facilitate users to park their vehicles, parking spots usually correspond to certain parking areas, and in order to facilitate users to view the standardized parking spots, each parking spot is drawn with a frame diagram (such as a rectangular white frame), and when the vehicle is parked within the frame diagram, it is considered that the vehicle is parked in compliance with the regulations. It should be understood that in actual use, in order to ensure that users can return the vehicle smoothly, parking areas are usually set with space margins, and when the vehicle is parked within a certain distance range from the boundary of the frame diagram, it is also assumed that the vehicle has been parked in compliance with regulations.

[0077] In step S200, the distance between the corresponding parked vehicle and the parking point is determined according to the position of each vehicle.

[0078] In this embodiment, since a parking spot usually corresponds to a parking area rather than a fixed position point, when determining the distance between a parked vehicle and a parking spot, a parking spot position reference line is first determined, and the position of the parking spot is represented by the position reference line, and then the distance between the corresponding parked vehicle and the parking spot is determined according to the distance between the vehicle position of the parked vehicle and the position reference line.

[0079] Figure 3 FIG. 4 is a flow chart of determining the distance between two objects according to an embodiment of the present invention. Figure 3 As shown, in this embodiment, the distance between the parked vehicle and the parking point is determined through the following steps.

[0080] In step S210, a position reference line corresponding to a parking point is determined according to the position of each vehicle.

[0081] In this embodiment, the vehicle position may be the position of the center of gravity of the vehicle, the vehicle positioning module, or other characteristic points or components on the vehicle. The position reference line may be a boundary line, a central axis, or other marking line used to indicate the position of the parking point in the area corresponding to the parking point, and the position reference line is determined according to the parking area formed by the vehicle positions of the parked vehicles in the historical parking orders.

[0082] Optionally, in this embodiment, the position reference line of the corresponding parking point is determined by fitting the position of each vehicle, and then the position reference line is used to represent the location of the corresponding parking point.

[0083] Furthermore, in an optional implementation, as Figure 4 As shown in , when determining the position reference line, the geographical location of each vehicle position P in the position coordinates is first represented by the longitude and latitude data, and then the longitude and latitude data of each vehicle position P are fitted by the least squares method to determine the position reference line L corresponding to the parking point A. The position reference line L corresponds to the marking line of the parking area (such as the boundary line, the central axis, etc.).

[0084] In another optional implementation, in this embodiment, the parking area corresponding to the parking point can be simulated according to the position of each vehicle, the boundary shape of the parking area can be determined, and the marking line in the boundary shape of the parking area can be used as the position reference line of the corresponding parking point. For example, taking the position reference line as the central axis, after simulating the boundary shape of the parking area as a rectangle, the midpoint positions of two opposite short sides are respectively selected, and the line connecting the two midpoint positions is determined as the position reference line of the corresponding parking point.

[0085] It should be noted that, considering the situation that there are vehicles that are effectively parked but not completely within the parking area frame corresponding to the parking spot, the position reference line L here corresponds to the marking line (such as the central axis, boundary line) of the parking area formed according to the vehicle position of the parked vehicle in the historical parking order, which may not be completely consistent with the marking line in the parking area frame represented by the actual parking spot on the ground, but it can be used to represent the location of the parking spot. Among them, effective parking of vehicles refers to parking conditions that meet the supervision requirements of relevant departments (orderly and neat parking). Compared with strictly parking the vehicle within the parking area frame, effective parking is set with a certain margin, which can make the vehicle parking more in line with reality.

[0086] In step S220, the distance between the corresponding parked vehicle and the parking point is determined according to the distance between each vehicle position and the position reference line.

[0087] In this embodiment, the distance between the vehicle position and the position reference line is represented by the vertical distance between the vehicle position and the position reference line, and the distance between the parked vehicle and the parking point is the vertical distance from the vehicle position to the position reference line. Figure 5 As shown, P1 and P2 are the vehicle positions corresponding to the parked vehicles in the parking spot A, and L is the position reference line of the parking spot A. The distance D1 between the vehicle position P1 and the parking spot A is the vertical distance from the vehicle position P1 to the position reference line L. The distance D2 between the vehicle position P2 and the parking spot A is the vertical distance from the vehicle position P2 to the position reference line L. Therefore, in this embodiment, the distance between the corresponding parked vehicle and the parking spot is determined according to the distance between each vehicle position and the position reference line.

[0088] In step S300, an adaptive threshold model is determined according to each Bluetooth signal value and each corresponding distance.

[0089] In this embodiment, since there is a mapping relationship between the Bluetooth signal value and the physical distance, when the monitored environmental factors change, for example, the parking time, the geographical environment of the parking location, the temperature, the humidity, etc., the actual physical distance represented by the same Bluetooth signal value may be different, or the Bluetooth signal value detected at the same actual physical distance may be different.

[0090] In this case, continuing to use a single and fixed Bluetooth signal threshold as the return judgment standard will bring a lot of uncertainty to the user's return operation. For example, the actual physical distance meets the requirements, but the Bluetooth signal value is less than the preset threshold, the user cannot actively return the car, and manual intervention is required to complete the return of the car. For example, the relationship between the Bluetooth signal value and the preset threshold at the same actual physical distance is uncertain. The Bluetooth signal value is sometimes greater than the preset threshold and sometimes less than the preset threshold. This causes the user to actively return the car at the same distance, or may not be able to actively return the car. The uncertainty of returning the car is large, which will bring a very poor car experience to the user. For example, the actual physical distance does not meet the requirements, but the Bluetooth signal value is greater than the preset threshold. The user can actively return the car, but the actual parking of the vehicle is not standardized.

[0091] Based on this, in this embodiment, the return data of standardized parking in the parking spot is selected to constitute the training data, and the adaptive threshold model is determined according to the Bluetooth signal value and the distance data in the training data. By fully considering the fluctuation of the mapping relationship between the Bluetooth signal value and the physical distance caused by the change of environmental factors in the process of determining the adaptive threshold model, the Bluetooth signal threshold determined by the adaptive threshold model can better represent the real physical distance, thereby reducing the impact of the Bluetooth signal change on the user's judgment of returning the car, and improving the probability and stability of the user's return pass.

[0092] Due to the influence of environmental factors, the same Bluetooth signal value may correspond to multiple different distances, or the same distance may correspond to multiple different Bluetooth signal values. Therefore, in this embodiment, the combination data of different Bluetooth signal values ​​and distances may be used to determine the adaptive threshold model.

[0093] Optionally, in this embodiment, an adaptive threshold model can be determined according to each Bluetooth signal value and each corresponding distance, that is, a plurality of distances corresponding to a Bluetooth signal value are taken as a group of data, and then the adaptive threshold model is determined according to the plurality of groups of data corresponding to each Bluetooth signal value. Alternatively, in this embodiment, an adaptive threshold model can also be determined according to each distance and each corresponding Bluetooth signal value, that is, a plurality of Bluetooth signal values ​​corresponding to a distance are taken as a group of data, and then the adaptive threshold model is determined according to the plurality of groups of data corresponding to each distance.

[0094] Furthermore, in this embodiment, the adaptive threshold model can be determined by each Bluetooth signal value and each corresponding distance in the historical order return information corresponding to a single parking spot, so that the adaptive threshold model can be applied to the corresponding parking spot, which is conducive to further improving the standardization of vehicle parking in the corresponding parking spot. In addition, considering that parking habits in the same area (such as a city or a region) or vehicle parking problems caused by environmental changes are universal, in this embodiment, the adaptive threshold model can also be determined according to the Bluetooth signal values ​​corresponding to multiple parking spots in the corresponding area and the distances corresponding to each Bluetooth signal value. Specifically, after obtaining the return information in the historical orders corresponding to each parking spot in the area, the return information of each parking spot can be integrated to determine the training data, and based on the same processing method as mentioned above, the adaptive threshold model is determined according to each Bluetooth signal value and each corresponding distance in the training data, so as to determine the Bluetooth signal threshold of each parking spot in the corresponding area through the adaptive threshold model.

[0095] The following is an example of the process of determining the adaptive threshold model corresponding to a single parking point.

[0096] Figure 6 FIG. 1 is a flow chart of determining an adaptive threshold model according to an embodiment of the present invention. Figure 6 As shown, in this embodiment, the adaptive threshold model is determined through the following steps.

[0097] In step S310, a reference distance corresponding to each Bluetooth signal value is determined according to at least one distance corresponding to the same Bluetooth signal value.

[0098] In this embodiment, when determining the adaptive threshold model based on the distances corresponding to the Bluetooth signal values, the reference distance represents the distance that can be stably represented by the corresponding Bluetooth signal value under the influence of environmental changes. Stable representation means that the reference distance can simultaneously represent the actual physical distance and the error distance caused by Bluetooth signal fluctuations.

[0099] Optionally, the reference distance in this embodiment can be the average value of each distance corresponding to the same Bluetooth signal value, or the percentile value of each distance corresponding to the same Bluetooth signal value, such as the 90th percentile value, the 95th percentile value, or the 99th percentile value. Further, the reference distance in this embodiment uses the average value of each distance, so as to be more compatible with the fluctuation of Bluetooth signal value caused by changes in environmental factors, while ensuring standardized parking, providing users with a relaxed car return environment, thereby improving the user's car experience.

[0100] Specifically, in this embodiment, Figure 7 The method shown in determines the reference distance corresponding to each Bluetooth signal value.

[0101] In step S410, at least one distance corresponding to the same Bluetooth signal value is determined.

[0102] In step S420, an average value is taken for each distance value, so as to determine the average value as a reference distance corresponding to the Bluetooth signal value.

[0103] In this embodiment, assuming that in the training data, the distances corresponding to the Bluetooth signal value S1 are D11, D12, D13 and D14, then the reference distance D1 corresponding to the Bluetooth signal value S1 is the average of the distances D11, D12, D13 and D14, that is, D1 = (D11 + D12 + D13 + D14) / 4. Thus, the reference distance corresponding to each Bluetooth signal value is determined by the above method.

[0104] In step S320, regression processing is performed on each Bluetooth signal value and the corresponding reference distance to determine an adaptive threshold model.

[0105] In this embodiment, after determining the reference distance corresponding to each Bluetooth signal value, a data pair of the Bluetooth signal value and the reference distance is constructed, and regression processing is performed on the Bluetooth signal value and the corresponding reference distance in each data pair to determine an adaptive threshold model.

[0106] Figure 8 FIG. 1 is a schematic diagram of determining an adaptive threshold model according to an embodiment of the present invention. Figure 8As shown, the horizontal axis in the figure represents the Bluetooth signal value (expressed as a negative value), and the vertical axis represents the reference distance corresponding to the Bluetooth signal value. It can be seen from the figure that the larger the Bluetooth signal value, the greater the corresponding Bluetooth signal strength and the smaller the corresponding reference distance. Taking the Bluetooth signal values ​​of -100 and -80 as an example, the reference distance corresponding to the vehicle position with a Bluetooth signal value of -100 is 3, and the reference distance corresponding to the vehicle position with a Bluetooth signal value of -80 is 2.93. The Bluetooth signal value -100<-80, the corresponding reference distance 3>2.93. Therefore, the closer the parked vehicle is to the parking spot, the larger the corresponding Bluetooth signal threshold should be, so as to ensure that the vehicle is parked in the parking area of ​​the parking spot in a standardized manner.

[0107] Optionally, in order to improve the convenience and efficiency of regression processing, this embodiment uses a univariate linear regression method to perform regression processing on each Bluetooth signal value and the corresponding reference distance, and then determines an adaptive threshold model, and uses the adaptive threshold model to characterize the functional relationship between the Bluetooth signal value and the reference distance, for example, D = f (rtd) = a1 × rtd + b1, where D is the reference distance, rtd is the Bluetooth signal value, and a1 and b1 are constants. Therefore, by fitting the above functional relationship, the values ​​of the constants a1 and b1 in the functional relationship are determined, and then the corresponding adaptive threshold model is determined.

[0108] It should be understood that in this embodiment, when performing regression processing on each Bluetooth signal value and the corresponding reference distance in each data pair, a univariate linear regression method can be used to perform regression processing on each Bluetooth signal value and the corresponding reference distance, or other methods can be used to determine the adaptive threshold model. For example, since the adaptive threshold model represents the corresponding relationship between the Bluetooth signal value and the reference distance, in this embodiment, a neural network model can also be used to extract and analyze features of the return vehicle information in multiple historical orders corresponding to the parking point, determine the corresponding relationship between the Bluetooth signal value and the reference distance and the adaptive threshold model, and then the Bluetooth signal threshold of the parking point can be predicted and determined through the adaptive threshold model.

[0109] In step S400, a Bluetooth signal threshold of a corresponding parking spot is determined according to an adaptive threshold model and a parking distance, wherein the parking distance is determined according to the distance between each parked vehicle in the corresponding parking spot and the parking spot.

[0110] In this embodiment, since the adaptive threshold model is determined based on the Bluetooth signal value when returning the vehicle at the parking spot (that is, the maximum value of the Bluetooth signal strength corresponding to the user's standardized return of the vehicle), after determining the adaptive threshold model, the Bluetooth signal threshold is determined according to the adaptive threshold model, and the Bluetooth signal threshold is used as the basis for judging whether the vehicle is returned at the parking spot. This can effectively monitor the parking position of the vehicle in the parking area corresponding to the parking spot, ensure that the vehicle is parked in a standardized and orderly manner, and meet the regulatory requirements of relevant departments.

[0111] Optionally, in this embodiment, by Fig. 9 The method in the embodiment determines the parking distance of the parking point, and after determining the parking distance, the Bluetooth signal threshold of the corresponding parking point can be determined by substituting the parking distance into the adaptive threshold model.

[0112] In step S510, the distances between each parked vehicle and the position reference line in the parking spot within a preset time period are respectively determined as historical distances.

[0113] In this embodiment, in order to improve the timeliness of the Bluetooth signal threshold, the parking distance is determined based on the vehicle return information within the preset time period, so as to determine the Bluetooth signal threshold that is more suitable for the parking spot according to the recent vehicle parking situation. Correspondingly, when determining the parking distance, the distance between each parked vehicle and the position reference line in the parking spot within the preset time period is determined as the historical distance. Among them, the method for determining the distance between each parked vehicle and the position reference line is consistent with the above content and will not be repeated here. At the same time, the setting of the corresponding duration of the preset time period can be set according to experience or actual usage scenarios, which can be a day, half a month or a month.

[0114] In step S520, an average value or a percentile value is taken for each historical distance to determine a parking distance of a corresponding parking point.

[0115] In this embodiment, the parking distance is a representative value of the distance between each parked vehicle and the parking point within a preset time period, which can reflect the historical parking situation of the corresponding parking point. After determining the historical distance of each parked vehicle in the parking point within the preset time period, the parking distance of the corresponding parking point is determined by taking the average or percentile value of each historical distance. The parking distance is the distance value obtained after taking the average or percentile value. Therefore, in this embodiment, the parking distance of the parking point is determined by the above method, which can make the Bluetooth signal threshold determined by the parking distance more in line with the actual parking needs of the vehicle in the parking point. This can not only meet the supervision requirements of vehicle parking in the parking point, but also provide users with stable and accurate return judgment conditions, reduce the impact of environmental changes on return judgment, and improve the pass rate and stability of user return, thereby improving the user's car experience.

[0116] In step S500, an enabling signal value is determined according to a Bluetooth signal threshold value, and the enabling signal value is used to represent a Bluetooth signal value that triggers the vehicle to complete a vehicle return process at a corresponding parking point.

[0117] In this embodiment, before determining the Bluetooth signal threshold, the vehicle return process is triggered by comparing the Bluetooth signal strength on the vehicle side with the preset threshold. Specifically, when the Bluetooth signal strength is greater than the preset threshold, it indicates that the vehicle parking complies with the specification, and guides the user to continue to complete the vehicle return operation. At the same time, considering the fluctuations caused by the change of the Bluetooth signal under the influence of environmental factors, the Bluetooth signal value of the parked vehicle whose actual distance meets the requirements may include both the Bluetooth signal value that reaches the preset threshold and the Bluetooth signal value that does not reach the preset threshold. Therefore, in this embodiment, after determining the Bluetooth signal threshold according to the Bluetooth signal value of the parked vehicle whose actual distance meets the requirements, the enabling signal value will be determined by the Bluetooth signal threshold and the preset threshold, and the enabling signal value will be used as the basis for whether the user's vehicle return application can be approved. In addition, since the threshold corresponding to the enabling signal value represents the Bluetooth signal strength, the larger the threshold, the closer the vehicle needs to be to the parking point to realize the vehicle return.

[0118] Fig.10 FIG. 1 is a flow chart of determining the enable signal value according to an embodiment of the present invention. Fig.10 As shown, the method for determining the enable signal value in this embodiment includes the following steps.

[0119] In step S610, the Bluetooth signal threshold is compared with a preset threshold corresponding to the historical vehicle return record.

[0120] In this embodiment, the signal threshold that better meets the actual parking requirement is determined by comparing the Bluetooth signal threshold and the preset threshold.

[0121] In step S620, it is determined whether the Bluetooth signal threshold is less than or equal to a preset threshold.

[0122] In this embodiment, when it is determined that the Bluetooth signal threshold is less than or equal to the preset threshold, step S630 is continued to be executed; when it is determined that the Bluetooth signal threshold is not less than or equal to the preset threshold, that is, when the preset threshold is less than the Bluetooth signal threshold, step S640 is continued to be executed.

[0123] In step S630, in response to the Bluetooth signal threshold being less than or equal to a preset threshold, the Bluetooth signal threshold is determined to be an enabling signal value.

[0124] In this embodiment, when the Bluetooth signal threshold is less than or equal to the preset threshold, it indicates that the parking area corresponding to the original preset threshold is too large and the risk of illegal parking is high. At this time, the Bluetooth signal threshold is determined as the enabling signal value, so that when the Bluetooth signal strength reaches the Bluetooth signal threshold, the vehicle position of the corresponding vehicle is determined to be located in the parking area of ​​the parking spot, which meets the vehicle parking requirements and allows the user to complete the vehicle return operation.

[0125] In step S640, in response to the preset threshold being less than the Bluetooth signal threshold, the preset threshold is determined to be an enabling signal value.

[0126] In this embodiment, when the preset threshold is less than the Bluetooth signal threshold, it indicates that the vehicle can meet the parking requirements when parked in the parking areas corresponding to the original preset threshold and the Bluetooth signal threshold, and the parking area corresponding to the preset threshold is larger than the parking area corresponding to the Bluetooth signal threshold. Therefore, in this embodiment, if the requirements are not strict, the preset threshold can continue to be used as the enabling signal value to judge the user's vehicle return operation; if the requirements are strict, the Bluetooth signal threshold is used as the enabling signal to judge whether the user's vehicle return operation is allowed.

[0127] Optionally, since the parking area corresponding to the preset threshold is larger than the parking area corresponding to the Bluetooth signal threshold, and the setting of the preset threshold usually leaves space margin for users, the parking area corresponding to the preset threshold will be larger than the area covered by the parking frame line marked on the ground of the parking spot. Therefore, in this embodiment, if the requirements are not strict, the preset threshold can continue to be used as the enabling signal value to judge the user's vehicle return operation, so as to provide users with more space options for parking while ensuring that the vehicle is parked in a standardized manner at the parking spot, and provide users with a more convenient vehicle return space, further improving the user experience.

[0128] The technical solution of the embodiment of the present invention determines an adaptive threshold model through the Bluetooth signal values ​​of each vehicle when it is parked in a parking spot and the corresponding distance between each parked vehicle and the parking spot, and determines the Bluetooth signal threshold of the corresponding parking spot according to the adaptive threshold model and the parking distance, and determines the enabling signal value according to the Bluetooth signal threshold, and then triggers the vehicle to complete the vehicle return process at the corresponding parking spot through the enabling signal value, so that the Bluetooth signal threshold and enabling signal value of each parking spot can take into account the influence of Bluetooth signal changes on the judgment of the distance between the parked vehicle and the parking spot, thereby reducing the influence of Bluetooth signal changes on the user's judgment on returning the vehicle, while ensuring the standardized parking of vehicles at the parking spot and meeting the supervision requirements of relevant departments, it can improve the user's vehicle return pass rate and stability at the parking spot.

[0129] Furthermore, in this embodiment, after the enable signal value for the user to return the vehicle is determined by the above method, the user is assisted in completing the vehicle return process based on the enable signal value.

[0130] Fig.11 FIG. 1 is a flow chart of a vehicle control method according to an embodiment of the present invention. Fig.11 As shown, the vehicle control method in this embodiment is applied to the server, and the server executes the following steps to implement the user's vehicle return operation.

[0131] In step S710, a return request of the vehicle to be returned is obtained, wherein the return request includes a Bluetooth real-time signal value, a vehicle location, and a target parking point.

[0132] In this embodiment, the real-time value of the Bluetooth signal is the signal strength value of the Bluetooth signal of the Bluetooth road stud closest to the vehicle received by the vehicle end, that is, the maximum Bluetooth signal value.

[0133] In step S720, the Bluetooth real-time signal value is compared with the enable signal value of the target parking point to determine whether the Bluetooth real-time signal value reaches the enable signal value.

[0134] In this embodiment, the enabling signal value represents the Bluetooth signal value that triggers the vehicle to complete the vehicle return process at the corresponding parking point. The enabling signal value is determined based on a predetermined adaptive threshold model and the parking distance of the target parking point. The adaptive threshold model is used to represent the corresponding relationship between the parking distance of the target parking point and each Bluetooth signal threshold. The parking distance is determined based on the distance between each parked vehicle and the target parking point in multiple historical orders corresponding to the target parking point.

[0135] Optionally, the method for determining the enable signal value in this embodiment may refer to the aforementioned content and will not be repeated here.

[0136] Furthermore, in this embodiment, when it is determined that the Bluetooth real-time signal value reaches the enabling signal value, that is, the Bluetooth real-time signal value is greater than or equal to the enabling signal value, step S730 is continued to be executed; when it is determined that the Bluetooth real-time signal value does not reach the enabling signal value, that is, the Bluetooth real-time signal is less than the enabling signal value, step S740 is continued to be executed.

[0137] In step S730, in response to the Bluetooth real-time signal value reaching the enabling signal value, the vehicle return process of the vehicle to be returned is executed.

[0138] In this embodiment, when the Bluetooth real-time signal value of the vehicle to be returned reaches the enabling signal value, it indicates that the vehicle position corresponding to the vehicle to be returned is located in the parking area of ​​the target parking point and meets the vehicle parking specifications. At this time, the user's return request is approved and the vehicle return process is run to assist the user in completing the return of the vehicle.

[0139] In step S740, in response to the Bluetooth real-time signal value not reaching the enabling signal value, the vehicle return process of the to-be-returned vehicle is not executed.

[0140] In this embodiment, when the Bluetooth real-time signal value of the vehicle to be returned does not reach the enabling signal value, it indicates that the vehicle position corresponding to the vehicle to be returned does not fall within the parking area of ​​the target parking point, which does not comply with the vehicle parking specifications. At this time, the user's return request needs to be rejected and the vehicle return process does not run, that is, the subsequent return process corresponding to the current return request is suspended.

[0141] Optionally, in this embodiment, a prompt message may be sent to the user or the user may be guided to move the vehicle to be returned to the parking area based on the difference between the Bluetooth real-time signal value and the enabling signal value to assist the user in returning the vehicle.

[0142] The technical solution of this embodiment is to run the return process of the vehicle to be returned after the user sends a return request, based on the comparison result of the Bluetooth real-time signal value in the return request and the predetermined enable signal value, and after the Bluetooth real-time signal value reaches the enable signal value, guide the user to complete the return operation. Since the enable signal value is determined based on the historical parking data of the target parking point after considering the Bluetooth signal fluctuation, it can provide an accurate and reliable basis for the user to return the vehicle, thereby providing the user with a reliable and stable return perception while achieving standardized parking of the vehicle, and improving the return experience.

[0143] Fig.12 Schematic diagram of an adaptive threshold determination device according to an embodiment of the present invention. Fig.12 As shown, the adaptive threshold determination device of this embodiment includes a data acquisition module 11, a distance determination module 12, a model determination module 13, a threshold determination module 14, and a return vehicle trigger module 15. Among them, the data acquisition module 11 is used to obtain training data, and the training data includes the vehicle position of each parked vehicle in multiple historical orders corresponding to the parking point and the Bluetooth signal value corresponding to each vehicle, and the Bluetooth signal value is the maximum value of the Bluetooth signal strength corresponding to when the user's return vehicle request passes. The distance determination module 12 is used to determine the distance between the corresponding parked vehicle and the parking point according to each vehicle position. The model determination module 13 is used to determine the adaptive threshold model according to each Bluetooth signal value and the corresponding distance. The threshold determination module 14 is used to determine the Bluetooth signal threshold of the corresponding parking point according to the adaptive threshold model and the parking distance, wherein the parking distance is determined according to the distance between each parked vehicle in the corresponding parking point and the parking point. The return vehicle trigger module 15 is used to determine the enable signal value according to the Bluetooth signal threshold, and the enable signal value is used to characterize the Bluetooth signal value that triggers the vehicle to complete the return vehicle process at the corresponding parking point.

[0144] Optionally, the distance determination module 12 in this embodiment is specifically used to determine the position reference line of the corresponding parking point according to the position of each vehicle when determining the distance between the parked vehicle and the parking point, and to determine the distance between the corresponding parked vehicle and the parking point according to the distance between the position of each vehicle and the position reference line, where the distance is the vertical distance from the vehicle position to the position reference line. Further, when determining the position reference line, it is specifically used to fit the position of each vehicle to determine the position reference line of the corresponding parking point.

[0145] Optionally, when determining the adaptive threshold model, the model determination module 13 in this embodiment is also used to determine the reference distance corresponding to each Bluetooth signal value according to at least one distance corresponding to the same Bluetooth signal value, and perform regression processing on each Bluetooth signal value and the corresponding reference distance to determine the adaptive threshold model. Further, when determining the reference distance, it is specifically used to determine at least one distance corresponding to the same Bluetooth signal value, and average the distance values ​​to determine the average value as the reference distance corresponding to the Bluetooth signal value.

[0146] Optionally, when determining the parking distance of a parking spot, the threshold determination module 14 in this embodiment is specifically used to determine the distance between each parked vehicle in the parking spot and the position reference line within a preset time period as a historical distance, and take an average or percentile value of each historical distance to determine the parking distance of the corresponding parking spot.

[0147] Optionally, when determining the enable signal value, the vehicle return trigger module 15 in this embodiment is specifically used to compare the Bluetooth signal threshold with a preset threshold corresponding to the historical vehicle return record, and in response to the Bluetooth signal threshold being less than or equal to the preset threshold, determine the Bluetooth signal threshold as the enable signal value; or in response to the preset threshold being less than the Bluetooth signal threshold, determine the preset threshold as the enable signal value.

[0148] The technical solution of this embodiment determines the enabling signal value of the corresponding parking point through the Bluetooth signal values ​​when the vehicle is parked and the corresponding distances, so that the Bluetooth signal threshold and enabling signal value of each parking point can take into account the influence of Bluetooth signal changes on the judgment of the distance between the parked vehicle and the parking point, thereby reducing the influence of Bluetooth signal changes on the user's judgment on returning the vehicle, and improving the pass rate and stability of users returning the vehicle at the parking point.

[0149] Fig.13 Schematic diagram of a vehicle control device according to an embodiment of the present invention. Fig.13 As shown, the vehicle control device of this embodiment includes: an information acquisition unit 21 and a process processing unit 22. The information acquisition unit 21 is used to obtain a return request for the vehicle to be returned, and the return request includes a Bluetooth real-time signal value, a vehicle position, and a target parking point. The process processing unit 22 is used to compare the Bluetooth real-time signal value with the enable signal value of the target parking point, and in response to the Bluetooth real-time signal value reaching the enable signal value, run the return process of the vehicle to be returned. The enable signal value is determined according to a predetermined adaptive threshold model and the parking distance of the target parking point. The adaptive threshold model is used to characterize the corresponding relationship between the parking distance of the target parking point and each Bluetooth signal threshold, and the parking distance is determined according to the distance between each parked vehicle and the target parking point in multiple historical orders corresponding to the target parking point.

[0150] The technical solution of this embodiment determines the enabling signal value based on the historical parking data of the target parking spot after considering the fluctuation of the Bluetooth signal, which can provide accurate and reliable judgment basis for the user to return the vehicle, and by comparing the Bluetooth real-time signal value in the return request with the predetermined enabling signal value, after the Bluetooth real-time signal value reaches the enabling signal value, the return process of the vehicle to be returned is run to guide the user to complete the return operation, which can provide the user with a reliable and stable return perception while realizing standardized parking of the vehicle, thereby improving the return experience.

[0151] Fig.14 Schematic diagram of an electronic device according to an embodiment of the present invention. Fig.14 The electronic device shown is a general data processing device, which includes a general computer hardware structure, which at least includes a processor 81 and a memory 82. The processor 81 and the memory 82 are connected via a bus 83. The memory 82 is suitable for storing instructions or programs executable by the processor 81. The processor 81 can be an independent microprocessor or a collection of one or more microprocessors. Thus, the processor 81 executes the instructions stored in the memory 82, thereby executing the method flow of the embodiment of the present invention as described above to realize the processing of data and the control of other devices. The bus 83 connects the above-mentioned multiple components together, and at the same time connects the above-mentioned components to the display controller 84 and the display device and the input / output (I / O) device 85. The input / output (I / O) device 85 can be a mouse, a keyboard, a modem, a network interface, a touch input device, a somatosensory input device, a printer, and other devices known in the art. Typically, the input / output device 85 is connected to the system via an input / output (I / O) controller 86.

[0152] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, devices (equipment) or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present application may adopt a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0153] The present application is described with reference to flowcharts of methods, apparatuses (devices) and computer program products according to embodiments of the present application. It should be understood that each process in the flowchart can be implemented by computer program instructions.

[0154] These computer program instructions may be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device that implements the process Figure 1A function specified in a process or multiple processes.

[0155] These computer program instructions may also be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce the instructions for implementing the process Figure 1 A device that specifies functions in a process or multiple processes.

[0156] Another embodiment of the present invention relates to a non-volatile storage medium for storing a computer-readable program, wherein the computer-readable program is used for a computer to execute part or all of the above method embodiments.

[0157] That is, those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by specifying relevant hardware through a program, and the program is stored in a storage medium, including several instructions for a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0158] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for determining an adaptive threshold, characterized in that: The method comprises: Acquire training data, the training data including vehicle positions of each parked vehicle in a plurality of historical orders corresponding to the parking spot and Bluetooth signal values ​​corresponding to each parked vehicle; Determining the distance between the corresponding parked vehicle and the parking point according to the position of each vehicle; Determine an adaptive threshold model according to each of the Bluetooth signal values ​​and each of the corresponding distances; Determine a Bluetooth signal threshold of a corresponding parking spot according to the adaptive threshold model and a parking distance, wherein the parking distance is determined according to a distance between each parked vehicle in the corresponding parking spot and the parking spot; An enabling signal value is determined according to the Bluetooth signal threshold, and the enabling signal value is used to represent a Bluetooth signal value that triggers the vehicle to complete a vehicle return process at a corresponding parking point.

2. The method according to claim 1, characterized in that Determining the adaptive threshold model according to each of the Bluetooth signal values ​​and the corresponding distances comprises: Determine a reference distance corresponding to each Bluetooth signal value according to at least one distance corresponding to the same Bluetooth signal value; Regression processing is performed on each of the Bluetooth signal values ​​and the corresponding reference distance to determine the adaptive threshold model.

3. The method according to claim 1, characterized in that Determining the distance between the corresponding parked vehicle and the parking point according to the position of each vehicle includes: Determine a position reference line corresponding to a parking point according to the position of each vehicle; The distance between the corresponding parked vehicle and the parking point is determined according to the distance between each vehicle position and the position reference line, and the distance is the vertical distance from the vehicle position to the position reference line.

4. The method according to claim 2, characterized in that: Determining the reference distance corresponding to each Bluetooth signal value according to at least one distance corresponding to the same Bluetooth signal value comprises: Determine at least one distance corresponding to the same Bluetooth signal value; An average value is taken for each of the distance values ​​to determine the average value as a reference distance corresponding to the Bluetooth signal value.

5. The method according to claim 3, characterized in that: Determining the parking distance according to the distance between each parked vehicle in the corresponding parking spot and the parking spot includes: Determine the distance between each parked vehicle at the parking spot and the position reference line within a preset time period as a historical distance; An average value or a percentile value is taken for each of the historical distances to determine a parking distance of a corresponding parking point.

6. The method according to claim 1, characterized in that Determining the enabling signal value according to the Bluetooth signal threshold comprises: Comparing the Bluetooth signal threshold with a preset threshold corresponding to a historical vehicle return record; In response to the Bluetooth signal threshold being less than or equal to the preset threshold, determining the Bluetooth signal threshold as an enabling signal value; In response to the preset threshold being less than the Bluetooth signal threshold, determining the preset threshold as an enable signal value.

7. The method according to claim 3, characterized in that Determining the position reference line corresponding to the parking point according to the position of each vehicle includes: Fitting is performed on the positions of the vehicles to determine a position reference line corresponding to the parking point.

8. A vehicle control method, characterized in that: The method comprises: Obtaining a return request of a to-be-returned vehicle, wherein the return request includes a Bluetooth real-time signal value, a vehicle location, and a target parking point; Comparing the Bluetooth real-time signal value with the enable signal value of the target parking point, the enable signal value being used to represent the Bluetooth signal value that triggers the vehicle to complete the vehicle return process at the corresponding parking point; In response to the Bluetooth real-time signal value reaching the enabling signal value, executing a vehicle return process of the vehicle to be returned; Among them, the enable signal value is determined according to a predetermined adaptive threshold model and the parking distance of the target parking point, the adaptive threshold model is used to characterize the corresponding relationship between the parking distance of the target parking point and each Bluetooth signal threshold, and the parking distance is determined according to the distance between each parked vehicle and the target parking point in multiple historical orders corresponding to the target parking point.

9. An adaptive threshold determination device, characterized in that: The device comprises: A data acquisition module, used to acquire training data, wherein the training data includes a vehicle position of each parked vehicle in a plurality of historical orders corresponding to a parking spot and a Bluetooth signal value corresponding to each of the vehicles; A distance determination module, used to determine the distance between the corresponding parked vehicle and the parking point according to the position of each vehicle; A model determination module, used to determine an adaptive threshold model according to each of the Bluetooth signal values ​​and the corresponding each of the distances; A threshold determination module, configured to determine a Bluetooth signal threshold of a corresponding parking spot according to the adaptive threshold model and a parking distance, wherein the parking distance is determined according to a distance between each parked vehicle in the corresponding parking spot and the parking spot; The vehicle return trigger module is used to determine the enable signal value according to the Bluetooth signal threshold, and the enable signal value is used to represent the Bluetooth signal value that triggers the vehicle to complete the vehicle return process at the corresponding parking point.

10. A vehicle control device, characterized in that: The device comprises: An information acquisition unit, used to acquire a return request of a to-be-returned vehicle, wherein the return request includes a Bluetooth real-time signal value, a vehicle location, and a target parking point; A process processing unit is used to compare the Bluetooth real-time signal value with the enable signal value of the target parking point, and in response to the Bluetooth real-time signal value reaching the enable signal value, run the vehicle return process of the to-be-returned vehicle, wherein the enable signal value is determined according to a predetermined adaptive threshold model and the parking distance of the target parking point, the adaptive threshold model is used to characterize the corresponding relationship between the parking distance of the target parking point and each Bluetooth signal threshold, and the parking distance is determined according to the distance between each parked vehicle and the target parking point in multiple historical orders corresponding to the target parking point.

11. A computer program product, characterized in that The computer program product comprises a computer program / instructions, and when the computer program / instructions are executed by a processor, the method according to any one of claims 1 to 8 is implemented.

12. An electronic device comprising a memory and a processor, characterized in that: The memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method according to any one of claims 1 to 8.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method steps of any one of claims 1 to 8 are implemented.

Images