Method, apparatus, vehicle, and storage medium for measuring the location of a vehicle key.

Abstract

This application provides a method, apparatus, vehicle, and storage medium for measuring the position of a vehicle key. Based on the distance between the vehicle key and multiple anchor points for position measurement on the vehicle, and a preset distance threshold, the first position of the key is determined to indicate that the key is in the vicinity of the vehicle. Based on the distance and a pre-trained first machine learning binary classifier, the second position of the key is determined to indicate that the key is outside the vehicle. Based on the distance and a pre-trained second machine learning binary classifier, the third position of the key is determined to indicate that the key is to the side of the vehicle. Based on the distance, a pre-trained machine learning regression model, and a preset triangulation algorithm, the final position coordinates of the key relative to the vehicle are determined. High-precision position measurement of the vehicle key is achieved by dividing the vehicle area into different hierarchical areas and determining the final position using different methods.

Description

Technical Field

[0001] This application relates to the field of automotive electronics technology, and particularly to a method and apparatus for measuring the position of a vehicle key, a vehicle, and a storage medium.

Background Art

[0002] With the progress of science and technology, the conventional mechanical vehicle key has gradually evolved into a smart key with keyless entry and keyless ignition functions. Furthermore, as the security-enhanced ultra-wideband (UWB) wireless access technology is applied to vehicle keys, vehicle keys have entered a new era that integrates the advantages of various wireless technologies. While the UWB wireless access technology has features such as resistance to relay attacks and high-precision ranging and position measurement, it is prone to reflection, diffraction, and multipath interference with the vehicle body and surrounding conductors during operation, which becomes an interference factor and affects the position measurement accuracy of the vehicle key.

[0003] In the conventional technology, in order to avoid these problems, it is common to apply machine learning methods to realize the position measurement of vehicle keys. However, machine learning requires a large-scale network and a large amount of computation, has high requirements for software / hardware resources, and there is a large deviation between the diverse changes in the actual environment outside the vehicle and the ideal environment during the collection of training sample data. Therefore, the position error during actual position measurement outside the vehicle tends to increase. Furthermore, due to the characteristics of the vast outdoor space and the narrow indoor space, there is a significant imbalance in the amount of training sample data sets inside and outside the vehicle, resulting in problems such as a decrease in the recognition rate inside the vehicle.

[0004] Based on the above, how to accurately and stably identify the position of the vehicle key has become an urgent issue in this field.

Summary of the Invention

Problems to be Solved by the Invention

[0005] This application aims to solve the problem of how to accurately and reliably locate the position of an automobile key, and provides a method, apparatus, vehicle, and storage medium for measuring the position of a vehicle key. [Means for solving the problem]

[0006] In a first embodiment, the present application provides a method for measuring the position of a vehicle key applied to a vehicle. Based on the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle, and a preset distance threshold, the first position of the vehicle key is determined, and the first position indicates that the vehicle key is in the vehicle's far-field or near-field. If the first position indicates that the vehicle key is in the vehicle's immediate vicinity, a second position of the vehicle key is determined based on the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle, and a pre-trained first machine learning binary classifier, wherein the second position indicates that the vehicle key is outside or inside the vehicle, and the first machine learning binary classifier is an algorithm for determining the position of the vehicle key based on the distance between the vehicle key and the position-measuring anchor points, which is pre-trained based on a dataset collected within the range of the vehicle's immediate vicinity. If the second position indicates that the vehicle key is outside the vehicle, a third position of the vehicle key is determined based on the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle, and a pre-trained second machine learning binary classifier, wherein the third position indicates that the vehicle key is to the side of the vehicle or on the vehicle body, and the second machine learning binary classifier is an algorithm for determining the position of the vehicle key based on the distance between the vehicle key and the position-measuring anchor points, which is pre-trained on a dataset collected in the area outside the vehicle. If the third position indicates that the vehicle key is to the side of the vehicle, the final position coordinates of the vehicle key relative to the vehicle are determined based on the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle, a pre-trained machine learning regression model, and a pre-configured triangulation algorithm, wherein the machine learning regression model is a pre-trained algorithm for determining the position of the vehicle key based on the distance between the vehicle key and the position-measuring anchor points, and is based on a dataset collected in the range to the side of the vehicle.

[0007] In accordance with the first embodiment, in some embodiments, if the third position indicates that the vehicle key is located to the side of the vehicle, the final position coordinates of the vehicle key relative to the vehicle are determined based on the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle, a pre-trained machine learning regression model, and a pre-configured triangulation algorithm. The first position coordinates of the vehicle key are determined based on the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle, and the pre-trained machine learning regression model. The second position coordinate of the vehicle key is determined based on the distance between the vehicle key and a plurality of anchor points for position measurement of the vehicle, and the triangulation algorithm. This includes determining the final position coordinates of the vehicle key relative to the vehicle based on the first and second position coordinates.

[0008] In accordance with the first embodiment, in several embodiments, the method is: If the first position indicates that the vehicle key is in the vehicle's far field, the method further includes determining the final position coordinates of the vehicle key relative to the vehicle based on the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle, and the triangulation algorithm.

[0009] In accordance with the first embodiment, in several embodiments, the method is: If the second location indicates that the vehicle key is inside the vehicle, the system determines that the vehicle key is in a first sub-region of the vehicle, based on the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle, and a pre-trained first machine learning multi-class classifier, the first sub-region including the driver's seat area, passenger seat area, rear seat area, or trunk area, and the first machine learning multi-class classifier is a pre-trained algorithm for determining the location of the vehicle key based on the distance between the vehicle key and position-measuring anchor points, based on a dataset collected within the interior of the vehicle.

[0010] In accordance with the first embodiment, in several embodiments, the method is: If the third position indicates that the vehicle key is on the vehicle body, the system determines that the vehicle key is in a second sub-region of the vehicle, based on the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle, and a pre-trained second machine learning multi-class classifier, the second sub-region including the hood, roof, or back door, and the second machine learning multi-class classifier is a pre-trained algorithm for determining the position of the vehicle key based on the distance between the vehicle key and position-measuring anchor points, based on a dataset collected over the vehicle body.

[0011] In accordance with the first embodiment, in some embodiments, before determining the first position of the vehicle key based on the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle and a preset distance threshold, the method is: To acquire a distance measurement signal between the vehicle key and a plurality of anchor points for position measurement of the vehicle, The further includes determining the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle based on the distance measurement signal.

[0012] In a second embodiment, the present application provides a vehicle key position measuring device, A first determination module for determining a first position of a vehicle key based on the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle, and a preset distance threshold, wherein the first position indicates that the vehicle key is in the vehicle's far-field or vehicle's near-field, If the first position indicates that the vehicle key is in the vehicle's immediate vicinity, a second decision module for determining a second position of the vehicle key based on the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle, and a pre-trained first machine learning binary classifier, wherein the second position indicates that the vehicle key is outside or inside the vehicle, and the first machine learning binary classifier is a pre-trained algorithm for determining the position of the vehicle key based on the distance between the vehicle key and the position-measuring anchor points, based on a dataset collected within the range of the vehicle's immediate vicinity. If the second position indicates that the vehicle key is outside the vehicle, a third decision module for determining a third position of the vehicle key based on the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle, and a pre-trained second machine learning binary classifier, wherein the third position indicates that the vehicle key is to the side of the vehicle or on the vehicle body, and the second machine learning binary classifier is a pre-trained algorithm for determining the position of the vehicle key based on the distance between the vehicle key and the position-measuring anchor points, based on a dataset collected in the area outside the vehicle. If the third position indicates that the vehicle key is located to the side of the vehicle, a fourth decision module determines the final position coordinates of the vehicle key relative to the vehicle based on the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle, a pre-trained machine learning regression model, and a pre-configured triangulation algorithm. The machine learning regression model is a fourth decision module, which is an algorithm for determining the position of a vehicle key based on the distance between the vehicle key and a position-measuring anchor point, and is pre-trained on a dataset collected in the lateral range of the vehicle. This includes,

[0013] In accordance with the second embodiment, in some embodiments, the fourth decision module is: Based on the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle, and the pre-trained machine learning regression model, the first position coordinates of the vehicle key are determined. of The first decision unit, A second determination unit for determining the second position coordinates of the vehicle key based on the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle, and the triangulation algorithm, The system includes a third determination unit for determining the final position coordinates of the vehicle key relative to the vehicle, based on the first and second position coordinates.

[0014] In accordance with the second embodiment, in some embodiments, the apparatus is: If the first position indicates that the vehicle key is in the vehicle's far field, the system further includes a fifth determination module for determining the final position coordinates of the vehicle key relative to the vehicle, based on the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle, and the triangulation algorithm.

[0015] In accordance with the second embodiment, in some embodiments, the apparatus is: If the second location indicates that the vehicle key is inside the vehicle, the system further includes a sixth decision module for determining that the vehicle key is in a first sub-region of the vehicle, based on the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle, and a pre-trained first machine learning multi-class classifier, wherein the first sub-region includes the driver's seat area, the passenger seat area, the rear seat area, or the trunk area, and the first machine learning multi-class classifier is a pre-trained algorithm for determining the location of the vehicle key based on the distance between the vehicle key and position-measuring anchor points, based on a dataset collected within the interior of the vehicle.

[0016] In accordance with the second embodiment, in some embodiments, the apparatus is: When the third position indicates that the vehicle key is in the vehicle body, based on the distances between the vehicle key and a plurality of position measurement anchor points of the vehicle, and a pre-trained second machine learning multi-class classifier, it further includes a seventh determination module for determining that the vehicle key is in a second sub-region of the vehicle, the second sub-region includes on the bonnet or on the roof or on the back door, and the second machine learning multi-class classifier is an algorithm for determining the position of the vehicle key based on the distances between the vehicle key and the position measurement anchor points, which is pre-trained based on a dataset collected within the range of the vehicle body.

[0017] According to a second aspect, in some embodiments 、 The apparatus An acquisition module for acquiring ranging signals between the vehicle key and a plurality of position measurement anchor points of the vehicle, Based on the ranging signals, it further includes an eighth determination module for determining the distances between the vehicle key and the plurality of position measurement anchor points of the vehicle.

[0018] In a third aspect, the present application further provides a vehicle, the vehicle includes a vehicle main body, a storage unit installed on the vehicle main body, an electronic control unit, and a plurality of position measurement anchor points, Computer-executable instructions are stored in the storage unit, The electronic control unit realizes the method described in any The first aspect by executing the computer-executable instructions stored in the storage unit. one item as described above.

[0019] In a fourth aspect, the present application further provides a computer-readable storage medium, on which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor Any one of the first aspects they are used to realize the method described above.

[0020] In a fifth embodiment, the present application provides a computer program product, the computer program product comprising a computer program, and the method according to any of the first embodiments is realized when the computer program is executed on a processor. [Effects of the Invention]

[0021] The vehicle key position measurement method, apparatus, vehicle, and storage medium according to the present invention obtain the distance between the vehicle key and a plurality of position measurement anchor points mounted on the vehicle body through communication between the vehicle key and a plurality of position measurement anchor points on the vehicle, determine a first position of the vehicle key based on the distance between the vehicle key and the plurality of position measurement anchor points on the vehicle and a preset distance threshold, if the first position indicates that the vehicle key is in the vicinity of the vehicle, determine a second position of the vehicle key based on the distance between the vehicle key and the plurality of position measurement anchor points on the vehicle and a pre-trained first machine learning binary classifier, if the second position indicates that the vehicle key is outside the vehicle, determine a third position of the vehicle key based on the distance between the vehicle key and the plurality of position measurement anchor points on the vehicle and a pre-trained second machine learning binary classifier, if the third position indicates that the vehicle key is to the side of the vehicle, determine the final position coordinates of the vehicle key relative to the vehicle based on the distance between the vehicle key and the plurality of position measurement anchor points on the vehicle, a pre-trained machine learning regression model, and a preset triangulation algorithm. By hierarchically dividing the vehicle area into multiple regions, the success rate and accuracy of vehicle key position recognition were improved. Furthermore, by integrating machine learning regression models and triangulation algorithms to correct the vehicle key's position coordinates, highly accurate and stable vehicle key recognition was achieved. [Brief explanation of the drawing]

[0022] The drawings attached herein are incorporated into the specification and constitute part of this specification, illustrating embodiments conforming to the present application and are used together with the specification to illustrate the principles of the present application. [Figure 1] This is an application scene diagram of the vehicle key position measurement method according to an embodiment of the present invention. [Figure 2] This is a flowchart of Embodiment 1 of the vehicle key position measurement method according to the embodiment of the present invention. [Figure 3] This is a specific flowchart of the vehicle key position measurement method according to the embodiment of the present invention. [Figure 4] This is a schematic diagram illustrating the division of the vehicle area according to an embodiment of the present invention. [Figure 5] This is a flowchart of Embodiment 2 of the vehicle key position measurement method according to the embodiment of the present invention. [Figure 6] This is a flowchart of Embodiment 3 of the vehicle key position measurement method according to the embodiment of the present invention. [Figure 7] This is a flowchart of Embodiment 4 of the vehicle key position measurement method according to the embodiment of the present invention. [Figure 8] This is a schematic diagram illustrating the division of the vehicle's functional area according to an embodiment of the present invention. [Figure 9] This is a schematic diagram of the structure of Embodiment 1 of the vehicle key position measuring device according to an embodiment of the present invention. [Figure 10] This is a schematic diagram of the structure of Embodiment 2 of the vehicle key position measuring device according to an embodiment of the present invention. [Figure 11] This is a schematic diagram of the structure of Embodiment 3 of the vehicle key position measuring device according to an embodiment of the present invention. [Figure 12] This is a schematic diagram of the structure of a vehicle according to an embodiment of the present application. Clear embodiments of the present application have already been shown through the above drawings and will be described in more detail below. These drawings and textual descriptions are not intended to limit the scope of the concept of the present application by any means, but are intended to explain the concept of the present application to those skilled in the art by reference to specific embodiments. [Modes for carrying out the invention]

[0023] Here, exemplary embodiments are described in detail, and examples are shown in the drawings. Where the drawings are referenced in the following description, unless otherwise noted, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments are not representative of all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application described in detail in the appended claims.

[0024] With the development of the automotive industry, the form and usage of keys have also changed significantly. The most common type of car key today is the smart key, which comes in a wide variety of forms and is no longer limited to the traditional key shape. For example, a card-type key can unlock the vehicle simply by sensing it near the door. Furthermore, by binding the key to a smart device, it becomes unnecessary to carry the key with you the next time you go out; all operations can be completed by simply bringing the smart device. Communication between the smart key and the vehicle is usually performed using UWB (ultra-wideband) wireless access technology. UWB wireless access technology has technical features such as resistance to relay attacks and the ability to measure distance and position with high precision. Regarding smart key location measurement, it is common to apply machine learning techniques to collect a large amount of training samples in various areas outside the vehicle and in different locations inside the vehicle, and then perform location measurement using the trained model. However, due to the large discrepancy between the diverse changes in the real environment outside the vehicle and the ideal environment during training sample data collection, the position error in actual location measurement outside the vehicle tends to increase. Furthermore, due to the characteristics of the vast space outside the vehicle and the narrow space inside the vehicle, a significant imbalance occurs in the amount of training sample data set inside and outside the vehicle, resulting in problems such as a decrease in recognition rate inside the vehicle. Moreover, when using the least squares method to measure the location of a smart key, when the key is near the vehicle body or inside the vehicle, factors such as shielding by the vehicle body and multiple reflections of radio waves inside the vehicle cause the location measurement output to become unstable and the accuracy to decrease.

[0025] To address the aforementioned problems, this invention provides a method for measuring the position of a vehicle key, enabling highly accurate and stable position measurement of the vehicle key. Specifically, regarding the position measurement of a smart key, a large number of vehicle area training samples are usually collected to train a machine learning model, and the position measurement is then performed using the trained model. However, due to the diversity of the actual environment outside the vehicle and the large difference in the amount of data collected inside and outside the vehicle, problems such as a decrease in recognition rate inside the vehicle arise. When measuring the position of a smart key using the least squares method, factors such as shielding of the vehicle body and multiple reflections of radio waves inside the vehicle cause the output of position measurement around the vehicle body and inside the vehicle to become unstable, resulting in a decrease in accuracy. In view of these problems, the inventors investigated the possibility of region-specific position measurement by integrating distance measurement / machine learning classification (identification) / machine learning regression (position measurement) / triangulation positioning algorithms based on the multipath distribution and delay-spreading characteristics of UWB signal propagation under different environments inside and outside the vehicle. Based on this, the present invention proposes the technical solution.

[0026] Figure 1 is an application scene diagram of a vehicle key position measurement method according to an embodiment of the present invention. As shown in Figure 1, the application scene includes at least a vehicle and a vehicle key. Here, a plurality of position measurement anchor points are installed on the vehicle, and the position measurement anchor points are UWB1, UWB2, UWB3, and UWB4 as shown in Figure 2. Here, the position measurement anchor points UWB1, UWB2, UWB3, and UWB4 are all located outside the vehicle body, and UWB1 and UWB4 are located at both corners of the front of the vehicle body, and UWB2 and UWB3 are located at both corners of the rear of the vehicle body. By positioning the position measurement anchor points outside the vehicle body and at the four corners of the front and rear of the vehicle body, it is possible to prevent the distance measurement signal between the key and the position measurement anchor points from being blocked, reflected, or diffracted by the vehicle body. A position measurement device is placed at the position measurement anchor points, and the position measurement device can determine the distance between the position measurement anchor points and the vehicle key, or the position measurement anchor points are anchor points that have a position measurement function. The position measurement device may be a UWB device with a UWB chip or UWB module built in, or a BLE device. (Bluetooth Low Energy)The location measuring device may be equipped with a module or BLE chip. The vehicle key further includes a BLE module or BLE chip. The vehicle key may be a physical key or a virtual key on a user terminal. The user terminal is a smart device such as a smartphone or tablet.

[0027] In this application, no restrictions are placed on the specific form or type of the physical device described above.

[0028] The present invention and how it solves the above-mentioned technical problems will be described in detail below through specific embodiments. Several of the following specific embodiments are combinable with respect to each other, and in some embodiments, redundant explanations of the same or similar concepts or processes may be omitted. The embodiments of the present invention will be described below with reference to the drawings.

[0029] Figure 2 is a flowchart of Embodiment 1 of the vehicle key position measurement method according to the embodiment of the present invention. As shown in Figure 2, the vehicle key position measurement method according to the present invention is applied to a vehicle and specifically includes S101 to S104.

[0030] In S101, the first position of the vehicle key is determined based on the distance between the vehicle key and multiple anchor points for position measurement on the vehicle, and a preset distance threshold.

[0031] In this step, UWB wireless technology achieves communication based on electromagnetic wave propagation. At different locations on the vehicle, the presence of conductors differs, resulting in differences in the effectiveness of signal transmission in communication between the vehicle key and the vehicle. To accurately identify the specific location of the vehicle key and accurately activate the functions in that area, the different locations on the vehicle are divided hierarchically, and the first location of the vehicle key is determined based on the distance between the vehicle key and multiple location-measuring anchor points on the vehicle, as well as a preset distance threshold.

[0032] Specifically, as shown in Figure 3, communication is performed between the vehicle key and multiple position-measuring anchor points mounted on the vehicle. Furthermore, distance measurement signals are obtained between the vehicle key and the multiple position-measuring anchor points of the vehicle using the multiple position-measuring anchor points. Based on the distance measurement signals, the distance between the vehicle key and the multiple position-measuring anchor points of the vehicle is determined. The shortest distance is selected from the distances between the vehicle key and the multiple position-measuring anchor points. The shortest distance is compared with a preset distance threshold to determine the first position of the vehicle key. If the shortest distance is greater than the preset distance threshold, the first position indicates that the vehicle is in the vehicle's far-field. If the shortest distance is less than the preset distance threshold, the first position indicates that the vehicle is in the vehicle's near-field.

[0033] In one specific embodiment, as shown in Figure 4, if the preset distance threshold is 3 meters and there are four anchor points for position measurement, the four anchor points are installed at the corners of the front and rear of the vehicle body, respectively, with the four anchor points as the centers of a circle and a radius of 3 meters as the vehicle's short-range field, as shown in Figure 4. the above Any region outside of the specified area is the vehicle's long-range field.

[0034] In S102, if the first position indicates that the vehicle key is in the vehicle's immediate vicinity, the second position of the vehicle key is determined based on the distance between the vehicle key and multiple position-measuring anchor points of the vehicle, and a pre-trained first machine learning binary classifier.

[0035] In this step, if the first position is determined to indicate that the vehicle key is in the vehicle near field by comparing the distance between the vehicle key and multiple anchor points for vehicle position measurement with a preset distance threshold, the vehicle near field is still a complex environment and could be outside the vehicle close to the vehicle body or inside the vehicle. Similar to the step above, in order to more accurately identify and position the vehicle near field, the vehicle near field is further subdivided into different layers and the distance between the vehicle key and multiple anchor points for vehicle position measurement is input to a pre-trained first machine learning binary classifier, thereby determining the second position of the vehicle key.

[0036] Specifically, as shown in Figure 3, the pre-trained first machine learning binary classifier is a model obtained by training a machine learning binary classifier based on a dataset collected in advance within the range of the vehicle's near field. The distance between the acquired vehicle key and multiple anchor points for vehicle position measurement is input to the pre-trained first machine learning binary classifier, and after processing, a first category value is obtained as the output. Here, the first category value represents a numerical value corresponding to the outside of the vehicle or a numerical value corresponding to the inside of the vehicle. If the output is a numerical value corresponding to the outside of the vehicle, the second position indicates that the vehicle key is outside the vehicle. If the output is a numerical value corresponding to the inside of the vehicle, the second position indicates that the vehicle key is inside the vehicle. Here, the category value can be represented numerically. For example, 0 corresponds to the outside of the vehicle and 1 corresponds to the inside of the vehicle. If the output is 0, the second position indicates that the vehicle key is outside the vehicle. If the output is 1, the second position indicates that the vehicle key is inside the vehicle.

[0037] Selectively, a Received Signal Strength Indication (RSSI) is obtained for each of the multiple location-measuring anchor points through communication between the vehicle key and multiple location-measuring anchor points. The RSSI represents the strength of the communication between the corresponding location-measuring anchor point and the vehicle key. Both the RSSI and the distance between the vehicle key and the multiple location-measuring anchor points of the vehicle can be input into a pre-trained first machine learning binary classifier to improve the accuracy of the output.

[0038] In S103, if the second position indicates that the vehicle key is outside the vehicle, the third position of the vehicle key is determined based on the distance between the vehicle key and multiple position-measuring anchor points of the vehicle, and a pre-trained second machine learning binary classifier.

[0039] In this step, if the second position obtained as a result of hierarchically dividing the vehicle's near-field by the above step indicates that the vehicle key is outside the vehicle, it means that the vehicle key is located in the surrounding environment of the vehicle. However, during communication between the vehicle key and multiple position-measuring anchor points, if the distance measurement signal transmitted from the vehicle key is a high-frequency signal, phenomena such as reflection, multipath interference, and diffraction occur when the high-frequency signal encounters conductive materials such as metal parts of the vehicle body or the surrounding human body. These phenomena are factors that destabilize position measurement. Therefore, the area outside the vehicle is further hierarchically divided, and the distance between the vehicle key and multiple position-measuring anchor points of the vehicle is input to a pre-trained second machine learning binary classifier, thereby determining the third position of the vehicle key.

[0040] Specifically, the pre-trained second machine learning binary classifier is a model obtained by training a machine learning binary classifier based on a dataset collected in advance within the range of the vehicle. The specific process of model analysis is the same as the analysis process of the pre-trained first machine learning binary classifier in the steps described above, and will not be explained again here.

[0041] As selectable, as shown in Figure 3, if the second position indicates that the vehicle key is outside the vehicle, a pre-trained machine learning binary classifier determines whether the vehicle key is within a predetermined distance range S1 around the vehicle body. If the vehicle key is outside the predetermined distance range S1 around the vehicle body, it indicates that the vehicle body has a relatively small influence on signal transmission between the vehicle key and the multiple position measurement anchor points. In this case, a triangulation algorithm is used to analyze and calculate the position of the vehicle key. If the vehicle key is within the predetermined distance range S1 around the vehicle body, the third position of the vehicle key is determined by the above method. For example, within a range of 1 meter from the vehicle body, the position measurement of the vehicle key is easily affected by the mounting positions of the multiple position measurement anchor points. If position measurement anchor points are also installed inside the vehicle, the distance between the vehicle key and the in-vehicle anchor points is essential for position measurement of the vehicle key within 1 meter from the vehicle body. Therefore, before determining the third position of the vehicle key, a pre-trained machine learning binary classifier is used to determine whether the vehicle key is within a range of 1 meter from the vehicle body or outside of a range of 1 meter from the vehicle body.

[0042] In S104, if the third position indicates that the vehicle key is to the side of the vehicle, the final position coordinates of the vehicle key relative to the vehicle are determined based on the distance between the vehicle key and multiple position-measuring anchor points of the vehicle, a pre-trained machine learning regression model, and a pre-configured triangulation algorithm.

[0043] In this step, the exterior of the vehicle is divided hierarchically, and assuming that the third position indicates the vehicle key is on the side of the vehicle, the distance between the vehicle key and multiple positioning anchor points on the vehicle is analyzed using a pre-trained machine learning regression model and a pre-configured triangulation algorithm, taking into account occlusion by the vehicle body, thereby determining the final position coordinates of the vehicle key relative to the vehicle. Here, the side of the vehicle mainly includes the left side, rear side, and right side of the vehicle. The position coordinates are three-dimensional coordinates.

[0044] Specifically, as shown in A3 in Figure 3, when the vehicle key is located on one of the sides of the vehicle, the pre-trained machine learning regression model is obtained by training on a dataset collected within the range of the vehicle's sides. The analysis process of the machine learning regression model is similar to that of a machine learning classifier. The distance between the vehicle key and multiple position-measuring anchor points of the vehicle is input to the pre-trained machine learning regression model. After processing, the first position coordinates of the vehicle key are output. Based on the distance between the vehicle key and multiple position-measuring anchor points of the vehicle, a set of anchor points is determined from the multiple position-measuring anchor points. The distance between the position-measuring anchor points in the anchor point set and the key is corrected to obtain the corrected distance. The positions of multiple corrected distances are analyzed and calculated to determine the second position coordinates of the vehicle key. The first and second position coordinates are averaged to finally obtain the final position coordinates of the vehicle key relative to the vehicle. Here, the set of anchor points corresponds one-to-one with the sides of the vehicle.

[0045] If the third position, as shown in A3 in Figure 3, indicates that the vehicle key is on the side of the vehicle, a pre-trained machine learning multi-class classifier determines whether the vehicle key is on the left side, rear side, or right side of the vehicle. After determining that the vehicle key is on one of these sides, the corresponding anchor point set is determined using the above method, and then analytical calculations are performed for position measurement.

[0046] The vehicle key position measurement method according to this embodiment determines a first position of the vehicle key based on the distance between the vehicle key and multiple position measurement anchor points of the vehicle, and a preset distance threshold. If the first position indicates that the vehicle key is in the vicinity of the vehicle, a second position of the vehicle key is determined based on the distance between the vehicle key and multiple position measurement anchor points of the vehicle, and a pre-trained first machine learning binary classifier. If the second position indicates that the vehicle key is outside the vehicle, the distance between the vehicle key and multiple position measurement anchor points of the vehicle, and a pre-trained second machine learning binary classifier is used. Based on the value classifier, a third position of the vehicle key is determined. If the third position indicates that the vehicle key is to the side of the vehicle, the final position coordinates of the vehicle key relative to the vehicle are determined based on the distance between the vehicle key and multiple position-measuring anchor points of the vehicle, a pre-trained machine learning regression model, and a pre-configured triangulation algorithm. The area of ​​the vehicle's surrounding environment is hierarchically divided, and the pre-trained machine learning regression model and pre-configured triangulation algorithm are applied to the area to the side near the vehicle to improve the accuracy of vehicle key position measurement and enhance identification efficiency.

[0047] Figure 5 is a flowchart of Embodiment 2 of the vehicle key position measurement method according to an embodiment of the present invention, and as shown in Figure 5, in the above embodiment, step S10 4 S10 4 1~S10 4 Includes 3. S10 4 In step 1, the first position coordinates of the vehicle key are determined based on the distance between the vehicle key and multiple anchor points for vehicle position measurement, and a pre-trained machine learning regression model.

[0048] In this step, in order to determine the first position coordinates of the vehicle key, the distances between the vehicle key and multiple position-measuring anchor points of the vehicle are input into a pre-trained machine learning regression model, and after processing, the first position coordinates of the vehicle key are obtained.

[0049] Specifically, a pre-trained machine learning regression model is obtained by training based on either a linear regressor, a logistic regressor, or a stepwise regressor. As an example, if the pre-trained machine learning regression model is trained based on a linear regressor, the distance between the vehicle key and multiple anchor points for vehicle position measurement is input to the pre-trained machine learning regression model. Let the input distance between the vehicle key and the multiple anchor points be X, and the output be Y. Then, the equation Y = b + ωX is used to obtain the first position coordinate of the vehicle key. In this equation, b is the intercept and ω is the weight, and both b and ω are obtained during the training process.

[0050] S10 4 In step 2, the second position coordinates of the vehicle key are determined based on the distance between the vehicle key and multiple anchor points for position measurement of the vehicle, and a triangulation algorithm.

[0051] In this step, a triangulation algorithm is used to determine the second position coordinates of the vehicle key in order to reduce the inaccuracies and instabilities of position measurement due to multipath interference, diffraction, and reflection.

[0052] Specifically, based on the distance between the vehicle key and multiple position-measuring anchor points on the vehicle, at least two position-measuring anchor points are selected from the multiple position-measuring anchor points, where the transmission method for the distance measurement signal is a non-line-of-sight transmission method, and these are designated as reference anchor points. If the number of reference anchor points exceeds two and the determined reference anchor points lie on the same straight line, the two reference anchor points with the maximum distance between them are designated as target reference anchor points. If the number of reference anchor points exceeds two and the determined reference anchor points do not lie on the same straight line, two adjacent reference anchor points whose connecting line is parallel to the ground are designated as target reference anchor points. If a Kerr point is determined and the number of reference anchor points exceeds two, and the determined reference anchor points are not collinear, the two reference anchor points whose sum of the distances from each of the two adjacent reference anchor points to the vehicle key is smallest are determined as target reference anchor points. The line connecting the two target reference anchor points is defined as the X-axis, and one target reference anchor point on the X-axis is defined as the coordinate origin to determine the local coordinate system. Based on the distances from each of the two target reference anchor points to the vehicle key, and the distance between the two target reference anchor points, the first coordinate of the vehicle key in the local coordinate system is determined, and a transformation process is performed on the first coordinate to obtain the second position coordinate.

[0053] S10 4 In step 3, the final position coordinates of the vehicle key relative to the vehicle are determined based on the first and second position coordinates.

[0054] In this step, after obtaining the first and second position coordinates of the vehicle key by different methods, the first and second position coordinates are averaged to make the vehicle key's position measurement more accurate and stable, thereby obtaining the final position coordinates of the vehicle key relative to the vehicle.

[0055] The vehicle key position measurement method according to this embodiment determines the first position coordinates of the vehicle key based on the distance between the vehicle key and multiple position measurement anchor points of the vehicle, and a pre-trained machine learning regression model; determines the second position coordinates of the vehicle key based on the distance between the vehicle key and multiple position measurement anchor points of the vehicle, and a triangulation algorithm; and determines the final position coordinates of the vehicle key relative to the vehicle based on the first and second position coordinates. Regarding the position of the vehicle key on the side of the vehicle, the results of the pre-trained machine learning regression model and the triangulation algorithm are combined to determine the position of the vehicle key. Position measurement To improve stability and increase accuracy.

[0056] Figure 6 is a flowchart of Embodiment 3 of the vehicle key position measurement method according to the embodiment of the present invention. As shown in Figure 6, the vehicle key position measurement method according to the present invention further includes steps S105 to S107 on top of Embodiment 1 described above. In S105, if the first position indicates that the vehicle key is in the vehicle's far field, the final position coordinates of the vehicle key relative to the vehicle are determined based on the distance between the vehicle key and multiple position-measuring anchor points of the vehicle, and a triangulation algorithm.

[0057] In this step, as shown in A1 in Figure 3, if the initial determination of the vehicle key indicates that the first position is in the vehicle's far-field, the final position coordinates of the vehicle key relative to the vehicle are determined based on the distance between the vehicle key and multiple position-measuring anchor points of the vehicle, and a triangulation algorithm. The specific processing steps are as described in step S10 of the above embodiment. 4 The process is the same as in step 2, and will not be explained again here.

[0058] In S106, if the second position indicates that the vehicle key is inside the vehicle, it is determined that the vehicle key is in a first sub-region of the vehicle based on the distance between the vehicle key and multiple position-measuring anchor points of the vehicle, and a pre-trained first machine learning multi-class classifier.

[0059] In S107, if the third position indicates that the vehicle key is on the vehicle body, it is determined that the vehicle key is in a second sub-region of the vehicle based on the distance between the vehicle key and multiple position-measuring anchor points of the vehicle, and a pre-trained second machine learning multi-class classifier.

[0060] In steps S106 and S107, the vehicle area is divided hierarchically, with the second location indicating that the vehicle key is inside the vehicle and the third location indicating that the vehicle key is on the vehicle body. In both cases, the vehicle key is subject to interference due to insufficient transmission of high-frequency signals. To accurately determine the specific location of the vehicle key, a dataset of the vehicle interior range and a dataset of the vehicle body range are collected in advance. When the second location indicates that the vehicle key is inside the vehicle, a machine learning multi-class classifier is used based on the dataset within the vehicle interior range, as shown in A2 in Figure 3. of A first pre-trained machine learning multi-class classifier is obtained, and the distance between the vehicle key and multiple anchor points for vehicle position measurement is input to the first pre-trained machine learning multi-class classifier, which outputs a second category value, the second category value representing a numerical value corresponding to indicating that the vehicle key is in a first sub-region of the vehicle, the first sub-region including the driver's seat area, passenger seat area, rear seat area, or trunk area. If the third position indicates that the vehicle key is in the vehicle body, the machine learning multi-class classifier, based on the dataset within the vehicle body range, as shown in A3 in Figure 3, of A second pre-trained machine learning multi-class classifier is obtained by training it, and the distance between the vehicle key and multiple anchor points for vehicle position measurement is input to the second pre-trained machine learning multi-class classifier to output a third category value, the third category value being a numerical value corresponding to indicating that the vehicle key is in a second sub-region of the vehicle, the second sub-region including the hood, roof, or back door.

[0061] In step S106, the vehicle's internal space is narrow, making it very difficult to accurately determine the location of the vehicle key. To improve accuracy, a dataset is collected in advance from within the front cabin and trunk area of ​​the vehicle's interior, as shown in A2 in Figure 3, to train a machine learning classifier. The trained model then determines whether the vehicle key is in the front cabin or trunk area. The specific process is the same as that of the machine learning classifier described above and will not be explained again here.

[0062] In step S107, the vehicle body also includes a certain predetermined distance above the vehicle body, for example, a certain predetermined distance above the vehicle engine hood, the vehicle roof, or the trunk area.

[0063] In one specific embodiment, taking as an example that the numerical value corresponding to the driver's seat area is 3, the numerical value corresponding to the passenger seat area is 4, the numerical value corresponding to the rear seat area is 5, and the numerical value corresponding to the trunk area is 6, if the output is 3, it is determined that the vehicle key is in the driver's seat area of ​​the vehicle; if the output is 4, it is determined that the vehicle key is in the passenger seat area of ​​the vehicle; if the output is 5, it is determined that the vehicle key is in the rear seat area of ​​the vehicle; and if the output is 6, it is determined that the vehicle key is in the trunk area of ​​the vehicle.

[0064] In this embodiment, the vehicle key position measurement method determines the final position coordinates of the vehicle relative to the vehicle based on the distance between the vehicle key and multiple position measurement anchor points of the vehicle, and a triangulation algorithm, if the first position indicates that the vehicle key is in the vehicle's far field. If the second position indicates that the vehicle key is inside the vehicle, it is determined that the vehicle key is in a first sub-region of the vehicle based on the distance between the vehicle key and multiple position measurement anchor points of the vehicle, and a pre-trained first machine learning multi-class classifier. If the third position indicates that the vehicle key is on the vehicle body, it is determined that the vehicle key is in a second sub-region of the vehicle based on the distance between the vehicle key and multiple position measurement anchor points of the vehicle, and a pre-trained second machine learning multi-class classifier. The identifiability and accuracy of vehicle key position measurement are improved by hierarchically dividing the vehicle's region.

[0065] Figure 7 is a flowchart of Embodiment 4 of the vehicle key position measurement method according to an embodiment of the present invention. As shown in Figure 7, the above Embodiment 1 further includes steps S108 to S109 before step S101. In S108, a distance measurement signal is acquired between the vehicle key and multiple anchor points for position measurement of the vehicle.

[0066] In this step, after the vehicle key and the vehicle are connected in a communicative manner, the position measuring devices installed at multiple position measuring anchor points of the vehicle activate the distance measuring operation, the vehicle key transmits distance measuring signals to the multiple position measuring anchor points, and the vehicle acquires distance measuring signals between the vehicle key and the multiple position measuring anchor points of the vehicle.

[0067] In S109, the distance between the vehicle key and multiple anchor points for position measurement of the vehicle is determined based on the distance measurement signal.

[0068] In this step, after the vehicle acquires a range measurement signal, the distance between the vehicle key and multiple anchor points for vehicle position measurement is obtained by multiplying the propagation time by the speed of light.

[0069] The vehicle key position measurement method according to this embodiment acquires a distance measurement signal between the vehicle key and multiple position measurement anchor points on the vehicle, determines the distance between the vehicle key and the multiple position measurement anchor points on the vehicle based on the distance measurement signal, and realizes wireless communication between the vehicle key and the vehicle.

[0070] As shown in Figure 8, when the vehicle key enters the S6 area, the welcome lights and welcome song are activated. Furthermore, based on the left / right position information of the key, the ground illumination on the user's side may be illuminated. When the vehicle key enters the S2 area... ( Within the contour area (0-2 meters), there are relatively many functional areas, such as the left front door, left rear door, right front door, right rear door, left tailgate, and right tailgate. In the left and right door areas, the corresponding door is opened, and in the tailgate area, a dwell trajectory pattern of the user holding the key can be formed to open the tailgate, lights, etc., based on the order and time the user stayed in the tailgate sub-area. High-precision positioning capabilities based on UWB make it possible to define different functions for different vehicle models, the range of sub-functional areas that realize those functions, and the description of operation sequences that realize different functions.

[0071] In the vehicle key position measurement method according to the embodiment of the present invention, particular attention should be paid to the machine learning classifier related to the above embodiment. This includes the need to collect separate training sample sets for each machine learning-neural network classifier with different functions, train the networks individually, and obtain dedicated network weight values. The area from which training sample data is collected must coincide with the area where classification is actually required. For example, in the case of a classifier that determines whether a vehicle is inside or outside, data should be collected at each location inside the vehicle (front compartment + trunk) to form the inside sample, and data should be collected at each location outside the vehicle (including the front engine hood, trunk lid, outside of the vehicle window, vehicle roof, and various locations within different ranges of 0-1 meter, 1-2 meters, 2-3 meters, and 3-6 meters outside the contour shown in Figure 4, as well as a certain height range) to form the outside sample. After training, the weight values ​​of the network should be obtained. The hyperparameters (number of hidden layers, number of nodes in each layer, etc.) of classifier networks with different functions should be experimentally set based on the requirements of metrics such as identification accuracy, and may be the same or different.

[0072] Figure 9 is a schematic diagram of the structure of Embodiment 1 of the vehicle key position measuring device according to an embodiment of the present invention. As shown in Figure 9, the vehicle key position measuring device 200 is A first determination module 201 for determining a first position of a vehicle key based on the distance between the vehicle key and multiple anchor points for position measurement of the vehicle, and a preset distance threshold, wherein the first position indicates that the vehicle key is in the vehicle's far-field or vehicle's near-field, A second decision module 202 for determining a second position of a vehicle key based on the distance between the vehicle key and multiple position-measuring anchor points of the vehicle, and a pre-trained first machine learning binary classifier, wherein the first position indicates that the vehicle key is in the vehicle's near field, and the second position indicates that the vehicle key is outside or inside the vehicle, and the first machine learning binary classifier is an algorithm for determining the position of the vehicle key based on the distance between the vehicle key and position-measuring anchor points, which is pre-trained on a dataset collected within the range of the vehicle's near field. A third decision module 203 for determining a third position of a vehicle key, where the second position indicates that the vehicle key is outside the vehicle, based on the distance between the vehicle key and multiple position-measuring anchor points of the vehicle, and a pre-trained second machine learning binary classifier, wherein the third position indicates that the vehicle key is to the side or on the vehicle body, and the second machine learning binary classifier is a pre-trained algorithm for determining the position of the vehicle key based on the distance between the vehicle key and position-measuring anchor points, based on a dataset collected in the area outside the vehicle. If the third position indicates that the vehicle key is to the side of the vehicle, the fourth decision module 204 is for determining the final position coordinates of the vehicle key relative to the vehicle based on the distance between the vehicle key and multiple position-measuring anchor points of the vehicle, a pre-trained machine learning regression model, and a pre-configured triangulation algorithm, wherein the machine learning regression model is an algorithm for determining the position of the vehicle key based on the distance between the vehicle key and position-measuring anchor points, which is pre-trained on a dataset collected in the range to the side of the vehicle.

[0073] Figure 10 is a schematic diagram of the structure of Embodiment 2 of the vehicle key position measuring device according to an embodiment of the present invention. As shown in Figure 10, the fourth determination module 204 is A first determination unit 2041 for determining the first position coordinates of a vehicle key based on the distance between the vehicle key and multiple anchor points for position measurement of the vehicle, and a pre-trained machine learning regression model, A second determination unit 2042 for determining the second position coordinates of the vehicle key based on the distance between the vehicle key and multiple anchor points for position measurement of the vehicle, and a triangulation algorithm, The system includes a third determination unit 2043 for determining the final position coordinates of the vehicle key relative to the vehicle, based on first and second position coordinates.

[0074] Figure 11 is a schematic diagram of the structure of Embodiment 3 of the vehicle key position measuring device according to an embodiment of the present invention. As shown in Figure 11, the vehicle key position measuring device 200 is If the first position indicates that the vehicle key is in the vehicle's far field, a fifth determination module 205 determines the final position coordinates of the vehicle key relative to the vehicle based on the distance between the vehicle key and multiple position-measuring anchor points of the vehicle, and a triangulation algorithm. If the second location indicates that the vehicle key is inside the vehicle, the sixth decision module 206 determines that the vehicle key is in a first sub-region of the vehicle based on the distance between the vehicle key and multiple position-measuring anchor points of the vehicle, and a pre-trained first machine learning multi-class classifier, wherein the first sub-region includes the driver's seat area, passenger seat area, rear seat area, or trunk area, and the first machine learning multi-class classifier is an algorithm for determining the location of the vehicle key based on the distance between the vehicle key and position-measuring anchor points, which is pre-trained on a dataset collected within the interior of the vehicle. If the third location indicates that the vehicle key is on the vehicle body, a seventh decision module 207 for determining that the vehicle key is in a second sub-region of the vehicle, based on the distance between the vehicle key and multiple position-measuring anchor points of the vehicle, and a pre-trained second machine learning multi-class classifier, wherein the second sub-region includes the hood, roof, or back door, and the second machine learning multi-class classifier is a pre-trained algorithm for determining the location of the vehicle key based on the distance between the vehicle key and position-measuring anchor points, based on a dataset collected within the vehicle body. An acquisition module 208 for acquiring distance measurement signals between the vehicle key and multiple anchor points for vehicle position measurement, The system further includes an eighth determination module 209 for determining the distance between a vehicle key and multiple anchor points for position measurement of the vehicle, based on a distance measurement signal.

[0075] The vehicle key position measuring device according to this embodiment is used to perform the vehicle key position measuring method in any of the above-described embodiments, and its implementation principle and technical effects are similar and will not be described again here.

[0076] Figure 12 is a schematic diagram of the structure of a vehicle according to an embodiment of the present invention. As shown in Figure 12, the vehicle includes a vehicle body 300, a memory unit 301, an electronic control unit 302, and a plurality of position measuring anchor points 303. Computer execution instructions are stored in the memory unit 301. The electronic control unit 302 implements the method in any of the embodiments by executing computer execution instructions stored in the memory unit 301. Multiple position-measuring anchor points 303 are used to enable communication between the vehicle and the vehicle key.

[0077] Embodiments of the present invention further provide a computer-readable storage medium in which computer execution instructions are stored, and which are used to implement the method in any embodiment when executed by a processor.

[0078] The computer-readable storage media described above can be realized by any type of volatile or non-volatile storage device, or a combination thereof. Examples include static random-access memory, electrically erasable programmable read-only memory, erasable programmable read-only memory, programmable read-only memory, read-only memory, magnetic storage devices, flash memory, magnetic disks, and optical disks. The readable storage medium can be any available medium accessible by a general-purpose or dedicated computer.

[0079] By selectively coupling a readable storage medium to the processor, the processor can be enabled to read information from and write information to the readable storage medium. Of course, the readable storage medium may also be a component of the processor. The processor and the readable storage medium may be located within an Application Specific Integrated Circuit (ASIC). Naturally, the processor and the readable storage medium may also exist as separate components within a device.

[0080] Embodiments of the present application further provide a computer program product, the computer program product comprising a computer program stored in a computer-readable storage medium, the computer program being read from the computer-readable storage medium by at least one processor, and the at least one processor being able to implement the technical invention according to any embodiment of the above method when executing the computer program.

[0081] A person skilled in the art will readily conceive of other embodiments of the Application after considering and practicing the inventions disclosed herein. The Application is intended to encompass all variations, uses, or adaptive modifications of the Application, including common or customary technical means known in the Art and not disclosed herein, in accordance with the general principles of the Application. The Specification and Examples are to be considered merely illustrative, and the true scope and spirit of the Application are indicated by the appended Claims.

[0082] It should be understood that this application is not limited to the exact configuration described above and shown in the drawings, and that various modifications and changes are possible without exceeding its scope. The scope of this application is limited only by the attached claims.

[0083] <Cross-reference of related applications> This application claims priority to the Chinese patent application filed with the China National Patent Office on June 16, 2023, with application number 2023107192340, titled "Method, apparatus, vehicle, and storage medium for measuring the position of a vehicle key," the entire contents of which are incorporated herein by reference.

Claims

1. A method for measuring the position of a vehicle key applied to a vehicle, Based on the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle, and a preset distance threshold, the first position of the vehicle key is determined, and the first position indicates that the vehicle key is in the vehicle's far-field or vehicle's near-field. If the first position indicates that the vehicle key is in the vehicle's immediate vicinity, a second position of the vehicle key is determined based on the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle, and a pre-trained first machine learning binary classifier, wherein the second position indicates that the vehicle key is outside or inside the vehicle, and the first machine learning binary classifier is an algorithm for determining the position of the vehicle key based on the distance between the vehicle key and the position-measuring anchor points, which is pre-trained based on a dataset collected within the range of the vehicle's immediate vicinity. If the second position indicates that the vehicle key is outside the vehicle, a third position of the vehicle key is determined based on the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle, and a pre-trained second machine learning binary classifier, wherein the third position indicates that the vehicle key is to the side of the vehicle or on the vehicle body, and the second machine learning binary classifier is an algorithm for determining the position of the vehicle key based on the distance between the vehicle key and the position-measuring anchor points, which is pre-trained based on a dataset collected in the area outside the vehicle. A method for measuring the position of a vehicle key, characterized in that, if the third position indicates that the vehicle key is to the side of the vehicle, the final position coordinates of the vehicle key relative to the vehicle are determined based on the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle, a pre-trained machine learning regression model, and a pre-configured triangulation algorithm, the machine learning regression model is an algorithm for determining the position of the vehicle key based on the distance between the vehicle key and the position-measuring anchor points, which is pre-trained based on a dataset collected in the range to the side of the vehicle.

2. If the third position indicates that the vehicle key is located to the side of the vehicle, then determining the final position coordinates of the vehicle key relative to the vehicle based on the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle, a pre-trained machine learning regression model, and a pre-configured triangulation algorithm, The first position coordinates of the vehicle key are determined based on the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle, and the pre-trained machine learning regression model. The second position coordinate of the vehicle key is determined based on the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle, and the triangulation algorithm. The method according to claim 1, characterized in that it includes determining the final position coordinates of the vehicle key relative to the vehicle based on the first position coordinates and the second position coordinates.

3. The aforementioned method, The method according to 1 or 2, further comprising determining the final position coordinates of the vehicle relative to the vehicle based on the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle, and the triangulation algorithm, if the first position indicates that the vehicle key is in the vehicle's far field.

4. The aforementioned method, The method according to 1 or 2, wherein if the second position indicates that the vehicle key is inside the vehicle, the method further includes determining that the vehicle key is in a first sub-region of the vehicle based on the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle, and a pre-trained first machine learning multi-class classifier, the first sub-region including the driver's seat area, the passenger seat area, the rear seat area, or the trunk area, and the first machine learning multi-class classifier is a pre-trained algorithm for determining the position of the vehicle key based on the distance between the vehicle key and position-measuring anchor points, based on a dataset collected within the interior of the vehicle.

5. The aforementioned method, The method according to 1 or 2, wherein if the third position indicates that the vehicle key is on the vehicle body, the method further includes determining that the vehicle key is in a second sub-region of the vehicle based on the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle, and a pre-trained second machine learning multi-class classifier, the second sub-region including the hood, roof, or back door, and the second machine learning multi-class classifier is a pre-trained algorithm for determining the position of the vehicle key based on the distance between the vehicle key and position-measuring anchor points, based on a dataset collected over the range of the vehicle body.

6. Before determining the first position of the vehicle key based on the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle and a preset distance threshold, the method: To acquire a distance measurement signal between the vehicle key and a plurality of anchor points for position measurement of the vehicle, The method according to claim 1, further comprising determining the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle based on the distance measurement signal.

7. A vehicle key position measuring device, It includes a first decision module, a second decision module, a third decision module, and a fourth decision module, The first determination module is used to determine a first position of the vehicle key based on the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle, and a preset distance threshold, and the first position is used to indicate that the vehicle key is in the vehicle's far-field or near-field. The second determination module is used to determine a second position of the vehicle key based on the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle, and a pre-trained first machine learning binary classifier, where the first position indicates that the vehicle key is in the vehicle's near field, and the second position indicates that the vehicle key is outside or inside the vehicle, and the first machine learning binary classifier is a pre-trained algorithm for determining the position of the vehicle key based on the distance between the vehicle key and the position-measuring anchor points, based on a dataset collected within the range of the vehicle's near field. The third decision module is used to determine a third position of the vehicle key based on the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle, and a pre-trained second machine learning binary classifier, where the second position indicates that the vehicle key is outside the vehicle, and the third position indicates that the vehicle key is to the side of the vehicle or on the vehicle body, and the second machine learning binary classifier is a pre-trained algorithm for determining the position of the vehicle key based on the distance between the vehicle key and the position-measuring anchor points, based on a dataset collected in the area outside the vehicle. The vehicle key position measuring device is characterized in that, when the third position indicates that the vehicle key is to the side of the vehicle, the fourth determination module is used to determine the final position coordinates of the vehicle key relative to the vehicle based on the distance between the vehicle key and a plurality of position measuring anchor points of the vehicle, a pre-trained machine learning regression model, and a pre-configured triangulation algorithm, wherein the machine learning regression model is an algorithm for determining the position of the vehicle key based on the distance between the vehicle key and the position measuring anchor points, which is pre-trained based on a dataset collected in the range to the side of the vehicle.

8. The aforementioned fourth decision module is, A first determination unit for determining the first position coordinates of the vehicle key based on the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle, and the pre-trained machine learning regression model, A second determination unit for determining the second position coordinates of the vehicle key based on the distance between the vehicle key and a plurality of position-measuring anchor points of the vehicle, and the triangulation algorithm, The apparatus according to claim 7, further comprising a third determination unit for determining the final position coordinates of the vehicle key relative to the vehicle based on the first and second position coordinates.

9. A vehicle comprising a vehicle body, a memory unit installed on the vehicle body, an electronic control unit, and a plurality of anchor points for position measurement, Computer execution instructions are stored in the aforementioned storage unit. The vehicle is characterized in that the electronic control unit implements the method according to any one of claims 1 to 6 by executing computer execution instructions stored in the memory unit.

10. A computer-readable storage medium, wherein a computer execution instruction is stored in the computer-readable storage medium, and the computer execution instruction is used to realize the vehicle key position measurement method described in any one of claims 1 to 6 when executed by a processor.

Images