Vehicle key positioning method and device, vehicle, and storage medium

Abstract

The application provides a vehicle key positioning method and device, a vehicle and a storage medium. According to the distance between the vehicle key and the plurality of positioning anchors of the vehicle, the distance threshold value is preset, the first position of the key is determined, the key is in the near field of the vehicle, the second position of the key is determined according to the distance, the first machine learning binary classifier is pre-trained, the key is outside the vehicle, the third position of the key is determined according to the distance, the second machine learning binary classifier is pre-trained, the key is on the side of the vehicle, the final position coordinates of the key relative to the vehicle are determined according to the distance, the machine learning regression model is pre-trained, and the triangular positioning algorithm is pre-set. By dividing the vehicle area into different hierarchical regions and determining the final position in different ways, the precise positioning of the vehicle key is realized.

Description

Technical Field

[0001] This application relates to the field of automotive electronics technology, and in particular to a vehicle key positioning method, device, vehicle, and storage medium. Background Technology

[0002] With technological advancements, the original mechanical car key has gradually evolved into a smart key for contactless entry and ignition. The application of security-enhanced Ultra-Wide Band (UWB) wireless access technology to car keys has ushered in a new era of comprehensively utilizing the advantages of various wireless technologies. While UWB wireless access technology offers advantages such as protection against relay attacks and high ranging and positioning accuracy, it is also susceptible to reflection, diffraction, and multipath interference from the vehicle itself or surrounding conductive objects, which can cause interference and affect the positioning accuracy of the car key.

[0003] In existing technologies, to avoid the above problems, machine learning methods are usually used to locate car keys. However, machine learning networks are large in scale, have a large computational load, and have high requirements for software and hardware. The actual environment outside the car is very different from the ideal environment when collecting training sample data, which leads to large errors in actual external positioning. The large range of external space and the small internal space of the car result in a large difference in the number of training sample sets inside and outside the car, which also leads to problems such as low recognition rate inside the car.

[0004] In conclusion, how to accurately and reliably locate car keys is a problem that urgently needs to be solved in this field. Summary of the Invention

[0005] This application provides a vehicle key positioning method, device, vehicle, and storage medium to solve the problem of how to accurately and stably locate a car key.

[0006] Firstly, this application provides a vehicle key positioning method, applied to a vehicle, comprising:

[0007] Based on the distance between the vehicle key and multiple positioning anchor points of the vehicle, and a preset distance threshold, a first position of the vehicle key is determined. The first position is used to indicate whether the vehicle key is in the far field or near field of the vehicle.

[0008] If the first position indicates that the vehicle key is in the near field of the vehicle, a second position of the vehicle key is determined by a pre-trained first machine learning binary classifier based on the distance between the vehicle key and multiple positioning anchor points of the vehicle. The second position is used to indicate whether the vehicle key is outside or inside the vehicle. The first machine learning binary classifier is an algorithm pre-trained based on a dataset collected within the near field of the vehicle to determine the position of the vehicle key based on the distance between the vehicle key and the positioning anchor points.

[0009] If the second position indicates that the vehicle key is outside the vehicle, a third position of the vehicle key is determined by a pre-trained second machine learning binary classifier based on the distance between the vehicle key and multiple positioning anchor points of the vehicle. The third position is used to indicate that the vehicle key is on the side or body of the vehicle. The second machine learning binary classifier is an algorithm pre-trained based on a dataset collected outside the vehicle to determine the position of the vehicle key based on the distance between the vehicle key and the positioning anchor points.

[0010] 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 multiple positioning anchor points of the vehicle, a pre-trained machine learning regression model, and a pre-set triangulation algorithm. The machine learning regression model is an algorithm pre-trained based on a dataset collected within the range to the side of the vehicle to determine the position of the vehicle key based on the distance between the vehicle key and the positioning anchor points.

[0011] In conjunction with the first aspect, in some embodiments, if the third position indicates that the vehicle key is located to the side of the vehicle, determining the final position coordinates of the vehicle key relative to the vehicle based on the distance between the vehicle key and multiple positioning anchor points of the vehicle, a pre-trained machine learning regression model, and a pre-set triangulation algorithm includes:

[0012] Based on the distance between the vehicle key and multiple positioning anchor points of the vehicle, the pre-trained machine learning regression model determines the first position coordinates of the vehicle key;

[0013] Based on the distance between the vehicle key and multiple positioning anchor points of the vehicle, the triangulation algorithm determines the second position coordinates of the vehicle key;

[0014] Based on the first position coordinates and the second position coordinates, the final position coordinates of the vehicle key relative to the vehicle are determined.

[0015] In conjunction with the first aspect, in some embodiments, the method further includes:

[0016] If the first position indicates that the vehicle key is in the far field of the vehicle, the triangulation algorithm determines the final position coordinates of the vehicle key relative to the vehicle based on the distance between the vehicle key and multiple positioning anchor points of the vehicle.

[0017] In conjunction with the first aspect, in some embodiments, the method further includes:

[0018] If the second location indicates that the vehicle key is inside the vehicle, a pre-trained first machine learning multi-classifier determines that the vehicle key is located in a first sub-region of the vehicle based on the distance between the vehicle key and multiple positioning anchor points of the vehicle. The first sub-region includes the driver's area, passenger area, rear seat area, or trunk. The first machine learning multi-classifier is an algorithm pre-trained based on a dataset collected within the vehicle's interior area to determine the location of the vehicle key based on the distance between the vehicle key and the positioning anchor points.

[0019] In conjunction with the first aspect, in some embodiments, the method further includes:

[0020] If the third location indicates that the vehicle key is on the vehicle body, a pre-trained second machine learning multi-classifier determines that the vehicle key is located in a second sub-region of the vehicle based on the distance between the vehicle key and multiple positioning anchor points of the vehicle. The second sub-region includes the hood, roof, or rear cover of the vehicle body. The second machine learning multi-classifier is an algorithm pre-trained based on a dataset collected within the vehicle body area to determine the location of the vehicle key based on the distance between the vehicle key and the positioning anchor points.

[0021] In conjunction with the first aspect, in some embodiments, before determining the first position of the vehicle key based on the distance between the vehicle key and multiple positioning anchor points of the vehicle and a preset distance threshold, the method further includes:

[0022] Acquire the distance measurement signal between the vehicle key and multiple positioning anchor points of the vehicle;

[0023] Based on the ranging signal, the distance between the vehicle key and multiple positioning anchor points of the vehicle is determined.

[0024] Secondly, this application provides a vehicle key locating device, comprising:

[0025] The first determining module is used to determine the first position of the vehicle key based on the distance between the vehicle key and multiple positioning anchor points of the vehicle and a preset distance threshold. The first position is used to indicate whether the vehicle key is in the far field or near field of the vehicle.

[0026] The second determining module is used to determine the second position of the vehicle key if the first position indicates that the vehicle key is in the near field of the vehicle, based on the distance between the vehicle key and multiple positioning anchor points of the vehicle and a pre-trained first machine learning binary classifier. The second position is used to indicate whether the vehicle key is outside or inside the vehicle. The first machine learning binary classifier is an algorithm pre-trained based on a dataset collected in the near field of the vehicle to determine the position of the vehicle key based on the distance between the vehicle key and the positioning anchor points.

[0027] The third determining module is used to determine the third position of the vehicle key if the second position indicates that the vehicle key is outside the vehicle, based on the distance between the vehicle key and multiple positioning anchor points of the vehicle and a pre-trained second machine learning binary classifier. The third position is used to indicate that the vehicle key is on the side or body of the vehicle. The second machine learning binary classifier is an algorithm pre-trained based on a dataset collected outside the vehicle to determine the position of the vehicle key based on the distance between the vehicle key and the positioning anchor points.

[0028] The fourth determining module is used to determine the final position coordinates of the vehicle key relative to the vehicle if the third position indicates that the vehicle key is on the side of the vehicle, based on the distance between the vehicle key and multiple positioning anchor points of the vehicle, a pre-trained machine learning regression model and a pre-set triangulation algorithm.

[0029] In conjunction with the second aspect, in some embodiments, the fourth determining module includes:

[0030] The first determining unit is used to determine the first position coordinates of the vehicle key based on the distance between the vehicle key and multiple positioning anchor points of the vehicle, and the pre-trained machine learning regression model. The machine learning regression model is an algorithm trained in advance based on a dataset collected in the side range of the vehicle to determine the position of the vehicle key based on the distance between the vehicle key and the positioning anchor points.

[0031] The second determining unit is used to determine the second position coordinates of the vehicle key based on the distance between the vehicle key and multiple positioning anchor points of the vehicle, and the triangulation algorithm.

[0032] The third determining unit is used to determine the final position coordinates of the vehicle key relative to the vehicle based on the first position coordinates and the second position coordinates.

[0033] In conjunction with the second aspect, in some embodiments, the apparatus further includes:

[0034] The fifth determining 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 multiple positioning anchor points of the vehicle and the vehicle, according to the triangulation algorithm, if the first position indicates that the vehicle key is in the far field of the vehicle.

[0035] In conjunction with the second aspect, in some embodiments, the apparatus further includes:

[0036] The sixth determining module is used to determine, if the second location indicates that the vehicle key is inside the vehicle, that the vehicle key is located in a first sub-region of the vehicle based on the distance between the vehicle key and multiple positioning anchor points of the vehicle, using a pre-trained first machine learning multi-classifier. The first sub-region includes the driver's area, passenger area, rear seat area, or trunk. The first machine learning multi-classifier is an algorithm pre-trained based on a dataset collected within the vehicle's interior area to determine the location of the vehicle key based on the distance between the vehicle key and the positioning anchor points.

[0037] In conjunction with the second aspect, in some embodiments, the apparatus further includes:

[0038] The seventh determining module is used to determine, if the third location indicates that the vehicle key is on the vehicle body, that the vehicle key is located in a second sub-region of the vehicle based on the distance between the vehicle key and multiple positioning anchor points of the vehicle, using a pre-trained second machine learning multi-classifier. The second sub-region includes the hood, roof, or rear cover of the vehicle body. The second machine learning multi-classifier is an algorithm pre-trained based on a dataset collected within the vehicle body area to determine the location of the vehicle key based on the distance between the vehicle key and the positioning anchor points.

[0039] In conjunction with the second aspect, in some embodiments, prior to the first determining module, the apparatus further includes:

[0040] The acquisition module is used to acquire the distance measurement signal between the vehicle key and multiple positioning anchor points of the vehicle;

[0041] The eighth determining module is used to determine the distance between the vehicle key and multiple positioning anchor points of the vehicle based on the ranging signal.

[0042] Thirdly, this application also provides a vehicle, including: a vehicle body, a storage unit disposed in the vehicle body, an electronic control unit, and a plurality of positioning anchor points;

[0043] The storage unit stores computer-executed instructions;

[0044] The electronic control unit executes the computer execution instructions stored in the storage unit to implement the method described in any of the above aspects.

[0045] Fourthly, this application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the methods described in any of the above aspects.

[0046] The vehicle key positioning method, device, vehicle, and storage medium provided in this application communicate with multiple positioning anchor points installed on the vehicle body to obtain the distance between the vehicle key and the multiple positioning anchor points. Based on the distance between the vehicle key and the multiple positioning anchor points, and a preset distance threshold, a first position of the vehicle key is determined. If the first position indicates that the vehicle key is in the near field of the vehicle, a second position of the vehicle key is determined based on the distance between the vehicle key and the multiple positioning anchor points using a pre-trained first machine learning binary classifier. 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 the multiple positioning anchor points using a pre-trained second machine learning binary classifier. 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 the multiple positioning anchor points using a pre-trained machine learning regression model and a pre-set triangulation algorithm. By dividing the vehicle domain into multiple hierarchical regions, the success rate and accuracy of vehicle key position recognition are improved. Furthermore, by using a machine learning regression model and a triangulation algorithm to fuse and revise the position coordinates of the vehicle key, accurate and stable recognition of the vehicle key is achieved. Attached Figure Description

[0047] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0048] Figure 1 This is an application scenario diagram of the vehicle key positioning method provided in the embodiments of this application;

[0049] Figure 2 A flowchart illustrating an embodiment of the vehicle key location method provided in this application;

[0050] Figure 3 This is a schematic diagram illustrating the specific process of the vehicle key positioning method provided in the embodiments of this application;

[0051] Figure 4 This is a schematic diagram of vehicle area division provided in an embodiment of this application;

[0052] Figure 5 A flowchart illustrating a second embodiment of the vehicle key location method provided in this application;

[0053] Figure 6 A flowchart illustrating a third embodiment of the vehicle key location method provided in this application;

[0054] Figure 7 A flowchart illustrating Embodiment 4 of the vehicle key positioning method provided in this application;

[0055] Figure 8 This is a schematic diagram of the vehicle functional area division provided in an embodiment of this application;

[0056] Figure 9 This is a schematic diagram of the structure of a vehicle key locating device according to an embodiment of this application;

[0057] Figure 10 This is a schematic diagram of the structure of a second embodiment of the vehicle key locating device provided in this application.

[0058] Figure 11 This is a schematic diagram of the structure of a third embodiment of the vehicle key locating device provided in this application.

[0059] Figure 12 This is a schematic diagram of the vehicle structure provided in an embodiment of this application.

[0060] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0061] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0062] With the continuous development of the automotive industry, the form and usage of keys have undergone tremendous changes. Today, the most common car key is the smart key. Smart keys come in various forms, and the key itself is no longer the traditional key; for example, a card key can be used to unlock the vehicle simply by being scanned at the door. Alternatively, the key can be linked to a smart device, eliminating the need to carry a physical key next time you leave the house, allowing you to complete all operations with just the smart device. Communication between smart keys and vehicles typically utilizes secure-enhanced Ultra-Wide Band (UWB) wireless access technology. UWB offers advantages such as protection against relay attacks and high ranging and positioning accuracy. For smart key positioning, machine learning methods are commonly used to collect a large number of training samples from different areas outside and inside the vehicle. The trained model is then used for positioning. However, the real-world environment outside the vehicle differs significantly from the ideal environment during training sample data collection, leading to large errors in actual external positioning. Furthermore, the vast external space and confined internal space result in a significant difference in the number of training samples between the two, leading to low recognition rates inside the vehicle. If the least squares method is used for smart key positioning, the positioning output becomes unstable and inaccurate if the smart key is near or inside the vehicle due to obstructions from the vehicle body and multiple reflections of radio waves inside the vehicle.

[0063] To address the aforementioned problems, this application provides a vehicle key positioning method that achieves accurate and stable vehicle key positioning. Specifically, for smart key positioning, a common approach is to train a machine learning model using a large number of vehicle-domain training samples, and then use the trained model for positioning. However, due to the variability of the actual external environment and the significant difference in the amount of data collected inside and outside the vehicle, problems such as low recognition rates inside the vehicle arise. If the least squares method is used for smart key positioning, factors such as vehicle body obstruction and multiple reflections of radio waves inside the vehicle lead to unstable positioning outputs and low positioning accuracy both around and inside the vehicle. Considering these problems, the inventors investigated whether it is possible to perform zonal positioning by comprehensively employing ranging / machine learning classification (recognition) / machine learning regression (positioning) / triangulation algorithms based on the multipath distribution and time delay spread characteristics of UWB signal propagation in different environments inside and outside the vehicle. Based on this, the technical solution of this application is proposed.

[0064] Figure 1 This is an application scenario diagram of the vehicle key positioning method provided in the embodiments of this application, such as... Figure 1 As shown, the application scenario includes at least a vehicle and a vehicle key. The vehicle has multiple positioning anchor points, as shown in the diagram. Figure 2The diagram shows UWB1, UWB2, UWB3, and UWB4. The positioning anchors UWB1, UWB2, UWB3, and UWB4 are all located outside the vehicle body, with UWB1 and UWB4 located at the two front corners of the vehicle, and UWB2 and UWB3 located at the two rear corners. The positioning anchors being located outside the vehicle body and at the four corners of the front and rear ensures that the distance measurement signal between the key and the positioning anchors is not blocked, reflected, or diffracted by the vehicle body. The positioning anchors are equipped with positioning devices that determine the distance between the anchors and the vehicle key. Alternatively, the anchors themselves can be positioning devices, which may include a UWB chip or UWB module, or a positioning device containing a BLE module or BLE chip. The vehicle key also includes a BLE module or BLE chip. The vehicle key can be a physical key or a virtual key on a user terminal. The user terminal can be a smartphone, tablet, or other smart terminal.

[0065] This application does not impose any restrictions on the specific form and type of the aforementioned physical equipment.

[0066] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0067] Figure 2 This is a flowchart illustrating an embodiment of the vehicle key positioning method provided in this application. Figure 2 As shown, the vehicle key positioning method provided in this application is applied to a vehicle and specifically includes:

[0068] S101: Determine the first position of the vehicle key based on the distance between the vehicle key and multiple positioning anchor points of the vehicle, and a preset distance threshold.

[0069] In this step, UWB wireless technology achieves communication based on electromagnetic wave propagation. Due to the different presence of conductors in different locations of the vehicle, the signal transmission effectiveness between the vehicle key and the vehicle varies. In order to accurately identify the specific location of the vehicle key and thus accurately activate the function in that area, the different locations of the vehicle are divided into layers, and the first location of the vehicle key is determined based on the distance between the vehicle key and multiple positioning anchor points of the vehicle and a preset distance threshold.

[0070] Specifically, such as Figure 3As shown, the vehicle communicates with multiple positioning anchor points installed on the vehicle via the vehicle key. It then obtains distance measurement signals between the vehicle key and these anchor points. Based on these signals, the distance between the vehicle key and the multiple anchor points is determined. The shortest distance among these distances is selected and compared with a preset distance threshold to determine the vehicle key's first position. If the shortest distance is greater than the preset distance threshold, the first position indicates the vehicle is in the far field; if the shortest distance is less than the preset distance threshold, the first position indicates the vehicle is in the near field.

[0071] In one specific implementation, such as Figure 4 As shown, taking a preset distance threshold of 3 meters and four positioning anchor points as an example, the four anchor points are respectively set at the corners of the front and rear of the vehicle. The area with a radius of 3 meters centered on each of the four anchor points is the vehicle's near field. Figure 4 The shaded area, and any area outside the shaded area, is the far field of the vehicle.

[0072] S102: If the first position indicates that the vehicle key is in the near field of the vehicle, the second position of the vehicle key is determined by a pre-trained first machine learning binary classifier based on the distance between the vehicle key and multiple positioning anchor points of the vehicle.

[0073] In this step, the distance between the vehicle key and multiple positioning anchor points of the vehicle is compared with a preset distance threshold. If the first position indicates that the vehicle key is in the near field of the vehicle, the near field of the vehicle is still a relatively complex environment, which may be outside the vehicle or inside the vehicle. Similar to the above steps, in order to accurately identify and locate, the near field of the vehicle is further divided into different levels. The distance between the vehicle key and multiple positioning anchor points of the vehicle is used as input and fed into a pre-trained first machine learning binary classifier to determine the second position of the vehicle key.

[0074] Specifically, such as Figure 3As shown, the pre-trained first machine learning binary classifier is a model trained on a dataset pre-collected within the vehicle's near-field range. The distances between the vehicle key and multiple positioning anchor points of the vehicle are input into the pre-trained first machine learning binary classifier. After processing, the output is a first category value, representing either the value corresponding to the exterior or interior of the vehicle. If the output is the value corresponding to the exterior, the second position indicates the vehicle key is outside the vehicle; if the output is the value corresponding to the interior, the second position indicates the vehicle key is inside the vehicle. The category value can be represented numerically, for example, 0 for exterior and 1 for interior. An output of 0 indicates the second position indicates the vehicle key is outside the vehicle, and an output of 1 indicates the second position indicates the vehicle key is inside the vehicle.

[0075] Optionally, by communicating between the vehicle key and multiple positioning anchors, the received signal strength indication (RSSI) corresponding to each of the multiple positioning anchors can be obtained. The RSSI is used to characterize the communication strength between the corresponding positioning anchor and the vehicle key. The RSSI and the distance between the vehicle key and the multiple positioning anchors of the vehicle are input into the pre-trained first machine learning binary classifier, which can improve the accuracy of the output.

[0076] S103: If the second position indicates that the vehicle key is outside the vehicle, the third position of the vehicle key is determined by a pre-trained second machine learning binary classifier based on the distance between the vehicle key and multiple positioning anchor points of the vehicle.

[0077] In this step, after the above steps to hierarchically divide the vehicle's near field, if the second position indicates that the vehicle key is outside the vehicle, it means that the vehicle key is located in the environment surrounding the vehicle. However, during the communication between the vehicle key and multiple positioning anchor points, when the ranging signal sent by the vehicle key is a radio frequency signal, the radio frequency signal will be reflected, multipath interference, diffraction and other phenomena when it encounters the metal parts of the vehicle body and the surrounding conductive objects such as people. These phenomena will cause positioning instability. Therefore, the external area of ​​the vehicle is further hierarchically divided, and the distance between the vehicle key and the multiple positioning anchor points of the vehicle is used as input to the pre-trained second machine learning binary classifier to determine the third position of the vehicle key.

[0078] Specifically, the pre-trained second machine learning binary classifier is a model trained on a dataset collected in advance outside the vehicle. The specific process of model analysis is the same as that of the pre-trained first machine learning binary classifier in the above steps, and will not be repeated here.

[0079] Optional, such as Figure 3 As shown, if the second position indicates that the vehicle key is outside the vehicle, a pre-trained machine learning binary classifier can be used to determine whether the vehicle key is within a preset distance range S1 around the vehicle body. If the vehicle key is outside the preset distance range S1, it means that the vehicle body has little influence on the signal transmission between the vehicle key and multiple positioning anchor points, and a triangulation algorithm is used to locate and interpret the vehicle key. If the vehicle key is within the preset distance range S1 around the vehicle body, the third position of the vehicle key is determined using the above method. For example, within 1 meter around the vehicle body, the location of the vehicle key is easily affected by the installation position of multiple positioning anchor points. If positioning anchor points are also installed inside the vehicle, the location of the vehicle key within 1 meter around the vehicle body needs to consider the distance between the vehicle key and the anchor points inside the vehicle. Therefore, before determining the third position of the vehicle key, a pre-trained machine learning binary classifier can be used to determine whether the vehicle key is within or outside 1 meter around the vehicle body.

[0080] S104: If the third position indicates that the vehicle key is on 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 positioning anchor points of the vehicle, a pre-trained machine learning regression model and a pre-set triangulation algorithm.

[0081] In this step, the vehicle's external layers are divided. If the third location indicates the vehicle key is on the side of the vehicle, due to vehicle body obstruction, a pre-trained machine learning regression model and a pre-defined triangulation algorithm are used to analyze the distances between the vehicle key and multiple positioning anchor points on the vehicle, thereby determining the final position coordinates of the vehicle key relative to the vehicle. 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.

[0082] Specifically, such as Figure 3 As shown in A3, if the vehicle key is located on any of the sides of the vehicle, the pre-trained machine learning regression model is trained based on the dataset collected within the vehicle's side range. Similar to the analysis process of a machine learning classifier, the distances between the vehicle key and multiple positioning anchor points of the vehicle are input into the pre-trained machine learning regression model. After processing, the first position coordinates of the vehicle key are output. Based on the distances between the vehicle key and multiple positioning anchor points of the vehicle, an anchor point set is determined from the multiple positioning anchor points. The distances between the positioning anchor points in the anchor point set and the key are then corrected to obtain the corrected distances. Multiple corrected distances are used for positioning interpretation to determine the second position coordinates of the vehicle key. The first position coordinates and the second position coordinates are averaged to obtain the final position coordinates of the vehicle key relative to the vehicle. Here, the anchor point set corresponds one-to-one with the side of the vehicle.

[0083] Optional, such as Figure 3As shown in A3, if the third position indicates that the vehicle key is on the side of the vehicle, the vehicle key can be located on the left, rear, or right side of the vehicle based on a pre-trained machine learning multi-classifier. After determining that the vehicle key is located on any one of the left, rear, or right side of the vehicle, the corresponding anchor point set is determined in the above manner and then the positioning calculation is performed.

[0084] The vehicle key positioning method provided in this embodiment determines the first position of the vehicle key based on the distance between the vehicle key and multiple positioning anchor points of the vehicle and a preset distance threshold. If the first position indicates that the vehicle key is in the near field of the vehicle, the second position of the vehicle key is determined by a pre-trained first machine learning binary classifier based on the distance between the vehicle key and multiple positioning anchor points of the vehicle. If the second position indicates that the vehicle key is outside the vehicle, the third position of the vehicle key is determined by a pre-trained second machine learning binary classifier based on the distance between the vehicle key and multiple positioning anchor points of 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 by a pre-trained machine learning regression model and a pre-set triangulation algorithm based on the distance between the vehicle key and multiple positioning anchor points of the vehicle. By dividing the surrounding environment of the vehicle into regional hierarchies and processing the area near the vehicle using a pre-trained machine learning regression model and a pre-set triangulation algorithm, the positioning accuracy of the vehicle key is improved and the recognition efficiency is enhanced.

[0085] Figure 5 This is a flowchart illustrating a second embodiment of the vehicle key location method provided in this application. Figure 5 As shown, based on the above embodiment, step S103 includes:

[0086] S1031: Based on the distance between the vehicle key and multiple positioning anchor points of the vehicle, a pre-trained machine learning regression model determines the first position coordinates of the vehicle key.

[0087] In this step, in order to determine the first position coordinates of the vehicle key, the distance between the vehicle key and multiple positioning anchor points of the vehicle is input into a pre-trained machine learning regression model. After processing, the first position coordinates of the vehicle key are obtained.

[0088] Specifically, the pre-trained machine learning regression model can be obtained by training on any of the following: a linear regressor, a logistic regressor, or a stepwise regressor. Taking the pre-trained machine learning regression model based on a linear regressor as an example, the distances between the vehicle key and multiple location anchor points of the vehicle are input into the pre-trained machine learning regression model. Let the input distances between the vehicle key and the multiple location anchor points of the vehicle be X, and the output be Y. Then, according to the formula... The process yields the first position coordinates of the vehicle key, where b is the intercept in the formula. For weights, b and All of these are obtained through the training process.

[0089] S1032: Based on the distance between the vehicle key and multiple positioning anchor points of the vehicle, a triangulation algorithm is used to determine the second position coordinates of the vehicle key.

[0090] In this step, for example, to reduce the inaccuracy and instability in positioning caused by multipath interference, diffraction, and reflection, the second position coordinates of the vehicle key are determined through a triangulation positioning algorithm.

[0091] Specifically, based on the distance between the vehicle key and multiple positioning anchor points of the vehicle, at least two positioning anchor points with unobstructed distance measurement signal transmission are selected as reference anchor points. If there are more than two reference anchor points and the determined reference anchor points are collinear, the two reference anchor points with the largest distance between them are determined as target reference anchor points. If there are more than two reference anchor points and the determined reference anchor points are not collinear, the two adjacent reference anchor points whose line connecting them is parallel to the ground are determined as target reference anchor points. If there are more than two reference anchor points and the determined reference anchor points are not collinear, the two adjacent reference anchor points whose sum of distances between them and the vehicle key is the smallest are determined as target reference anchor points. The line connecting the two target reference anchor points is taken as the X-axis, and one of the target reference anchor points on the X-axis is taken as the origin to determine a local coordinate system. Based on the distances between each of the two target reference anchor points and the vehicle key, as well as the distance between the two target reference anchor points, the first coordinate of the vehicle key in the local coordinate system is determined. Then, the first coordinate is transformed to obtain the second position coordinate.

[0092] S1033: Determine the final position coordinates of the vehicle key relative to the vehicle based on the first position coordinates and the second position coordinates.

[0093] In this step, after obtaining the first and second position coordinates of the vehicle key through different methods, in order to make the vehicle key positioning more accurate and stable, the first and second position coordinates are averaged to obtain the final position coordinates of the vehicle key relative to the vehicle.

[0094] The vehicle key positioning method provided in this embodiment determines the first position coordinates of the vehicle key based on the distance between the vehicle key and multiple positioning anchor points of the vehicle and a pre-trained machine learning regression model. Based on the distance between the vehicle key and multiple positioning anchor points of the vehicle and a triangulation algorithm, the second position coordinates of the vehicle key are determined. Based on the first and second position coordinates, the final position coordinates of the vehicle key relative to the vehicle are determined. For 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 fused, which improves the stability of the vehicle key and increases the accuracy.

[0095] Figure 6 This is a flowchart illustrating Embodiment 3 of the vehicle key positioning method provided in this application. Figure 6 As shown, based on the above embodiment one, the vehicle key positioning method provided in this application further includes:

[0096] S105: If the first position indicates that the vehicle key is in the far field of the vehicle, the final position coordinates of the vehicle key relative to the vehicle are determined by the triangulation algorithm based on the distance between the vehicle key and multiple positioning anchor points of the vehicle.

[0097] In this step, such as Figure 3 As shown in A1, by determining the initial level of the vehicle key, if the first position indicates that the vehicle key is in the far field of the vehicle, the final position coordinates of the vehicle key relative to the vehicle are determined by the triangulation algorithm based on the distance between the vehicle key and multiple positioning anchor points of the vehicle. The specific processing process is the same as the processing process of step S1032 in the above embodiment, and will not be repeated here.

[0098] S106: If the second position indicates that the vehicle key is inside the vehicle, the first machine learning multi-classifier, which is pre-trained, determines that the vehicle key is located in the first sub-region of the vehicle based on the distance between the vehicle key and multiple positioning anchor points of the vehicle.

[0099] S107: If the third position indicates that the vehicle key is on the vehicle body, the pre-trained second machine learning multi-classifier determines that the vehicle key is located in the second sub-region of the vehicle based on the distance between the vehicle key and multiple positioning anchor points of the vehicle.

[0100] In steps S106 and S107, by dividing the vehicle area into hierarchical levels, the second position indicates that the vehicle key is inside the vehicle, and the third position indicates that the vehicle key is on the vehicle body. When the vehicle key is inside or on the vehicle body, it is subject to interference from insufficient radio frequency signal transmission. To accurately determine the specific location of the vehicle key, datasets within the vehicle's interior and within the vehicle body are pre-collected. For the second position indicating that the vehicle key is inside the vehicle, such as... Figure 3As shown in Figure A2, a machine learning multi-classifier is trained on a dataset within the vehicle's interior to obtain a pre-trained first machine learning multi-classifier. Then, the distances between the vehicle key and multiple positioning anchor points on the vehicle are input into this pre-trained first machine learning multi-classifier, outputting a second category value. This second category value represents the numerical value corresponding to the vehicle key being located in a first sub-region of the vehicle, which may include the driver's area, passenger area, rear seat area, or trunk. For a third location indicating the vehicle key is on the vehicle body, such as... Figure 3 As shown in A3, based on the dataset within the vehicle body area, the machine learning multi-classifiers are trained separately to obtain a pre-trained second machine learning multi-classifier. Then, the distance between the vehicle key and multiple positioning anchor points of the vehicle is input into the pre-trained second machine learning multi-classifier, and the third category value is output. The third category value represents the value corresponding to the vehicle key being located in the second sub-region of the vehicle. The second sub-region includes the hood, roof, or rear cover of the vehicle.

[0101] Optionally, in step S106, the vehicle interior space is small, and the vehicle key positioning is not very accurate. In order to make the vehicle key positioning more accurate, such as... Figure 3 As shown in A2, a dataset of data collected in the front cabin and trunk of the vehicle is used to train a machine learning classifier. The trained model determines whether the vehicle key is located in the front cabin or the trunk. The specific process is the same as the aforementioned machine learning classifier process, and will not be repeated here.

[0102] In step S107, the vehicle body also includes an area with a certain reserved distance above the vehicle body, such as an area with a certain reserved distance above the vehicle hood, roof, or trunk.

[0103] In one specific implementation, taking the value corresponding to the driver's side area as 3, the value corresponding to the passenger side area as 4, the value corresponding to the rear seat area as 5, and the value corresponding to the trunk as 6 as an example, if the output is 3, it is determined that the vehicle key is located in the driver's side area of ​​the vehicle; if the output is 4, it is determined that the vehicle key is located in the passenger side area of ​​the vehicle; if the output is 5, it is determined that the vehicle key is located in the rear seat area of ​​the vehicle; and if the output is 6, it is determined that the vehicle key is located in the trunk of the vehicle.

[0104] The vehicle key positioning method provided in this embodiment, if the first position indicates that the vehicle key is in the far field of the vehicle, determines the final position coordinates of the vehicle key relative to the vehicle using a triangulation algorithm based on the distance between the vehicle key and multiple positioning anchor points of the vehicle. If the second position indicates that the vehicle key is inside the vehicle, determines that the vehicle key is located in the first sub-region of the vehicle using a pre-trained first machine learning multi-classifier based on the distance between the vehicle key and multiple positioning anchor points of the vehicle. If the third position indicates that the vehicle key is on the vehicle body, determines that the vehicle key is located in the second sub-region of the vehicle using a pre-trained second machine learning multi-classifier based on the distance between the vehicle key and multiple positioning anchor points of the vehicle. By dividing the vehicle into regional hierarchical divisions, the recognizability and accuracy of vehicle key positioning are improved.

[0105] Figure 7 This is a flowchart illustrating Embodiment 4 of the vehicle key positioning method provided in this application. Figure 7 As shown, based on the above embodiment one, before step S101, the following is also included:

[0106] S108: Obtain the distance measurement signal between the vehicle key and multiple positioning anchor points of the vehicle.

[0107] In this step, after the vehicle key establishes a communication connection with the vehicle, the positioning devices at multiple positioning anchor points on the vehicle initiate distance measurement operations. The vehicle key sends distance measurement signals to these anchor points, and the vehicle receives the distance measurement signals between the vehicle key and the multiple positioning anchor points.

[0108] S109: Determine the distance between the vehicle key and multiple positioning anchor points of the vehicle based on the ranging signal.

[0109] In this step, after the vehicle acquires the ranging signal, the distance between the vehicle key and multiple positioning anchor points of the vehicle is obtained by multiplying the propagation time by the speed of light.

[0110] The vehicle key positioning method provided in this embodiment obtains the distance measurement signal between the vehicle key and multiple positioning anchor points of the vehicle, and determines the distance between the vehicle key and multiple positioning anchor points of the vehicle based on the distance measurement signal, thereby realizing wireless communication between the vehicle key and the vehicle.

[0111] Figure 8The diagram shows that after the vehicle key enters S6, it should turn on the welcome lights / welcome music, etc., and based on the left / right information of the key, it can also turn on the puddle light on the user's side. After the vehicle key enters S2 meters (the 0-2 meter range of the outline), there are many functional areas, such as left front door / left rear door / right front door / right rear door / tailgate left / tailgate right, etc. When in the left / right door area, the corresponding door should be opened. In the tailgate area, based on the user's order and duration of presence in the tailgate sub-area, a pattern of the user's presence can be generated to open the tailgate / lights, etc. Based on the high-precision positioning capabilities of UWB, different vehicle models can define different functions, sub-functional areas to achieve these functions, and action sequences to describe the different functions.

[0112] In the vehicle key positioning method provided in this application embodiment, regarding the machine learning classifiers involved in the above embodiments, it is worth noting that different functional machine learning-neural network decision-makers need to collect training sample sets separately and train the network separately to obtain dedicated network weights; the area for collecting training sample data must be consistent with the area that needs to be actually classified. For example, for a classifier that determines whether the vehicle is inside or outside, data needs to be collected at various locations inside the vehicle (front compartment + trunk) as inside samples, and at various locations outside the vehicle (including the front hood, trunk lid, outer windows, roof, and other areas within the outline) as outside samples. Figure 4 Data is collected at various locations (0-1 meter, 1-2 meter, 2-3 meter, 3-6 meter, and a certain height range) outside the outline shown in the figure as vehicle exterior samples. After training, the weights of the network are obtained. The hyperparameters of the classifier network with different functions (such as the number of hidden layers, the number of nodes per layer, etc.) need to be set through experiments according to the requirements of indicators such as recognition accuracy. They can be the same or different.

[0113] Figure 9 This is a schematic diagram of the structure of a vehicle key locating device according to an embodiment of this application, as shown in the figure. Figure 9 As shown, the vehicle key locating device 200 includes:

[0114] The first determining module 201 is used to determine the first position of the vehicle key based on the distance between the vehicle key and multiple positioning anchor points of the vehicle and a preset distance threshold. The first position is used to indicate whether the vehicle key is in the far field or near field of the vehicle.

[0115] The second determining module 202 is used to determine the second position of the vehicle key if the first position indicates that the vehicle key is in the near field of the vehicle, based on the distance between the vehicle key and multiple positioning anchor points of the vehicle, using a pre-trained first machine learning binary classifier. The second position is used to indicate whether the vehicle key is outside or inside the vehicle. The first machine learning binary classifier is an algorithm pre-trained based on a dataset collected within the near field range of the vehicle, used to determine the position of the vehicle key based on the distance between the vehicle key and the positioning anchor points.

[0116] The third determining module 203 is used to determine the third position of the vehicle key if the second position indicates that the vehicle key is outside the vehicle, based on the distance between the vehicle key and multiple positioning anchor points of the vehicle, using a pre-trained second machine learning binary classifier. The third position indicates that the vehicle key is on the side or body of the vehicle. The second machine learning binary classifier is an algorithm pre-trained based on a dataset collected outside the vehicle to determine the position of the vehicle key based on the distance between the vehicle key and the positioning anchor points.

[0117] The fourth determining module 204 is used to determine the final position coordinates of the vehicle key relative to the vehicle if the third position indicates that the vehicle key is located on the side of the vehicle, based on the distance between the vehicle key and multiple positioning anchor points of the vehicle, a pre-trained machine learning regression model and a pre-set triangulation algorithm. The machine learning regression model is an algorithm pre-trained based on a dataset collected within the range on the side of the vehicle to determine the position of the vehicle key based on the distance between the vehicle key and the positioning anchor points.

[0118] Figure 10 This is a schematic diagram of the structure of a second embodiment of the vehicle key locating device provided in this application, as shown below. Figure 10 As shown, the fourth determining module 204 includes:

[0119] The first determining unit 2041 is used to determine the first position coordinates of the vehicle key based on the distance between the vehicle key and multiple positioning anchor points of the vehicle and a pre-trained machine learning regression model.

[0120] The second determining unit 2042 is used to determine the second position coordinates of the vehicle key based on the distance between the vehicle key and multiple positioning anchor points of the vehicle and the triangulation algorithm.

[0121] The third determining unit 2043 is used to determine the final position coordinates of the vehicle key relative to the vehicle based on the first position coordinates and the second position coordinates.

[0122] Figure 11 This is a schematic diagram of the structure of a third embodiment of the vehicle key locating device provided in this application, as shown below. Figure 11 As shown, the vehicle key locator 200 also includes:

[0123] The fifth determining module 205 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 multiple positioning anchor points of the vehicle and the vehicle, and a triangulation algorithm, if the first position indicates that the vehicle key is in the far field of the vehicle.

[0124] The sixth determining module 206 is used to determine, if the second position indicates that the vehicle key is inside the vehicle, that the vehicle key is located in a first sub-region of the vehicle based on the distance between the vehicle key and multiple positioning anchor points of the vehicle, using a pre-trained first machine learning multi-classifier. The first sub-region includes the driver's area, passenger area, rear seat area, or trunk. The first machine learning multi-classifier is an algorithm pre-trained based on a dataset collected within the vehicle's interior area to determine the location of the vehicle key based on the distance between the vehicle key and the positioning anchor points.

[0125] The seventh determination module 207 is used to determine, if the third position indicates that the vehicle key is on the vehicle body, that the vehicle key is located in a second sub-region of the vehicle based on the distance between the vehicle key and multiple positioning anchor points of the vehicle, using a pre-trained second machine learning multi-classifier. The second sub-region includes the hood, roof, or rear cover of the vehicle body. The second machine learning multi-classifier is an algorithm pre-trained based on a dataset collected within the vehicle body area to determine the position of the vehicle key based on the distance between the vehicle key and the positioning anchor points.

[0126] The acquisition module 208 is used to acquire the distance measurement signal between the vehicle key and multiple positioning anchor points of the vehicle.

[0127] The eighth determining module 209 is used to determine the distance between the vehicle key and multiple positioning anchor points of the vehicle based on the ranging signal.

[0128] The vehicle key locating device provided in this embodiment is used to execute the vehicle key locating method in any of the aforementioned method embodiments. Its implementation principle and technical effect are similar, and will not be described again here.

[0129] Figure 12 This is a structural schematic diagram of the vehicle provided in the embodiments of this application, such as... Figure 12 As shown, the vehicle includes: a vehicle body 300, a storage unit 301, an electronic control unit 302, and multiple positioning anchor points 303;

[0130] Storage unit 301 stores computer-executed instructions.

[0131] The electronic control unit 302 executes computer-executable instructions stored in the memory to implement the method in any of the embodiments.

[0132] Multiple positioning anchors 303 are used to enable communication with the vehicle key.

[0133] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the method in any of the embodiments.

[0134] The aforementioned computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory, electrically erasable programmable read-only memory, erasable programmable read-only memory, programmable read-only memory, read-only memory, magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0135] Optionally, a readable storage medium can be coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Alternatively, the readable storage medium can be an integral part of the processor. Both the processor and the readable storage medium can reside in application-specific integrated circuits (ASICs). Of course, the processor and the readable storage medium can also exist as discrete components in the device.

[0136] This application also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium, and when the at least one processor executes the computer program, it can implement the technical solutions provided in any of the above method embodiments.

[0137] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0138] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for locating a vehicle key, characterized in that, Applied to vehicles, including: Based on the distance between the vehicle key and multiple positioning anchor points of the vehicle, and a preset distance threshold, a first position of the vehicle key is determined. The first position is used to indicate whether the vehicle key is in the far field or near field of the vehicle. If the first position indicates that the vehicle key is in the near field of the vehicle, a second position of the vehicle key is determined by a pre-trained first machine learning binary classifier based on the distance between the vehicle key and multiple positioning anchor points of the vehicle. The second position is used to indicate whether the vehicle key is outside or inside the vehicle. The first machine learning binary classifier is an algorithm pre-trained based on a dataset collected within the near field of the vehicle to determine the position of the vehicle key based on the distance between the vehicle key and the positioning anchor points. If the second position indicates that the vehicle key is outside the vehicle, a third position of the vehicle key is determined by a pre-trained second machine learning binary classifier based on the distance between the vehicle key and multiple positioning anchor points of the vehicle. The third position is used to indicate that the vehicle key is on the side or body of the vehicle. The second machine learning binary classifier is an algorithm pre-trained based on a dataset collected outside the vehicle to determine the position of the vehicle key based on the distance between the vehicle key and the positioning anchor points. 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 multiple positioning anchor points of the vehicle, a pre-trained machine learning regression model, and a pre-set triangulation algorithm. The machine learning regression model is an algorithm pre-trained based on a dataset collected within the range to the side of the vehicle to determine the position of the vehicle key based on the distance between the vehicle key and the positioning anchor points.

2. The method according to claim 1, characterized in that, 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 distances between the vehicle key and multiple positioning anchor points of the vehicle, a pre-trained machine learning regression model, and a pre-set triangulation algorithm, including: Based on the distance between the vehicle key and multiple positioning anchor points of the vehicle, the pre-trained machine learning regression model determines the first position coordinates of the vehicle key; Based on the distance between the vehicle key and multiple positioning anchor points of the vehicle, the triangulation algorithm determines the second position coordinates of the vehicle key; Based on the first position coordinates and the second position coordinates, the final position coordinates of the vehicle key relative to the vehicle are determined.

3. The method according to claim 1 or 2, characterized in that, The method further includes: If the first position indicates that the vehicle key is in the far field of the vehicle, the triangulation algorithm determines the final position coordinates of the vehicle key relative to the vehicle based on the distance between the vehicle key and multiple positioning anchor points of the vehicle.

4. The method according to claim 1 or 2, characterized in that, The method further includes: If the second location indicates that the vehicle key is inside the vehicle, a pre-trained first machine learning multi-classifier determines that the vehicle key is located in a first sub-region of the vehicle based on the distance between the vehicle key and multiple positioning anchor points of the vehicle. The first sub-region includes the driver's area, passenger area, rear seat area, or trunk. The first machine learning multi-classifier is an algorithm pre-trained based on a dataset collected within the vehicle's interior area to determine the location of the vehicle key based on the distance between the vehicle key and the positioning anchor points.

5. The method according to claim 1 or 2, characterized in that, The method further includes: If the third location indicates that the vehicle key is on the vehicle body, a pre-trained second machine learning multi-classifier determines that the vehicle key is located in a second sub-region of the vehicle based on the distance between the vehicle key and multiple positioning anchor points of the vehicle. The second sub-region includes the hood, roof, or rear cover of the vehicle body. The second machine learning multi-classifier is an algorithm pre-trained based on a dataset collected within the vehicle body area to determine the location of the vehicle key based on the distance between the vehicle key and the positioning anchor points.

6. The method according to claim 1, characterized in that, Before determining the first position of the vehicle key based on the distance between the vehicle key and multiple positioning anchor points of the vehicle and a preset distance threshold, the method further includes: Acquire the distance measurement signal between the vehicle key and multiple positioning anchor points of the vehicle; Based on the ranging signal, the distance between the vehicle key and multiple positioning anchor points of the vehicle is determined.

7. A vehicle key locating device, characterized in that, include: The first determining module is used to determine the first position of the vehicle key based on the distance between the vehicle key and multiple positioning anchor points of the vehicle and a preset distance threshold. The first position is used to indicate whether the vehicle key is in the far field or near field of the vehicle. The second determining module is used to determine the second position of the vehicle key if the first position indicates that the vehicle key is in the near field of the vehicle, based on the distance between the vehicle key and multiple positioning anchor points of the vehicle and a pre-trained first machine learning binary classifier. The second position is used to indicate whether the vehicle key is outside or inside the vehicle. The first machine learning binary classifier is an algorithm pre-trained based on a dataset collected in the near field of the vehicle to determine the position of the vehicle key based on the distance between the vehicle key and the positioning anchor points. The third determining module is used to determine the third position of the vehicle key if the second position indicates that the vehicle key is outside the vehicle, based on the distance between the vehicle key and multiple positioning anchor points of the vehicle and a pre-trained second machine learning binary classifier. The third position is used to indicate that the vehicle key is on the side or body of the vehicle. The second machine learning binary classifier is an algorithm pre-trained based on a dataset collected outside the vehicle to determine the position of the vehicle key based on the distance between the vehicle key and the positioning anchor points. The fourth determining module is used to determine the final position coordinates of the vehicle key relative to the vehicle if the third position indicates that the vehicle key is located on the side of the vehicle, based on the distance between the vehicle key and multiple positioning anchor points of the vehicle, a pre-trained machine learning regression model and a pre-set triangulation algorithm. The machine learning regression model is an algorithm pre-trained based on a dataset collected within the range on the side of the vehicle to determine the position of the vehicle key based on the distance between the vehicle key and the positioning anchor points.

8. The apparatus according to claim 7, characterized in that, The fourth determining module includes: The first determining unit is used to determine the first position coordinates of the vehicle key based on the distance between the vehicle key and multiple positioning anchor points of the vehicle, and the pre-trained machine learning regression model. The second determining unit is used to determine the second position coordinates of the vehicle key based on the distance between the vehicle key and multiple positioning anchor points of the vehicle, and the triangulation algorithm. The third determining unit is used to determine the final position coordinates of the vehicle key relative to the vehicle based on the first position coordinates and the second position coordinates.

9. A vehicle, characterized in that, include: The vehicle body includes a storage unit, an electronic control unit, and multiple positioning anchor points. The storage unit stores computer-executed instructions; The electronic control unit executes the computer execution instructions stored in the storage unit to implement the method as described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the vehicle key location method as described in any one of claims 1 to 6.

Images