User intention recognition method, device and equipment applied to vehicles

Abstract

The present disclosure provides a method, device, and equipment for identifying user intentions applied to vehicles, which relates to vehicle control technology, including: obtaining communication information between an ultra-wideband anchor point set on the vehicle and an ultra-wideband tag set in a terminal device, and determining a first position of the terminal device according to the communication information; determining a user identification area of ​​the user according to sensor data and the first position, and determining a continuous second position of the user identification area according to the sensor data; determining a user action trajectory according to a correspondence between a preset block and a position and a continuous second position; each block includes multiple positions; comparing the user action trajectory with the preset action trajectory to obtain a comparison result, and determining the user intention according to the comparison result, and the user intention is used to control the vehicle. The ultra-wideband technology and sensor data can be used to determine the user action trajectory, and compare the preset action trajectory, and determine the user intention according to the comparison result. The accuracy of user intention recognition can be improved.

Description

Technical Field

[0001] The present disclosure relates to vehicle control technology, and more particularly to a method, device, and apparatus for identifying user intentions applied to a vehicle. Background Art

[0002] At present, with the development of science and technology, intelligent control of vehicles is becoming more and more popular.

[0003] In the prior art, vehicles can be controlled by intelligently identifying user intentions. For example, a commonly used tailgate opening method is called "step back detection". This method uses a low-frequency sensor installed at the rear of the vehicle to sense the distance between the user and the rear of the vehicle. When the user stands in the area near the rear of the vehicle for a while, then steps back from the rear of the vehicle and stands again for a while, the tailgate is unlocked.

[0004] However, low-frequency sensors have a small range and low accuracy, resulting in the need to improve the accuracy of identifying user intentions. Summary of the invention

[0005] The present disclosure provides a method, device, and apparatus for identifying user intention in a vehicle, which can improve the accuracy of identifying user intention to a certain extent.

[0006] According to a first aspect of the present disclosure, a method for identifying user intention applied to a vehicle is provided, the method comprising:

[0007] Acquire communication information between an ultra-wideband anchor point set on the vehicle and an ultra-wideband tag set in a terminal device, and determine a first position of the terminal device according to the communication information;

[0008] Acquire sensor data, and determine a user identification area of ​​the user based on the sensor data and the first position, and determine a second position continuous with the user identification area based on the sensor data;

[0009] Determine the user motion trajectory according to the correspondence between the preset blocks and the positions and the continuous second positions; wherein each block includes a plurality of positions;

[0010] The user motion trajectory is compared with a preset motion trajectory to obtain a comparison result, and the user intention is determined according to the comparison result, and the user intention is used to control the vehicle.

[0011] According to a second aspect of the present disclosure, a user intention recognition device applied to a vehicle is provided, the device comprising:

[0012] a first position determining unit, configured to obtain communication information between an ultra-wideband anchor point provided on the vehicle and an ultra-wideband tag provided in the terminal device, and determine a first position of the terminal device according to the communication information;

[0013] a second position determination unit, configured to acquire sensor data, determine a user identification area of ​​the user according to the sensor data and the first position, and determine a continuous second position of the user identification area according to the sensor data;

[0014] A user motion trajectory determining unit, configured to determine the user motion trajectory according to a correspondence between a preset block and a position and the continuous second position; wherein each block includes a plurality of positions;

[0015] A comparison unit is used to compare the user action trajectory with a preset action trajectory to obtain a comparison result, and determine the user intention according to the comparison result, wherein the user intention is used to control the vehicle.

[0016] According to a third aspect of the present disclosure, an electronic device is provided, including a memory and a processor; wherein:

[0017] The memory is used to store computer programs;

[0018] The processor is used to read the computer program stored in the memory and execute the user intention recognition method applied to a vehicle as described in the first aspect according to the computer program in the memory.

[0019] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the user intention recognition method applied to a vehicle as described in the first aspect is implemented.

[0020] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program, which, when executed by a processor, implements the user intention recognition method applied to a vehicle as described in the first aspect.

[0021] The user intention recognition method, device, and equipment provided by the present disclosure for use in a vehicle include: obtaining communication information between an ultra-wideband anchor point set on the vehicle and an ultra-wideband tag set in a terminal device, and determining a first position of the terminal device according to the communication information; obtaining sensor data, and determining a user identification area of ​​the user according to the sensor data and the first position, and determining a continuous second position of the user identification area according to the sensor data; determining a user action trajectory according to a correspondence between a preset block and a position and a continuous second position; wherein each block includes a plurality of positions; comparing the user action trajectory with a preset action trajectory to obtain a comparison result, and determining the user intention according to the comparison result, and the user intention is used to control the vehicle. In the user intention recognition method, device, and equipment provided by the present solution for use in a vehicle, ultra-wideband technology and sensor data with high accuracy can be used to determine the user action trajectory, and the preset action trajectory can be compared to determine the user intention according to the comparison result. The method provided by the present solution can improve the accuracy of user intention recognition to a certain extent. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A schematic flow chart of a method for identifying user intention applied to a vehicle according to an exemplary embodiment of the present disclosure;

[0023] Figure 2 A schematic diagram of a signal connection and positioning process between a terminal device and a vehicle shown in an exemplary embodiment of the present disclosure;

[0024] Figure 3 A schematic diagram showing a vehicle tailgate area divided into multiple blocks according to an exemplary embodiment of the present disclosure;

[0025] Figure 4 A schematic diagram of a user action trajectory shown in an exemplary embodiment of the present disclosure;

[0026] Figure 5 A schematic flow chart of a method for identifying user intention applied to a vehicle according to another exemplary embodiment of the present disclosure;

[0027] Figure 6 A schematic diagram of a preset action trajectory shown in an exemplary embodiment of the present disclosure;

[0028] Figure 7 A schematic diagram of a user intention recognition process applied to a vehicle according to an exemplary embodiment of the present disclosure;

[0029] Figure 8 A structural diagram of a user intention recognition device applied to a vehicle according to an exemplary embodiment of the present disclosure;

[0030] Fig. 9 The present invention is a structural diagram of an electronic device according to an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0031] At present, with the development of science and technology, intelligent control of vehicles is becoming more and more popular. In the prior art, vehicles can be controlled by intelligently identifying user intentions. For example, a commonly used tailgate opening method is called "step back detection". This method uses a low-frequency (frequency is 125KHz) sensor set at the rear of the vehicle to sense the distance between the user and the rear of the vehicle. When the user stands in the area near the rear of the vehicle for a while, steps back from the rear of the vehicle and stands for a while again, the tailgate is unlocked.

[0032] However, low-frequency sensors have a small range and low accuracy, and the accuracy of identifying user intentions needs to be improved; and low-frequency methods do not have the ability to prevent relay attacks and cannot meet anti-theft requirements.

[0033] In order to solve the above technical problems, the solution provided by the present disclosure can use ultra-wideband technology and sensor data with higher accuracy to determine the user's motion trajectory, and compare it with the preset motion trajectory, and determine the user's intention based on the comparison result. Ultra-wideband technology and sensor data have a larger ranging range and higher accuracy than the low-frequency sensors used in the prior art. Therefore, the user's motion trajectory determined by ultra-wideband technology is more accurate, which can improve the accuracy of user intention recognition to a certain extent. In addition, ultra-wideband technology has the ability to prevent relay attacks and can pass the anti-theft safety test requirements of the automotive industry (for example, the test of Thatcham, the anti-theft safety testing organization of the British automotive industry).

[0034] Figure 1 The present invention is a flowchart of a method for identifying user intention applied to a vehicle according to an exemplary embodiment of the present invention.

[0035] like Figure 1 As shown, the user intention recognition method applied to a vehicle provided in this embodiment includes:

[0036] Step 101, obtaining communication information between an ultra-wideband anchor point set on a vehicle and an ultra-wideband tag set in a terminal device, and determining a first position of the terminal device according to the communication information.

[0037] The method provided by the present disclosure may be executed by a body control module (BCM). The BCM can obtain communication information between an ultra-wideband anchor point set on the vehicle and an ultra-wideband tag set in a terminal device, and determine the first position of the terminal device according to the communication information.

[0038] Among them, Ultra Wideband (UWB) is a carrier-free communication technology that uses non-sinusoidal narrow pulses in the nanosecond to microsecond range to transmit data.

[0039] The terminal device has the function of a vehicle key. The terminal device can be a physical key with a UWB chip, a Bluetooth Low Energy (BLE) chip, or a mobile phone with a UWB chip, a BLE chip, or an embedded Secure Element (eSE), such as Figure 2 as shown in .

[0040] The communication information may include the time when the information is sent and received, etc. According to the time when the information is sent and received and the propagation speed, the distance between the terminal device and the ultra-wideband anchor point can be determined. When multiple ultra-wideband anchor points are set in the vehicle, the location of the terminal device can be accurately determined.

[0041] Among them, the UWB anchor point and the UWB tag are both transceivers of UWB signals. Specifically, the UWB anchor point can receive the communication information sent by the UWB tag, and can use the information sending time included in the communication information, the time when the UWB anchor point receives the information, and the speed of light to calculate the time of flight (ToF) distance between the UWB anchor point and the UWB tag.

[0042] Specifically, multiple ultra-wideband anchor points can be set in the vehicle, and each ultra-wideband anchor point will obtain a ToF distance between the ultra-wideband tag, and the BCM can obtain the ToF distance between each ultra-wideband anchor point and the ultra-wideband tag from these multiple ultra-wideband anchor points. The BCM can use the preset coordinate system, the coordinates of multiple ultra-wideband anchor points in the preset coordinate system, and determine the first position of the terminal device in the preset coordinate system based on these multiple ToF distances. Among them, the preset coordinate system can use the geometric center of the vehicle as the coordinate origin. Among them, the preset coordinate system can be a two-dimensional coordinate system or a three-dimensional coordinate system.

[0043] Specifically, Figure 2 The figure shows a schematic diagram of the signal connection and positioning process between the terminal device and the vehicle. Specifically, when the terminal device is far away from the vehicle, the terminal device can first establish a communication connection with the vehicle through BLE; the ultra-wideband tag set in the terminal device sends communication information, and the ultra-wideband anchor point set in the vehicle receives the communication information sent by the ultra-wideband tag. According to the received communication information, the ToF distance between each ultra-wideband anchor point and the ultra-wideband tag is calculated, and the BCM can obtain multiple ToF distances through the controller area network (Controller Area Network, CAN) bus, and use these multiple ToF distances to determine the first position of the terminal device in the preset coordinate system.

[0044] Among them, Figure 2The UWB marked in the mobile phone represents an ultra-wideband tag; UWB1~4 marked in the vehicle represent four ultra-wideband anchor points set outside the vehicle; UWB5~7 marked in the vehicle represent three ultra-wideband anchor points set inside the vehicle.

[0045] Step 102 , acquiring sensor data, and determining a user identification area of ​​the user according to the sensor data and the first position, and determining a second position continuous with the user identification area according to the sensor data.

[0046] The sensor is arranged on the vehicle, and can be, for example, a camera, structured light, millimeter wave radar, etc.

[0047] Among them, the user identification area may include the user's hands, feet, head, body, etc.

[0048] Specifically, if the user identification area is the user's foot area, the continuous second positions can be used to represent the continuous position information of the user's foot.

[0049] Specifically, the user's location may be determined based on the sensor information.

[0050] The user identification information corresponding to the first position is determined according to the first position of the terminal device, wherein the user identification information includes the corresponding relationship between the user's position and the user identification area information. For example, when the user's position is p1, the corresponding user identification area is the foot.

[0051] After the user identification area is determined, the continuous second positions of the user identification area can be determined according to the sensor data, for example, the second positions of the foot during movement.

[0052] Step 103, determining the user motion trajectory according to the preset correspondence between the block and the position and the continuous second position; wherein each block includes a plurality of positions.

[0053] Specifically, the area around the vehicle can be divided into multiple blocks. Figure 3 As shown, the tailgate area of ​​the vehicle is divided into multiple blocks. Figure 31, 2, 3, 4, 5, 6, 7 in the figure represent block 1, block 2, block 3, block 4, block 5, block 6, and block 7 respectively. Blocks 1-4 are 4 non-overlapping blocks. Block 5 is formed by merging blocks 1 and 2, block 6 is formed by merging blocks 3 and 4, and block 7 is formed by merging blocks 1, 2, 3, and 4. The range of block 1 is (x1±a, y1±b), which means a plane rectangular block with a center of point (x1, y1) and a range of ±a / ±b in the x / y axis direction; blocks 2, 3, and 4 are the same as block 1 except for the center position; the range of block 5 is (x5±a, y5±2b), which means a plane rectangular block with a center of point (x5, y5) and a range of ±a / ±2b in the x / y axis direction. The ranges of blocks 6 and 7 can be obtained similarly. in, Figure 3 The points (x1, y1), (x2, y2), (x3, y3), (x4, y4), (x5, y5), and (x6, y6) marked in the figure represent the geometric center points of blocks 1-6 respectively.

[0054] Further, such as Figure 3 As shown, block 5 overlaps with block 1, and block 5 contains block 1. Therefore, when the second position belongs to block 1, the second position also belongs to block 5; two user action trajectories can be generated based on block 1 and block 5.

[0055] The user action trajectory may represent the relationship between the blocks to which the user's second position belongs and the changes over time. Specifically, different blocks may be distinguished by different numbers. Figure 4 As shown, it is a user action trajectory diagram, wherein the horizontal axis represents time, and the vertical axis represents the number of the block to which the second position belongs.

[0056] Step 104 , compare the user motion trajectory with the preset motion trajectory to obtain a comparison result, and determine the user intention based on the comparison result, and the user intention is used to control the vehicle.

[0057] The preset motion trajectory is a motion trajectory preset according to actual conditions, which can characterize the changing relationship of the block over time.

[0058] Specifically, a plurality of preset motion trajectories corresponding to the first position may be pre-set. The user motion trajectory may be compared with each preset motion trajectory. If the user motion trajectory successfully matches a preset motion trajectory, the user intention corresponding to the preset motion trajectory may be determined as the user intention. The vehicle action may be controlled according to the user intention.

[0059] The user intention may include, for example, opening a side door, opening a tailgate, turning on headlights, parking, etc., which is not limited in this embodiment.

[0060] The user intention recognition method applied to a vehicle provided by the present disclosure includes: obtaining communication information between an ultra-wideband anchor point set on the vehicle and an ultra-wideband tag set in a terminal device, and determining a first position of the terminal device according to the communication information; obtaining sensor data, and determining a user identification area of ​​the user according to the sensor data and the first position, and determining a continuous second position of the user identification area according to the sensor data; determining a user action trajectory according to a correspondence between a preset block and a position and a continuous second position; wherein each block includes a plurality of positions; comparing the user action trajectory with a preset action trajectory to obtain a comparison result, and determining the user intention according to the comparison result, and the user intention is used to control the vehicle. In the method adopted in the present disclosure, the position of the terminal device can be determined by using ultra-wideband technology; the user action trajectory can be obtained by using sensor data and the position of the terminal device; and the user action trajectory can be compared with the preset action trajectory to determine the user intention. The user intention recognition method adopted in this scheme can improve the accuracy of user intention recognition to a certain extent.

[0061] Figure 5 The present invention is a flowchart of a method for identifying user intention applied to a vehicle according to another exemplary embodiment of the present invention.

[0062] like Figure 5 As shown, the user intention recognition method applied to a vehicle provided in this embodiment includes:

[0063] Step 501: Authenticate the terminal device.

[0064] Specifically, when the terminal device is far away from the vehicle, the terminal device can first establish a communication connection with the vehicle through BLE and complete the identity authentication of the terminal device.

[0065] Specifically, the vehicle can send identity authentication information to the terminal device, and the terminal device replies to the vehicle after receiving the identity authentication information. If the replied information matches, it is determined that the identity authentication is successful.

[0066] Step 502: Acquire communication information between an ultra-wideband anchor point set on the vehicle and an ultra-wideband tag set in the terminal device, and acquire relative motion information of the terminal device.

[0067] Specifically, the relative motion information of the terminal device may be acquired through a sensor provided on the terminal device.

[0068] In one achievable manner, the sensor for collecting the relative motion information of the terminal device includes at least one of the following: an electronic accelerometer and an electronic gyroscope.

[0069] Specifically, the relative motion information includes the object's motion direction and speed information.

[0070] Among them, the electronic accelerometer is an inertial sensor that can measure the acceleration of an object when it moves in space. It has the characteristics of small size and light weight. Common three-axis accelerometer chips are available.

[0071] Among them, the electronic gyroscope uses the Coriolis force caused by mutually orthogonal motion and rotation to convert the angular velocity of a rotating object into a voltage proportional to the angular velocity. It can measure the angular velocity of an object when it moves in space. Common electronic gyroscope chips include three-axis electronic gyroscopes.

[0072] Among them, the Coriolis force, also known as the Coriolis force, is a description of the deviation of the linear motion of a particle in a rotating system due to inertia relative to the rotating system. The Coriolis force comes from the inertia of the object's motion.

[0073] Step 503, determining the initial position of the terminal device according to the communication information; determining the first position of the terminal device according to the initial position and the relative motion information.

[0074] Specifically, after step 503, step 504A may be executed, or step 504B may be executed.

[0075] Specifically, step 504A and step 504B do not conflict with each other and can be performed simultaneously. Specifically, if the user identification area data is used to match the preset motion trajectory, step 504A is performed, and if the terminal device data is used to match the preset motion trajectory, step 504B is performed.

[0076] Specifically, the transmission frequency of the UWB signal can be preset, and the first position of the terminal device can be determined in combination with the relative motion information between two UWB signals. The first position of the terminal device can be determined using the initial position of the terminal device and the relative motion information, so that the obtained first position can be more accurate.

[0077] Step 504A: Determine the device block where the terminal device is located according to the first position and the correspondence between the preset block and the position.

[0078] The correspondence between the preset blocks and the positions is a correspondence between the blocks and the positions that is preset according to actual conditions. The area within a certain range around the vehicle can be divided into multiple blocks according to actual conditions, and each block includes multiple positions.

[0079] According to the first position, the correspondence between the preset block and the position can be queried to obtain the block corresponding to the first position, and the block is the device block where the terminal device is located.

[0080] Step 505 , acquiring sensor data, and determining the user position of the user according to the sensor data; and determining the user block where the user is located according to the correspondence between the preset block and the position and the user position.

[0081] Specifically, the sensor data may be acquired by using the sensors provided in the vehicle, and the user position of the user may be determined based on the sensor data, wherein the type and quantity of the sensors used are not limited.

[0082] In one possible implementation, the sensor includes at least one of the following: a camera, a structured light, and a millimeter wave radar.

[0083] Specifically, if the sensor is a camera, the user can be identified from the image data collected by the camera using a preset network, and the user's position can be determined.

[0084] Specifically, if the sensor is structured light, the user can be identified from the point cloud data and the user's position can be determined by using the acquired point cloud data and a preset network.

[0085] Specifically, if the sensor is a millimeter wave radar, point cloud data can be acquired through the millimeter wave radar, and a preset network can be used to identify the user from the point cloud data and determine the user's position.

[0086] The correspondence between the preset blocks and the positions is a correspondence between the blocks and the positions that is preset according to actual conditions. The area within a certain range around the vehicle can be divided into multiple blocks according to actual conditions, and each block includes multiple positions.

[0087] According to the user's location, the correspondence between the preset block and the location can be queried to obtain the block corresponding to the user's location, and the block is the user block where the user is located.

[0088] Step 506, determining the user identification information corresponding to the device block according to the preset correspondence between the block and the user identification information; wherein the user identification information includes the correspondence between the user block and the user identification area.

[0089] The preset correspondence between the block and the user identification information is a correspondence between the block and the user identification information that is preset according to actual conditions.

[0090] The corresponding relationship between the preset block and the user identification information can be queried according to the device block to obtain the user identification information corresponding to the device block, and the user identification information includes the corresponding relationship between the user block and the user identification area.

[0091] Step 507: Determine the user identification area according to the user block and the correspondence between the user block and the user identification area.

[0092] Specifically, the user identification area may be determined by querying the corresponding relationship between the user block and the user identification area in the user identification information corresponding to the device block according to the user block.

[0093] Step 508: using a preset network model, identifying a user identification area of ​​the user in the sensor data.

[0094] The preset network model may be a preset network model for identifying a user identification area of ​​a user. The preset network model may be, for example, a pre-trained neural network model.

[0095] For example, if the user identification area of ​​the user is the user's hand area, the preset network model can be used to identify the user's hand area in the sensor data.

[0096] Step 509: Determine a second position of the user identification area according to the sensor data and preset parameters of the sensor.

[0097] The preset parameters are parameters preset according to actual conditions. The preset parameters refer to the conversion relationship between the position information of the sensor data and the preset coordinate system. The preset coordinate system may take the geometric center of the vehicle as the coordinate origin. The preset coordinate system may be a two-dimensional coordinate system or a three-dimensional coordinate system. The first position may also be represented in the preset coordinate system.

[0098] Specifically, the position of the geometric center point of the user identification area identified in the sensor data in the sensor data and preset parameters can be used to obtain the position of the geometric center point in the preset coordinate system, which is the second position of the user identification area.

[0099] Step 510, determining the user motion trajectory according to the correspondence between the preset blocks and the positions and the continuous second positions; wherein each block includes a plurality of positions.

[0100] Specifically, the principle and specific implementation of step 510 are similar to those of step 103 and will not be described in detail.

[0101] Step 511, determining the block where the terminal device is located according to the continuous first positions and the corresponding relationship between the preset blocks and positions.

[0102] The correspondence between the preset blocks and the positions is a correspondence between the blocks and the positions that is preset according to actual conditions. The area within a certain range around the vehicle can be divided into multiple blocks according to actual conditions, and each block includes multiple positions.

[0103] According to the continuous first positions, the correspondence between the preset blocks and the positions can be queried to obtain the block corresponding to the first position, and the block is the block where the terminal device is located.

[0104] Step 512, according to the correspondence between the preset blocks and the preset action trajectories, determine the preset action trajectory for comparison with the user action trajectory; the preset action trajectory includes a plurality of first trajectories connected in sequence; the first trajectory includes a first block and a dwell time corresponding to the first block; the user action trajectory includes a plurality of second trajectories connected in sequence, the second trajectory includes a second block and a dwell time corresponding to the second block.

[0105] The corresponding relationship between the preset blocks and the preset action tracks is preset according to actual conditions.

[0106] The preset motion trajectory is a motion trajectory preset according to actual conditions. The preset motion trajectory can be used to characterize the relationship between the change of the block where the user identification area of ​​the user is located over time.

[0107] Specifically, the corresponding relationship between the preset block and the preset action trajectory can be queried according to the block where the terminal device is located, so as to obtain the preset action trajectory corresponding to the block where the terminal device is located.

[0108] Specifically, one block may correspond to multiple preset action trajectories.

[0109] Step 513, comparing the first trajectory and the second trajectory in the same order; if the first block of the first trajectory is the same as the second block of the second trajectory, and the dwell time corresponding to the second block belongs to the target range, then determining that the second trajectory is matched successfully; wherein the target range is determined based on the dwell time corresponding to the first block.

[0110] like Figure 6 The figure shows a preset motion track, wherein the horizontal axis represents time and the vertical axis represents the block number. Figure 6 The t1, Δt1, t2, Δt2, t3, and Δt3 identified in are used to characterize time intervals. Block 1 and the duration of stay in block 1, t1+Δt1, constitute a first trajectory. Among them, t1 can be used to represent the minimum duration of stay in block 1; t1+Δt1 can be used to represent the maximum duration of stay in block 1. The target range can be greater than or equal to t1 and less than or equal to t1+Δt1. If the second trajectory with the same order as the corresponding first trajectory represents a duration of stay in block 1 that is greater than or equal to t1 and less than or equal to t1+Δt1, it can be determined that the second trajectory matches successfully.

[0111] In one possible implementation, a prompt message is generated when comparing the user action trajectory with the preset action trajectory; the prompt message is used to prompt the user to complete an action corresponding to the user's intention.

[0112] Output prompt messages through voice or light.

[0113] Specifically, when the user is performing an action (the vehicle can obtain the user's action trajectory based on the user's action, and compare the user's action trajectory with the preset action trajectory), the vehicle can give the user certain guidance and status indications to prompt the user to complete the action corresponding to the user's intention.

[0114] Furthermore, there are many specific implementation methods for prompt messages, such as using the existing lights at the rear of the vehicle (such as brake lights, high-mounted brake lights, turn signals, and reverse lights), buzzers, etc., adding a pointer light (focus LED) at the center of the block, or projecting the block frame line in some way, etc., and adding voice prompts, etc. Specifically, the role of the prompt message can be to inform the user whether the dwell time at the current location is sufficient, and where to move to next and how long to stay, etc. With the prompt message, the user does not need to remember the specific actions corresponding to the user's intention, and can just follow the prompt message, which not only reduces the probability of misoperation, but also facilitates operation.

[0115] Thereafter, based on the next set of first tracks and second tracks in the same order, step 513 is continued to be executed until all second tracks in the user motion track and all first tracks in the preset motion track are successfully matched, and it is determined that the user motion track is successfully matched.

[0116] Specifically, according to the order of each second track in the user action track and the order of each first track in the preset action track, the second tracks with the same order can be compared with the first tracks. When a group of first tracks with the same order matches the second track, the next group of first tracks with the same order is compared with the second track in order, and each first track has a corresponding second track for comparison. If each group of compared second tracks successfully matches the first track, it is determined that the user action track matches successfully.

[0117] In one achievable manner, if the comparison result between the user motion trajectory and the preset motion trajectory is not a match, then the step of determining a second continuous position of the user recognition area according to the sensor data is continued.

[0118] Specifically, if during the matching process of the user motion trajectory and the preset motion trajectory, a group of first trajectories and second trajectories with the same order do not match, then it is determined that the comparison result between the user motion trajectory and the preset motion trajectory is not matched.

[0119] Furthermore, if the comparison result between the user motion trajectory and the preset motion trajectory is not a match, the step of determining a second continuous position of the user recognition area according to the sensor data may be continued.

[0120] Step 514: If the user motion trajectory successfully matches the preset motion trajectory, the intention corresponding to the preset motion trajectory is determined as the user intention, and the user intention is used to control the vehicle.

[0121] Specifically, after step 514, step 516 may be executed.

[0122] Specifically, the correspondence between the preset action trajectory and the user intention can be preset according to actual conditions.

[0123] Optionally, one user intention may be expressed by multiple preset action tracks, that is, one user intention may correspond to multiple preset action tracks. However, one preset action track only corresponds to one user intention.

[0124] Step 504B, determining the trajectory of the terminal device according to the corresponding relationship between the preset blocks and the positions and the continuous first positions.

[0125] Specifically, the continuous blocks where the terminal device is located may be determined according to the correspondence between the preset blocks and the positions and the continuous first positions; and then the trajectory of the terminal device may be determined according to the continuous blocks where the terminal device is located.

[0126] The terminal device trajectory may represent the change relationship over time of the block to which the first position of the terminal device belongs.

[0127] Step 515 , compare the terminal device trajectory with the preset action trajectory to obtain a comparison result, and determine the user intention based on the comparison result, and the user intention is used to control the vehicle.

[0128] Specifically, the block where the terminal device is located can be determined based on the correspondence between the preset block and the position and the first position; then, using the block where the terminal device is located, the correspondence between the preset block and the preset action trajectory is queried to determine the preset action trajectory for comparison with the terminal device trajectory.

[0129] Specifically, the comparison between the terminal device trajectory and the preset action trajectory is similar to the principle and implementation method of the comparison between the user action trajectory and the preset action trajectory, and will not be repeated here.

[0130] Step 516: If the first position of the terminal device meets the preset condition, the vehicle is controlled to close and lock the doors.

[0131] The preset condition is preset according to actual conditions. For example, the preset condition may be that the first position of the terminal device is out of a preset range around the vehicle; or the first position of the terminal device indicates that the distance between the terminal device and the vehicle is greater than a preset distance.

[0132] For example, Figure 3 As shown in , when the UWB technology detects that the terminal device leaves the block range marked as 7, the tailgate is automatically folded and locked.

[0133] Specifically, in the method adopted in this embodiment, the UBW technology can be used to determine the first position based on the relative motion information, and the second position can be determined based on the first position and the sensor data, which can improve the accuracy of the detected position information to a certain extent; then the terminal device trajectory is determined based on the first position, and the user action trajectory is determined based on the second position; and the terminal device trajectory and / or the user action trajectory are matched with the preset action trajectory, which can improve the accuracy of user intention recognition to a certain extent. Moreover, the preset action trajectory in this embodiment can be pre-set according to the actual situation, which can enhance the user experience.

[0134] Furthermore, if the terminal device trajectory is matched with the preset action trajectory to match the first user intention; and the user action trajectory is matched with the preset action trajectory to match the second user intention; and the first user intention and the second user intention are different. Then the vehicle can be controlled according to the first user intention and the second user intention. For example, if the first user intention is to turn on the position lights and the second user intention is to open the tailgate, the vehicle can be operated to turn on the position lights and open the tailgate at the same time.

[0135] Figure 7 The figure is a schematic diagram of a user intention recognition process applied to a vehicle according to an exemplary embodiment of the present disclosure.

[0136] like Figure 7 As shown, the first position of the terminal device can be determined based on the communication information between the ultra-wideband anchor point set on the vehicle and the ultra-wideband tag set in the terminal device;

[0137] The device block where the terminal device is located can be determined according to the first position and the correspondence between the preset position and the block; and the user identification information corresponding to the device block and the preset action track corresponding to the device block can be determined according to the device block, the correspondence between the preset block and the user identification information, and the correspondence between the preset block and the preset action track. Specifically, different blocks can be distinguished by different numbers.

[0138] The user position can be determined according to the sensor data, and then the user block can be determined according to the correspondence between the preset block and the position; the user identification area can be determined according to the user block and the correspondence between the preset block and the user identification area; the second position of the user identification area can be determined according to the sensor data;

[0139] The terminal device motion trajectory can be determined based on the continuous first positions; the user motion trajectory can be determined based on the continuous second positions; the terminal device motion trajectory and / or the user motion trajectory can be compared with the preset motion trajectory to obtain a comparison result. If there is no match, the step of determining the continuous second positions and / or the continuous first positions is continued. If there is a match, the intention corresponding to the preset motion trajectory that successfully matches is determined to be the user intention, and the vehicle is controlled according to the user intention.

[0140] Figure 8 The present invention is a structural diagram of a user intention recognition device applied to a vehicle according to an exemplary embodiment of the present invention.

[0141] like Figure 8 As shown, the user intention recognition device 800 applied to a vehicle provided by the present disclosure includes:

[0142] The first position determining unit 810 is used to obtain communication information between the ultra-wideband anchor point set on the vehicle and the ultra-wideband tag set in the terminal device, and determine the first position of the terminal device according to the communication information;

[0143] A second position determination unit 820 is used to obtain sensor data, and determine a user identification area of ​​the user according to the sensor data and the first position, and determine a second position of the user identification area according to the sensor data;

[0144] The user motion trajectory determining unit 830 is used to determine the user motion trajectory according to the correspondence between the preset blocks and the positions and the continuous second positions; wherein each block includes a plurality of positions;

[0145] The comparison unit 840 is used to compare the user's motion trajectory with the preset motion trajectory to obtain a comparison result, and determine the user's intention based on the comparison result. The user's intention is used to control the vehicle.

[0146] A second position determination unit 820, specifically configured to determine the device block where the terminal device is located according to the first position and the correspondence between the preset block and the position;

[0147] Determine the user position of the user according to the sensor data; determine the user block where the user is located according to the correspondence between the preset block and the position and the user position;

[0148] Determine the user identification information corresponding to the device block according to the correspondence between the preset blocks and the user identification information; wherein the user identification information includes the correspondence between the user block and the user identification area;

[0149] The user identification area is determined according to the user block and the corresponding relationship between the user block and the user identification area.

[0150] The second location determination unit 820 is specifically configured to identify a user identification area of ​​a user in the sensor data using a preset network model;

[0151] A second position of the user recognition area is determined according to the sensor data and preset parameters of the sensor.

[0152] The comparison unit 840 is specifically configured to determine the block where the terminal device is located according to the continuous first positions and the corresponding relationship between the preset blocks and positions;

[0153] According to the correspondence between the preset blocks and the preset motion trajectories, a preset motion trajectory for comparison with the user motion trajectory is determined.

[0154] The comparison unit 840 is specifically used to preset that the action trajectory includes a plurality of first trajectories connected in sequence; the first trajectory includes a first block and a dwell time corresponding to the first block; the user action trajectory includes a plurality of second trajectories connected in sequence, the second trajectory includes a second block and a dwell time corresponding to the second block; compare the first trajectory and the second trajectory in the same order; if the first block of the first trajectory is the same as the second block of the second trajectory, and the dwell time corresponding to the second block belongs to a target range, then determine that the second trajectory is matched successfully; wherein the target range is determined based on the dwell time corresponding to the first block;

[0155] Continue to compare the next set of first tracks and second tracks in the same order until all the second tracks in the user motion track and all the first tracks in the preset motion track are successfully matched, and then it is determined that the user motion track is successfully matched.

[0156] The first position determination unit 810 is further used to obtain relative motion information of the terminal device;

[0157] Determine the initial position of the terminal device based on the communication information;

[0158] The first position of the terminal device is determined according to the initial position and relative motion information.

[0159] In one achievable manner, the sensor for collecting the relative motion information of the terminal device includes at least one of the following: an electronic accelerometer and an electronic gyroscope.

[0160] The user motion trajectory determining unit 830 is further configured to determine the trajectory of the terminal device according to the correspondence between the preset blocks and the positions and the continuous first positions.

[0161] The comparison unit 840 is further used to compare the terminal device trajectory with the preset action trajectory to obtain a comparison result, and determine the user intention based on the comparison result.

[0162] The comparison unit 840 is further configured to continue to execute the step of determining a second continuous position of the user recognition area according to the sensor data if the comparison result between the user motion trajectory and the preset motion trajectory is not matched.

[0163] The comparison unit 840 is specifically configured to determine the intention corresponding to the preset action trajectory as the user intention if the user action trajectory successfully matches the preset action trajectory.

[0164] In one possible implementation, the sensor includes at least one of the following: a camera, a structured light, and a millimeter wave radar.

[0165] The first location determination unit 810 is further configured to perform identity authentication on the terminal device before acquiring the communication information.

[0166] The comparison unit 840 is further used to generate a prompt message when comparing the user action trajectory with the preset action trajectory; the prompt message is used to prompt the user to complete the action corresponding to the user's intention;

[0167] Output prompt messages through voice or light.

[0168] The comparison unit 840 is also used to control the vehicle to close and lock the door if the first position of the terminal device meets the preset condition.

[0169] Fig. 9 The present invention is a structural diagram of an electronic device according to an exemplary embodiment of the present invention.

[0170] like Fig. 9 As shown, the electronic device provided in this embodiment includes:

[0171] Memory 901;

[0172] Processor 902; and

[0173] Computer programs;

[0174] The computer program is stored in the memory 901 and is configured to be executed by the processor 902 to implement any of the above methods for identifying user intentions applied to a vehicle.

[0175] This embodiment also provides a computer-readable storage medium on which a computer program is stored. The computer program is executed by a processor to implement any of the above methods for identifying user intentions applied to a vehicle.

[0176] This embodiment also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned user intention recognition methods applied to a vehicle.

[0177] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0178] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for identifying user intention in a vehicle, characterized in that: The method comprises: Acquire communication information between an ultra-wideband anchor point set on the vehicle and an ultra-wideband tag set in a terminal device, and determine a first position of the terminal device according to the communication information; Acquire sensor data, and determine the device block where the terminal device is located according to the first position and the correspondence between the preset block and the position; determine the user position of the user according to the sensor data; determine the user block where the user is located according to the correspondence between the preset block and the position and the user position; determine the user identification information corresponding to the device block according to the correspondence between the preset block and the user identification information; wherein the user identification information includes the correspondence between the user block and the user's body feature part; determine the user's body feature part according to the user block, the correspondence between the user block and the user's body feature part, and determine a second continuous position of the user's body feature part according to the sensor data; Determine the user motion trajectory according to the correspondence between the preset blocks and the positions and the continuous second positions; wherein each block includes a plurality of positions; The user action trajectory is compared with a preset action trajectory to obtain a comparison result, and a user intention is determined according to the comparison result, wherein the user intention is used to control the vehicle, and the preset action trajectory includes a plurality of first trajectories connected in sequence; the first trajectory includes a first block and a stay duration corresponding to the first block; the user action trajectory includes a plurality of second trajectories connected in sequence, and the second trajectory includes a second block and a stay duration corresponding to the second block.

2. The method according to claim 1, characterized in that The step of determining the continuous second positions of the characteristic parts of the user's body according to the sensor data comprises: Using a preset network model, identifying the characteristic body part of the user in the sensor data; The second position of the characteristic part of the user's body is determined according to the sensor data and preset parameters of the sensor.

3. The method according to claim 1, characterized in that Before comparing the user motion trajectory with the preset motion trajectory to obtain a comparison result, the method further includes: Determine the block where the terminal device is located according to the continuous first positions and the correspondence between the preset blocks and positions; According to the correspondence between the preset blocks and the preset motion trajectories, a preset motion trajectory for comparison with the user motion trajectory is determined.

4. The method according to claim 1, characterized in that: The comparing the user motion trajectory with the preset motion trajectory to obtain a comparison result includes: Compare the first trajectory and the second trajectory in the same order; if the first block of the first trajectory is the same as the second block of the second trajectory, and the dwell time corresponding to the second block belongs to the target range, then determine that the second trajectory is matched successfully; wherein the target range is determined based on the dwell time corresponding to the first block; Continue to compare the next group of the first trajectories and the second trajectories in the same order until all the second trajectories in the user motion trajectory and all the first trajectories in the preset motion trajectory are successfully matched, and then determine that the user motion trajectory is successfully matched.

5. The method according to claim 1, characterized in that Also includes: Acquiring relative motion information of the terminal device; The determining the first position of the terminal device according to the communication information includes: Determine the initial position of the terminal device according to the communication information; The first position of the terminal device is determined according to the initial position and the relative motion information.

6. The method according to claim 5, characterized in that The sensor for collecting the relative motion information of the terminal device includes at least one of the following: an electronic accelerometer and an electronic gyroscope.

7. The method according to claim 6, characterized in that Also includes: Determine the trajectory of the terminal device according to the correspondence between the preset blocks and the positions and the continuous first positions; The terminal device trajectory is compared with a preset action trajectory to obtain a comparison result, and the user intention is determined according to the comparison result.

8. The method according to claim 1, characterized in that Also includes: If the comparison result between the user motion trajectory and the preset motion trajectory is not a match, the step of determining a second continuous position of the user identification area according to the sensor data is continued.

9. The method according to claim 1, characterized in that: Determining the user intention according to the comparison result includes: If the user motion trajectory successfully matches the preset motion trajectory, the intention corresponding to the preset motion trajectory is determined as the user intention.

10. The method according to claim 1 or 2, characterized in that: The sensor includes at least one of the following: a camera, a structured light, and a millimeter wave radar.

11. The method according to claim 1, characterized in that: Before acquiring the communication information, the method further includes: authenticating the terminal device.

12. The method according to claim 1, characterized in that Also includes: When comparing the user action trajectory with the preset action trajectory, a prompt message is generated; the prompt message is used to prompt the user to complete the action corresponding to the user's intention; The prompt message is outputted in a voice or light manner.

13. The method according to claim 1, characterized in that Also includes: If the first position of the terminal device meets the preset condition, the vehicle is controlled to close and lock the doors.

14. A user intention recognition device applied to a vehicle, characterized in that: The device comprises: a first position determining unit, configured to obtain communication information between an ultra-wideband anchor point provided on the vehicle and an ultra-wideband tag provided in the terminal device, and determine a first position of the terminal device according to the communication information; a second position determination unit, configured to obtain sensor data, determine a characteristic part of a user's body according to the sensor data and the first position, and determine a continuous second position of the characteristic part of the user's body according to the sensor data; A user motion trajectory determining unit, configured to determine the user motion trajectory according to a correspondence between a preset block and a position and the continuous second position; wherein each block includes a plurality of positions; a comparison unit, configured to compare the user motion trajectory with a preset motion trajectory to obtain a comparison result, and determine a user intention according to the comparison result, wherein the user intention is used to control the vehicle; the preset motion trajectory comprises a plurality of first trajectories connected in sequence; the first trajectory comprises a first block and a stay duration corresponding to the first block; the user motion trajectory comprises a plurality of second trajectories connected in sequence, the second trajectory comprises a second block and a stay duration corresponding to the second block; The second position determination unit is specifically configured to determine the device block where the terminal device is located according to the first position and the correspondence between the preset block and the position; Determine the user position of the user according to the sensor data; determine the user block where the user is located according to the correspondence between the preset block and the position and the user position; Determine the user identification information corresponding to the device block according to the correspondence between the preset blocks and the user identification information; wherein the user identification information includes the correspondence between the user block and the user identification area; The characteristic body part of the user is determined according to the user block and the correspondence between the user block and the characteristic body part of the user.

15. An electronic device, characterized in that: comprising a memory and a processor; wherein, The memory is used to store computer programs; The processor is used to read the computer program stored in the memory and execute the method according to any one of claims 1 to 13 according to the computer program in the memory.

16. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the processor executes the computer-executable instructions, the method described in any one of claims 1 to 13 is implemented.

17. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method described in any one of claims 1 to 13 is implemented.

Images