Vehicle control method, device and equipment based on voice positioning and storage medium

Abstract

The invention relates to a vehicle control method and device based on voice positioning, equipment and a storage medium, and the method comprises the steps: carrying out voiceprint recognition in response to a received voice wake-up instruction sent by a user; in response to passing of voiceprint recognition, a voice parking instruction sent by a user is obtained and analyzed; in response to the identified target parking direction in the parking instruction of the user, the vehicle is controlled to be parked in the target parking direction; in response to a target parking direction which is not recognized in the parking instruction of the user, recognizing the orientation of the user, and controlling the vehicle to run near the user; and in response to the fact that the target parking direction and the orientation of the user in the user parking instruction are not recognized, the current state of the vehicle is kept, and the user instruction continues to be obtained. According to the method and the device, the user can start and realize parking only through a simple voice instruction, the whole parking process is free from manual operation, the independent travel capability is improved, and convenient and safe parking experience is provided for the user.

Description

Technical Field

[0001] The present application relates to the field of intelligent parking technology, and in particular to a vehicle control method, device, equipment and storage medium based on voice positioning. Background Art

[0002] At present, there are many ways to control the parking of vehicles outside the vehicle in the industry, including mobile phone or tablet computer control, key control, and voice control. Among them, the technology of controlling vehicle parking with mobile phones and tablet computers is relatively mature, and most car companies also use this method when doing parking outside the vehicle. In the existing technology, there are few solutions for controlling parking outside the vehicle by key or voice, but in some scenarios, users are inconvenient or do not want to operate remote control devices such as mobile phones or keys for remote parking, but use voice to park. However, parking by voice cannot determine the parking direction, which brings inconvenience to parking by voice. Summary of the invention

[0003] Based on this, the present application provides a vehicle control method, device, equipment and storage medium based on voice positioning, which determines the position of the user's vehicle based on voice positioning to determine the parking direction.

[0004] In a first aspect, a vehicle control method based on voice positioning comprises:

[0005] In response to receiving a voice wake-up command issued by a user, performing voiceprint recognition;

[0006] In response to the voiceprint recognition being successful, obtaining and parsing a voice parking instruction issued by the user, wherein the voice parking instruction includes a target parking direction and a location of the user;

[0007] In response to identifying a target parking direction in a user's parking instruction, controlling the vehicle to park in the target parking direction;

[0008] In response to not recognizing the target parking direction in the user's parking instruction, recognizing the location of the user, and controlling the vehicle to travel near the user;

[0009] In response to not recognizing the target parking direction and the user's position in the user's parking instruction, maintaining the current state of the vehicle and continuing to obtain the user instruction.

[0010] Further,

[0011] In response to identifying a target parking direction in a user parking instruction, controlling the vehicle to park in the target parking direction includes:

[0012] In response to the target parking direction including a plurality of parking positions, controlling the vehicle to park in the target parking direction;

[0013] In response to receiving a target parking position sent by a user, a parking path is formed and the vehicle is controlled to park at the target parking position; in response to not receiving the target parking position sent by the user, the user's location is obtained and the vehicle is controlled to park at a parking position close to the user.

[0014] Further, in response to not identifying the target parking direction in the user's parking instruction, identifying the location of the user, and controlling the vehicle to travel near the user includes:

[0015] In response to receiving a parking instruction from a user while the vehicle is controlled to travel near the user, the vehicle is controlled to park based on the parking instruction from the user.

[0016] Furthermore, the voice parking instruction also includes a parking intention. In response to receiving that the parking intention is to park out and not receiving a target parking direction, the vehicle is controlled to park out of the parking space toward the user's location according to the user's location and park.

[0017] Furthermore, obtaining and parsing the voice parking instruction issued by the user includes:

[0018] Acquire the user's voice parking instructions in real time and judge the parking conditions, and update the vehicle's parking status in real time based on the user's voice parking instructions.

[0019] Further, in response to receiving a voice wake-up command issued by a user, performing voiceprint recognition includes:

[0020] In response to the voiceprint recognition failing, feedback is given to the user, and the user is prompted to enter the voiceprint.

[0021] In a second aspect, a vehicle control device based on voice positioning comprises:

[0022] Identity recognition module: in response to receiving a voice wake-up command from the user, performs voiceprint recognition;

[0023] Parking instruction receiving and parsing module: in response to the voiceprint recognition being passed, obtaining and parsing the voice parking instruction issued by the user, wherein the voice parking instruction includes the target parking direction and the user's location;

[0024] Parking execution module: in response to recognizing the target parking direction in the user's parking instruction, controlling the vehicle to park in the target parking direction; in response to not recognizing the target parking direction in the user's parking instruction, recognizing the user's location, controlling the vehicle to drive near the user; in response to not recognizing the target parking direction and the user's location in the user's parking instruction, maintaining the current state of the vehicle and continuing to obtain user instructions.

[0025] A third aspect provides a vehicle, comprising the control device described in the second aspect.

[0026] According to a fourth aspect, a computer device comprises:

[0027] at least one processor; and

[0028] a memory communicatively connected to the at least one processor; wherein,

[0029] The memory stores computer instructions that can be executed by the at least one processor, and the computer instructions are executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect.

[0030] In a fifth aspect, a computer-readable storage medium stores computer instructions thereon, wherein the computer instructions are used to cause a computer to execute the method described in the first aspect.

[0031] The present invention allows the user to issue a parking instruction outside the vehicle before parking, and determines the orientation of the user's vehicle based on voice positioning to determine the parking direction, and then controls the vehicle to park in the direction of the user who issued the parking instruction. The present invention combines automatic driving, voice recognition and voice positioning technology, so that the user only needs a simple voice instruction to start and complete parking. The entire parking process is free from manual operation, which improves the ability to travel independently and provides users with a convenient and safe parking experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 A schematic flow chart of a vehicle control method based on voice positioning in one embodiment of the present invention;

[0033] Figure 2 A schematic diagram of locating a user's position by using a sound source according to an embodiment of the present invention;

[0034] Figure 3 This is a schematic diagram of a vehicle traveling toward a user in one embodiment of the present invention;

[0035] Figure 4 A schematic diagram of a vehicle parking in a user-oriented parking space in one embodiment of the present invention;

[0036] Figure 5 In one embodiment of the present invention, the vehicle turns according to the user's orientation;

[0037] Figure 6 A schematic diagram of parking out of a vertical parking space in one embodiment of the present invention;

[0038] Figure 7 A schematic diagram of parking out of a horizontal parking space in one embodiment of the present invention;

[0039] Figure 8 This is a flow chart of voice parking outside the vehicle in one embodiment of the present invention;

[0040] Fig. 9 A flow chart of determining whether parking conditions are currently met in one embodiment of the present invention;

[0041] Fig.10 A structural block diagram of a control device in one embodiment of the present invention;

[0042] Fig.11 FIG. 1 is a block diagram of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION

[0043] The present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0044] As an embodiment of the present application, a vehicle control method based on voice positioning, such as Figure 1 As shown, the method includes:

[0045] Step 101: In response to receiving a voice wake-up command issued by a user, performing voiceprint recognition;

[0046] Voiceprint recognition is used to confirm whether the user is a legitimate user of the vehicle; if the voiceprint recognition fails, the user is prompted to enter the voiceprint, and based on the voiceprint entry procedure, the user can choose to enter the voiceprint; after the voiceprint recognition passes, the user can continue to issue parking instructions.

[0047] Exemplarily, when extracting voiceprint features, MFCC (Mel frequency cepstral coefficients) and LPC (linear predictive coding) methods can be used to extract voiceprint features; in voiceprint model training, deep learning models (such as CNN, RNN) can be used to train voiceprint recognition models; real-time recognition can be achieved by optimizing the model, for example, model updates can be regularly pushed through OTA technology, known problems can be fixed, and model performance and response speed can be improved.

[0048] Exemplarily, the method for optimizing the voiceprint model includes:

[0049] (1) Collect speech samples in different environments, including different background noises, speaking speeds, and volumes;

[0050] (2) Use noise reduction algorithms (such as spectral subtraction and Wiener filtering) to reduce background noise and delete samples with poor quality or that do not meet the requirements;

[0051] (3) Superimpose different types of noise on clean speech samples to generate more diverse training data;

[0052] (4) Increase data diversity by changing the speed and pitch of speech.

[0053] As an example, the specific steps of voiceprint recognition include:

[0054] (1) Voice wake-up:

[0055] The user issues a specific voice wake-up command (such as "Hi, car"); the microphone array outside the car captures the command and transmits it to the voiceprint recognition module.

[0056] (2) Voiceprint recognition:

[0057] The voiceprint recognition module processes the captured voice signal and extracts the voiceprint features; compares the extracted voiceprint features with the pre-stored user voiceprint template; if the match is successful, the user's identity is confirmed; otherwise, the user is prompted to enter the voiceprint.

[0058] (3) Voiceprint Recording

[0059] The user is required to repeat the specified voice command (such as "I am a user") multiple times to obtain multiple groups of voiceprint samples; a noise reduction algorithm is used to reduce the impact of environmental noise on voiceprint recording and perform environmental noise suppression; the recorded voiceprint features are stored as the user's voiceprint template; and the user is informed through voice that the voiceprint recording is successful.

[0060] (4) Voiceprint recognition again:

[0061] After the user enters the voiceprint, voiceprint recognition is performed again to confirm the user's identity; if the match is successful, the user is allowed to continue to issue parking instructions.

[0062] Step 102:

[0063] In response to the voiceprint recognition being successful, obtaining and parsing a voice parking instruction issued by the user, wherein the voice parking instruction includes a target parking direction and a location of the user;

[0064] Specifically, command parsing is based on information from speech recognition, such as "Please park the car on my right side", extracting words such as "right side" that indicate direction, understanding the user's intention, and determining the target parking direction and the user's location. For example, "right side" in "Please park the car on my right side" is the target parking direction, and "my" indicates the user's location.

[0065] Of course, in addition to analyzing the voice parking instructions issued by the user, the analysis can also include analyzing the parking conditions of the vehicle itself to determine whether subsequent parking actions can be performed safely.

[0066] Step 103: In response to recognizing the target parking direction in the user's parking instruction, controlling the vehicle to park in the target parking direction; in response to not recognizing the target parking direction in the user's parking instruction, recognizing the user's location, controlling the vehicle to travel near the user; in response to not recognizing the target parking direction and the user's location in the user's parking instruction, maintaining the current state of the vehicle and continuing to obtain user instructions.

[0067] In order to solve the problem that users are not convenient or do not want to operate remote control devices such as mobile phones or keys to perform remote parking in some scenarios, this application can control the vehicle to perform remote parking through voice control by users outside the vehicle. The parking direction can be sent in the parking instruction. At this time, the vehicle actively responds and parks according to the position information first; if only the user's position information is recognized, the vehicle drives to the vicinity of the user. In another scenario, if the vehicle responds that it does not recognize the target parking direction and the user's position in the user's parking instruction, the vehicle maintains the current state and waits to continue to obtain user instructions.

[0068] In order to solve the problem that the parking direction cannot be determined when parking by voice, the present application can, on the other hand, determine the user's relative position to the vehicle through the voice positioning function, and then park the vehicle in the direction of the user.

[0069] Of course, during parking, including parking in and out, the vehicle interacts with the user before performing each action. The vehicle performs actions based on voice instructions. Automatic parking serves as an auxiliary function of voice instructions and feeds back the status of the parking process and the final parking status to the user.

[0070] The present invention allows the user to issue a parking instruction outside the vehicle before parking, and determines the orientation of the user's vehicle based on voice positioning to determine the parking direction, and then controls the vehicle to park in the direction of the user who issued the parking instruction. The present invention combines automatic driving, voice recognition and voice positioning technology, so that the user only needs a simple voice instruction to start and complete parking. The entire parking process is free from manual operation, which improves the ability to travel independently and provides users with a convenient and safe parking experience.

[0071] In one embodiment of the present application, in response to identifying a target parking direction in a user parking instruction, controlling the vehicle to park in the target parking direction includes:

[0072] In response to the target parking direction including a plurality of parking positions, controlling the vehicle to park in the target parking direction;

[0073] In response to receiving a target parking position sent by a user, a parking path is formed and the vehicle is controlled to park at the target parking position; in response to not receiving the target parking position sent by the user, the user's location is obtained and the vehicle is controlled to park at a parking position close to the user.

[0074] Specifically, when the vehicle is parked,

[0075] After the user finds the target parking space in the car, he / she leaves the car. When the user moves to the vicinity of the target parking space, he / she activates voice parking and issues parking instructions. The vehicle makes a position judgment based on the voice parking instructions, and at the same time combines the real-time perceived information about the vehicle's surroundings to form a parking path and make real-time adjustments, and parks in the parking space according to the parking path.

[0076] Specifically, the user finds the target parking space in the car, including searching for the target parking space through the in-car display screen and searching for the target parking space outside the car with the naked eye. If the target parking space is found through the in-car display screen, it does not matter whether the passengers in the car get off before parking. At this time, there is no need to plan the path and park based on the positioning information of the parking instruction outside the car. Of course, this mode can also be switched. The user gets off the car and moves to the vicinity of the target parking space, activates voice parking and issues a parking instruction, which can include clear parking direction information. The vehicle makes a direction judgment based on the voice parking instruction, and combines the real-time perceived vehicle surrounding information to form a parking path and adjust it in real time, and parks in the parking space according to the parking path.

[0077] The following is an example scenario that describes the process of a user finding a target parking space in the car, getting out of the car, and activating the vehicle to automatically park through voice parking commands. This scenario includes steps such as environmental perception, orientation judgment, path planning, and real-time adjustment.

[0078] Exemplary application scenarios:

[0079] The user drives into the parking lot: the vehicle's cameras, ultrasonic sensors and radars start working to scan the surrounding environment; the image processing module identifies vacant parking spaces through computer vision algorithms (such as YOLO) and marks them on the in-vehicle display screen; the user sees the marked vacant parking spaces through the in-vehicle display screen and selects one as the target parking space; and / or combines human visual recognition to search for vacant parking spaces.

[0080] The user parks the vehicle near a target parking space, then gets out of the vehicle and walks to the target parking space to confirm the specific location of the parking space.

[0081] The user stands near the target parking space and speaks a specific voice wake-up command (such as "Hi, car"); the vehicle's microphone array captures the command and starts the voice recognition function to identify the user. After the identity is recognized, the user continues to say: "Please park the car in this parking space." If the specific location information is received, the car is parked according to the location command information; otherwise, the vehicle's microphone array determines the user's relative position in the vehicle through sound source localization technology (such as TDOA algorithm), and determines the specific location of the target parking space based on the user's relative position;

[0082] The vehicle's cameras, ultrasonic sensors and radars scan the surroundings again to ensure that there are no new obstacles. They also detect the size, shape, lane lines and road signs of the target parking space to confirm that it is suitable for parking the vehicle.

[0083] The optimal parking path is calculated based on the vehicle's current position and the position of the target parking space; the path planning takes into account the vehicle's size, turning radius, and surrounding obstacles;

[0084] The vehicle starts to drive along the planned path, while the sensors continue to monitor changes in the surrounding environment; if new obstacles or environmental changes are detected, the path planning module will adjust the parking path in real time to avoid the obstacles.

[0085] Exemplarily, after scanning the surrounding environment, map information corresponding to the surrounding environment of the current vehicle can be constructed, including information such as parking spaces, lane lines, road signs, obstacles, etc. Then, the parking starting point can be determined based on the vehicle position information, and then an empty parking space can be detected in the map information as the parking end point. Then, based on the preset path search algorithm, a corresponding real-time parking path can be generated according to the surrounding scene map, the parking starting point and the parking end point. The real-time parking path can be the shortest path or the optimal path. The vehicle status information of the current vehicle (such as vehicle speed, steering angle, acceleration, etc.) can also be collected through on-board sensors to constrain the path planning of the real-time parking path.

[0086] The vehicle gradually approaches the target parking space along the adjusted path. During this process, the vehicle's control unit (such as ECU or TCU) controls the vehicle's steering, acceleration and braking to ensure smooth and safe parking in the parking space.

[0087] After the vehicle successfully parks in the target parking space, the vehicle informs the user through a voice prompt that parking is complete, such as "Parking is complete, please check the vehicle position."

[0088] As an embodiment of the present application, in response to not identifying the target parking direction in the user's parking instruction, identifying the user's location, and controlling the vehicle to travel near the user includes:

[0089] In response to receiving a parking instruction from a user while the vehicle is controlled to travel near the user, the vehicle is controlled to park based on the parking instruction from the user.

[0090] Specifically, during the parking process, the user activates voice parking and issues a parking instruction after getting off the vehicle. The vehicle makes a direction judgment based on the voice parking instruction. If the target parking direction in the user's parking instruction is not recognized, but the user's location is recognized, the vehicle plans a route based on the real-time perceived information around the vehicle and drives to the place where the voice is issued. During the driving process, the parking space is detected in real time. If a parking space is detected, the vehicle stops and feeds back the information of the detected parking space to the user. The vehicle parks in the parking space based on the last voice parking instruction issued by the user.

[0091] For example, when the vehicle is driving towards the source of the vehicle, the vehicle's sensors (such as cameras, ultrasonic sensors, radars) continuously scan the surrounding environment to find an empty parking space; when a suitable empty parking space is detected, the location information of the parking space is recorded, the vehicle stops driving, and informs the user through a voice prompt: "A vacant parking space has been found, please confirm whether to park here." If the user replies through voice: "Yes, park here.", the vehicle parks at the parking space; during this process, the user can issue a variety of voice parking instructions to the vehicle, such as Figure 5 As shown, such as: "Drive the car over here", "Park to my left / right", "Park in front of me / behind me", "Find a perpendicular parking space and park", "Find a parallel parking space and park", "Find a diagonal parking space and park", "Start parking", "Pause parking", "Stop parking", etc., until the vehicle responds to the last voice parking command issued by the user, such as Figure 4 As shown, if the voice parking command "drive the car in" is issued, the vehicle responds and executes to complete parking in the parking space.

[0092] Using multiple voice parking commands can significantly improve the user experience, while also enhancing the safety and efficiency of the system, adapting to a variety of parking scenarios, and providing greater flexibility and reliability. These benefits make the automatic parking system more intelligent and user-friendly, providing users with a more comfortable and convenient driving experience.

[0093] In the above embodiment, the vehicle determines the direction based on the voice parking command. If the user's position is recognized, the parking path is formed and adjusted in real time based on the real-time perceived vehicle surrounding information to park in the direction of the user. If the user's position is not recognized, the parking direction command is input and the vehicle is parked in the direction input by voice until parking is completed in the parking space.

[0094] In one embodiment of the present application, when parking, after the vehicle moves to the place where the voice parking command is issued, the vehicle stops moving; it waits for the user to perform on-board operations or further make various instructions similar to those mentioned above, until it parks in the parking space based on the last voice parking command issued by the user.

[0095] In one embodiment of the present application, during the process of driving to the place where the voice is issued, when it is recognized that the user issues a voice command to park in front of the vehicle, or in front of the left or right front, the vehicle as a whole drives forward; when it is recognized that the user issues a voice command to park behind the vehicle, or in rear left or right rear, the vehicle as a whole drives backward.

[0096] For example, Figure 2 As shown, based on the sound source recognition technology, the user's position relative to the vehicle can be determined, including the front of the vehicle, the left front of the vehicle, the right front of the vehicle, the rear of the vehicle, the left rear of the vehicle, the right rear of the vehicle, the left side of the vehicle, and the right side of the vehicle; as shown Figure 3 As shown, when it is recognized that the user issues a parking voice command in front of the vehicle, or in the front left or right, the vehicle drives forward at a low speed; when it is recognized that the user issues a parking voice command behind the vehicle, or in the rear left or right, the vehicle drives backward at a low speed.

[0097] Explanatory, the sound source identification technology determines the location of the sound source by analyzing the time difference or intensity difference of the sound signal reaching multiple microphones. The sound source positioning can be achieved based on the time difference method, the intensity difference method or the beamforming method. Specifically, the time difference method compares the time difference of the sound signals received by different microphones, and uses the time difference and the distance between the microphones to calculate the location of the sound source through the triangulation method. The intensity difference method compares the intensity difference of the sound signals received by different microphones, and estimates the direction of the sound source through the intensity difference and the layout of the microphones. The beamforming method enhances the sound signal from a specific direction through weighting and phase adjustment, and determines the direction of the sound source through the results of beamforming.

[0098] Exemplarily, multiple microphones can be installed at different positions of the vehicle, such as the front, rear, left and right sides of the vehicle, to capture sound signals; the sound signals collected from the microphone array are processed, sound source localization calculations are performed based on the above-mentioned methods, and the parking operation of the vehicle is coordinated according to the sound source localization calculation results.

[0099] In one embodiment of the present application, when the vehicle is driving towards the place where the voice is issued, if a parking space is detected, the vehicle will park at the parking space in response to the voice parking command issued by the user according to the method described in the above embodiment; if the vehicle detects multiple parking spaces, such as Figure 4 As shown, the user issues a voice parking command, such as "park the car in" or "park the car in the parking space on the right", and the vehicle responds to the voice parking command issued by the user and parks the car in the parking space at the user's location or directly parks according to the direction information contained in the voice parking command.

[0100] In one embodiment of the present application, the voice parking instruction also includes a parking intention. In response to receiving that the parking intention is to park out and not receiving a target parking direction, the vehicle is controlled to park out of the parking space toward the user's location and park according to the user's location.

[0101] When parking, the user activates voice parking outside the vehicle and issues a parking command. The vehicle determines the direction based on the voice parking command, and combines the real-time perceived vehicle surrounding information to plan the route and drive to the location where the voice is issued.

[0102] For example, the vehicle locates the user's position based on the parking instruction, and then determines the parking direction, and controls the vehicle to park out in combination with the current parking space type. Parking space types include vertical parking spaces, horizontal parking spaces, and diagonal parking spaces. The vehicle determines the current parking space type in the following ways: based on the memory of the last parking space and based on the environment in which the vehicle is located.

[0103] When judging the current parking space type based on the memory of the last parking space, it relies on the data recorded when the vehicle was parked before, which is applicable to fixed parking spaces or parking lots frequently used by users. The recorded data information includes location information: recording the specific location coordinates of the parking space; parking space type: recording whether the parking space is a vertical parking space, a horizontal parking space, or a diagonal parking space; environmental characteristics: recording the environmental characteristics around the parking space, such as ground markings, obstacles, etc.

[0104] When judging the current parking space type based on the environment in which the vehicle is located, the sensors and image processing technology on the vehicle are used to identify the parking space type in the current environment in real time. When collecting data, the surrounding environment images can be captured based on the cameras installed on the front, back and sides of the vehicle; the obstacle distance around the vehicle can be detected based on the ultrasonic sensor; and the long-distance obstacle detection and environmental perception can be performed based on the vehicle-mounted radar. After pre-processing operations such as denoising and enhancement on the collected images, computer vision algorithms (such as YOLO and SSD) are used to identify the parking space marking lines in the image to determine the parking space type.

[0105] For example, when it is recognized that the user issues a parking instruction on the left side, left front or left rear of the vehicle, and the current parking space is perpendicular, the vehicle is controlled to park perpendicularly to the left; when it is recognized that the user issues a parking instruction on the right side, right front or right rear of the vehicle, and the current parking space is perpendicular, the vehicle is controlled to park perpendicularly to the right. Figure 6 shown.

[0106] For example, when it is recognized that the user issues a parking instruction on the left side, left front or left rear of the vehicle, and the current parking space is horizontal, the vehicle is controlled to park horizontally to the left; when it is recognized that the user issues a parking instruction on the right side, right front or right rear of the vehicle, and the current parking space is horizontal, the vehicle is controlled to park horizontally to the right, such as Figure 7 shown.

[0107] As an embodiment of the present invention, obtaining and parsing a voice parking instruction issued by a user includes:

[0108] Acquire the user's voice parking instructions in real time and judge the parking conditions, and update the vehicle's parking status in real time based on the user's voice parking instructions.

[0109] In response to a voice parking instruction issued by a user through voiceprint recognition, a parking condition determination is performed;

[0110] Before parking, the voiceprint needs to be identified to determine whether the parking command should be responded to; after the voiceprint recognition is passed, the parking conditions need to be judged to ensure the safety and feasibility of subsequent parking operations.

[0111] Security considerations include:

[0112] By detecting obstacles and the environment around the vehicle, collisions can be avoided during parking. If there are pedestrians, other vehicles or other obstacles around, parking can be paused or the parking operation can be stopped or adjusted in time.

[0113] Make sure that the vehicle is not damaged by the parking maneuver. For example, if the parking space is too small or the ground is uneven, it may cause scratches or undercarriage damage to the vehicle.

[0114] If the parking conditions are not met, the user can be reminded and appropriate measures can be taken to circumvent them until the parking conditions are met, ensuring the safety of the user and others during the parking process.

[0115] Feasibility considerations include:

[0116] Different environments (such as parking lots, roadside parking, etc.) have different requirements for parking. By judging the conditions, it can be determined whether the current environment is suitable for automatic parking.

[0117] Detect the size of the target parking space to ensure that it can accommodate the vehicle. If the parking space is too small, the user can be prompted to choose another parking space.

[0118] Check whether the ground is flat to avoid parking on uneven ground which may cause the vehicle to tilt or become unstable.

[0119] Of course, parking conditions are based on the normal status of the vehicle system. On the one hand, it is necessary to confirm that the key systems of the vehicle (such as motors, sensors, etc.) are in normal working condition. If a system fails, it may affect the safety and accuracy of the parking operation. On the other hand, it is necessary to ensure that all doors and trunks are closed to avoid damage or inconvenience during parking.

[0120] In one embodiment of the present application, the vehicle control utilization includes a voice positioning module, an environmental perception module, a parking control module and a parking execution module, and the parking condition judgment includes: the vehicle is operating normally, the vehicle doors are closed and the space around the vehicle meets the parking requirements; the vehicle is operating normally includes the voice positioning module, the environmental perception module, the parking control module and the parking execution module all operating normally.

[0121] The above-mentioned voice positioning module is installed on the vehicle and can confirm the legitimacy of the user's identity in the vehicle based on the voiceprint of the user's voice. If the user is a legitimate user in the vehicle, the vehicle can execute the user's parking command, otherwise the user's parking command will not be executed. The voice positioning module can identify the specific parking intention in the user's voice through generalized voice recognition technology, including one or more of starting parking, pausing parking, continuing parking, exiting parking, parking in, parking out, moving forward, moving backward, parking out to the left, and parking out to the right, and can convert the recognized parking intention into a corresponding signal and send it to the parking control module.

[0122] The voice positioning module includes a sound receiver and a voice announcer. There can be multiple sound receivers installed outside the vehicle. By comparing the energy strength of the same sound received by each sound receiver, the user's relative position to the vehicle is determined, including one or more of the front of the vehicle, the left front of the vehicle, the right front of the vehicle, the rear of the vehicle, the left rear of the vehicle, the right rear of the vehicle, the left side of the vehicle, the right side of the vehicle, and parking in the direction of the user, and the identified user position is sent to the parking control module. The position is divided as follows: Figure 2 The voice announcer of the voice positioning module can receive the voice announce command of the parking control module and make voice announce to inform the current parking status.

[0123] The parking control module can receive the parking instruction from the voice positioning module and determine whether the parking instruction can be executed. If the parking conditions are met, the user's parking instruction is executed, otherwise the parking instruction is not executed. When parking, the user needs to drive the vehicle to search and select a parking space, and then activate voice parking to park the vehicle through voice instructions. When parking, the parking control module can determine the parking direction according to the user's position identified by the voice positioning module. When it is identified that the user is on the left side, left front or left rear of the vehicle and issues a parking instruction, the parking control module controls the vehicle to plan to park to the left; when it is identified that the user is on the right side, right front or right rear of the vehicle and issues a parking instruction, the parking control module controls the vehicle to plan to park to the right. The parking control module can also park according to the parking direction in the user's voice instruction. When controlling forward and backward movement, when recognizing that the user sends a voice command to park in the direction of the user in front of the vehicle, the left front, or the right front, the parking control module controls the vehicle to move forward; when recognizing that the user sends a voice command to park in the direction of the user in the rear, the left rear, or the right rear, the parking control module controls the vehicle to move backward. During the parking process, the user can pause parking, continue parking, or exit parking by voice. The parking actuator executes the parking action under the control of the parking control module to complete the parking.

[0124] For example, the process of determining whether the parking condition is currently met by the parking control module in the above example covers the entire parking process, such as Fig. 9 As shown, the specific process includes:

[0125] 1) The parking control module receives the parking instruction and enters the parking process;

[0126] 2) The parking control module determines whether the current parking conditions are met, including: the vehicle modules are working normally; the vehicle doors are closed; the space around the vehicle meets the parking requirements; if the parking conditions are met, parking begins; if the parking conditions are not met, parking ends and the parking status is fed back to the user through the voice positioning module;

[0127] 3) During the whole process of parking, the parking control module shall always detect whether there are any conditions that lead to parking exit, such as: any module working abnormally or the user actively exiting the parking. If the exit condition occurs, the parking will be exited and the parking status will be fed back to the user through the voice positioning module; if the exit condition does not occur, the parking will be carried out normally;

[0128] 4) During the whole process of parking, the parking control module should always detect whether there are any conditions that cause parking to be suspended, such as: the car door is opened or the user actively suspends parking or encounters an obstacle on the parking path, etc. If a suspension condition occurs, the parking is suspended and the parking status is fed back to the user through the voice positioning module; if no suspension condition occurs, parking is carried out normally;

[0129] 5) When the conditions for suspending parking occur, suspend parking; if the suspension conditions disappear within a specified time after suspending parking, such as within 1 minute, and the user resumes parking, continue parking; otherwise, exit parking and feedback the parking status to the user through the voice positioning module.

[0130] In one embodiment of the present application, it is determined whether the voice parking instruction contains direction information. If it does not contain direction information, the user's direction is determined by voice positioning; if it contains direction information, parking is performed directly according to the direction information. The direction information can be included in the initial voice parking instruction or in subsequent parking instructions.

[0131] For example, Figure 8 As shown, the parking direction determination process includes the following steps:

[0132] 1) The user wakes up the vehicle through voice, so that the vehicle can receive the next parking instruction;

[0133] 2) After the vehicle receives the wake-up command, it performs voiceprint recognition to confirm whether the user is a legitimate user of the vehicle;

[0134] 3) If the voiceprint recognition fails, you will be prompted to enter the voiceprint;

[0135] 4) After the voiceprint recognition is passed, the user can continue to issue parking instructions;

[0136] 5) After the user issues a parking command, the direction of the sound source of the parking command is determined, thereby determining the relative position of the user to the vehicle;

[0137] 6) If the user's position relative to the vehicle is not successfully identified, or parking cannot be performed in the identified direction, the user is required to input the parking direction by voice;

[0138] 7) Control the vehicle to park according to the parking command position or the direction input by the owner's voice until it reaches the final position.

[0139] In one embodiment of the present application, a vehicle control device based on voice positioning, such as Fig.10 As shown, the device comprises:

[0140] Identity recognition module: in response to receiving a voice wake-up command from the user, performs voiceprint recognition;

[0141] Parking instruction receiving and parsing module: in response to the voiceprint recognition being passed, obtaining and parsing the voice parking instruction issued by the user, wherein the voice parking instruction includes the target parking direction and the user's location;

[0142] Parking execution module: in response to recognizing the target parking direction in the user's parking instruction, controlling the vehicle to park in the target parking direction; in response to not recognizing the target parking direction in the user's parking instruction, recognizing the user's location, controlling the vehicle to drive near the user; in response to not recognizing the target parking direction and the user's location in the user's parking instruction, maintaining the current state of the vehicle and continuing to obtain user instructions.

[0143] Further, in response to identifying the target parking direction in the user's parking instruction, controlling the vehicle to park in the target parking direction includes:

[0144] In response to the target parking direction including a plurality of parking positions, controlling the vehicle to park in the target parking direction;

[0145] In response to receiving a target parking position sent by a user, a parking path is formed and the vehicle is controlled to park at the target parking position; in response to not receiving the target parking position sent by the user, the user's location is obtained and the vehicle is controlled to park at a parking position close to the user.

[0146] Further, in response to not identifying the target parking direction in the user's parking instruction, identifying the location of the user, and controlling the vehicle to travel near the user includes:

[0147] In response to receiving a parking instruction from a user while the vehicle is controlled to travel near the user, the vehicle is controlled to park based on the parking instruction from the user.

[0148] Furthermore, the voice parking instruction also includes a parking intention. In response to receiving that the parking intention is to park out and not receiving a target parking direction, the vehicle is controlled to park out of the parking space toward the user's location according to the user's location and park.

[0149] Furthermore, the obtaining and parsing of the voice parking instruction issued by the user includes:

[0150] Acquire the user's voice parking instructions in real time and judge the parking conditions, and update the vehicle's parking status in real time based on the user's voice parking instructions.

[0151] Further, in response to receiving a voice wake-up instruction issued by a user, performing voiceprint recognition includes:

[0152] In response to the voiceprint recognition failing, feedback is given to the user, and the user is prompted to enter the voiceprint.

[0153] In one embodiment of the present application, a vehicle includes the control device described in the above embodiment.

[0154] like Fig.11, is a block diagram of a computer device according to an embodiment of the present application. The computer device is intended to represent various forms of digital computers or mobile devices. The digital computer may include a desktop computer, a portable computer, a workbench, a personal digital assistant, a server, a mainframe computer, and other suitable computers. The mobile device may include a tablet computer, a smart phone, a wearable device, etc.

[0155] like Fig.11 As shown, computer device 400 includes computing unit 401, ROM 402, RAM 403, bus 404, and input / output (I / O) interface 405, and computing unit 401, ROM 402, and RAM 403 are connected to each other through bus 404. Input / output (I / O) interface 405 is also connected to bus 404.

[0156] The computing unit 401 may perform various processes in the method embodiment of the present application according to computer instructions stored in a read-only memory (ROM) 402 or computer instructions loaded from a storage unit 408 into a random access memory (RAM) 403. The computing unit 401 may be a variety of general and / or special processing components with processing and computing capabilities. The computing unit 401 may include, but is not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc.

[0157] In some embodiments, the method provided by the embodiments of the present application may be implemented as a computer software program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 408 .

[0158] RAM 409 may also store various programs and data required for the operation of device 400. Part or all of a computer program may be loaded and / or installed on device 400 via ROM 402 and / or communication unit 409.

[0159] The input unit 406, output unit 407, storage unit 408 and communication unit 409 in the computer device 400 can be connected to the I / O interface 405. The input unit 406 can be, for example, a keyboard, a mouse, a touch screen, a microphone, etc. The output unit 407 can be, for example, a display, a speaker, an indicator light, etc. The device 400 can exchange information, data, etc. with other devices through the communication unit 409.

[0160] It should be noted that the device may also include other components necessary for normal operation, or may only include components necessary for implementing the solution of the present application, rather than all the components shown in the figure.

[0161] Various implementations of the systems and techniques described herein can be realized in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof.

[0162] The computer instructions for implementing the method of the present application can be written in any combination of one or more programming languages. These computer instructions can be provided to the computing unit 401, so that when the computer instructions are executed by the computing unit 401 such as a processor, the steps involved in the method embodiment of the present application are executed.

[0163] The present application also provides a computer-readable storage medium on which computer instructions are stored, and the computer instructions are used to enable a computer to execute the screen focus control method described in any of the above embodiments.

[0164] The computer-readable storage medium provided in the present application may be a tangible medium that may contain or store computer instructions for executing the steps involved in the method embodiments of the present application. The computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, and other forms of storage media.

[0165] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A vehicle control method based on voice positioning, characterized in that: The method includes: In response to receiving a voice wake-up command issued by a user, performing voiceprint recognition; In response to the voiceprint recognition being successful, obtaining and parsing a voice parking instruction issued by the user, wherein the voice parking instruction includes a target parking direction and a location of the user; In response to identifying a target parking direction in a user's parking instruction, controlling the vehicle to park in the target parking direction; In response to not recognizing the target parking direction in the user's parking instruction, recognizing the location of the user, and controlling the vehicle to travel near the user; In response to not recognizing the target parking direction and the user's position in the user's parking instruction, maintaining the current state of the vehicle and continuing to obtain the user instruction.

2. A vehicle control method based on voice positioning as claimed in claim 1, characterized in that: In response to identifying the target parking direction in the user's parking instruction, controlling the vehicle to park in the target parking direction includes: In response to the target parking direction including a plurality of parking positions, controlling the vehicle to park in the target parking direction; In response to receiving a target parking position sent by a user, a parking path is formed and the vehicle is controlled to park at the target parking position; in response to not receiving the target parking position sent by the user, the user's location is obtained and the vehicle is controlled to park at a parking position close to the user.

3. A vehicle control method based on voice positioning as claimed in claim 1, characterized in that: In response to not identifying the target parking direction in the user's parking instruction, identifying the location of the user, and controlling the vehicle to travel near the user includes: In response to receiving a parking instruction from a user while the vehicle is controlled to travel near the user, the vehicle is controlled to park based on the parking instruction from the user.

4. The vehicle control method based on voice positioning according to claim 1, characterized in that: The voice parking instruction also includes a parking intention. In response to receiving that the parking intention is to park out and not receiving a target parking direction, the vehicle is controlled to park out of the parking space toward the user's location according to the user's location and park.

5. The vehicle control method based on voice positioning according to claim 1, characterized in that: The obtaining and parsing of the voice parking instruction issued by the user includes: Acquire the user's voice parking instructions in real time and judge the parking conditions, and update the vehicle's parking status in real time based on the user's voice parking instructions.

6. The vehicle control method based on voice positioning according to claim 1, characterized in that: In response to receiving a voice wake-up instruction issued by a user, performing voiceprint recognition includes: In response to the voiceprint recognition failing, feedback is given to the user, and the user is prompted to enter the voiceprint.

7. A vehicle control device based on voice positioning, characterized in that: The device includes: Identity recognition module: in response to receiving a voice wake-up command from the user, performs voiceprint recognition; Parking instruction receiving and parsing module: in response to the voiceprint recognition being passed, obtaining and parsing the voice parking instruction issued by the user, wherein the voice parking instruction includes the target parking direction and the user's location; Parking execution module: in response to recognizing the target parking direction in the user's parking instruction, controlling the vehicle to park in the target parking direction; in response to not recognizing the target parking direction in the user's parking instruction, recognizing the user's location, controlling the vehicle to drive near the user; in response to not recognizing the target parking direction and the user's location in the user's parking instruction, maintaining the current state of the vehicle and continuing to obtain user instructions.

8. A vehicle, characterized in that: Comprising the control device as claimed in claim 7.

9. A computer device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores computer instructions that can be executed by the at least one processor, and the computer instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 6.

10. A computer-readable storage medium having computer instructions stored thereon, characterized in that: The computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 6.

Images