Vehicle control methods, devices, vehicles and storage media

Abstract

This application provides a vehicle control method, apparatus, vehicle, and storage medium. The method, applied in the vehicle field, includes: detecting the adjustment angle of a seat in the vehicle; if the adjustment angle is greater than a preset angle threshold, determining to disable the recognition function of a first microphone in the vehicle's initial voice recognition system, and performing signal enhancement processing on the audio signal collected by a second microphone to obtain a target voice recognition system; if a first voice command is detected, obtaining the target voice region of the first voice command based on the first voice command and the target voice recognition system; and controlling a target component in the target voice region to execute the control command. This method can accurately provide voice control services to users by precisely locating the position when the user issues a voice command, thus improving the user experience.

Description

Technical Field

[0001] This application relates to the field of vehicles, and more specifically, to a vehicle control method, apparatus, vehicle, and storage medium in the field of vehicle control technology. Background Technology

[0002] With the rapid development of vehicle control technology, voice technology is being used more and more widely in vehicles. Many models are equipped with multi-zone voice recognition systems, which can usually cover all seating areas in the vehicle, allowing passengers to control various functions of the vehicle through voice commands.

[0003] However, in some cases, existing voice recognition systems may misidentify the user's location, leading to incorrect actions and impacting the user experience.

[0004] Therefore, when a user's voice command is detected in a vehicle, how to accurately provide voice control services to the user and improve the user experience is a problem that needs to be solved. Summary of the Invention

[0005] This application provides a vehicle control method, apparatus, vehicle, and storage medium. The method can accurately provide voice control services to users by precisely locating the user's position when issuing a voice command, thereby improving the user experience.

[0006] Firstly, a vehicle control method is provided, the method comprising:

[0007] The system detects the adjustment angle of the seat in the vehicle; if the adjustment angle is greater than a preset angle threshold, it determines to disable the recognition function of the first microphone in the vehicle's initial voice recognition system and performs signal enhancement processing on the audio signal collected by the second microphone to obtain the target voice recognition system; wherein, the first microphone is a microphone in the area adjacent to the seat in the adjustment direction corresponding to the adjustment angle; the second microphone is a microphone in the area where the seat is located; if a first voice command is detected, the target sound region of the first voice command is obtained based on the first voice command and the target voice recognition system; wherein, the first voice command is used to represent the control command of the target component in the vehicle; the target component in the target sound region is controlled to execute the control command.

[0008] In the embodiments of this application, by detecting the adjustment angle of the seat in the vehicle, if the detected adjustment angle is greater than a preset angle threshold, the recognition function of the pickup device adjacent to the pickup device in the target seat's sound zone along the direction of the seat adjustment angle is turned off, and signal enhancement processing is performed on the pickup device in the seat's sound zone to obtain an adjusted voice recognition system; based on the adjusted voice recognition system, the user's voice command is detected, and the sound zone where the user issued the voice command is determined through location recognition; based on the determined sound zone, the components in the vehicle are controlled to perform operations; in the above scheme, when the seat adjustment angle is greater than the preset angle threshold, because the pickup device adjacent to the pickup device in the direction of the adjustment angle is turned off, the recognition function of the pickup device in the target seat's sound zone is turned off. The system's ability to identify adjacent microphones within a specific area prevents the voice command from being mistakenly located in the same area as the adjacent seat when the seat is reclined at a large angle. Furthermore, by enhancing the signal of the microphone in the seat's area, interference from other audio signal components is reduced. This also avoids the problem of signal attenuation of the voice command due to the distance between the sound source and the microphone in the seat's area at a large reclined angle, preventing the microphone in that area from detecting the voice command. Therefore, the accuracy of voice command localization is improved, providing users with accurate voice control services and enhancing the user experience.

[0009] In conjunction with the first aspect, some possible implementations also include:

[0010] The system detects whether a user is on the seat; if the adjustment angle is greater than a preset angle threshold, it determines to disable the recognition function of the first microphone in the vehicle's initial voice recognition system and performs signal enhancement processing on the audio signal collected by the second microphone, including: if a user is detected on the seat and the adjustment angle is greater than a preset angle threshold, it determines to disable the recognition function of the first microphone and performs signal enhancement processing on the audio signal collected by the second microphone.

[0011] In the embodiments of this application, when a user is detected on the seat and the seat adjustment angle is greater than a preset angle threshold, the voice recognition system is adjusted to obtain an adjusted voice recognition system. Because this adjustment process disables the recognition function of the pickup devices adjacent to the pickup device in the seat's acoustic zone along the direction of the seat adjustment angle, and performs signal enhancement processing on the pickup device in the seat's acoustic zone, it can avoid misrecognition of voice commands. For example, when a user sits on the seat and adjusts the seat's recline angle significantly, the voice recognition system might mistakenly locate the user's position as the seat behind the user's seat when recognizing the user's voice command. Through the above solution, the accuracy of voice command positioning can be improved, thereby providing users with accurate voice control services and enhancing the user experience.

[0012] Combining the first aspect and the above implementation methods, some possible implementation methods for detecting whether a user is on the seat include:

[0013] Acquire the pressure sensor values ​​of each seat in the vehicle; based on the pressure sensor values, determine whether a user is in the seat; or, acquire an image of the vehicle's cabin; based on the cabin image, determine whether a user is in the seat.

[0014] In one implementation of this application, by acquiring the values ​​of pressure sensors in each seat, when the pressure sensors detect pressure distribution or changes in the seats, it is possible to determine which seats have users present based on these values, thereby determining how to adjust the voice recognition system to achieve accurate recognition and positioning of voice commands. In another implementation, by acquiring cabin images of the vehicle, and using image recognition algorithms to determine which seats have users present, it is possible to determine how to adjust the voice recognition system to achieve accurate recognition and positioning of voice commands.

[0015] In combination with the first aspect and the above implementation methods, in some possible implementation methods, signal enhancement processing is performed on the audio signal acquired by the second pickup device, including:

[0016] The audio signal component from the target direction in the audio signal acquired by the second pickup device is subjected to signal enhancement processing; wherein, the target direction is obtained based on the time and phase information of the acquired audio signal.

[0017] In the embodiments of this application, the location of the user's voice command is determined by the time and phase information of the collected audio signal. The audio signal component of the audio signal collected by the second pickup device at that location is enhanced. Because of the signal enhancement, the interference generated by the audio signal components in other locations is reduced, which can more accurately identify and locate the user and avoid the problem that the user who issued the voice command is too far away from the pickup device in the sound zone of his / her seat, resulting in the inability to identify the user.

[0018] Combining the first aspect and the above implementation methods, in some possible implementation methods, detecting the adjustment angle of the seat in the vehicle includes:

[0019] Acquire images of the vehicle's seats; determine the seat adjustment angle based on the seat images.

[0020] In the embodiments of this application, by acquiring image information in the cockpit, the adjustment angle of the seat is determined based on the image information. By determining the adjustment angle of the seat, the voice recognition system can be adjusted to avoid misidentifying the user's position in the wrong seat position due to a large adjustment angle of the seat, thereby improving the accuracy of voice command positioning.

[0021] In combination with the first aspect and the above implementation methods, some possible implementation methods also include:

[0022] If the adjustment angle is less than or equal to the preset angle threshold, when the second voice command is detected, the target voice region of the second voice command is determined based on the second voice command and the initial voice recognition system.

[0023] In the embodiments of this application, if the seat adjustment angle is less than or equal to a preset angle threshold, the voice command is recognized based on the initial voice recognition system, that is, the audio signals collected by all the microphones in the cabin are acquired, and the target sound region is determined based on the audio signals collected by all the microphones. Therefore, it is ensured that when the user's seat adjustment angle returns to less than the preset angle threshold, the voice recognition system can accurately recognize and locate the voice command.

[0024] In combination with the first aspect and the above implementation methods, some possible implementation methods also include:

[0025] Obtain the area inside the vehicle and / or the dimensions of the seats inside the vehicle; determine a preset angle threshold based on the area inside the vehicle and / or the dimensions of the seats inside the vehicle.

[0026] In the embodiments of this application, the area inside the vehicle and / or the dimensions of the seats inside the vehicle are obtained, wherein a preset angle threshold is positively correlated with the area of ​​the cabin; that is, the larger the area inside the vehicle, the larger the preset angle. Therefore, it is possible to optimize the configuration for different vehicle types and cabin layouts, ensuring that voice recognition can be performed in a suitable manner in various in-vehicle environments.

[0027] Secondly, a vehicle control device is provided, comprising:

[0028] The acquisition module is used to detect the adjustment angle of the seats in the vehicle;

[0029] The processing module is used to determine to disable the recognition function of the first microphone in the vehicle's initial voice recognition system if the adjustment angle is greater than a preset angle threshold, and to perform signal enhancement processing on the audio signal collected by the second microphone to obtain the target voice recognition system; wherein, the first microphone is the microphone corresponding to the adjacent area of ​​the seat area in the adjustment direction corresponding to the adjustment angle; the second microphone is the microphone in the seat area; if a first voice command is detected, the target sound region of the first voice command is obtained based on the first voice command and the target voice recognition system; wherein, the first voice command is used to represent the control command of the target component in the vehicle; and the target component in the target sound region is controlled to execute the control command.

[0030] It should be understood that the extensions, limitations, explanations and descriptions of the relevant content in the first aspect above also apply to the same content in the second aspect.

[0031] Thirdly, a car is provided, including:

[0032] Memory, used to store executable program code;

[0033] A processor for calling and running executable program code from memory, causing the computer to perform the methods of the first aspect or any possible implementation thereof.

[0034] Fourthly, a computer-readable storage medium is provided that stores computer program code, which, when executed on a computer, causes the computer to perform the methods described in the first aspect or any possible implementation thereof. Attached Figure Description

[0035] Figure 1 This is a schematic diagram of a four-zone vehicle provided in an embodiment of this application;

[0036] Figure 2 This is a schematic diagram of a vehicle seat at different tilt angles according to an embodiment of this application;

[0037] Figure 3 This is a schematic diagram of a six-tone vehicle provided in an embodiment of this application;

[0038] Figure 4 This is a schematic flowchart of a vehicle control method provided in an embodiment of this application;

[0039] Figure 5 This is a schematic diagram of a four-zone vehicle control method provided in an embodiment of this application;

[0040] Figure 6 This is a schematic diagram of a six-zone vehicle control method provided in an embodiment of this application;

[0041] Figure 7 This is a schematic flowchart of another vehicle control method provided in an embodiment of this application;

[0042] Figure 8 This is a schematic flowchart of another vehicle control method provided in the embodiments of this application;

[0043] Figure 9 This is a schematic diagram of the structure of a vehicle control device provided in an embodiment of this application;

[0044] Figure 10 This is a schematic diagram of the structure of a vehicle provided in an embodiment of this application. Detailed Implementation

[0045] The technical solutions in this application will be clearly and thoroughly described below with reference to the accompanying drawings. In the description of the embodiments of this application, unless otherwise stated, " / " means "or," for example, A / B can mean A or B. "And / or" in the text is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Furthermore, in the description of the embodiments of this application, "multiple" refers to two or more than two.

[0046] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

[0047] The following is combined with Figures 1 to 3 The application scenarios of this solution are illustrated with examples.

[0048] Figure 1 This is a schematic diagram of a four-tone vehicle provided in an embodiment of this application.

[0049] For example, Figure 1 The four-zone vehicle 100 includes seats 101, 102, 103, and 104; seat 101 is the driver's seat, seat 102 is the front passenger seat, seat 103 is the left seat in the second row, and seat 104 is the right seat in the second row. The sound zones in the vehicle can be divided according to the areas where the seats are located; for example, each seat's preset range can correspond to a separate sound zone. Figure 1 As shown in (b), seat 101 corresponds to pitch range 105, seat 102 corresponds to pitch range 106, seat 103 corresponds to pitch range 107, and seat 104 corresponds to pitch range 108; wherein, pitch range 105 is the left front pitch range, pitch range 106 is the right front pitch range, pitch range 107 is the left rear pitch range, and pitch range 108 is the right rear pitch range.

[0050] Each zone is equipped with a sound pickup device; seats 101 and 102 are the front seats of the four-zone vehicle 100, and their backrest angles can usually be adjusted.

[0051] It should be noted that, in the embodiments of this application, the adjustment angle of the seat refers to the reclining angle of the seat back.

[0052] Figure 2 This is a schematic diagram of a vehicle seat at different tilt angles according to an embodiment of this application.

[0053] For example, Figure 2Scenario 200 includes seats 102 and 104. A user sits on seat 102, and the adjustment angle of seat 102 is relatively small, such as... Figure 2 As shown in (a), the user's head is relatively close to the microphone in sound zone 106, and the scene inside the cockpit at this time is as follows. Figure 1 As shown in (a), when a user issues a voice command that only controls the target component without specifying a location, the location of the voice command is located in audio zone 106 via voice recognition, and the component in audio zone 106 is controlled. For example, when a user issues the voice command "turn on seat heating," the location of the voice command is located in audio zone 106 via voice recognition, and the seat 102 in audio zone 106 is controlled to perform the seat heating function. When the user is sitting on seat 102, and the seat 102 has a large adjustment angle, as shown in (a), the system can adjust the position accordingly. Figure 2 As shown in (b), the user's head is closer to the pickup device in zone 108 than to the pickup device in zone 106. At this time, the seating arrangement within the cockpit is as follows: Figure 2 As shown in (c), in this case, when the user actually wants to control the seat 102 where he is currently located to perform some functions and issues a voice command, the existing voice recognition technology does not take into account the influence of the user's riding posture when issuing the voice command. It will identify the user's position when issuing the voice command as the voice zone 108 and mistakenly judge that the user is on the seat 104, thus executing the wrong operation.

[0054] It should be understood that the above combination Figure 1 and Figure 2 Taking a four-tone vehicle as an example, the solution in this application can also be applied to a six-tone vehicle, such as... Figure 3 As shown.

[0055] Figure 3 This is a schematic diagram of a six-tone vehicle provided in an embodiment of this application.

[0056] For example, Figure 3 The six-zone vehicle 300 includes seats 301, 302, 303, 304, 305, and 306; among them, seat 301 is the driver's seat, seat 302 is the front passenger seat, seat 303 is the left seat of the second row, seat 304 is the right seat of the second row, seat 305 is the left seat of the third row, and seat 306 is the right seat of the second row. The sound zones in the vehicle can be divided according to the area where the seats are located; for example, each seat's preset range can correspond to a separate sound zone; for example, as... Figure 3As shown in (b), seat 301 corresponds to register 307, seat 302 corresponds to register 308, seat 303 corresponds to register 309, seat 304 corresponds to register 310, seat 305 corresponds to register 311, and seat 306 corresponds to register 312; wherein, register 307 is the left front register, register 308 is the right front register, register 309 is the left middle register, register 310 is the right middle register, 311 is the left rear register, and 312 is the right rear register.

[0057] Each zone is equipped with a sound pickup device; seats 301, 302, 303 and 304 are the front and middle row seats of the six-zone vehicle 300, and users can usually adjust their backrest angle.

[0058] For example, in a six-zone vehicle, when a user sits in seat 304, the backrest angle can be adjusted. In this case, if the seat backrest adjustment angle is large, the aforementioned issues will also occur. Figure 2 In scenario (b), the seating arrangement within the cockpit is as follows: Figure 2 As shown in (d), when a user issues a voice command, the existing technology may misidentify the user's current seat 304 as seat 306, resulting in the incorrect execution of operations targeting seat 306 and affecting the user's riding experience.

[0059] In view of this, this application provides a vehicle control method. This method detects the adjustment angle of a seat in the vehicle. If the detected adjustment angle is greater than a preset angle threshold, the recognition function of the pickup device adjacent to the pickup device in the target seat's audio range along the direction of the seat adjustment angle is disabled. The audio signal collected by the pickup device in the target seat's audio range is then enhanced to obtain an adjusted voice recognition system. Based on the adjusted voice recognition system, the user's voice command is detected, and the audio range where the user issued the voice command is determined through location recognition. Based on the determined audio range, the components in the vehicle are controlled to perform operations. In the above scheme, when the seat adjustment angle is greater than the preset angle threshold, the adjustment angle is disabled... The system identifies the microphone adjacent to the microphone in the seat's acoustic zone, thus preventing the misdirection of voice commands to the acoustic zone of adjacent seats when the seat is reclined at a large angle. By enhancing the audio signal collected by the microphone in the seat's acoustic zone, interference from other audio signal components is reduced. This also avoids the signal attenuation of voice commands caused by the distance between the sound source and the microphone in the seat's acoustic zone due to a large recline angle, preventing the microphone in the seat's acoustic zone from failing to detect the audio signal. Therefore, the accuracy of voice command localization is improved, providing users with accurate voice control services and enhancing the user experience.

[0060] The following is combined with Figures 4 to 7 A vehicle control method provided in the embodiments of this application will be described in detail.

[0061] Figure 4 This is a schematic flowchart illustrating a vehicle control method provided in an embodiment of this application. Figure 4 As shown, method 400 includes S410 to S440, which are described in detail below.

[0062] For example, Figure 4 The vehicle control 400 shown can be executed by the vehicle; or by the processor in the vehicle; or by a chip in the processor of the vehicle.

[0063] S410, Inspect the adjustment angle of the seats in the vehicle.

[0064] In one implementation, the above method includes:

[0065] Acquire images of the vehicle's seats; determine the seat adjustment angle based on the seat images.

[0066] The image information refers to images of the various seats in the cockpit. If there are occupants in the cockpit, the image information includes the occupants.

[0067] In one possible implementation, the vehicle is equipped with an Occupant Monitoring System (OMS) that acquires image information of the cabin through an image acquisition device within the cabin. This image acquisition device can be an OMS camera, thus achieving the purpose of acquiring in-vehicle images without adding any additional hardware to the vehicle. In the absence of an OMS, the image acquisition device can also be other cameras within the vehicle, such as a camera positioned above the central control screen, or a camera located in other locations; this application embodiment does not limit the specific choice. The number of image acquisition devices can be one or more, sufficient to cover multiple seats within the cabin.

[0068] It should be noted that the collection of image information requires the user's permission and authorization. Only after the user's permission and authorization can the image information in the cockpit be obtained.

[0069] For example, OMS is used to acquire image information in the cockpit, and a deep learning algorithm is used to identify the seat adjustment angle. First, the acquired image information is preprocessed, and the preprocessed image information is input into a pre-trained deep learning model. The model calculates the seat adjustment angle by recognizing features such as the seat outline and edges. In the embodiments of this application, the seat adjustment angle refers to the angle at which the seat back is adjusted backward.

[0070] Optionally, if a user is seated in the seat, the system acquires images of the seat area captured by the in-cabin camera, analyzes the key points and contours of the human body based on features such as the user's head, shoulders, and torso using deep learning algorithms, identifies the posture of the person in the vehicle, and determines the adjustment angle of the seat based on the overlapping area between the key points of the human body and the seat position.

[0071] Optionally, if a passenger moves or adjusts their posture inside the vehicle, the passenger's position and posture are updated through continuous image analysis to enable more accurate voice command recognition and execution.

[0072] In the above solution, by acquiring image information from the cockpit, the adjustment angle of the seat is determined based on the image information. By determining the adjustment angle of the seat, the voice recognition system can be adjusted to avoid misidentifying the user's position in the wrong seat position due to a large adjustment angle, thereby improving the accuracy of voice command positioning.

[0073] In one implementation, the above method further includes:

[0074] Obtain the area inside the vehicle and / or the dimensions of the seats inside the vehicle; determine a preset angle threshold based on the area inside the vehicle and / or the dimensions of the seats inside the vehicle.

[0075] The preset angle threshold is related to the maximum adjustable angle of the seat. For example, the preset angle threshold is set to 70% of the maximum adjustable angle of the seat. The maximum adjustable angle of the seat is related to the area of ​​the cabin and / or the size of the seats in the cabin. For example, the maximum adjustable angle of the seat is positively correlated with the area of ​​the cabin, that is, the larger the area of ​​the cabin, the larger the maximum adjustable angle of the seat. The area of ​​the cabin includes the space between the front and rear seats and the height between the roof and the floor. The size of the seats in the cabin refers to the specific dimensions of the seats in the cabin, including the length, width, depth of the seat, and the height of the backrest.

[0076] For example, a preset angle threshold is set in the vehicle based on the area of ​​the cabin and / or the size of the seats in the cabin; and the user can personalize the preset angle threshold.

[0077] Therefore, by determining preset angle thresholds based on the cabin area and / or the dimensions of the seats, the vehicle can adapt to different model configurations, ensuring that the seat adjustment angle settings are reasonable and effective. Users can adjust the thresholds according to their personal preferences, thereby obtaining a riding experience that better suits their habits, improving the accuracy of the system, and avoiding misjudgments and misoperations.

[0078] In the above solution, the area inside the vehicle and / or the dimensions of the seats are obtained. A preset angle threshold is positively correlated with the cabin area; that is, the larger the area inside the vehicle, the larger the preset angle. Therefore, it is possible to optimize the configuration for different vehicle types and cabin layouts, ensuring that appropriate methods can be used for voice recognition in various in-vehicle environments.

[0079] S420. If the adjusted angle is greater than the preset angle threshold, determine to turn off the recognition function of the first pickup device in the vehicle's initial voice recognition system, and perform signal enhancement processing on the audio signal collected by the second pickup device to obtain the target voice recognition system.

[0080] The first pickup device is a pickup device located in the area adjacent to the seat in the adjustment direction corresponding to the adjustment angle; the second pickup device is a pickup device located in the area where the seat is located.

[0081] In the embodiments of this application, if the seat adjustment angle is detected to be greater than a preset angle threshold, the identification and positioning function of the sound pickup device in the area adjacent to the seat in the adjustment direction corresponding to the seat adjustment angle is turned off, and the audio signal collected by the sound pickup device in the seat area is subjected to signal enhancement processing to obtain the adjusted target speech recognition system.

[0082] For example, for Figure 5 The four-zone vehicle 100 shown detects that the adjustment angles of all seats in the vehicle do not exceed the preset angle threshold. At this point, the voice recognition system is the initial voice recognition system. Figure 5 As shown in (c), the microphones in each sound zone are performing normal voice recognition and localization functions. If the adjustment angle of the seat 102 in the vehicle exceeds a preset angle threshold, the microphones corresponding to the sound zone behind the seat 102 are turned off, and the signal of the microphones in the area where the seat 102 is located is enhanced. At this time, the voice recognition system is the target voice recognition system, as shown in (c). Figure 5 As shown in (d) in the figure.

[0083] Similarly, for Figure 6 The six-zone vehicle 300 shown detects that the adjustment angles of all seats in the vehicle do not exceed the preset angle threshold. At this point, the voice recognition system is in its initial state. Figure 6 As shown in (c), the microphones in each sound zone are performing normal voice recognition and localization functions. If the adjustment angle of the seat 304 in the vehicle exceeds a preset angle threshold, the microphones corresponding to the sound zone behind the seat 304 are turned off, and the signal of the microphones in the area where the seat 304 is located is enhanced. At this time, the voice recognition system is the target voice recognition system, as shown in (c). Figure 6 As shown in (d) in the figure.

[0084] In one implementation, the above method further includes:

[0085] The system detects whether a user is on the seat; if the adjustment angle is greater than a preset angle threshold, it determines to disable the recognition function of the first microphone in the vehicle's initial voice recognition system and performs signal enhancement processing on the audio signal collected by the second microphone, including: if a user is detected on the seat and the adjustment angle is greater than a preset angle threshold, it determines to disable the recognition function of the first microphone and performs signal enhancement processing on the audio signal collected by the second microphone.

[0086] In the embodiments of this application, it is detected whether there is a user on the seat in the vehicle. If a user is detected on the seat and the adjustment angle of the seat is greater than a preset angle threshold, the identification and positioning function of the sound pickup device in the area adjacent to the seat in the adjustment direction corresponding to the seat adjustment angle is turned off, and the audio signal collected by the sound pickup device in the seat area is subjected to audio enhancement processing to obtain the adjusted target speech recognition system.

[0087] It should be understood that when the seat adjustment angle exceeds a preset angle threshold, if the user is seated, their posture is close to lying flat, and their head is closer to the microphone adjacent to the target area in the direction of the seat adjustment angle. Because the user's head is closer to the microphone adjacent to the target area in the direction of the seat adjustment angle, when a voice command is issued, the amplitude of the audio signal obtained by the microphone is low due to the distance between the sound source and the microphone in the seat area. This causes the voice recognition system to locate the sound source in the right rear sound zone when the user issues a voice command while seated, thus executing an incorrect operation. Therefore, in this solution, to avoid the above problem, by judging whether the adjustment angle exceeds the preset angle threshold, the voice recognition system can be adjusted to accurately locate the user's position when issuing a voice command, thus providing accurate voice control services to the user and improving the user experience.

[0088] In one implementation, the above method includes:

[0089] Acquire the pressure sensor values ​​of each seat in the vehicle; based on the pressure sensor values, determine whether a user is in the seat; or, acquire an image of the vehicle's cabin; based on the cabin image, determine whether a user is in the seat.

[0090] Implementation Method 1:

[0091] In the embodiments of this application, the values ​​of pressure sensors configured in each seat of the vehicle are obtained, and the presence of a user in the seat is determined by the magnitude and distribution of the values.

[0092] For example, pressure values ​​are detected by distributed pressure sensors arranged in the seat cushion, and the presence of a user is determined by comparing the sensor data from each seat; for example, for a seat like... Figure 1 The four-zone vehicle 100 shown acquires the values ​​of various pressure sensors arranged in the seat cushions and backrests of seats 101, 102, 103, and 104. For example, if the value of the pressure sensor arranged in the seat cushion of seats 101, 103, and 104 is 0, and the value of the pressure sensor arranged in the seat cushion of seat 102 is 50N, then it can be determined that there is a user in seat 102.

[0093] In the above solution, by acquiring the values ​​of the pressure sensors in each seat, when the pressure sensors detect the pressure distribution or changes in the seat, it is possible to determine which seats have users based on these values, thereby determining how to adjust the voice recognition system to achieve accurate recognition and positioning of voice commands.

[0094] Implementation Method Two:

[0095] In the embodiments of this application, a cabin image of the vehicle is acquired, and by acquiring the cabin image of the vehicle, an image recognition algorithm is used to determine whether a user is in the seat.

[0096] For example, by acquiring images captured by in-cabin cameras, and based on features such as the user's head, shoulders, and torso, deep learning algorithms are used to analyze key points and contours of the human body to identify whether a user is in the seat.

[0097] In the above solution, by acquiring cabin images in the vehicle, and using image recognition algorithms to determine which seats have users, the system determines how to adjust the voice recognition system to achieve accurate recognition and positioning of voice commands.

[0098] In one implementation, the above method further includes:

[0099] The audio signal component from the target direction in the audio signal acquired by the second pickup device is subjected to signal enhancement processing; wherein, the target direction is obtained based on the time and phase information of the acquired audio signal.

[0100] The second pickup device is a pickup device located in the area of ​​the seat where the adjustment angle is greater than a preset angle threshold; the target orientation includes the direction of arrival (DOA) information, which is used to indicate the direction in which the user issues a voice command; the time information of the audio signal refers to the time when the audio signal arrives at the target pickup device; the phase information refers to the phase when the audio signal arrives at the pickup device.

[0101] For example, a fixed beamforming algorithm can be used to perform a weighted summation of the acquired audio signals to form a beam from the target direction, thereby enhancing the amplitude of the original audio signal; or an adaptive beamforming algorithm can be used to adapt to changing sound source locations and noise environments, and enhance the audio signal based on the changing sound source locations and noise environments.

[0102] In the above scheme, the location of the user's voice command is determined by the time and phase information of the collected audio signal. The audio signal component of the audio signal collected by the second pickup device at that location is enhanced. Because of the signal enhancement, the interference of the audio signal components in other locations is reduced, which can more accurately identify and locate the user and avoid the problem that the user who issued the voice command is too far away from the pickup device in the sound zone of his / her seat, resulting in the inability to identify the user.

[0103] S430. If the first voice command is detected, the target voice region of the first voice command is obtained based on the first voice command and the target voice recognition system.

[0104] The first voice command is a voice command issued by the user to control target components in the vehicle. For example, the first voice command can be used to control the seats in the vehicle, such as seat heating, seat ventilation, and seat massage. It can also be used to control the windows and air conditioning in the vehicle, such as adjusting the opening and closing degree of the windows, the fan speed of the air conditioning, and the direction of the air conditioning.

[0105] For example, when the seat adjustment angle in a vehicle is less than a preset angle threshold, the initial speech recognition system, during speech recognition and localization, determines the preliminary target location by detecting the signal amplitude of the user's voice command, the arrival time of each pickup device, and the phase difference. Based on the preliminary target location information, the initial speech recognition system calculates the confidence level for each voice region. The confidence level calculation is affected by factors such as signal amplitude, signal arrival time, and noise. For example, a larger signal amplitude usually means that the sound source is closer to the pickup device in the voice region, and the higher the confidence level. The initial speech recognition system combines the confidence levels of each voice region to calculate and thus determine the voice region. For a target speech recognition system, during speech recognition and localization, the initial target location is determined by detecting the signal amplitude of the user's voice command, the time of arrival at each pickup device, and the phase difference. The target speech recognition system then enhances the audio signal components from the target location collected by the pickup devices in the sound zone where the seat with the largest adjustment angle is located. Based on the enhanced signal, the confidence level is calculated to determine the sound zone. The enhancement process includes using beamforming technology to enhance the amplitude of the signal components in the target location while filtering interference from other directions.

[0106] Optionally, the target speech recognition system can determine the target speech region by comparing the signal strength of the audio signals collected by the pickup devices in each speech region and identifying the speech region corresponding to the pickup device with the highest signal strength.

[0107] Another implementation also includes:

[0108] If the adjustment angle is less than or equal to the preset angle threshold, when the second voice command is detected, the target voice region of the second voice command is determined based on the second voice command and the initial voice recognition system.

[0109] The second voice command is a voice command issued by the user to control target components in the vehicle. For example, the second voice command can be used to control the seats in the vehicle, such as seat heating, seat ventilation, and seat massage. It can also be used to control the windows and air conditioning in the vehicle, such as adjusting the opening and closing degree of the windows, the fan speed of the air conditioning, and the direction of the air conditioning.

[0110] For example, such as Figure 1 As shown in (b), in the four-zone vehicle 100, the sound zones in the cabin are divided into: zone 105, zone 106, zone 107, and zone 108. If the adjustment angle of the user's seat 102 is detected to be less than or equal to a preset angle threshold, such as... Figure 2 As shown in (a), when recognizing and locating voice commands, the audio signals collected by the pickup devices in all sound zones of the cockpit, namely sound zones 105, 106, 107 and 108, are processed.

[0111] It should be understood that when performing voice recognition using audio signals collected by the pickup devices in each sound zone, since the adjustment angle of seat 102 is less than or equal to the preset angle threshold, it means that the user is in a relatively upright or normal sitting posture. At this time, the sound source of the user's voice command is closest to the pickup device in sound zone 106. The signal strength of the audio signal collected by the pickup device in sound zone 106 is stronger than that of the signal collected by other pickup devices, and it will not be mistakenly identified and located in other sound zones. Therefore, when the seat adjustment angle is less than or equal to the preset angle threshold, the audio signals collected by all pickup devices in the cabin are collected, effectively integrating the information of the audio source and enhancing clarity and accuracy.

[0112] S440, controls target components in the target audio region based on voice commands.

[0113] The target components refer to the driver's seat, front passenger seat, seats in the left and right areas of the second row, windows, and air conditioning. Voice commands can control functions such as seat heating, seat ventilation, seat massage, air conditioning fan speed adjustment, air conditioning operation, and window operation in the corresponding audio regions. For example, the user's voice commands are collected and processed with noise filtering and signal enhancement to improve audio quality. Feature values ​​are extracted from the processed audio signal to identify key parameters representing speech characteristics, such as Mel-frequency cepstral coefficients. These feature values ​​are then input into a pre-trained model for training, enabling the model to learn and recognize different speech patterns. Finally, pattern matching is used to match the speech features of the input user's voice commands with known patterns in the model, ultimately outputting the speech recognition result. The target components in the target audio regions are then controlled based on the speech recognition result.

[0114] In one embodiment of this application, the conversion of voice commands into text employs Automatic Speech Recognition (ASR) technology, including preprocessing the voice commands and inputting the processed audio features into an acoustic model and a language model. After decoding and post-processing, the text is output in the form of a text stream. Specifically, the preprocessing includes: sampling and quantization, where the audio signal is sampled and quantized into a digital signal after being acquired by a pickup device; noise reduction, where environmental noise is reduced through noise suppression techniques; and feature extraction, where features such as Mel-frequency cepstral coefficients, filter bank energy, and spectrograms are extracted from the audio signal.

[0115] In one implementation, the voice command issued by the user can be a voice command that includes the type and location of the target component; for example, the voice command is "Please heat the passenger seat". In this case, it is not necessary to use voice recognition to locate the voice region where the user issued the voice command and control the heating component in the passenger seat to heat it.

[0116] The above scheme detects the adjustment angle of the vehicle seats. If the detected seat adjustment angle exceeds a preset angle threshold, the recognition function of the pickup devices adjacent to the target seat's audio range in the direction of the seat adjustment angle is disabled. The audio signal collected by the pickup devices in the target seat's audio range is then enhanced to obtain an adjusted voice recognition system. Based on this adjusted system, the user's voice commands are detected, and the audio range where the user issued the command is determined through location recognition. The determined audio range is then used to control the vehicle's components to perform operations. In this scheme, when the seat adjustment angle exceeds the preset angle threshold, the recognition function of the pickup devices adjacent to the target seat's audio range in the direction of the adjustment angle is disabled. The system's ability to identify adjacent microphones avoids the problem of misdirecting voice commands to the adjacent seat's audio range when the seat is reclined at a large angle. Furthermore, by enhancing the audio signal collected by the microphone in the seat's audio range, interference from other audio signal components is reduced. This also prevents signal attenuation of voice commands due to the distance between the sound source and the microphone in the seat's audio range, which could prevent the microphone from detecting the voice command. Therefore, the accuracy of voice command localization is improved, providing users with accurate voice control services and enhancing the user experience.

[0117] The following is combined with Figure 7 Another vehicle control method provided in the embodiments of this application will be illustrated by example.

[0118] Figure 7 This is a schematic flowchart illustrating a specific application of a vehicle control method provided in an embodiment of this application. For example... Figure 7 As shown, method 700 includes steps S710 to S780, which are described in detail below.

[0119] S710, Check the adjustment angle of the seats in the vehicle.

[0120] Alternatively, the implementation of S710 can be found in [reference needed]. Figure 4 The relevant descriptions in S410 are omitted here.

[0121] S720: Obtain the area of ​​the cabin and the dimensions of the seats in the cabin, and determine a preset angle threshold based on the area of ​​the cabin and the dimensions of the seats in the cabin.

[0122] For example, the configuration data of the vehicle cabin, including the area and dimensions of each seat, is read, and based on this information, a preset angle threshold is calculated to determine the magnitude of seat adjustment.

[0123] Alternatively, the implementation of the S720 can be found in [reference needed]. Figure 4The relevant descriptions in S410 are omitted here.

[0124] S730: Determine whether the seat adjustment angle is greater than the preset angle threshold; if yes, execute S740 to S760; if no, execute S770.

[0125] In the embodiments of this application, if the seat adjustment angle is greater than a preset angle threshold, it means that the user's posture is close to lying flat, and the head is closer to the microphone adjacent to the microphone in the seat area in the direction of the seat adjustment angle. At this time, it is easy to be interfered with. Therefore, S740 is executed; that is, the recognition function of the first microphone in the initial voice recognition system is turned off. If the seat adjustment angle is less than or equal to the preset angle threshold, it means that the user is in a relatively upright or normal sitting posture. When issuing a voice command, it is usually not mistakenly recognized and triggered by the microphone adjacent to the microphone in the seat area in the direction of the seat adjustment angle. At this time, by collecting the audio signals collected by all microphones in the cabin, S770 is executed, that is, the voice command is recognized and located based on the initial voice recognition system.

[0126] S740, disable the recognition function of the first pickup device in the initial voice system.

[0127] The first pickup device refers to the pickup device that is adjacent to the pickup device in the area where the seat is located in the direction of the seat's adjustment angle.

[0128] Alternatively, the implementation of the S740 can be found in [reference needed]. Figure 4 The relevant description of the implementation method in S420 will not be repeated here.

[0129] S750: Perform signal enhancement processing on the audio signal acquired by the second pickup device.

[0130] The second sound pickup device refers to the sound pickup device in the area where the seat is located.

[0131] Alternatively, the implementation of the S750 can be found in [reference needed]. Figure 4 The relevant description of the implementation method in S420 will not be repeated here.

[0132] S760: Based on the adjusted target speech recognition system, the voice command is recognized and located to obtain the target voice region.

[0133] The adjusted target speech recognition system refers to a speech recognition system that has its first pickup device in the initial speech recognition system turned off and the audio signal collected by the second pickup device has been enhanced.

[0134] Alternatively, the implementation of the S760 can be found in [reference needed]. Figure 4The relevant description of the implementation method in S430 will not be repeated here.

[0135] S770: Based on the initial speech recognition system, the voice command is recognized and located to obtain the target voice region.

[0136] Alternatively, the implementation of the S770 can be found in [reference needed]. Figure 4 The relevant description of the implementation method in S430 will not be repeated here.

[0137] S780, based on voice command control of target components in the target audio region.

[0138] The target components refer to the driver's seat, passenger seat, seats in the left and right areas of the second row, windows, and air conditioning; the voice commands can control seat heating, seat ventilation, seat massage, air conditioning fan speed adjustment, air conditioning opening and closing, and window opening and closing in the corresponding voice zones.

[0139] Alternatively, the implementation of the S780 can be found in [reference needed]. Figure 4 The relevant description of the implementation method in S440 will not be repeated here.

[0140] In the embodiments of this application, by detecting the adjustment angle of the seat in the vehicle, if the detected adjustment angle is greater than a preset angle threshold, the recognition function of the pickup device adjacent to the pickup device in the target seat's sound zone along the direction of the seat adjustment angle is turned off, and signal enhancement processing is performed on the pickup device in the seat's sound zone to obtain an adjusted voice recognition system; based on the adjusted voice recognition system, the user's voice command is detected, and the sound zone where the user issued the voice command is determined through location recognition; based on the determined sound zone, the components in the vehicle are controlled to perform operations; in the above scheme, when the seat adjustment angle is greater than the preset angle threshold, because the pickup device adjacent to the pickup device in the direction of the adjustment angle is turned off, the recognition function of the pickup device in the target seat's sound zone is turned off. The system's ability to identify adjacent microphones within a specific area prevents the misdirection of voice commands to the adjacent seat's acoustic zone when the seat is reclined at a large angle. By enhancing the signal of the microphone in the seat's acoustic zone, interference from other audio signal components is reduced. This also avoids the signal attenuation that can occur when the sound source is far from the microphone in the seat's acoustic zone due to a large recline, preventing the microphone in that zone from detecting the voice command. Therefore, the accuracy of voice command localization is improved, providing users with accurate voice control services and enhancing the user experience. The following section combines... Figure 8 Taking the passenger seat in a four-zone vehicle as an example, and the voice command being the control command for seat heating, the vehicle control method provided in this application embodiment is illustrated.

[0141] Figure 8 This is a schematic flowchart illustrating another vehicle control method provided in an embodiment of this application. Figure 8 As shown, method 800 includes S801 to S807, which are described in detail below.

[0142] S801, Vehicle power detected.

[0143] For example, when a user presses the vehicle's start button or turns the key to start the engine, the vehicle's power system is turned on. The vehicle detects this change in power-on state, thereby triggering subsequent initialization and the activation of related functions.

[0144] S802: A user has been detected in the front passenger seat.

[0145] Alternatively, the implementation of S802 can be found in [reference needed]. Figure 4 The relevant descriptions in S420 are omitted here.

[0146] S803. Determine whether the adjustment angle of the passenger seat is greater than the preset angle threshold; if yes, execute S804; if no, execute S803 again after a preset time interval.

[0147] In the embodiments of this application, it is determined whether the adjustment angle of the passenger seat is greater than a preset angle threshold. If it is greater than the preset angle threshold, S804 is executed, that is, the initial voice recognition system is adjusted to obtain the target voice recognition system. If it is less than or equal to the preset angle threshold, S803 is executed again after a preset time interval, that is, the adjustment angle of the seat is re-detected after a preset time interval.

[0148] S804. Disable the voice recognition function of the pickup device corresponding to the area behind the passenger seat in the initial voice recognition system, and enhance the audio signal collected by the pickup device corresponding to the passenger seat area to obtain the adjusted target voice recognition system.

[0149] Alternatively, the implementation of S804 can be found in [reference needed]. Figure 4 The relevant descriptions in S420 are omitted here.

[0150] S805. Based on the target speech recognition system and the detected speech commands, determine the target voice region.

[0151] Alternatively, the implementation of S805 can be found in [reference needed]. Figure 4 The relevant descriptions in S430 are omitted here.

[0152] S806: Recognize the voice command, determine the target component as the passenger seat and the control information as turning on the seat heating function.

[0153] For example, the voice command issued by the user is collected, the voice command is converted into a digital signal, and the feature vector is extracted. The feature vector is input into a pre-trained ASR model to determine that the target component is the seat, the control information is seat heating, and combined with the determined target sound zone as the right front sound zone where the passenger seat is located, the target component is determined to be the passenger seat.

[0154] S807, control the passenger seat to turn on the seat heating function.

[0155] For example, the vehicle's seats are equipped with heating elements embedded in the seat cushion and backrest, which are heated by resistance wires or heating pads. After determining that the target component is the passenger seat and the control information is to turn on the seat heating function, the seat heating command is sent to the electronic unit for controlling the seat via the vehicle's Controller Area Network (CAN) bus. After receiving the command, the electronic unit turns on the heating element of the passenger seat.

[0156] Optionally, the above solution is illustrated by the example of detecting someone in the front passenger seat. This application can detect each seat in the vehicle and is not limited to this. The above solution is illustrated by the example of a voice command for seat heating. The voice commands of this application can also be seat massage, air conditioning fan speed adjustment, air conditioning on / off, and window opening / closing, etc.

[0157] In the embodiments of this application, by combining the adjustment angle of the vehicle's seat with the adjustment of the voice recognition system, accurate response to user voice commands is achieved. When a large seat adjustment angle is detected, the initial voice recognition system is adjusted. The voice recognition function of the pickup device corresponding to the area behind the passenger seat in the initial voice recognition system is disabled, and the audio signal collected by the pickup device corresponding to the passenger seat area is enhanced to obtain the adjusted target voice recognition system. Based on the adjusted target voice recognition system, the user's voice commands are recognized, thereby more accurately determining the target voice region and executing the corresponding control commands, such as activating the seat heating function. This method reduces the possibility of misoperation, improves the accuracy of voice recognition, and enhances the user experience.

[0158] The above text combined Figures 1 to 8 This application provides a detailed description of a vehicle control method based on its embodiments; the following will be combined with... Figure 9 and Figure 10 The apparatus embodiments of this application are described in detail below. It should be understood that the apparatus in the embodiments of this application can perform the various methods described in the foregoing embodiments of this application, that is, the specific working processes of the various products described below can be referred to the corresponding processes in the foregoing method embodiments.

[0159] Figure 9This is a schematic diagram of a vehicle control device provided in an embodiment of this application. The device 900 includes a detection module 910 and a processing module 920.

[0160] The detection module 910 is used to detect the adjustment angle of the seat in the vehicle; the processing module 920 is used to determine to disable the recognition function of the first microphone in the initial voice recognition system of the vehicle if the adjustment angle is greater than a preset angle threshold, and to perform signal enhancement processing on the audio signal collected by the second microphone to obtain the target voice recognition system; wherein, the first microphone is a microphone in the area adjacent to the seat in the adjustment direction corresponding to the adjustment angle; the second microphone is a microphone in the area where the seat is located; if a first voice command is detected, the target voice region of the first voice command is obtained based on the first voice command and the target voice recognition system; wherein, the first voice command is used to represent the control command of the target component in the vehicle; the target component in the target voice region is controlled to execute the control command.

[0161] Optionally, as an embodiment, the processing module 920 is specifically used for:

[0162] The system detects whether a user is on the seat; if the adjustment angle is greater than a preset angle threshold, it determines to disable the recognition function of the first microphone in the vehicle's initial voice recognition system and performs signal enhancement processing on the audio signal collected by the second microphone, including: if a user is detected on the seat and the adjustment angle is greater than a preset angle threshold, it determines to disable the recognition function of the first microphone and performs signal enhancement processing on the audio signal collected by the second microphone.

[0163] Optionally, as an embodiment, the processing module 920 is further configured to:

[0164] Acquire the pressure sensor values ​​of each seat in the vehicle; based on the pressure sensor values, determine whether a user is in the seat; or, acquire an image of the vehicle's cabin; based on the cabin image, determine whether a user is in the seat.

[0165] Optionally, as an embodiment, the processing module 920 is specifically used for:

[0166] The audio signal component from the target direction in the audio signal acquired by the second pickup device is subjected to signal enhancement processing; wherein, the target direction is obtained based on the time and phase information of the acquired audio signal.

[0167] Optionally, as an embodiment, the processing module 920 is specifically used for:

[0168] Acquire images of the vehicle's seats; determine the seat adjustment angle based on the seat images.

[0169] Optionally, as an embodiment, the processing module 920 is further configured to:

[0170] If the adjustment angle is less than or equal to the preset angle threshold, when the second voice command is detected, the target voice region of the second voice command is determined based on the second voice command and the initial voice recognition system.

[0171] Optionally, as an embodiment, the processing module 920 is further configured to:

[0172] Obtain the area inside the vehicle and / or the dimensions of the seats inside the vehicle; determine a preset angle threshold based on the area inside the vehicle and / or the dimensions of the seats inside the vehicle.

[0173] It should be noted that the aforementioned vehicle control device 900 is embodied in the form of a functional unit. The term "module" here can be implemented in software and / or hardware, without specific limitations.

[0174] For example, a "module" can be a software program, hardware circuitry, or a combination of both that implements the above-described functions. Hardware circuitry may include application-specific integrated circuits (ASICs), electronic circuitry, a processor (e.g., a shared processor, a proprietary processor, or a group processor) and memory for executing one or more software or firmware programs, integrated logic circuitry, and / or other suitable components that support the described functions.

[0175] Therefore, the units of the various examples described in the embodiments of this application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0176] Figure 10 This is a schematic diagram of the structure of a vehicle provided in an embodiment of this application.

[0177] For example, vehicle 1000 includes: processor 1010, memory 1020 and executable program code 1030.

[0178] For example, vehicle 1000 includes one or more processors 1010, which can support vehicle 1000 in implementing the vehicle generation method in the method embodiment. Processor 1010 can be a general-purpose processor or a special-purpose processor. For example, processor 1010 can be a central processing unit (CPU), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, such as discrete gates, transistor logic devices, or discrete hardware components.

[0179] For example, the processor 1010 can be used to control the vehicle 1000, execute software programs, and process data from the software programs. The vehicle 1000 may also include a communication unit for receiving and transmitting signals.

[0180] For example, the vehicle 1000 may include one or more memories 1020, on which executable program code 1030 is stored. The executable program code 1030 can be run by the processor 1010 to generate instructions, causing the processor 1010 to execute the generation method described in the above method embodiments according to the instructions.

[0181] Optionally, the memory 1020 may also store data. Optionally, the processor 1010 may also read data stored in the memory 1020, which may be stored at the same memory address as the executable program code 1030, or the data may be stored at a different memory address than the executable program code 1030.

[0182] For example, the processor 1010 and memory 1020 can be configured separately or integrated together, for example, integrated on the system-on-chip (SOC) of the terminal device.

[0183] For example, the memory 1020 can be used to store the relevant program of the vehicle generation method provided in the embodiments of this application, and the processor 1020 can be used to call the executable program code 1030 stored in the memory 1020 when controlling the vehicle to execute the vehicle control method of the embodiments of this application.

[0184] This application also provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the vehicle control method of any of the foregoing embodiments.

[0185] The computer-readable storage medium may include, but is not limited to, any type of disk, including floppy disks, optical disks, Digital Video Discs (DVDs), Compact Disc Read-Only Memory (CD-ROM), microdrives, and magneto-optical disks, read-only memory (ROM), random access memory (RAM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), dynamic random access memory (DRAM), video random access memory (VRAM), flash memory devices, magnetic cards or optical cards, nanosystems (including molecular memory ICs), or any type of medium or device suitable for storing instructions and / or data.

[0186] This application also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned related steps to implement a vehicle control method as described in the above embodiments.

[0187] In addition, the electronic device provided in the embodiments of this application may specifically be a chip, component or module. The electronic device may include a connected processor and a memory. The memory is used to store instructions. When the electronic device is running, the processor may call and execute the instructions to make the chip execute a vehicle control method in the above embodiments.

[0188] The vehicle, computer-readable storage medium, computer program product or chip provided in this application are all used to execute the corresponding vehicle control method provided above. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects of the corresponding vehicle control method provided above, and will not be repeated here.

[0189] Through the above description of the embodiments, those skilled in the art will understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0190] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0191] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A vehicle control method, characterized in that, The method includes: Check the adjustment angle of the seats in the vehicle; If the adjustment angle is greater than a preset angle threshold, the recognition function of the first pickup device in the initial voice recognition system of the vehicle is turned off, and the audio signal collected by the second pickup device is subjected to signal enhancement processing to obtain the target voice recognition system; wherein, the first pickup device is the pickup device in the area adjacent to the seat area in the adjustment direction corresponding to the adjustment angle; the second pickup device is the pickup device in the area where the seat is located; If a first voice command is detected, the target voice region of the first voice command is obtained based on the first voice command and the target voice recognition system; wherein, the first voice command is used to represent a control command for a target component in the vehicle; The target component in the target sound region is controlled to execute the control command.

2. The method according to claim 1, characterized in that, Also includes: Detect whether a user is in the seat; If the adjustment angle is greater than a preset angle threshold, the system determines to disable the recognition function of the first microphone in the vehicle's initial voice recognition system, and to perform signal enhancement processing on the audio signal collected by the second microphone, including: If the user is detected on the seat and the adjustment angle is greater than the preset angle threshold, the recognition function of the first microphone is turned off, and the audio signal collected by the second microphone is subjected to the signal enhancement processing.

3. The method according to claim 2, characterized in that, The detection of whether a user is on the seat includes: Obtain the pressure sensor values ​​of each seat in the vehicle; based on the pressure sensor values, determine whether the user is in the seat; Alternatively, acquire an image of the vehicle's cabin; based on the cabin image, determine whether the user is present in the seat.

4. The method according to claim 1, characterized in that, The signal enhancement processing of the audio signal acquired by the second pickup device includes: The signal enhancement processing is performed on the audio signal component from the target direction in the audio signal acquired by the second pickup device; wherein the target direction is obtained based on the time and phase information of the acquired audio signal.

5. The method according to claim 1, characterized in that, The adjustment angle of the seats in the vehicle being tested includes: Obtain images of the vehicle's seats; Based on the seat image, the adjustment angle of the seat is determined.

6. The method according to any one of claims 1 to 5, characterized in that, Also includes: If the adjustment angle is less than or equal to the preset angle threshold, when the second voice command is detected, the target voice region of the second voice command is determined based on the second voice command and the initial voice recognition system.

7. The method according to any one of claims 1 to 5, characterized in that, Also includes: Obtain the area inside the vehicle and / or the dimensions of the seats inside the vehicle; The preset angle threshold is determined based on the area inside the vehicle and / or the dimensions of the seats inside the vehicle.

8. A vehicle control device, characterized in that, The device includes: The detection module is used to detect the adjustment angle of the seats in the vehicle; The processing module is configured to, if the adjustment angle is greater than a preset angle threshold, determine to disable the recognition function of the first microphone in the vehicle's initial voice recognition system, and perform signal enhancement processing on the audio signal collected by the second microphone to obtain a target voice recognition system; wherein, the first microphone is a microphone corresponding to the adjacent area of ​​the seat location in the adjustment direction corresponding to the adjustment angle; the second microphone is a microphone in the seat location area; if a first voice command is detected, the target voice region of the first voice command is obtained based on the first voice command and the target voice recognition system; wherein, the first voice command is used to represent a control command for a target component in the vehicle; and control the target component in the target voice region to execute the control command.

9. A vehicle, characterized in that, The vehicles include: Memory, used to store executable program code; A processor for calling and running the executable program code from the memory, causing the vehicle to perform the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed, implements the method as described in any one of claims 1 to 7.

Images