Cabin voice interaction method and device and storage medium

Abstract

The invention discloses a cockpit voice interaction method and device and a storage medium, and belongs to the technical field of vehicle control. The method comprises the steps of collecting sound information of a driver; acquiring a detection result and a control instruction of the elderly driver based on the sound information of the driver, wherein the detection result of the elderly driver is used for indicating whether the driver is an elderly driver; in response to the obtained detection result that the driver is the elderly driver, the vehicle is controlled to start a working mode suitable for the elderly; controlling the vehicle to execute the control instruction; collecting comprehensive noise values inside and outside the vehicle; calculating a broadcast volume and a broadcast speed based on the comprehensive noise value; and broadcasting the execution condition of the control instruction according to the broadcasting volume and the broadcasting speed. The accuracy of instruction recognition and voice broadcast functions of the cabin is improved, voice instructions of old people can be recognized more easily, voice broadcast content can be heard more easily, and therefore driving experience and driving safety are improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of vehicle control technology, and in particular to a cockpit voice interaction method, device, and storage medium. Background Art

[0002] As the population ages, the number of elderly drivers is also increasing. Some elderly drivers are prone to hearing loss, slow speech, or unclear pronunciation, which can affect the accuracy of cockpit voice interaction commands and voice reception. Therefore, identifying elderly drivers and adjusting the cockpit's command recognition and voice broadcast functions based on their specific attributes, thereby improving their accuracy, is a challenge that needs to be addressed. Summary of the Invention

[0003] The present invention provides a method, device, and storage medium for cockpit voice interaction, which can be used to improve the accuracy of cockpit command recognition and voice broadcast functions. The technical solution is as follows:

[0004] In one aspect, an embodiment of the present application provides a cockpit voice interaction method, the method comprising:

[0005] Collect driver's voice information;

[0006] obtaining a detection result and a control instruction for an elderly driver based on the voice information of the driver, wherein the detection result for the elderly driver is used to indicate whether the driver is an elderly driver;

[0007] In response to obtaining the elderly driver detection result that the driver is the elderly driver, controlling the vehicle to start an elderly-friendly working mode;

[0008] controlling the vehicle to execute the control instruction;

[0009] Collecting comprehensive noise values inside and outside the vehicle;

[0010] Calculating the broadcast volume and broadcast speed based on the comprehensive noise value;

[0011] The execution status of the control instruction is announced according to the announcement volume and the announcement speed.

[0012] In another aspect, a cockpit voice interaction device is provided, the device comprising:

[0013] The first acquisition module is used to collect the driver's voice information;

[0014] a first acquisition module, configured to acquire a detection result and a control instruction of an elderly driver based on the voice information of the driver, wherein the detection result of the elderly driver is used to indicate whether the driver is an elderly driver;

[0015] a second obtaining module, configured to control the vehicle to start an elderly-friendly working mode in response to obtaining a detection result of the elderly driver indicating that the driver is the elderly driver;

[0016] A control module, configured to control the vehicle to execute the control instruction;

[0017] A second acquisition module is used to collect the comprehensive noise value inside and outside the vehicle;

[0018] A calculation module, configured to calculate a broadcast volume and a broadcast speech rate based on the comprehensive noise value;

[0019] The announcement module is used to announce the execution status of the control instruction according to the announcement volume and the announcement speed.

[0020] On the other hand, a non-transitory computer-readable storage medium is also provided, characterized in that a computer program is stored in the computer-readable storage medium, and the computer program is loaded and executed by a processor to implement any of the above-mentioned cabin voice interaction methods.

[0021] On the other hand, a computer program product is provided, comprising computer instructions, which, when executed by a processor, implement the steps of any of the above-mentioned cockpit voice interaction methods.

[0022] The technical solution provided by this application brings at least the following beneficial effects:

[0023] This application collects the driver's voice information to determine whether the driver is an elderly driver and obtains control instructions; if the driver is an elderly driver, controls the vehicle to turn on the elderly-friendly working mode to improve the driving experience of the elderly driver; controls the vehicle to execute the control instructions; and collects the comprehensive noise value inside and outside the vehicle, and calculates the broadcast volume and broadcast speed based on the comprehensive noise value; then broadcasts the execution status of the control instructions according to the broadcast volume and broadcast speed, thereby improving the accuracy of the cockpit's command recognition and voice broadcast functions, making it easier for the elderly's voice commands to be recognized and easier to hear the content of the voice broadcast, thereby improving the driving experience and driving safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0025] Figure 1 This is a schematic diagram of an implementation environment provided by an embodiment of the present application;

[0026] Figure 2 This is a flow chart of a cockpit voice interaction method provided by an embodiment of the present application;

[0027] Figure 3 is an accent correction table provided in an embodiment of the present application;

[0028] Figure 4 This is a structural diagram of a cockpit voice interaction device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] In order to make the objectives, technical solutions and advantages of this application clearer, the implementation methods of this application will be further described in detail below with reference to the accompanying drawings.

[0030] This application embodiment provides a cockpit voice interaction method, please refer to Figure 1 , which shows a schematic diagram of the implementation environment of the method provided in the embodiments of the present application. The implementation environment may include: a BCM (Body Control Module) 11, a bone conduction sensor 12, a capacitive microphone array 13, a MEMS (Micro-Electro-Mechanical Systems Microphone) 14, a vibration sensor 15, an on-board digital signal processor or audio processing chip 16, a cloud server 17, an on-board audio system 18, and a center console display 19.

[0031] Optionally, a bone conduction sensor 12 is mounted on the steering wheel to collect vibration signals from the driver's skeletal structure, generating corresponding driver voice information based on the vibration signals and transmitting it to the BCM 11. A capacitive microphone array 13 is mounted on the driver's seat roof to collect human voice information near the driver's seat and transmit it to the BCM 11. An onboard digital signal processor or audio processing chip 16 pre-processes the combined human voice information near the driver's seat and the driver's voice information, ultimately collecting the driver's voice information. A cloud server 17 uses this pre-processed driver voice information to obtain detection results and control instructions for elderly drivers and transmits them to the BCM 11.

[0032] Exemplarily, MEMS 14 is deployed in the center of the vehicle roof, the dashboard, and the headrests of each seat to collect wind noise, tire noise, music, navigation voice, and human voices inside and outside the vehicle and send them to BCM 11; vibration sensors 15 are installed on the vehicle body frame, doors, and chassis to collect structure-conducted noise and send it to BCM 11. The noise values of wind noise, tire noise, music, navigation voice, human voices inside and outside the vehicle, and structure-conducted noise of the equipment can be combined to obtain a comprehensive noise value inside and outside the vehicle, which is used to calculate the broadcast volume and broadcast speed.

[0033] In one possible implementation, the vehicle audio system 18 is configured to announce the execution status of control commands at a specified volume and speed. The center console display screen 19 is configured to display the execution status of control commands in a preset, larger font. The BCM 11, bone conduction sensor 12, capacitive microphone array 13, MEMS 14, vibration sensor 15, vehicle digital signal processor or audio processing chip 16, cloud server 17, vehicle audio system 18, and center console display screen 19 establish a communication connection via a wired or wireless network.

[0034] Based on the above Figure 1 In the implementation environment shown, the present application embodiment provides a cockpit voice interaction method such as Figure 2 As shown, taking the method applied to BCM as an example, the method includes steps 201 to 207.

[0035] In step 201 , the BCM collects driver's voice information.

[0036] In one possible implementation, the BCM collects the driver's voice information, including but not limited to: using a bone conduction sensor on the steering wheel and a condenser microphone array on the driver's ceiling. The bone conduction sensor on the steering wheel collects vibration signals from the driver's skeletal structure and generates corresponding driver voice information based on the vibration signals; the condenser microphone array on the driver's ceiling collects human voice information near the driver's seat; and the driver's voice information collected by the bone conduction sensor is combined with the human voice information near the driver's seat to generate the final collected driver voice information.

[0037] Exemplarily, after the driver's voice information is finally collected, the voice information is preprocessed to remove noise. Optionally, the BCM uses an onboard digital signal processor or audio processing chip to perform denoising, filtering, downsampling, pre-emphasis, and endpoint detection on the final collected driver's voice information to remove noise, enhance useful voice information, and determine the starting and ending points of the voice information.

[0038] In step 202 , the BCM obtains a detection result and a control instruction for an elderly driver based on the driver's voice information. The detection result for the elderly driver is used to indicate whether the driver is an elderly driver.

[0039] In one possible implementation, after completing preprocessing of the driver's voice information, the BCM obtains the detection result and control instructions of the elderly driver based on the driver's voice information, wherein the detection result of the elderly driver is used to indicate whether the driver is an elderly driver.

[0040] Optionally, BCM obtains the detection results of elderly drivers based on the driver's voice information, including: extracting the frequency, intensity, speaking speed and stress position of the sound information; comparing the frequency, intensity, speaking speed and stress position with a preset elderly group sound feature library to obtain the detection results of the elderly driver.

[0041] For example, BCM uploads the pre-processed sound information to a cloud server, and then uses a voiceprint recognition algorithm to extract features of the sound information, including frequency, intensity, speaking speed, and stress position. After obtaining the frequency, intensity, speaking speed, and stress position of the sound information, BCM compares the frequency, intensity, speaking speed, and stress position with a preset voice feature library for the elderly population.

[0042] In one possible implementation, if the elderly group sound feature library contains conversation samples that are similar to the frequency, intensity, speaking speed and stress position of the driver's voice information, a detection result of an elderly driver is obtained, indicating that the driver is an elderly driver; if the elderly group sound feature library does not contain conversation samples that are similar to the frequency, intensity, speaking speed and stress position of the driver's voice information, a detection result of an elderly driver is obtained, indicating that the driver is not an elderly driver.

[0043] For example, the preset sound feature library for the elderly group includes a sample database of common conversations including Mandarin and eight major dialects, wherein the sample data includes conversation content, frequency, intensity, speaking speed and stress position. The sound feature library for the elderly group can be collected in advance through experiments.

[0044] In one possible implementation, the BCM obtains control commands based on the driver's voice information, including: in response to obtaining a detection result indicating that the driver is an elderly driver, performing elderly accent correction on the voice information and identifying the control commands in the voice information. Exemplarily, the BCM compares the driver's voice information with an accent correction table in a voice feature library for the elderly population to identify the control commands in the voice information.

[0045] For example, the accent correction table is as follows Figure 3As shown. The error types corrected include but are not limited to: initial consonant confusion, final simplification and flat intonation. Exemplarily, for the error type of initial consonant confusion, such as the confusion of flat and retroflex tongue, the initial consonant confusion can be corrected by context-sensitive Markov correction. For the error type of final simplification, such as simplifying "ian" to "in", the final simplification can be corrected by dynamic final template matching. For the error type of flat intonation, such as reading the fourth tone as the first tone, the flat intonation can be corrected by supplementing the prosody model. Optionally, the dynamic template and the prosody model belong to the accent correction table.

[0046] In step 203 , in response to obtaining a detection result indicating that the driver is an elderly driver, the BCM controls the vehicle to start an elderly-friendly working mode.

[0047] For example, after obtaining the elderly driver detection result, if the elderly driver detection result is obtained, the BCM controls the vehicle to activate the elderly-friendly operating mode, including: the BCM controls the air conditioning temperature to a temperature and wind speed suitable for elderly people, adjusts the air conditioning wind speed to a wind speed suitable for elderly people, increases the gear shift delay, and adjusts the seat to a more comfortable position when parking. In one possible implementation, the elderly-friendly temperature, elderly-friendly wind speed, more comfortable seat position, and gear shift delay can be predetermined and set through experiments.

[0048] In step 204 , the BCM controls the vehicle to execute the control command.

[0049] Optionally, after the vehicle turns on the elderly-friendly working mode, the BCM controls the vehicle to execute control instructions, among which common control instructions include but are not limited to: "navigating to a designated location", "turning on and off the air conditioner", "adjusting the air conditioner temperature or wind speed", "turning on and off the windows", "seat heating" and "audio control".

[0050] In step 205 , the BCM collects comprehensive noise values inside and outside the vehicle.

[0051] In one possible implementation, during the execution of control instructions, the BCM collects comprehensive noise values inside and outside the vehicle, where the comprehensive noise includes but is not limited to wind noise, tire noise, music, navigation voice, human voices inside and outside the vehicle, and structural conduction noise of the equipment.

[0052] Optionally, the BCM collects comprehensive noise values inside and outside the vehicle, including: BCM collects wind noise, tire noise, music, navigation voice and human voices inside and outside the vehicle through MEMS deployed in the center of the vehicle roof, the instrument panel and the headrests of each seat; directly collects structure-conducted noise through vibration sensors installed on the vehicle body frame, doors and chassis; and combines the noise values of wind noise, tire noise, music, navigation voice, human voices inside and outside the vehicle and the structure-conducted noise of the equipment to obtain the comprehensive noise value inside and outside the vehicle.

[0053] For example, the noise values of wind noise, tire noise, music, navigation voice, human voices inside and outside the vehicle, and structure-borne noise from equipment are combined to obtain a comprehensive noise value inside and outside the vehicle. This includes uploading the noise values of wind noise, tire noise, music, navigation voice, human voices inside and outside the vehicle, and structure-borne noise from equipment to a data processing module, performing frequency domain analysis on the noise to separate the various noise types, and calculating the comprehensive noise value based on preset weighting coefficients and the noise values of the various noise types. Optionally, the preset weighting coefficients can be pre-set based on experience.

[0054] In step 206 , the BCM calculates the announcement volume and announcement speed based on the comprehensive noise value.

[0055] In one possible implementation, after completing the collection of the comprehensive noise values inside and outside the vehicle, the BCM calculates the broadcast volume based on the comprehensive noise values, including: calculating the noise change rate and the ratio of the comprehensive noise value to the preset baseline noise value based on the comprehensive noise value; calculating the broadcast volume based on the noise change rate and the ratio.

[0056] For example, statistics are collected on the comprehensive noise value within a certain time period, the noise change rate is calculated based on the duration of the comprehensive noise value within the certain time period, and a preset baseline noise threshold and a default baseline volume are set based on experience, wherein the certain time period can be set based on experience. After determining the noise change rate, the preset baseline noise value, and the default baseline volume, the formula for calculating the broadcast volume is as follows:

[0057] V target =V base +ΔV

[0058] V target V is the volume you want to set. base is the default reference volume, ΔV is the volume that needs to be adjusted, and the formula for calculating the volume ΔV that needs to be adjusted is as follows:

[0059]

[0060] k1 is the steady-state adjustment coefficient, k2 is the transient adjustment coefficient, N is the comprehensive noise value, N0 is the preset reference noise threshold, is the noise change rate. Optionally, k1 controls the long-term intensity of the integrated noise's effect on the broadcast volume, typically set to 3.2. k2 controls the response speed of the broadcast volume to sudden noise changes, typically set to 0.8.

[0061] In one possible implementation, after the calculation of the broadcast volume is completed, the broadcast speech rate is calculated based on the comprehensive noise value, including: calculating a first difference between the comprehensive noise value and a preset baseline noise value, and a second difference between the preset maximum noise value and the comprehensive noise value based on the comprehensive noise value; and calculating the broadcast speech rate based on the first difference and the second difference.

[0062] For example, a preset maximum noise value and a default reference speech speed can be set based on experience, and the formula for calculating the broadcast speech speed is as follows:

[0063]

[0064] S target S is the speech speed that needs to be set. base is the default reference speaking speed, a is the speech attenuation factor, N max is the preset maximum noise value. Optionally, the speech attenuation factor a is the speech rate attenuation factor, which is usually set to 0.35; the preset maximum noise value N max Usually set to 85 decibels; the default reference speech rate is S base Typically set to 4 words per second.

[0065] In step 207, the BCM announces the execution status of the control instruction according to the announcement volume and announcement speed.

[0066] In one possible implementation, after calculating the broadcast volume and broadcast speed, the BCM broadcasts the execution status of the control command according to the broadcast volume and broadcast speed, including: the BCM controls the vehicle audio system to broadcast the execution status of the control command according to the broadcast volume and broadcast speed. Optionally, the execution status of the control command includes but is not limited to the vehicle arriving at a designated location, the vehicle encountering an obstacle while driving, the air conditioning being turned on or off, the air conditioning being adjusted to a specified temperature or wind speed, the windows being opened or closed, the seat heating being completed, or the audio system being controlled according to the command.

[0067] For example, while the execution status of the control command is broadcast according to the broadcast volume and broadcast speed, the execution status of the control command is displayed on the display screen of the center console in a preset large font. The font size can be set and adjusted on the screen of the center console.

[0068] The embodiment of the present application collects the driver's voice information to determine whether the driver is an elderly driver and obtains control instructions; if the driver is an elderly driver, controls the vehicle to start an elderly-friendly working mode to improve the driving experience of the elderly driver; controls the vehicle to execute the control instructions; and collects the comprehensive noise value inside and outside the vehicle, and calculates the broadcast volume and broadcast speed based on the comprehensive noise value; then broadcasts the execution status of the control instructions according to the broadcast volume and broadcast speed, thereby improving the accuracy of the cockpit's command recognition and voice broadcast functions, making it easier for the elderly's voice commands to be recognized and easier to hear the content of the voice broadcast, thereby improving the driving experience and driving safety.

[0069] See also Figure 3 , an embodiment of the present application provides a cockpit voice interaction device, the device comprising:

[0070] The first collection module 301 is used to collect the driver's voice information;

[0071] A first acquisition module 302 is configured to acquire a detection result and a control instruction for an elderly driver based on the driver's voice information, wherein the detection result for the elderly driver is used to indicate whether the driver is an elderly driver;

[0072] The second acquisition module 303 is configured to control the vehicle to start an elderly-friendly working mode in response to obtaining a detection result indicating that the driver is an elderly driver;

[0073] A control module 304 is used to control the vehicle to execute control instructions;

[0074] The second acquisition module 305 is used to collect the comprehensive noise value inside and outside the vehicle;

[0075] A calculation module 306 is used to calculate the broadcast volume and broadcast speed based on the comprehensive noise value;

[0076] The announcement module 307 is used to announce the execution status of the control instruction according to the announcement volume and announcement speed.

[0077] In one possible implementation, the first acquisition module 302 is used to extract the frequency, intensity, speaking rate and stress position of the sound information; compare the frequency, intensity, speaking rate and stress position with a preset elderly group sound feature library to obtain the detection results of the elderly driver.

[0078] In a possible implementation, the first acquisition module 302 is configured to, in response to obtaining a detection result indicating that the driver is an elderly driver, perform elderly accent correction on the sound information and identify control instructions in the sound information.

[0079] In a possible implementation, the calculation module 306 is configured to calculate a noise change rate and a ratio of the comprehensive noise value to a preset reference noise value based on the comprehensive noise value; and calculate a broadcast volume based on the noise change rate and the ratio.

[0080] In one possible implementation, the calculation module 306 is configured to calculate a first difference between the comprehensive noise value and a preset baseline noise value, and a second difference between the preset maximum noise value and the comprehensive noise value based on the comprehensive noise value; and calculate the broadcast speech rate based on the first difference and the second difference.

[0081] In a possible implementation, the first acquisition module 301 is further configured to pre-process the sound information to remove noise from the sound information.

[0082] This device collects the driver's voice information to determine whether the driver is an elderly driver and obtain control instructions; if the driver is an elderly driver, it controls the vehicle to start an elderly-friendly working mode to improve the driving experience of the elderly driver; controls the vehicle to execute control instructions; and collects the comprehensive noise value inside and outside the vehicle, and calculates the broadcast volume and broadcast speed based on the comprehensive noise value; then broadcasts the execution status of the control instructions according to the broadcast volume and broadcast speed, thereby improving the accuracy of the cockpit's command recognition and voice broadcast functions, making it easier for the elderly's voice commands to be recognized and easier to hear the content of the voice broadcast, thereby improving the driving experience and driving safety.

[0083] It should be noted that the apparatus provided in the above embodiments is merely illustrated by the division of the above functional modules when implementing its functions. 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. In addition, the apparatus and method embodiments provided in the above embodiments are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0084] In an exemplary embodiment, a computer-readable storage medium is also provided, in which at least one computer program is stored. The at least one computer program is loaded and executed by a processor of a computer device to enable the computer to implement any of the above-mentioned cockpit voice interaction methods.

[0085] In one possible implementation, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0086] In an exemplary embodiment, a computer program product or program is also provided. The computer program product or program includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform any of the aforementioned cockpit voice interaction methods.

[0087] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and signals involved in this application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions. For example, the driver's voice information, the test results of the elderly driver, the control instructions, the comprehensive noise value inside and outside the vehicle, and the execution of the control instructions involved in this application are all obtained with full authorization.

[0088] It should be understood that the term "plurality" used herein refers to two or more. "And / or" describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can mean: A exists alone, A and B exist simultaneously, or B exists alone. The character " / " generally indicates an "or" relationship between the associated objects.

[0089] It should be noted that the terms "first," "second," etc. (if any) in the specification and claims of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the numbers used in this way are interchangeable where appropriate so that the embodiments of the application described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the application as detailed in the appended claims.

[0090] The above description is merely an exemplary embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A cockpit voice interaction method, characterized in that: The method comprises: Collect driver's voice information; obtaining a detection result and a control instruction for an elderly driver based on the voice information of the driver, wherein the detection result for the elderly driver is used to indicate whether the driver is an elderly driver; In response to obtaining the elderly driver detection result that the driver is the elderly driver, controlling the vehicle to start an elderly-friendly working mode; controlling the vehicle to execute the control instruction; Collecting comprehensive noise values inside and outside the vehicle; Calculating the broadcast volume and broadcast speed based on the comprehensive noise value; The execution status of the control instruction is announced according to the announcement volume and the announcement speed.

2. The method according to claim 1, characterized in that Obtaining a detection result of an elderly driver based on the driver's voice information includes: Extracting the frequency, intensity, speaking speed and stress position of the sound information; The frequency, intensity, speaking speed and stress position are compared with a preset elderly group sound feature library to obtain a detection result of the elderly driver.

3. The method according to claim 2, characterized in that Acquiring a control instruction based on the driver's voice information includes: In response to obtaining the elderly driver detection result that the driver is the elderly driver, the elderly accent is corrected on the sound information, and the control instructions in the sound information are identified.

4. The method according to claim 1, wherein Calculating the broadcast volume based on the comprehensive noise value includes: Calculating a noise change rate and a ratio of the comprehensive noise value to a preset reference noise value based on the comprehensive noise value; The announcement volume is calculated based on the noise change rate and the ratio.

5. The method according to claim 4, characterized in that Calculating the broadcast speech rate based on the comprehensive noise value includes: Calculating a first difference between the integrated noise value and the preset baseline noise value, and a second difference between a preset maximum noise value and the integrated noise value based on the integrated noise value; The announcement speech rate is calculated based on the first difference and the second difference.

6. The method according to claim 1, characterized in that After collecting the driver's voice information, the method further includes: The sound information is preprocessed to remove noise from the sound information.

7. A cockpit voice interaction device, characterized in that: The device comprises: The first acquisition module is used to collect the driver's voice information; a first acquisition module, configured to acquire a detection result and a control instruction of an elderly driver based on the voice information of the driver, wherein the detection result of the elderly driver is used to indicate whether the driver is an elderly driver; a second obtaining module, configured to control the vehicle to start an elderly-friendly working mode in response to obtaining a detection result of the elderly driver indicating that the driver is the elderly driver; A control module, configured to control the vehicle to execute the control instruction; A second acquisition module is used to collect the comprehensive noise value inside and outside the vehicle; A calculation module, configured to calculate a broadcast volume and a broadcast speech rate based on the comprehensive noise value; The announcement module is used to announce the execution status of the control instruction according to the announcement volume and the announcement speed.

8. The device according to claim 7, characterized in that The first acquisition module is used to extract the frequency, intensity, speaking speed and stress position of the sound information; compare the frequency, intensity, speaking speed and stress position with a preset elderly group sound feature library to obtain the detection result of the elderly driver.

9. A computer program product, comprising computer instructions, which, when executed by a processor, implement the steps of the cockpit voice interaction method according to any one of claims 1 to 6.

10. A non-transitory computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which is loaded and executed by a processor to implement the cockpit voice interaction method according to any one of claims 1 to 6.

Images