Method for dynamically switching audio zones, voice interaction method, device, medium, and vehicle

Abstract

The present invention discloses a method for dynamically switching sound zones in a vehicle, a voice interaction method, a device, a medium, and a vehicle, and relates to the field of intelligent vehicle technology. The method aims to solve the problem of poor voice control effects on intelligent vehicles. The method for dynamically switching sound zones in a vehicle comprises: dynamically acquiring personnel distribution information of personnel in the vehicle; determining a sound zone layout method that matches the current personnel distribution information; and switching the actual sound zone layout method in the vehicle according to the sound zone layout method that matches the current personnel distribution information. By dynamically acquiring the distribution information of personnel in the vehicle and dynamically determining the sound zone layout method, it is possible to change the sound zone layout method when the personnel distribution changes, thereby improving the accuracy of acquiring the personnel's voices, and further improving the effect of voice control on the intelligent vehicle.

Description

Technical Field

[0001] The present invention relates to the field of intelligent vehicle technology, and in particular to a method for dynamically switching sound zones in a vehicle, a voice interaction method, a device, a medium, and a vehicle. Background Art

[0002] With the development of technology, smart cars have entered people's lives. More and more smart cars are equipped with voice control functions, allowing passengers to control the vehicle through voice.

[0003] The interior of a vehicle is typically divided into multiple audio zones. When a passenger in one audio zone uses voice control, the vehicle can ignore sounds from other audio zones to prevent them from interfering with the passenger's voice control. However, the current layout of audio zones within vehicles is fixed. When a passenger in one audio zone uses voice control, that passenger cannot use voice interaction devices in other audio zones to control the vehicle, even if no passengers are in other audio zones. This improves the effectiveness of voice control.

[0004] Accordingly, this field requires a new technical solution to solve the above problems. Summary of the Invention

[0005] In order to overcome the above-mentioned defects, the present invention is proposed to provide a method for dynamically switching sound zones in a vehicle, a voice interaction method, a device, a medium and a vehicle that solve or at least partially solve the problem of poor voice control effect of the vehicle.

[0006] In a first aspect, a method for dynamically switching sound zones in a vehicle is provided, the method comprising:

[0007] Dynamically obtain the personnel distribution information of people in the vehicle;

[0008] Determine the layout of the audio zones that matches the current personnel distribution information;

[0009] The actual audio zone layout in the vehicle is switched according to the audio zone layout that matches the current occupant distribution information.

[0010] Dynamically obtain the personnel distribution information of people in the vehicle;

[0011] Determine the layout of the audio zones that matches the current personnel distribution information;

[0012] The actual audio zone layout in the vehicle is switched according to the audio zone layout that matches the current occupant distribution information.

[0013] In one technical solution of the above-mentioned method for dynamically switching the sound zones in a vehicle, the step of "dynamically obtaining the distribution information of the occupants in the vehicle" specifically includes dynamically obtaining the distribution information of the occupants in the vehicle by the following means:

[0014] Obtaining initial occupant distribution information obtained by detecting multiple different types of in-vehicle detection information;

[0015] Final occupant distribution information is determined based on initial occupant distribution information obtained through respective detection of a plurality of different types of in-vehicle detection information.

[0016] In one technical solution of the above-mentioned method for dynamically switching vehicle interior sound zones, the step of "determining final occupant distribution information based on initial occupant distribution information obtained by detecting multiple different types of in-vehicle detection information" specifically includes:

[0017] Determining the highest priority in-vehicle detection information among multiple different types of in-vehicle detection information;

[0018] The final occupant distribution information is determined based on the initial occupant distribution information obtained through the in-vehicle detection information with the highest priority.

[0019] In one technical solution of the above-mentioned method for dynamically switching vehicle interior sound zones, the step of "determining final occupant distribution information based on initial occupant distribution information obtained by detecting multiple different types of in-vehicle detection information" specifically includes:

[0020] Obtain the largest amount of initial personnel distribution information;

[0021] The final personnel distribution information is determined based on the initial personnel distribution information obtained.

[0022] In one technical solution of the above-mentioned method for dynamically switching audio zones in a vehicle, the step of "determining an audio zone layout that matches the current occupant distribution information" specifically includes:

[0023] Determining the number of sound zones in the vehicle according to the number of people in the current person distribution information, so as to form a sound zone for each person;

[0024] Determine the coverage of the sound zone corresponding to each person according to the position of each person in the current personnel distribution information;

[0025] According to the number of voice zones and the coverage of the voice zones corresponding to each person, a voice zone layout method that matches the current personnel distribution information is determined.

[0026] In one technical solution of the above-mentioned method for dynamically switching vehicle interior sound zones, the in-vehicle detection information includes image information and / or seat sensor information and / or radar information. The method further includes obtaining initial occupant distribution information by:

[0027] Perform human body recognition on the image information and determine the initial personnel distribution information based on the results of human body recognition;

[0028] and / or,

[0029] Determine whether the corresponding seat is occupied based on the seat sensor information, and determine the initial occupant distribution information based on the determination result;

[0030] and / or,

[0031] The radar information is used to identify whether there is a heartbeat signal in the vehicle, and the initial personnel distribution information is determined based on the identification results.

[0032] In a second aspect, a voice interaction method is provided, the method comprising:

[0033] The actual layout of the sound zones in the vehicle is switched by using any of the above-mentioned methods for dynamically switching the sound zones in the vehicle;

[0034] After receiving a voice wake-up command issued by a person in the vehicle to the vehicle voice system, localize the sound source of the voice wake-up command;

[0035] Determine the voice zone corresponding to the person based on the sound source localization result, so as to conduct voice interaction with the person through the voice zone;

[0036] After receiving a voice wake-up command issued by a person in the vehicle to the vehicle voice system, localize the sound source of the voice wake-up command;

[0037] The voice zone corresponding to the person is determined based on the result of the sound source localization, so that voice interaction with the person can be carried out through the voice zone.

[0038] In a third aspect, a computer device is provided, which includes a processor and a storage device, wherein the storage device is suitable for storing multiple program codes, and the program codes are suitable for being loaded and run by the processor to execute the method for dynamically switching the sound zones in a vehicle as described in any of the technical solutions of the above-mentioned method for dynamically switching the sound zones in a vehicle.

[0039] In a fourth aspect, a computer-readable storage medium is provided, which stores a plurality of program codes, wherein the program codes are suitable for being loaded and run by a processor to execute the method for dynamically switching the sound zones in a vehicle as described in any one of the technical solutions of the above-mentioned method for dynamically switching the sound zones in a vehicle.

[0040] In a fifth aspect, a vehicle is provided, comprising the computer device described in the above-mentioned computer device technical solution.

[0041] The above one or more technical solutions of the present invention have at least one or more of the following beneficial effects:

[0042] In implementing the technical solution of the present invention, it is possible to dynamically obtain the occupant distribution information of the occupants in the vehicle, determine the audio zone layout that matches the current occupant distribution information, and then switch the actual audio zone layout in the vehicle based on the audio zone layout that matches the current occupant distribution information. Through the above-described implementation, it is possible to ensure that the actual audio zone layout in the vehicle is consistent with the actual occupant distribution information in the vehicle, so that there are people in each audio zone, and everyone can fully utilize the voice interaction device in their audio zone to interact with the vehicle and perform voice control of the vehicle. This overcomes the problem in the prior art that when a passenger in a certain audio zone uses the voice control function, even if there are no passengers in other audio zones, the passenger cannot use the voice interaction device in other audio zones to perform voice control of the vehicle, thereby reducing the control effect of the voice control.

[0043] When dynamically switching the sound zones in the vehicle, the final occupant distribution information is determined by obtaining the initial occupant distribution information based on different types of in-vehicle detection information. Different types of in-vehicle detection information can be combined. By setting priority or counting the initial occupant distribution information with the largest number of statistics as the final occupant distribution information, the interference of erroneous in-vehicle detection information caused by hardware failure is reduced, and the robustness of obtaining occupant distribution information is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The disclosure of the present invention will become more easily understood with reference to the accompanying drawings. Those skilled in the art will readily appreciate that these drawings are for illustrative purposes only and are not intended to limit the scope of protection of the present invention. Among them:

[0045] Figure 1 is a flow chart showing the main steps of a method for dynamically switching sound zones in a vehicle according to an embodiment of the present invention;

[0046] Figure 2 1 is a flow chart of the main steps of a voice interaction method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0047] Some embodiments of the present invention are described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0048] In the description of the present invention, "module" and "processor" may include hardware, software or a combination of the two. A module may include hardware circuits, various suitable sensors, communication ports, memories, and may also include software parts, such as program codes, or may be a combination of software and hardware. The processor may be a central processing unit, a microprocessor, an image processor, a digital signal processor or any other suitable processor. The processor has data and / or signal processing functions. The processor may be implemented in software, hardware or a combination of the two. Non-transitory computer-readable storage media include any suitable media that can store program codes, such as magnetic disks, hard disks, optical disks, flash memories, read-only memories, random access memories, etc. The term "A and / or B" represents all possible combinations of A and B, such as just A, just B or A and B.

[0049] The directional terms used in this document, such as "front", "rear", etc., are based on the front-to-rear direction of the vehicle after the component is installed on the vehicle.

[0050] An embodiment of the method for dynamically switching sound zones in a vehicle provided by the present invention will be described below with reference to the accompanying drawings.

[0051] Specifically, see the attached Figure 1 , Figure 1 FIG. 1 is a flow chart showing the main steps of a method for dynamically switching the sound zones in a vehicle according to an embodiment of the present invention. Figure 1 As shown, the dynamic switching of the vehicle interior sound zones in the embodiment of the present invention mainly includes the following steps S101 to S103.

[0052] Step S101: Dynamically obtain the distribution information of people in the vehicle.

[0053] Vehicle occupants include the driver and passengers. The distribution information of the occupants in the vehicle includes the number of occupants and their locations. Dynamic acquisition of the distribution information can be performed at fixed intervals, continuously after the vehicle is started, or when the vehicle doors are opened and / or closed. The present invention does not impose any restrictions on the timing of dynamically acquiring the distribution information.

[0054] Step S102: Determine a voice zone layout that matches the current personnel distribution information.

[0055] The layout of audio zones includes the number and location of audio zones. Matching occupant distribution information means matching the number and location of occupants within the vehicle. The number of audio zones should match the number of occupants, and the locations of the audio zones should match the locations of the occupants.

[0056] For example, if the current occupant distribution information of a vehicle is that there is a driver in the main driving seat, a passenger in the front passenger seat, and no passengers in the back row, then a sound zone should be set for each of the driver and the passenger, and no sound zone should be set for the back row.

[0057] Step S103: switching the actual audio zone layout mode in the vehicle according to the audio zone layout mode that matches the current occupant distribution information.

[0058] Since the occupant distribution information in the vehicle may change at any time, it is necessary to switch the actual audio zone layout mode in the vehicle to an audio zone layout mode that matches the current occupant distribution information.

[0059] For example, a vehicle currently has one audio zone, located in the driver's seat. However, the audio zone layout that matches the current occupant distribution is to have one audio zone each for the driver and passenger, with no audio zone for the rear seats. Therefore, the vehicle's actual audio zone layout needs to be changed to have one audio zone each for the driver and passenger, with no audio zone for the rear seats.

[0060] By dynamically acquiring the occupant distribution information of the vehicle's occupants based on the methods described in steps S101 to S103 above, the most up-to-date occupant distribution information can be immediately obtained whenever the number or location of occupants changes. By ensuring that the actual layout of the vehicle's audio zones aligns with the latest occupant distribution information, the vehicle can determine the coverage of its audio zones based on actual needs. This allows for multiple voice interaction devices within a single audio zone, enabling the vehicle to more accurately identify the voices of occupants within the zone, thereby improving the vehicle's voice control capabilities.

[0061] The above steps S101 to S103 are further explained below.

[0062] In one embodiment of the present invention, the step of “dynamically acquiring the distribution information of the people in the vehicle” specifically includes dynamically acquiring the distribution information of the people in the vehicle through steps 11 to 12.

[0063] Step 11: Obtain initial personnel distribution information obtained by detecting multiple different types of in-vehicle detection information.

[0064] Different types of in-vehicle detection information are obtained through different sensors in the vehicle, including but not limited to obtaining sensor information through the following methods: obtaining image information in the vehicle through a camera, obtaining weight information on the seat through a seat sensor, obtaining object information in the vehicle through a radar, etc.

[0065] Step 12: Determine final occupant distribution information based on initial occupant distribution information obtained through detection of multiple different types of in-vehicle detection information.

[0066] A single in-vehicle sensor can only partially reflect a single type of in-vehicle detection information, and a single in-vehicle sensor is very likely to malfunction, ultimately resulting in erroneous in-vehicle detection information being fed back. By using the method of steps 11 and 12 to combine the initial occupant distribution information to determine the final occupant distribution information, we can avoid misjudgments caused by using the initial occupant distribution information obtained from a single in-vehicle detection as the final occupant distribution information.

[0067] The following describes the method for obtaining the final personnel distribution information in an embodiment of the present invention.

[0068] In one embodiment of the present invention, the step of “determining final occupant distribution information based on initial occupant distribution information obtained by detecting multiple different types of in-vehicle detection information” specifically includes:

[0069] Step 21: Determine the highest priority in-vehicle detection information among multiple different types of in-vehicle detection information.

[0070] Because the accuracy of the initial occupant distribution information determined based on different types of in-vehicle detection information varies, it is necessary to set priorities for each type of in-vehicle detection information. The higher the credibility of the initial occupant distribution information obtained from the in-vehicle detection information, the higher the priority of the in-vehicle detection information. The credibility of the initial occupant distribution information obtained from the in-vehicle detection information is positively correlated with the priority of the in-vehicle detection information. The credibility of the initial occupant distribution information obtained from the in-vehicle detection information can be determined by counting the percentage of times the initial occupant distribution information matches the actual in-vehicle occupant distribution information within a preset number of times. For example, the preset number of times can be 1000, and the initial occupant distribution information obtained from the image information captured by the camera matches the actual in-vehicle occupant distribution information 990 times, resulting in a credibility of the image information captured by the camera of 99%. On the other hand, the initial occupant distribution information obtained from the seat sensor information captured by the seat sensor matches the actual in-vehicle occupant distribution information 890 times, resulting in a credibility of the seat sensor information captured by the seat sensor of 89%. Since the credibility of the image information collected by the camera is higher than that of the seat sensor information, it can be determined that the image information collected by the camera has a higher priority than the seat sensor information. Of course, other methods may also be used to determine the credibility of the in-vehicle detection information, and the present invention does not limit the method for determining the credibility of the in-vehicle detection information.

[0071] Step 22: Determine the final occupant distribution information based on the initial occupant distribution information obtained through the in-vehicle detection information with the highest priority.

[0072] If the initial personnel distribution information obtained by the in-vehicle detection information with high priority conflicts with the initial personnel distribution information obtained by the in-vehicle detection information with low priority, the initial personnel distribution information obtained by the in-vehicle detection information with high priority shall prevail, and the final personnel distribution information shall be determined based on the initial personnel distribution information obtained by the in-vehicle detection information with high priority.

[0073] For example, if the sensors in a vehicle include a camera and a seat sensor, the image information collected by the camera has a higher priority than the seat sensor information. Based on the seat sensor information, the initial occupant distribution information is determined to indicate that there are two occupants in the vehicle, one in the main driver's seat and the other in the front passenger seat. However, based on the image information collected by the camera, the initial occupant distribution information is determined to indicate that there is only one occupant in the main driver's seat. In this case, the initial occupant distribution information determined based on the seat sensor information conflicts with the initial occupant distribution information determined based on the image information collected by the camera. Because the image information collected by the camera has a higher priority than the seat sensor information, the final occupant distribution information is determined to indicate that there is only one occupant in the main driver's seat.

[0074] By setting priorities for different types of in-vehicle detection information based on the credibility of the initial personnel distribution information obtained from the in-vehicle detection information, the in-vehicle detection information with high credibility of the initial personnel distribution information obtained from the in-vehicle detection information is set to high priority, and the in-vehicle detection information with low credibility of the initial personnel distribution information obtained from the in-vehicle detection information is set to low priority. This can ensure that in the event of a conflict in the initial personnel distribution information determined based on the in-vehicle detection information, the accuracy of the personnel distribution information can still be guaranteed to the greatest extent.

[0075] In addition to the above method of determining the final personnel distribution information by using the initial personnel distribution information obtained through the in-vehicle detection information with the highest priority, the present invention also provides another method for determining the final personnel distribution information.

[0076] Specifically, in one embodiment of the present invention, the step of "determining final occupant distribution information based on initial occupant distribution information obtained by detecting multiple different types of in-vehicle detection information" specifically includes:

[0077] Step 31: Obtain the largest amount of initial personnel distribution information.

[0078] For example, if two types of in-car detection information determine the initial occupant distribution information as having only one person in the driver's seat, and only one type of in-car detection information determines the initial occupant distribution information as having two people in the vehicle, one in the driver's seat and the other in the passenger seat, then the initial occupant distribution information determined by the two types of in-car detection information is regarded as the type of initial occupant distribution information with the largest number of people, i.e., the type with only one person in the driver's seat.

[0079] Step 32: Determine the final personnel distribution information based on the obtained initial personnel distribution information.

[0080] If the initial occupant distribution information for each vehicle is different, the method from steps 31 to 32 can be used to select the initial occupant distribution information with the largest number of entries to determine the final occupant distribution information. By integrating different types of in-vehicle detection information, the probability of misjudging the final occupant distribution information due to sensor anomalies in the vehicle is reduced.

[0081] The following describes how the present invention detects and obtains the initial personnel distribution information.

[0082] In one embodiment of the present invention, the in-vehicle detection information includes image information and / or seat sensor information and / or radar information. The method for dynamically switching in-vehicle sound zones provided by the present invention can obtain initial occupant distribution information by detecting the following:

[0083] Perform human body recognition on the image information and determine the initial personnel distribution information based on the results of human body recognition.

[0084] Human body recognition in image information can be performed using a model based on a neural network, a method based on image geometric features, or a model based on a feature face method, or other methods can be used for human body recognition. The present invention does not limit the method for performing human body recognition. The result of human body recognition includes the location of the human body and the number of human bodies. For example, the result of human body recognition is that there are two human bodies in the car, one in the main driver's seat and the other in the co-pilot seat. Then, based on the result of human body recognition, it can be determined that the initial personnel distribution information determined this time is that there are two people in the car, and they are located in the main driver's seat and the co-pilot seat respectively.

[0085] The seat sensor information is used to determine whether the corresponding seat is occupied, and the initial occupant distribution information is determined based on the judgment result.

[0086] If the weight on a seat in the seat sensor data is zero, it is assumed that there is no one in the seat. If the weight on a seat is not zero, it is assumed that there is a person in the seat. Alternatively, a preset weight threshold can be set. If the weight on a seat is greater than or equal to the preset weight threshold, it is considered to be occupied. If the weight on a seat is less than the preset weight threshold, it is considered to be unoccupied. By counting the number of seats with people and the location of the seats with people, the initial occupancy distribution information can be determined.

[0087] The radar information is used to identify whether there is a heartbeat signal in the vehicle, and the initial personnel distribution information is determined based on the identification results.

[0088] The radar can be a millimeter-wave radar. The millimeter-wave radar information can be used to determine the position and number of objects that generate heartbeats in the car. The objects with heartbeats are the people in the car. Because the heartbeat frequency of ordinary people is generally 0.8-2.0Hz, the forward displacement of the heart in a single heartbeat is 0.1-0.5 mm, and the backward displacement is 0.01-0.2 mm, the position and number of people in the car can be determined by counting the position and number of objects in the vehicle with the same frequency and displacement amplitude as the heart, thereby obtaining the initial personnel distribution information. Of course, other methods can also be used to identify whether there is a heartbeat signal in the vehicle based on radar information. The present invention does not limit the method of identifying whether there is a heartbeat signal in the vehicle based on radar information.

[0089] Using radar information and image information to determine the initial occupant distribution information is more accurate, but the judgment process is more complicated. The judgment process using seat sensors is convenient but may cause misjudgment due to the presence of non-personnel objects on the seats.

[0090] The following describes the step of determining a voice zone layout that matches the current personnel distribution information (step S102).

[0091] Specifically, in one embodiment of the present invention, the step of "determining a voice zone layout matching the current personnel distribution information" specifically includes:

[0092] Step 41: Determine the number of sound zones in the vehicle according to the number of people in the current person distribution information, so as to form a sound zone for each person.

[0093] In order to prevent the voices of other people in the vehicle from interfering with the voice of the person currently voice-controlling the vehicle, a voice zone should be formed for each person.

[0094] Step 42: Determine the coverage of the sound zone corresponding to each person according to the position of each person in the current person distribution information.

[0095] For example, if a person is sitting in the back row of the main driver's seat, and there is only one person in that row, then the entire row where that person is located can be used as the corresponding sound zone coverage. If two people are sitting on the left and right of the back row of the main driver's seat, then the back row of the main driver's seat can be divided into two left and right sound zones, corresponding to the two people. The sound zone range for the person sitting on the left of the back row of the main driver's seat is the left half of the back row, and the sound zone range for the person sitting on the right of the back row of the main driver's seat is the right half of the back row.

[0096] Step 43: Determine a layout of the audio zones that matches the current personnel distribution information based on the number of audio zones and the coverage of the audio zones corresponding to each person.

[0097] By determining the coverage of the sound zone based on the location and number of occupants, the size of the sound zone can be dynamically adjusted. If there is only one person in the rear seat behind the driver's seat, the entire rear seat can be set as a sound zone, allowing more microphones to collect the voice of the person in the rear seat, improving the accuracy of speech recognition and enhancing the effectiveness of voice control of the vehicle.

[0098] The following describes an embodiment of the voice interaction method provided by the present invention.

[0099] Specifically, see the attached Figure 2 , Figure 2 FIG. 1 is a flow chart showing the main steps of a voice interaction method according to an embodiment of the present invention. Figure 2 As shown, the voice interaction method in the embodiment of the present invention mainly includes the following steps S201 to S203.

[0100] Step S201: The actual layout of the sound zones in the vehicle is switched using the method for dynamically switching the sound zones in the vehicle as described in the above-mentioned embodiment.

[0101] The layout of the sound zones in the vehicle is switched, that is, the number, position and coverage of the sound zones are switched to the latest determined ones.

[0102] Step S202: After receiving a voice wake-up command issued by a person in the vehicle to the vehicle voice system, the sound source of the voice wake-up command is located.

[0103] In order to receive the sounds made by people in the vehicle, multiple sets of voice interaction devices are arranged in the main driver's seat, the co-driver's seat and the rear passenger seat of the vehicle, and each set of voice interaction devices includes a microphone. Since the distances between the people in the vehicle and the microphones are different, there is a time delay difference when the sounds made by the people in the vehicle are transmitted to different microphones. When locating the sound source, a positioning method based on the estimation of the time delay of arrival (TDOA) can be used. Since the energy of the sound is attenuated during the propagation process, the energy of the sound made by the people in the vehicle is different when it is transmitted to different microphones. When locating the sound source, a positioning method based on controllable beamforming with maximum output power can be used. Since the above two types of sound source positioning are well known to those skilled in the art, they will not be repeated here. Of course, those skilled in the art can also use other methods to locate the sound source, and the present invention does not make specific limitations.

[0104] Step S203: determining the voice zone corresponding to the person according to the result of the sound source localization, so as to perform voice interaction with the person through the voice zone.

[0105] After determining the voice zone corresponding to the person who issues the voice wake-up command, sounds from other voice zones can be ignored, thereby avoiding interference of sounds from other voice zones on voice interaction.

[0106] The voice interaction method of steps S201 to S203 described above allows for timely changes to the layout of audio zones when the location or number of people changes. The vehicle can determine the coverage of audio zones based on actual needs, allowing multiple voice interaction devices to reside within a single audio zone. This improves the accuracy of collected speech and enhances the effectiveness of voice control for occupants. After localizing the sound source of a voice wake-up command, the audio zone in which the sound source resides can be determined, allowing sounds from other audio zones to be ignored to prevent interference with the source, thereby enhancing the effectiveness of voice control in the vehicle.

[0107] It should be pointed out that although the various steps in the above embodiments are described in a specific order, those skilled in the art will understand that in order to achieve the effects of the present invention, different steps do not have to be performed in such an order. They can be performed simultaneously (in parallel) or in other orders. These changes are within the scope of protection of the present invention.

[0108] Those skilled in the art will appreciate that all or part of the processes in the method for implementing the above-mentioned embodiment of the present invention may also be accomplished by instructing the relevant hardware through a computer program. The computer program may be stored in a computer-readable storage medium. When the computer program is executed by a processor, it may implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which may be in source code form, object code form, executable file, or some intermediate form. The computer-readable storage medium may include: any entity or device, medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory, random access memory, electric carrier signal, telecommunication signal, and software distribution medium capable of carrying the computer program code. It should be noted that the content contained in the computer-readable storage medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable storage media do not include electric carrier signals and telecommunication signals.

[0109] Furthermore, the present invention also provides a computer device. In one embodiment of the computer device according to the present invention, the computer device includes a processor and a storage device. The storage device can be configured to store a program for executing the method for dynamically switching vehicle audio zones or the voice interaction method according to the above-described method embodiment. The processor can be configured to execute the program in the storage device, which includes but is not limited to a program for executing the method for dynamically switching vehicle audio zones or the voice interaction method according to the above-described method embodiment. For ease of explanation, only the portions relevant to the embodiments of the present invention are shown. For specific technical details not disclosed, please refer to the method section of the embodiments of the present invention. The computer device can be a control device formed by various electronic devices.

[0110] Furthermore, the present invention also provides a computer-readable storage medium.

[0111] In one embodiment of a computer-readable storage medium according to the present invention, the computer-readable storage medium may be configured to store a program for executing the method for dynamically switching vehicle audio zones or the voice interaction method described in the above-described method embodiments. This program may be loaded and executed by a processor to implement the above-described method for dynamically switching vehicle audio zones or the voice interaction method. For ease of illustration, only portions relevant to the embodiments of the present invention are shown; for specific technical details not disclosed, please refer to the method section of the embodiments of the present invention. The computer-readable storage medium may be a storage device formed of various electronic devices. Optionally, in embodiments of the present invention, the computer-readable storage medium is non-transitory.

[0112] Furthermore, the present invention provides a vehicle. In one embodiment of a vehicle according to the present invention, the vehicle may include the computer device described in the aforementioned computer device embodiment. In this embodiment, the vehicle may be an autonomous vehicle, an unmanned vehicle, or other similar vehicle. Furthermore, based on the type of power source, the vehicle in this embodiment may be a fuel vehicle, an electric vehicle, a hybrid vehicle using a combination of electric and fuel, or a vehicle using other new energy sources.

[0113] Thus far, the technical solution of the present invention has been described in conjunction with an embodiment shown in the accompanying drawings. However, it is readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.

Claims

1. A method for dynamically switching sound zones in a vehicle, characterized in that: The method comprises: Dynamically obtaining occupant distribution information of occupants in the vehicle through multiple different types of in-vehicle detection information; determining the number of sound zones in the vehicle according to the number of people in the current person distribution information, so as to form a sound zone for each person; Determine the coverage of the sound zone corresponding to each of the persons according to the position of each of the persons in the current person distribution information; Determining a voice zone layout that matches the current personnel distribution information according to the number of the voice zones and the coverage of the voice zones corresponding to each of the personnel; The actual sound zone layout mode in the vehicle is switched according to the sound zone layout mode that matches the current personnel distribution information.

2. The method for dynamically switching the sound zones in a vehicle according to claim 1, characterized in that: The step of “dynamically obtaining the personnel distribution information of the personnel in the vehicle” specifically includes dynamically obtaining the personnel distribution information of the personnel in the vehicle by the following methods: Obtaining initial occupant distribution information obtained by detecting multiple different types of in-vehicle detection information; Final occupant distribution information is determined based on the initial occupant distribution information obtained by respectively detecting a plurality of different types of in-vehicle detection information.

3. The method for dynamically switching the sound zones in a vehicle according to claim 2, characterized in that: The step of “determining final occupant distribution information based on the initial occupant distribution information obtained by respectively detecting the plurality of different types of in-vehicle detection information” specifically includes: Determining the in-vehicle detection information with the highest priority among the multiple different types of in-vehicle detection information; The final personnel distribution information is determined according to the initial personnel distribution information obtained through the in-vehicle detection information with the highest priority.

4. The method for dynamically switching vehicle interior sound zones according to claim 2, characterized in that: The step of “determining final occupant distribution information based on the initial occupant distribution information obtained by respectively detecting the plurality of different types of in-vehicle detection information” specifically includes: Obtaining the largest amount of the initial personnel distribution information; Final personnel distribution information is determined based on the acquired initial personnel distribution information.

5. The method for dynamically switching vehicle interior sound zones according to claim 2, characterized in that: The in-vehicle detection information includes image information and / or seat sensor information and / or radar information. The method further includes obtaining the initial occupant distribution information by detecting in the following manner: Performing human body recognition on the image information, and determining the initial personnel distribution information according to the result of the human body recognition; and / or, determining whether a corresponding seat is occupied according to the seat sensor information, and determining the initial occupant distribution information according to the determination result; and / or, It is determined whether a heartbeat signal exists in the vehicle according to the radar information, and the initial personnel distribution information is determined according to the identification result.

6. A voice interaction method, characterized in that: The method comprises: The actual layout of the sound zones in the vehicle is switched using the method for dynamically switching the sound zones in the vehicle according to any one of claims 1 to 5; After receiving a voice wake-up command issued by a person in the vehicle to the vehicle voice system, performing sound source positioning on the voice wake-up command; The voice zone corresponding to the person is determined according to the result of the sound source localization, so as to perform voice interaction with the person through the voice zone.

7. A computer device comprising a processor and a storage device, wherein the storage device is suitable for storing a plurality of program codes, characterized in that: The program code is suitable for being loaded and run by the processor to execute the method for dynamically switching the sound zones in a vehicle according to any one of claims 1 to 5 or the voice interaction method according to claim 6.

8. A computer-readable storage medium storing a plurality of program codes, characterized in that: The program code is suitable for being loaded and run by a processor to execute the method for dynamically switching sound zones in a vehicle according to any one of claims 1 to 5 or the voice interaction method according to claim 6.

9. A vehicle, characterized in that: The vehicle includes the computer device of claim 7.

Images