Sound signal processing method and vehicle

Abstract

The invention discloses a sound signal processing method and a vehicle, and relates to the technical fields of artificial intelligence, intelligent connection vehicles, V2X and the like, and the vehicle can recognize the sources of a plurality of sound signals and eliminate the interference of noise based on the corresponding relation between the sound signals and identification information, and can more accurately determine the functions or effects of the sound signals. In the method, a vehicle receives a vehicle sound signal, and the vehicle sound signal comes from a vehicle-mounted application in a vehicle cabin and / or vehicle components except the vehicle cabin. And then, the vehicle determines corresponding identification information according to the vehicle sound signal, and plays first voice prompt information according to the identification information in response to a first voice input operation of the user, and the first voice prompt information comprises source information of the vehicle sound signal.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, and in particular to a sound signal processing method and a vehicle. Background Art

[0002] Smart cars are usually composed of multiple functional domains, such as chassis domain, body domain, power domain, safety domain, intelligent driving domain, intelligent cockpit domain, etc. When the components in the functional domain are in different scenarios, the corresponding speakers of the functional domain may play different sounds. For example, the safety domain speaker will play the seat belt warning sound when the user is not wearing a seat belt, and the low-speed pedestrian warning sound when driving at a low speed, etc. The body domain speaker will play the left or right turn prompt sound, the hazard warning prompt sound, the back door is not closed warning sound, etc.

[0003] After the smart car plays the above sound, if the user wants to turn it off, he can send a control command to the smart car. The smart car can determine what kind of sound is currently being played or what function it has (such as the alarm sound indicating what kind of fault it is, the prompt sound indicating what kind of situation it is, etc.) based on the user's control command, and then turn off the corresponding sound.

[0004] In some technical solutions, when determining the currently playing sound, the smart car needs to first pick up the sound, then specifically identify the content of the sound, and determine the function of the sound based on the content of the sound. However, when there is noise in the environment where the smart car is located, the smart car will also pick up the noise at the same time, so that the smart car cannot accurately identify the content of the sound under the interference of the noise, and further cannot accurately determine the function of the played sound. Summary of the invention

[0005] The embodiments of the present application provide a sound signal processing method and a vehicle, which can determine the source information of the sound signal through the identification information of the sound signal, thereby eliminating the interference of noise and more accurately determining the function or effect of the sound signal.

[0006] To achieve the above objectives, the embodiments of the present application adopt the following technical solutions:

[0007] In a first aspect, an embodiment of the present application provides a sound signal processing method, which is applied to a vehicle, wherein the vehicle receives a vehicle sound signal, wherein the vehicle sound signal comes from an on-board application in a vehicle cabin and / or a vehicle component other than the vehicle cabin. Afterwards, the vehicle determines corresponding identification information based on the vehicle sound signal, and, in response to a first voice input operation by a user, plays a first voice prompt information based on the identification information, wherein the first voice prompt information includes source information of the vehicle sound signal.

[0008] In the above method, the vehicle can detect sound signals from multiple sources, such as from vehicle applications, from vehicle components, etc. Moreover, based on the correspondence between the sound signal and the identification information, the sources of multiple sound signals can be identified. There is no need to determine the source of the sound signal by sound content recognition, thereby eliminating the interference of noise and more accurately determining the function or effect of the sound signal.

[0009] In addition, corresponding identification information is established for multiple sound signals. Through interaction with the user, the voice prompt information can be more clearly and accurately determined based on the identification information, providing the user with the source information of the sound signal, thereby improving the user's interaction experience with the vehicle. Moreover, detecting sound signals based on identification information can also make the detection of sound signals clearer, and it is also easier to detect the key sound signals that the user is concerned about from the acquired sound signals.

[0010] In some possible application scenarios, if the user wants to control the sound signal played by the vehicle through voice commands, there is no need to say which sound signal or signals the vehicle is currently playing. The vehicle can determine the source of the sound signal based on the identification information of the sound signal being played, and then determine the corresponding sound signal and control the sound signal. In this way, the user does not need to know which sound signal or signals the vehicle is currently playing, and the user's experience of interacting with the vehicle can also be improved.

[0011] In addition, since the above method in the embodiment of the present application does not need to identify the content of the sound signal to determine the source of the sound signal, it will not increase the computing load of sound recognition, and there is no need to train the sound recognition algorithm, thereby reducing the time for algorithm maintenance and allowing users to use the voice recognition function on the vehicle (such as the in-vehicle voice assistant) more conveniently. If the speaker that plays the sound signal is set outside the vehicle, since the vehicle has obtained the identification information of the sound signal, when the user speaks a voice command for the sound signal, the above method in the embodiment of the present application can also accurately determine the source of the sound signal through the identification information, thereby avoiding the problem of being unable to identify the external sound signal of the vehicle through sound recognition.

[0012] In an implementation of the first aspect, the vehicle receiving the vehicle sound signal may include receiving a first message from an in-vehicle application in a vehicle cabin, wherein the first message includes information related to the vehicle sound signal; or receiving a second message from a vehicle component, wherein the second message includes information related to the vehicle sound signal. In another implementation, the vehicle may also detect ambient sound in an environment where the vehicle is located, and detect the vehicle sound signal from the ambient sound.

[0013] In this implementation, when an in-vehicle application or vehicle component has a need to play a sound signal, the in-vehicle application or vehicle component will send a message or notification, so that the vehicle can obtain the corresponding vehicle sound signal according to the message or notification. Alternatively, if the vehicle is playing a vehicle sound signal, the vehicle can also detect the corresponding vehicle sound signal from the ambient sound. In this way, the vehicle can obtain sound signals through multiple methods and channels, making it easier to obtain the sound signals that users are concerned about.

[0014] In an implementation of the first aspect, in response to a first voice input operation by a user, the vehicle obtains description information of a vehicle sound signal corresponding to the identification information according to the identification information, wherein the description information includes one or more of type information, sound location information, name information, and generation reason information of the vehicle sound signal. Afterwards, the vehicle plays the first voice prompt information according to the description information of the vehicle sound signal.

[0015] The description information is used to describe the type, priority, name, and cause of the vehicle sound signal. Therefore, the function of the vehicle sound signal can be determined based on the description information. For example, if the name of the vehicle sound signal is "power battery fault indicator light", then the function of the vehicle sound signal can be determined to be a power battery fault warning sound. The vehicle can further determine the source of the vehicle sound signal based on the description information, thereby avoiding the use of audio recognition to determine the source of the vehicle sound signal.

[0016] In an implementation of the first aspect, there is a correspondence between the identification information and the description information of the vehicle sound signal, and the correspondence is pre-stored in the vehicle, or the correspondence is configured by the vehicle in response to a user's operation.

[0017] In this implementation, identification information of the vehicle sound signal is set, and a correspondence between the identification information and the description information is established. Based on the correspondence, the description information can be more accurately determined based on the identification information, and the source information of the vehicle sound signal can be determined based on the description information, thereby providing users with more accurate voice prompts and improving user experience.

[0018] In an implementation of the first aspect, the vehicle determines the sound source position of the vehicle sound signal according to the description information of the vehicle sound signal. If the vehicle sound signal is generated at the cockpit speaker, the vehicle controls the cockpit speaker to play the vehicle sound signal. If the vehicle sound signal is generated at other speakers except the cockpit speaker, the vehicle controls the other speakers to play the vehicle sound signal.

[0019] In this implementation, the sound signal provided by the vehicle can be played at any location in the vehicle, which makes the reminder method for vehicle abnormalities, failures or changes in working status more flexible, making it easier for users to understand the vehicle's abnormalities, failures or working status in a timely manner.

[0020] In one possible implementation of the first aspect, the user's first voice input operation includes asking for information about the source of the sound being played. Furthermore, the first voice prompt information includes information about the source of the vehicle sound signal. In this implementation, the vehicle can perform voice interaction with the user, receive the user's voice input, or obtain the user's voice command, and prompt the user with information about the source of the vehicle sound signal being played, thereby solving the user's need to understand the vehicle sound signal.

[0021] In one implementation of the first aspect, the vehicle responds to a second voice input operation by the user and, based on source information of the vehicle sound signal being played, performs a control operation on the vehicle sound signal being played, wherein the second voice input operation is used to instruct control of the vehicle sound signal being played, and the control operation includes turning off the vehicle sound signal being played and / or playing a fault clearance guidance corresponding to the vehicle sound signal being played.

[0022] In this implementation, the vehicle can interact with the user through voice, receive the user's voice input, or obtain the user's voice commands, and help the user perform corresponding operations on the vehicle sound signal being played.

[0023] In an implementation of the first aspect, the vehicle saves identification information of the vehicle sound signal that has been played. After the vehicle sound signal is played, the vehicle responds to a third voice input operation of the user, determines the source information of the vehicle sound signal that has been played according to the saved identification information of the vehicle sound signal that has been played, and plays the second voice prompt information. The third voice input operation is used to inquire about the source information of the vehicle sound signal that has been played, and the second voice prompt information includes the source information of the vehicle sound signal that has been played.

[0024] In this implementation, the vehicle can interact with the user through voice, receive the user's voice input, or obtain the user's voice commands, and prompt the user with the source information of the vehicle sound signal that is being played, thereby solving the user's need to understand the vehicle sound signal.

[0025] In an implementation method of the first aspect, the vehicle responds to a fourth voice input operation by the user, and performs a control operation on the vehicle sound signal that has been played according to source information of the vehicle sound signal that has been played, wherein the fourth voice input operation is used to instruct the control of the vehicle sound signal that has been played, and the control operation includes turning off the vehicle sound signal that has been played and / or playing a fault clearance guidance corresponding to the vehicle sound signal that has been played.

[0026] In this implementation, the vehicle can interact with the user through voice, receive the user's voice input, or obtain the user's voice commands, and help the user perform corresponding operations on the vehicle sound signals that have been played.

[0027] In one implementation of the first aspect, the vehicle sound signal includes multiple sound signals. When the cabin speakers and / or other speakers play multiple sound signals simultaneously, the vehicle plays a third voice prompt information in response to the user's first voice input operation, wherein the third voice prompt information includes source information corresponding to the multiple sound signals respectively.

[0028] In this implementation, when there are multiple vehicle sound signals, the user can also be made aware of which vehicle sound signals are currently being played simultaneously through interaction with the user, so that the user can select the vehicle sound signal that he wants to control.

[0029] In an implementable manner of the first aspect, in response to a second voice input operation of a user, the vehicle plays inquiry information corresponding to a plurality of sound signals in sequence according to source information corresponding to the plurality of sound signals, wherein the inquiry information is used to inquire whether to perform a control operation on the sound signal corresponding to the inquiry information. Within a preset time period after playing the inquiry information, the vehicle responds to a fifth voice input operation of the user and performs a control operation on the sound signal corresponding to the inquiry information according to source information of the sound signal corresponding to the inquiry information, wherein the fifth voice input operation is used to instruct to perform a control operation on the sound signal corresponding to the inquiry information.

[0030] In this implementation, when the vehicle sound signal includes multiple ones, the vehicle sequentially asks the user which vehicle sound signal he wants to control, so that the vehicle sound signal that the user wants to control can be determined more accurately among the multiple vehicle sound signals.

[0031] In one possible implementation of the first aspect, the first voice prompt information is also used to indicate the sound position information of the vehicle sound signal. And, in another possible implementation, the vehicle determines the source application and / or source component corresponding to the vehicle sound signal according to the description information of the vehicle sound signal, wherein the first voice prompt information also includes the source application information and / or source component information of the vehicle sound signal. Thus, the user can understand the playback position of the vehicle sound signal.

[0032] In an implementation of the first aspect, if the vehicle sound signal played by the cabin speaker includes at least two sound signals, the vehicle obtains priority information in the description information corresponding to each sound signal. The vehicle controls the cabin speaker to play the sound signal with the highest priority at a volume greater than the volume of other sound signals; or, the vehicle controls the cabin speaker to play the sound signal with the highest priority and pauses playing other sound signals, and after the sound signal with the highest priority is played, the vehicle controls the cabin speaker to continue playing other sound signals.

[0033] In this implementation, the vehicle sound signal with the highest priority can be, for example, a safety alarm sound, a prompt sound, etc. When multiple vehicle sound signals are played at the same time, the volume of the vehicle sound signal with the highest priority is greater than the volume of other vehicle sound signals, or the vehicle sound signal with the highest priority is played first, so that such vehicle sound signals can be more prominent, attracting the user's attention, allowing the user to promptly deal with some faults or situations that may affect safe driving, and reduce the occurrence of dangerous accidents. In an implementation of the first aspect, after determining the corresponding identification information based on the vehicle sound signal, the vehicle plays a fourth voice prompt information, wherein the fourth voice prompt information includes the source information of the vehicle sound signal. This implementation can achieve the purpose of playing prompt information for the user without user interaction, thereby improving the user's experience.

[0034] In one possible implementation of the first aspect, the first voice input operation includes inputting a pronoun referring to a vehicle sound signal being played and / or a pronoun used to refer to the current moment. In this implementation, the user can use the pronoun to implement voice interaction with the vehicle, and the vehicle can also accurately determine the vehicle sound signal that the user wants to operate based on the pronoun, which can also improve the user's interaction experience with the vehicle.

[0035] In one possible implementation of the first aspect, the third voice input operation includes inputting a pronoun for referring to a vehicle sound signal that has been played and / or a pronoun for referring to a historical moment. In this implementation, the user can also use the pronoun to implement voice interaction with the vehicle, and the vehicle can also accurately determine the vehicle sound signal that the user wants to operate based on the pronoun, which can also improve the user's interaction experience with the vehicle.

[0036] In a second aspect, a vehicle is provided, comprising a vehicle cabin and at least one vehicle component, wherein the vehicle cabin is communicatively connected to the at least one vehicle component.

[0037] A vehicle cockpit is used to receive a vehicle sound signal; the vehicle sound signal comes from an on-board application and / or vehicle components in the vehicle cockpit; the vehicle cockpit is used to determine corresponding identification information based on the vehicle sound signal; the vehicle cockpit is also used to respond to a user's first voice input operation and play a first voice prompt information based on the identification information, the first voice prompt information including source information of the vehicle sound signal.

[0038] In one implementation of the second aspect, the vehicle cabin is also used to receive a first message from an on-board application; the first message includes information related to the vehicle sound signal; or, to receive a second message from a vehicle component; the second message includes information related to the vehicle sound signal.

[0039] In an implementation of the second aspect, the vehicle cabin is further used to detect ambient sound of the vehicle's environment and detect vehicle sound signals from the ambient sound.

[0040] In an implementation method of the second aspect, the vehicle cockpit is also used to respond to the user's first voice input operation, and obtain, based on the identification information, descriptive information of the vehicle sound signal corresponding to the identification information; the descriptive information includes one or more of the type information, sound location information, name information, and cause information of the vehicle sound signal; and play the first voice prompt information based on the descriptive information of the vehicle sound signal.

[0041] In an implementation of the second aspect, there is a correspondence between the identification information and the description information of the vehicle sound signal, and the correspondence is pre-stored in the vehicle, or the correspondence is configured by the vehicle in response to the user's operation.

[0042] In an implementation method of the second aspect, the vehicle cabin is also used to determine the sound source position of the vehicle sound signal based on the description information of the vehicle sound signal; if the source position of the vehicle sound signal is the cabin speaker, the cabin speaker is controlled to play the vehicle sound signal; if the source position of the vehicle sound signal is other speakers except the cabin speaker, the other speakers are controlled to play the vehicle sound signal.

[0043] In one implementation of the second aspect, the vehicle cockpit is also used to respond to a second voice input operation of the user and perform a control operation on the vehicle sound signal being played based on source information of the vehicle sound signal being played; the second voice input operation is used to instruct control of the vehicle sound signal being played, and the control operation includes turning off the vehicle sound signal being played and / or playing a fault clearance guidance corresponding to the vehicle sound signal being played.

[0044] In an implementation method of the second aspect, the vehicle cockpit is also used to save identification information of the vehicle sound signal that has been played; after the vehicle sound signal is played, in response to a third voice input operation of the user, the source information of the vehicle sound signal that has been played is determined based on the saved identification information of the vehicle sound signal that has been played, and the second voice prompt information is played; the third voice input operation is used to inquire about the source information of the vehicle sound signal that has been played, and the second voice prompt information includes the source information of the vehicle sound signal that has been played.

[0045] In an implementation method of the second aspect, the vehicle cockpit is also used to respond to a fourth voice input operation of the user and perform a control operation on the played vehicle sound signal based on source information of the played vehicle sound signal; the fourth voice input operation is used to instruct the control of the played vehicle sound signal, and the control operation includes turning off the played vehicle sound signal and / or playing a fault clearance guidance corresponding to the played vehicle sound signal.

[0046] In an implementation method of the second aspect, the vehicle sound signal includes multiple sound signals, and the vehicle cabin is also used to play a third voice prompt information in response to the user's first voice input operation when the cabin speaker and / or other speakers play multiple sound signals at the same time; the third voice prompt information includes source information corresponding to the multiple sound signals respectively.

[0047] In an implementation method of the second aspect, the vehicle cockpit is also used to respond to the user's second voice input operation, and play inquiry information corresponding to multiple sound signals respectively according to the source information corresponding to the multiple sound signals; the inquiry information is used to inquire whether to perform a control operation on the sound signal corresponding to the inquiry information; within a preset time length after playing the inquiry information, in response to the user's fifth voice input operation, a control operation is performed on the sound signal corresponding to the inquiry information according to the source information of the sound signal corresponding to the inquiry information; the fifth voice input operation is used to indicate a control operation on the sound signal corresponding to the inquiry information.

[0048] In an implementation method of the second aspect, the vehicle cockpit is also used to determine the source application and / or source component corresponding to the vehicle sound signal based on the description information of the vehicle sound signal; the first voice prompt information also includes the source application information and / or source component information of the vehicle sound signal.

[0049] In an implementation method of the second aspect, the vehicle cabin is also used to obtain priority information in the description information corresponding to each sound signal if the vehicle sound signal played by the cabin speaker includes at least two sound signals; control the volume of the cabin speaker playing the sound signal with the highest priority to be greater than the volume of playing other sound signals; or control the cabin speaker to play the sound signal with the highest priority and pause playing other sound signals, and after the sound signal with the highest priority is played, control the cabin speaker to continue playing other sound signals.

[0050] In an implementation manner of the second aspect, the vehicle cockpit is further used to play fourth voice prompt information after determining the identification information corresponding to the vehicle sound signal; the fourth voice prompt information includes source information of the vehicle sound signal.

[0051] In a third aspect, a vehicle is provided, comprising a memory and one or more processors; the memory is coupled to the processor; wherein the memory stores computer program code, the computer program code comprises computer instructions, and when the computer instructions are executed by the processor, the vehicle executes the sound signal processing method as in the first aspect and any implementation thereof.

[0052] In a fourth aspect, a computer-readable storage medium is provided, comprising computer instructions. When the computer instructions are executed on a vehicle, the vehicle executes the sound signal processing method as in the first aspect and any implementation thereof.

[0053] In a fifth aspect, a computer program product is provided. When the computer program product is run on a vehicle, the vehicle executes the sound signal processing method in the first aspect and any implementation thereof.

[0054] It can be understood that the beneficial effects that can be achieved by the vehicle described in the second aspect, the vehicle described in the third aspect, the computer-readable storage medium described in the fourth aspect, and the computer program product described in the fifth aspect can be referred to the beneficial effects in the first aspect and any possible design method thereof, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 The structure of the vehicle shown in the embodiment of the present application is shown in FIG. Figure 1 ;

[0056] Figure 2 The structure of the vehicle shown in the embodiment of the present application is shown in FIG. Figure 2 ;

[0057] Figure 3 The process diagram of the sound signal processing method shown in the embodiment of the present application is as follows Figure 1 ;

[0058] Figure 4 The process diagram of the sound signal processing method shown in the embodiment of the present application is as follows Figure 2 ;

[0059] Figure 5 The process diagram of the sound signal processing method shown in the embodiment of the present application is as follows Figure 3 ;

[0060] Figure 6 Schematic diagram of a vehicle display screen shown in an embodiment of the present application Figure 1 ;

[0061] Figure 7 Schematic diagram of a vehicle display screen shown in an embodiment of the present application Figure 2 ;

[0062] Figure 8 A schematic diagram of a vehicle speaker according to an embodiment of the present application;

[0063] Fig. 9 The process diagram of the sound signal processing method shown in the embodiment of the present application is as follows Figure 4 ;

[0064] Fig.10 The structure of the vehicle shown in the embodiment of the present application is shown in FIG. Figure 3 . DETAILED DESCRIPTION

[0065] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application. Among them, in the description of the present application, unless otherwise specified, " / " indicates that the objects associated before and after are in an "or" relationship, for example, A / B can represent A or B; "and / or" in the present application is only a description of the association relationship of the associated objects, indicating that there can be three relationships, for example, A and / or B, which can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. And, in the description of the present application, unless otherwise specified, "multiple" refers to two or more than two. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple. In addition, in order to facilitate the clear description of the technical solutions of the embodiments of the present application, in the embodiments of the present application, the words "first", "second" and the like are used to distinguish the same items or similar items with substantially the same functions and effects. Those skilled in the art will understand that the words "first", "second" and the like do not limit the quantity and execution order, and the words "first", "second" and the like do not necessarily limit the differences. At the same time, in the embodiments of the present application, the words "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or design solutions. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete manner for ease of understanding.

[0066] In addition, the business scenarios described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. A person of ordinary skill in the art can appreciate that with the emergence of new business scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0067] Current smart cars are usually composed of multiple functional domains, such as chassis domain, body domain, power domain, safety domain, intelligent driving domain, intelligent cockpit domain (such as vehicle cockpit), etc. When the components in the functional domain are in different scenes, the speakers corresponding to the functional domain may play different sound signals accordingly. For example, the speakers in the safety domain will play the seat belt warning sound when the user is not wearing a seat belt, and the low-speed pedestrian warning sound when driving at a low speed, etc. The speakers in the body domain will play the left or right turn prompt sound, the hazard warning prompt sound, the back door is not closed warning sound, etc.

[0068] After the smart car plays the above sound signal, the user can hear the corresponding sound and speak a voice command to turn off the sound to the in-vehicle voice assistant installed on the smart car, so that the smart car controls the sound signal to stop playing. In such a technical solution, the user needs to know which sound signal or sounds the smart car is currently playing. For example, if the smart car is currently playing the seat belt warning sound, the user needs to accurately say "turn off the seat belt warning sound" before the smart car stops playing this sound signal.

[0069] However, there are many sound signals that can be played by smart cars, and most of the sound signals are just different in frequency. The human ear may not be able to distinguish the specific differences between different sound signals. Faced with a large number of alarm sounds or prompt sounds, users cannot remember which sound each sound signal corresponds to or what function it has, or which specific alarm sound or prompt sound it is. Although the prompt information corresponding to the current sound signal may be displayed on the instrument panel of the smart car when some sound signals are played, the user who is driving cannot pay attention to the prompt information in time. If the user relies solely on the sound heard by the ears to distinguish, the user who is driving cannot specifically distinguish what the sound signal played by the smart car is prompting or what function it has. Furthermore, the user who is driving may not be able to control the smart car to turn off the sound through voice commands, which affects the interactive experience between the user and the smart car.

[0070] Alternatively, after the smart car plays the above sound signal, if the user wants to turn it off, he can send a control command to the smart car's in-vehicle voice assistant. The smart car can determine what kind of sound signal is currently playing or what function it has (such as the alarm sound indicating what kind of fault it is, the prompt sound indicating what kind of situation it is, etc.) according to the user's control command, and then turn off the corresponding sound signal. When determining the currently playing sound signal, the smart car needs to first pick up the sound signal through the in-vehicle voice assistant, then specifically identify the content of the sound signal, and determine what function the sound has based on the content of the sound signal.

[0071] However, when there is noise in the environment where the smart car is located, the smart car will also pick up the noise at the same time through the in-vehicle voice assistant, so that the smart car cannot accurately identify the content of the sound signal under the interference of the noise, or misidentification occurs, and it is impossible to accurately determine the function of the played sound signal. In addition, the in-vehicle voice assistant needs to obtain the sound signal played by the smart car in real time, which will increase the computing power load of sound recognition. When the sound signal of the new functional domain component of the smart car increases, it is also necessary to retrain the sound recognition algorithm of the in-vehicle voice assistant, which will also increase the time for algorithm maintenance and make the use of the in-vehicle voice assistant more complicated. In addition, if the speaker that plays the sound signal is set outside the smart car, the smart voice assistant inside the smart car may not be able to obtain the sound signal.

[0072] Based on the above content, an embodiment of the present application provides a method for processing a sound signal. In the method, a vehicle receives a vehicle sound signal, wherein the vehicle sound signal comes from an on-board application in a vehicle cabin or a vehicle component other than the vehicle cabin. Afterwards, the vehicle determines corresponding identification information based on the vehicle sound signal, and in response to a first voice input operation of a user, plays a first voice prompt information based on the identification information, wherein the first voice prompt information includes source information of the vehicle sound signal.

[0073] In the above-mentioned sound signal processing method, the vehicle can detect sound signals from multiple sources, such as from vehicle-mounted applications, from vehicle components, etc. Moreover, based on the correspondence between the sound signal and the identification information, the sources of multiple sound signals can be identified. There is no need to determine the source of the sound signal by sound recognition, thereby eliminating the interference of noise and more accurately determining the function or effect of the sound signal.

[0074] In addition, corresponding identification information is established for multiple sound signals. Through interaction with the user, the voice prompt information can be more clearly and accurately determined based on the identification information, providing the user with the source information of the sound signal, thereby improving the user's interaction experience with the vehicle. Moreover, detecting sound signals based on identification information can also make the detection of sound signals clearer, and it is also easier to detect the key sound signals that the user is concerned about from the acquired sound signals.

[0075] In some possible application scenarios, if the user wants to control the sound signal played by the vehicle through voice commands, there is no need to say which sound signal or signals the vehicle is currently playing. The vehicle can determine the source of the sound signal based on the identification information of the sound signal being played, and then determine the corresponding sound signal and control the sound signal. In this way, the user does not need to know which sound signal or signals the vehicle is currently playing, and the user's experience of interacting with the vehicle can also be improved.

[0076] In addition, since the above method in the embodiment of the present application does not need to identify the content of the sound signal to determine the source of the sound signal, it will not increase the computing load of sound recognition, and there is no need to train the sound recognition algorithm, thereby reducing the time for algorithm maintenance and allowing users to use the voice recognition function on the vehicle (such as the in-vehicle voice assistant) more conveniently. If the speaker that plays the sound signal is set outside the vehicle, since the vehicle has obtained the identification information of the sound signal, when the user speaks a voice command for the sound signal, the above method in the embodiment of the present application can also accurately determine the source of the sound signal through the identification information, thereby avoiding the problem of being unable to identify the external sound signal of the vehicle through sound recognition.

[0077] The above-mentioned sound signal processing method provided in the embodiment of the present application can be applied to Figure 1 In the vehicle shown. Figure 1 The vehicle may include multiple functional domains, such as a power domain, a chassis domain, a body domain, a safety domain, an intelligent driving domain, an intelligent cockpit domain (such as a vehicle cockpit), etc. Different functional domains may provide different functions, and different functional domains include different structures or components on the vehicle, and the components in each functional domain are interconnected, and the functional domains may communicate with each other through the vehicle gateway.

[0078] Exemplarily, the above chassis domain can provide functions such as braking, steering, and transmission, and specifically can include springs, shock absorbers, suspension arms, steering rods, transmissions, clutches, drive shafts, differentials, brake pads, brake discs, brake oil pipes, brakes, steering columns, steering gears, steering gears, and other components. The body domain can include components such as instrument panels (or instrument screens), interior lights, exterior lights, windows, sunroofs, door locks, air conditioners, sensors, rearview mirrors, wipers, seats, seat belts, charging ports, and fuel filler ports. The power domain can provide power for the vehicle, and specifically can include power batteries, engines, motors, sensors, inverters, reducers, high-voltage control boxes, transformers, and other components. The safety domain can include components, radars, and various sensors of other functional domains. When any component is abnormal or the sensor detects an abnormality, the safety domain provides corresponding safety reminders and other functions, or the safety domain can also provide parking assistance services, etc. The intelligent driving domain can also include components, radars, and various sensors of other functional domains, and provide functions such as driving assistance in combination with components, radars, and various sensors of other functional domains. The smart cockpit domain (such as the vehicle cockpit) can not only include components of other functional domains, radars, various sensors, etc., but also include the central control screen (or display screen) and various installed vehicle application software. The smart cockpit domain (such as the vehicle cockpit) can control other functional domains, or interact with users to help users control other functional domains.

[0079] In addition, different functional domains may also include corresponding controllers, control units, etc. For example, the chassis domain may include a chassis domain controller or a chassis domain microcontroller unit (MCU), the body domain includes a body domain controller or a body domain MCU, the power domain includes a power domain controller or a power domain MCU, the safety domain includes a safety domain controller or a safety domain MCU, the intelligent driving domain includes an intelligent driving domain controller or an intelligent driving domain MCU, and the intelligent cockpit domain (such as a vehicle cockpit) includes a cockpit controller or a cockpit MCU. The controller or MCU of each functional domain can be connected to each vehicle component included in the functional domain, respectively, to obtain detection data from the vehicle components and / or to control the vehicle components.

[0080] In some possible application scenarios, each functional domain may also include speakers belonging to this functional domain. For example, the chassis domain may include chassis speakers, the body domain includes body speakers, the power domain includes power speakers, the safety domain includes safety speakers, the smart driving domain includes smart driving speakers, and the smart cockpit domain (such as the vehicle cockpit) includes cockpit speakers, etc. When the functional domain includes a speaker, the speaker may include at least one, and the speaker may be set on a certain component of the functional domain, such as on the dashboard, or may be set independently of any component. In addition, the speaker may be set inside or outside the vehicle.

[0081] Based on the above content, it can be known that the vehicle includes a large number of components. If different components have abnormalities, failures or changes in working status, they may affect the operation of the vehicle and the safe driving of the user. Therefore, in the embodiment of the present application, when the vehicle has an abnormal situation or a change in working status (for example, receiving a corresponding event) in a component, the vehicle can play a corresponding sound signal to the user, thereby reminding the user to check the situation or resolve the fault. In some possible application scenarios, the on-board applications in the vehicle cabin may include interactive applications such as intelligent voice assistants. After the user hears the sound corresponding to the sound signal, he can also understand the function of the sound signal played by the vehicle through interaction with the intelligent voice assistant, such as indicating which one or which situations, indicating which one or which faults, etc., and can also control the sound signal played by the vehicle.

[0082] In the embodiment of the present application, a corresponding sound signal can be set for each component that may have an abnormality, failure, or change in working state (or called a sound event), and corresponding identification information can be set for each sound signal, wherein the identification information is used to distinguish sound signals with different functions or effects. In addition, corresponding description information can also be set for each sound signal, and the description information includes one or more of the source information, type information, priority information, name information, sound location information, cause information, and playback mode of the sound signal. And, the identification information of each sound signal corresponds to the corresponding description information one by one, or has a corresponding relationship.

[0083] In some possible application scenarios, the correspondence between the identification information and the description information of the sound signal can be saved in the form of preset audio information or in the form of a preset information list, that is, the preset audio information or the preset information list includes at least one correspondence. The correspondence between the identification information and the description information can be configured according to the user's selection operation, or automatically updated according to the user's habits, preferences, etc. The vehicle can obtain the preset audio information, preset information list, etc. from the cloud device, or the preset audio information, preset information list, etc. can also be pre-configured in the vehicle.

[0084] In some possible application scenarios, when a component in a target functional domain in a vehicle is abnormal, fails, or changes in working state, the target functional domain will receive the corresponding sound event, and in response to the sound event, obtain the corresponding sound signal. If the target functional domain includes a speaker of this functional domain, the functional domain may control the speaker of this functional domain to play the sound signal, and send a message to the smart cockpit domain (such as a vehicle cockpit), the message including information related to the sound signal, such as indication information of the sound signal, identification information corresponding to the sound signal, etc. If the target functional domain does not include a speaker, the sound signal will not be played in this functional domain, but a message will be sent to the smart cockpit domain (such as a vehicle cockpit), the message including information related to the sound signal, such as indication information of the sound signal, identification information corresponding to the sound signal, etc. The smart cockpit domain (such as the vehicle cockpit) obtains the description information of the sound signal from the preset audio information according to the identification information of the received sound signal, and determines whether the sound signal is generated by the cockpit speaker according to the sound generation location information in the description information. If so, the smart cockpit domain (such as the vehicle cockpit) controls the cockpit speaker to play the sound signal. It can be understood that regardless of whether the above sound signal is played by the cockpit speaker, the smart cockpit domain (such as the vehicle cockpit) will receive the identification information corresponding to the sound signal.

[0085] In addition, the sound position information in the above description information can be set according to whether the functional domain has a speaker. For example, if the chassis domain includes a speaker, then the sound signal corresponding to the sound event from the chassis domain can be set to be played by the speaker of the chassis domain, that is, the sound position of the sound signal corresponding to the sound event is the chassis domain speaker; or, if the chassis domain does not include a speaker, then the sound signal corresponding to the sound event from the chassis domain can be set to be played by the cabin speaker, that is, the sound position of the sound signal corresponding to the sound event is the cabin speaker.

[0086] In other possible application scenarios, in addition to the above-mentioned intelligent voice assistants, the in-vehicle applications installed in the smart cockpit domain (such as the vehicle cockpit) may also include media applications (such as music applications, radio, etc.), call applications, navigation applications, etc. These applications may also have the need to play sound signals or generate sound events when running. For example, the music application plays music, the call application plays call voice, and the navigation application plays navigation voice.

[0087] In an embodiment of the present application, a corresponding sound type may also be set for each sound event corresponding to the above-mentioned vehicle-mounted application, such as an alarm type, a call type, a voice interaction type, a prompt type, an operation type, a media type, etc. In addition, corresponding identification information is also set for each sound type, and the identification information can be used to distinguish sound signals of different functions, or to distinguish different sound signals from different vehicle-mounted applications. In addition, corresponding description information may also be set for each sound signal, similarly including one or more of the source information, category information (or type information), priority information, name information, sound location information, cause information, and playback mode of the sound signal. And, the identification information of each sound signal corresponds to the corresponding description information one by one, or has a corresponding relationship. It can be understood that the above-mentioned preset audio information or preset information list may also include identification information and description information of different sound signals corresponding to the vehicle-mounted application.

[0088] In some possible application scenarios, when the in-vehicle application of the smart cockpit domain (such as the vehicle cockpit) needs to play a sound signal, the smart cockpit domain (such as the vehicle cockpit) will control the cockpit speaker to play the corresponding sound signal. At the same time, the smart cockpit domain (such as the vehicle cockpit) will also save the identification information corresponding to the sound type of the sound signal. After listening to the sound corresponding to the sound signal, the user can also understand the function or role of the sound signal played by the vehicle through interaction with the intelligent voice assistant, such as indicating which one or which situations, indicating which one or which faults, etc., and can also control the sound signal played by the vehicle.

[0089] It is understandable that the smart cockpit domain (such as a vehicle cockpit) can receive messages including sound signal identification information sent by other functional domains, and can also obtain messages including sound signal identification information played by this functional domain. The timing and time required for playing sound signals in each functional domain may be different, and the timing and time required for playing sound signals by the vehicle-mounted applications of the smart cockpit domain (such as a vehicle cockpit) may also be different. Therefore, the time when the smart cockpit domain (such as a vehicle cockpit) receives the identification information may be different. After the smart cockpit domain (such as a vehicle cockpit) obtains the identification information, the identification information can be saved in sequence according to the reception time (or the time when the sound signal is played). The order of the reception time of the identification information can characterize the order of the playback time of the sound signal corresponding to the identification information on the vehicle. Whether the sound signal is played on the cockpit domain speaker or on other speakers, it can be regarded as being played on the vehicle. In addition, the smart cockpit domain (such as a vehicle cockpit) can determine the identification information of the sound signal currently being played by the vehicle, or the identification information of the sound signal played in the past period of time according to the order of the reception time of the identification information.

[0090] Based on the above content, in some possible application scenarios, after the smart cockpit domain (such as the vehicle cockpit) obtains the identification information of the sound signal, it can determine the source information of the sound signal played by the vehicle (such as the cockpit speaker and / or the speaker of the target functional domain) according to the identification information of the sound signal and the preset audio information. Among them, the source information can be determined according to the above description information of the sound signal. For example, the smart cockpit domain (such as the vehicle cockpit) obtains the description information of the sound signal from the preset audio information according to the identification information of the sound signal, and then determines the source information of the sound signal according to the description information of the sound signal. It can be understood that the above-mentioned other functional domains include the target functional domain. In some possible application scenarios, during the process of the vehicle playing the sound signal, the smart cockpit domain (such as the vehicle cockpit) can receive the user's first voice input instruction, and in response to the first voice input instruction, play the first voice prompt information, and the first voice prompt information includes the source information of the sound signal. Among them, the first voice input instruction is used to inquire about the source information of the sound signal being played, for example, the user asks "What is this sound", "What is playing now", etc., as well as the first voice prompt information played in the smart cockpit domain (such as a vehicle cockpit), such as "This is music", "This is the reminder sound for not fastening the seat belt", etc.

[0091] In addition, the first voice prompt information played in the smart cockpit domain (such as a vehicle cockpit) may also indicate the sound location information of the sound signal; and, the smart cockpit domain (such as a vehicle cockpit) may determine the description information of the sound signal based on the identification information of the sound signal and the preset audio information, and determine the source application and / or source component corresponding to the sound signal based on the source information of the sound signal in the description information, that is, which on-board application and which vehicle component the sound signal comes from, and the first voice prompt information played in the smart cockpit domain (such as a vehicle cockpit) also includes the source application information and / or source component information of the sound signal.

[0092] In other possible application scenarios, the smart cockpit domain (such as a vehicle cockpit) can pick up sound signals in real time through smart voice assistants, etc., so as to determine the user's voice input commands from the sound signals. In addition, the smart cockpit domain will also pick up ambient sound. If the ambient sound also includes sound signals played by the vehicle, the smart cockpit domain (such as a vehicle cockpit) can identify it, and determine the identification information of the sound signal based on the identified content, and play the corresponding first voice prompt information based on the identification information. It can be seen that the smart cockpit domain (such as a vehicle cockpit) can obtain sound signals through multiple methods and channels, making it easier to obtain the sound signals that users are concerned about.

[0093] In other possible application scenarios, the smart cockpit domain (such as a vehicle cockpit) can also receive a second voice input instruction from the user, and in response to the second voice input instruction, perform a control operation on the sound signal according to the source information of the sound signal being played. The second voice input instruction is used to instruct the control of the sound signal being played, for example, the user says "turn off this sound", "how to turn off this sound", etc. The control operation includes turning off the sound signal and / or playing the fault clearance guidance corresponding to the sound signal. For example, when the sound signal played by the vehicle indicates a power battery fault, if the user says "how to turn off this sound", the smart cockpit domain (such as a vehicle cockpit) can play the fault clearance guidance of "please fasten your seat belts".

[0094] In some possible application scenarios, after the sound signal is played, the smart cockpit domain (such as the vehicle cockpit) can receive the user's third voice input command, and in response to the third voice input command, determine the source information of the sound signal according to the identification information of the saved sound signal and the preset audio information, and play the second voice prompt information for prompting the source information of the played sound signal. Among them, the third voice input command is used to inquire about the source information of the played sound signal, for example, the user asks "what sound just now", "what sound was played at 12:30 today", and the second voice prompt information played by the smart cockpit domain (such as the vehicle cockpit), such as "what was played just now was music", "what was played at 12:30 today was a reminder sound for not fastening the seat belt", etc.

[0095] In other possible application scenarios, the smart cockpit domain (such as a vehicle cockpit) can also receive a fourth voice input instruction, and in response to the fourth voice input operation, perform a control operation on the sound signal played by the vehicle according to the source information of the sound signal played. Among them, the fourth voice input instruction is used to instruct the control of the sound signal played, for example, the user says "turn off this sound", "how to turn off this sound", etc. The control operation includes turning off the sound signal that has been played and / or playing the fault clearance guidance corresponding to the sound signal that has been played. For example, when the sound signal played by the vehicle indicates that the seat belt is not fastened, if the user says "how to turn off this sound", the smart cockpit domain (such as the vehicle cockpit) can play the fault clearance guidance of "please fasten your seat belt".

[0096] In some possible application scenarios, when the sound signals played by the cockpit speaker include at least two, the smart cockpit domain (such as the vehicle cockpit) can obtain the priority information in the description information corresponding to each sound signal, and control the cockpit speaker to play the sound signal with the highest priority at a higher volume than the volume of other sound signals; or, control the cockpit speaker to play the sound signal with the highest priority, pause playing other sound signals, and control the cockpit speaker to continue playing other sound signals after the sound signal with the highest priority is played. Among them, the sound signal with the highest priority can be, for example, a safety alarm sound, prompt sound, etc. When multiple sound signals are played at the same time, the volume of the sound signal with the highest priority is higher than the volume of other sound signals, or the sound signal with the highest priority is played first, so that such sound signals can be more prominent, attract the user's attention, and allow the user to promptly deal with some faults or situations that may affect safe driving, thereby reducing the occurrence of dangerous accidents.

[0097] In other possible application scenarios, when the target functional domain's speaker plays at least two sound signals, the target functional domain may also obtain the priority information in the description information corresponding to each sound signal, and control the target functional domain's speaker to play the sound signal with the highest priority at a volume greater than the volume of other sound signals; or, control the target functional domain's speaker to play the sound signal with the highest priority and pause playing other sound signals, and after the sound signal with the highest priority is played, control the target functional domain's speaker to continue playing other sound signals.

[0098] In some possible application scenarios, after receiving the identification information of the sound signal, the smart cockpit (such as the vehicle cockpit) can directly play the fourth voice prompt information, wherein the fourth voice prompt information can include the source information of the sound signal, thereby playing the prompt information for the user without user interaction, thereby improving the user experience.

[0099] In some possible application scenarios, the smart cockpit domain (such as a vehicle cockpit) can control the cockpit speaker to play the first voice prompt information, the second voice prompt information, the fourth voice prompt information, the inquiry information, etc. It can also control the speaker of the target functional domain to play the first voice prompt information, the second voice prompt information, the fourth voice prompt information, the inquiry information, etc.

[0100] It can be understood that the functions implemented or the execution methods implemented by the above-mentioned smart cockpit domain (such as vehicle cockpit) and target cockpit domain are all implemented through the controllers of the smart cockpit domain (such as vehicle cockpit) and the target cockpit domain.

[0101] For other possible application scenarios, see Figure 2 As shown, other target functional domains except the smart cockpit domain (such as the vehicle cockpit) can respectively include an event detection module and an information sending module, etc. Among them, when a vehicle component in the target functional domain has an abnormality, a fault, or a change in working status, the event detection module in the target functional domain will detect the corresponding event (such as the first sound event) and obtain the sound signal corresponding to the event and the identification information of the sound signal. The information sending module sends the identification information of the sound signal to the smart cockpit domain (such as the vehicle cockpit) through a message or the like. In addition, the event detection module can also determine the description information of the sound signal in the preset audio information according to the identification information of the sound signal. If it is determined according to the description information that the sound signal needs to be played on the speaker of the current target functional domain, the event detection module can control the speaker of this functional domain to play the sound signal corresponding to the identification information.

[0102] The smart cockpit domain (such as a vehicle cockpit) may include an information acquisition module, a first audio module, a second audio module, an audio setting module, and a speech recognition module, etc. Among them, the information acquisition module may also include an information receiving module and an audio output module. The information receiving module can receive the identification information of the sound signal (such as the first sound signal) sent by the target functional domain, and determine the description information of the sound signal in the preset audio information according to the identification information, and determine whether the sound signal needs to be played on the cockpit speaker according to the description information. If the sound signal needs to be played on the cockpit speaker, the information receiving module sends the identification information of the sound signal to the first audio module, and the first audio module obtains the sound signal according to the identification information, and sends the sound signal and the identification information to the audio output module, and the audio output module outputs the sound signal to the cockpit speaker for playback.

[0103] If the smart cockpit domain (such as a vehicle cockpit) itself generates a sound event (such as a second occurrence event), for example, a component in the smart cockpit domain (such as a vehicle cockpit) has an abnormality, a fault, or a sound change in the working state, or the in-vehicle application in the smart cockpit domain (such as a vehicle cockpit) needs to make a sound (such as playing music, playing a prompt tone), etc., then the second audio module obtains the sound event and sends the sound signal (such as the second sound signal) and the identification information of the sound signal corresponding to the sound event to the audio output module, and the audio output module outputs the sound signal to the cockpit speaker for playback. In some possible application scenarios, the second audio module can also represent the in-vehicle application itself and can directly trigger the sound event. In other possible application scenarios, the sound event generated in the smart cockpit domain (such as a vehicle cockpit) can be played on the cockpit speaker by default.

[0104] It is understandable that the above-mentioned information receiving module can obtain the identification information of the sound signal corresponding to the sound event not generated by this functional domain, and the audio output module can obtain the identification information of the sound signal corresponding to the sound event generated by this functional domain, or the audio output module can obtain the identification information of the sound signal played by the speaker of this functional domain. Moreover, in some possible application scenarios, the information receiving module and the audio output module can record the start time, end time, and the time of receiving the identification information corresponding to the sound event, for example, record the time when the power battery fault prompt sound starts playing, the time when the playback ends, the time when the identification information of the power battery fault prompt sound is received, etc., and record the time when the music starts playing, the time when the playback ends, and the time when the identification information of the music is received, etc.

[0105] In some possible application scenarios, the above-mentioned voice recognition module can realize the functions of interactive applications such as the aforementioned intelligent voice assistant. The voice recognition module will pick up the sound in the cockpit, including the ambient sound and the user's voice (such as the first voice input instruction), and determine which sound signal needs to be determined according to the user's instruction. The source. For example, the user says "what is this sound", and the voice recognition module can determine the source information of the sound signal being played by the vehicle based on the pronoun "this"; or, the user says "what sound was just played", and the voice recognition module can determine the source information of the sound signal played by the vehicle based on the pronoun "just". In addition, the voice recognition module can also play prompt information (such as the first voice prompt information) for prompting the source information, so as to achieve the purpose of interacting with the user. Among them, the voice recognition module can obtain the identification information of the sound signal from the audio output module or the information receiving module.

[0106] In addition, if the user wants to further control the sound signal to turn off or learn how to turn off the sound signal after receiving the above prompt information (such as the first voice prompt information), he can continue to interact with the voice recognition module, such as saying "turn off this music" and other control instructions or voice content (such as the second voice input instruction). The voice recognition module picks up this instruction and sends a control instruction to the audio setting module, and the audio setting module implements the sound signal control operation. Exemplarily, if the sound signal is played by the cockpit speaker, the audio setting module can control the cockpit speaker to stop playing the sound signal; if the sound signal is played by the speaker of the target functional domain, the audio setting module can send a control instruction to the target functional domain, and the event detection module of the target functional domain controls the speaker of the functional domain to stop playing the sound signal according to the control instruction.

[0107] For example, taking the security domain as an example, Figure 3 As shown, when the vehicle is being driven, if the passenger seat belt included in the safety domain is not fastened by the passenger user, the event detection module of the safety domain will detect the corresponding sound event, and then the event detection module will obtain the sound signal and identification information corresponding to the sound event. The event detection module can also determine the description information of the sound signal in the preset audio information according to the identification information of the sound signal. If it is determined according to the description information that the sound signal needs to be played on the speaker of the current safety domain, the event detection module can control the speaker of the safety domain to play the sound signal corresponding to the identification information. At the same time, the information sending module of the safety domain sends the identification information of the sound signal to the smart cockpit domain, which is received by the information receiving module of the smart cockpit domain. The information receiving module can determine the description information of the sound signal in the preset audio information according to the identification information, and determine whether the sound signal needs to be played on the cockpit speaker according to the description information. If the sound signal needs to be played on the cabin speaker, the information receiving module sends the identification information of the sound signal to the first audio module, the first audio module obtains the sound signal according to the identification information, and sends the sound signal and the corresponding identification information to the audio output module, and the audio output module outputs the sound signal to the cabin speaker for playback.

[0108] When the vehicle plays a sound signal, the user can ask the voice recognition module (or intelligent voice assistant) "What is this sound?" In response to this voice command, the voice recognition module determines the identification information of the currently playing sound signal from the audio output module or the information receiving module. The voice recognition module then determines the prompt information based on the identification information and preset audio information, and plays the voice prompt information, such as playing the voice prompt "This is the sound of the passenger seat belt not being fastened."

[0109] In addition, after playing the above voice prompt, the voice recognition module can continue to receive the user's voice content, such as receiving the user's words "turn off this sound". The voice recognition module responds to this voice command and sends a control command for the user to turn off the sound signal to the audio setting module. In this case, if the sound signal is played by the cockpit speaker, the audio setting module controls the cockpit speaker to stop playing the sound signal; and if the sound signal is played by the speaker of the security domain, the audio setting module sends a control command to the security domain, and the event detection module of the security domain controls the speaker of the security domain to stop playing the sound signal according to the control command.

[0110] In some possible application scenarios, when the user interacts with the voice recognition module (or intelligent voice assistant), he can also ask the voice recognition module for more specific ways to operate the sound signal, such as "how to turn off this sound". The voice recognition module can then obtain the operation prompt information or fault clearance guidance for turning off the sound signal based on the description information of the played sound signal, and play it to the user, such as playing voice content such as "Please fasten your seat belt, co-pilot user", so as to prompt the user to perform further operations.

[0111] In some possible application scenarios, the first voice prompt information played by the voice recognition module (or intelligent voice assistant) can also be an incoming call prompt information or an incoming call ringtone, etc., to prompt the user that he is currently being called. When the second voice input instruction input or spoken by the user is an instruction to answer the call, the voice recognition module controls the cabin speaker or the speaker of the target functional domain to play the voice content after the incoming call is connected.

[0112] In some possible application scenarios, regardless of whether the operation on the sound signal fails or succeeds, the voice recognition module (or intelligent voice assistant) will play the corresponding voice prompt information for the user, such as "the sound has been turned off" or "the sound has failed to be turned off", etc. Alternatively, in other possible application scenarios, some prompt sounds, alarm sounds, etc. in the vehicle may be configured to not be turned off if the corresponding abnormal situation is not resolved. In this way, the audio setting module may fail to turn off the sound. In this case, the voice recognition module can also obtain the operation prompt information for turning off the sound signal based on the description information of the played sound signal and play it to the user, thereby prompting the user how to perform further operations to turn off the sound signal.

[0113] In some possible application scenarios, the vehicle itself may not play any sound signal, but there is noise or sound from other people or things in the environment around the vehicle. In this case, the user interacts with the voice recognition module (or intelligent voice assistant), such as inputting the above-mentioned voice command of "what is this sound", because the sound signal is not a sound signal from any functional domain of the vehicle itself, therefore, the information receiving module, audio output module, etc. of the vehicle will not receive the corresponding identification information, and then, the voice recognition module cannot obtain the identification information of the sound signal from the information receiving, audio output module, etc., or the information receiving module, audio output module, etc. do not save the identification information of the sound signal currently played or recently played (such as the last time played) by the vehicle. Since the voice recognition module cannot obtain the identification information of the sound signal, the voice recognition module can accurately determine that the sound signal to be controlled by the user is not played by the vehicle, thereby prompting the user. In this way, it is also possible to reduce the situation where the voice recognition module misidentifies noise as a sound signal played by the vehicle, and plays wrong prompt information for the user.

[0114] Alternatively, the vehicle itself does not play any sound information, and the user interacts with the voice recognition module and inputs "What is this sound?" The voice recognition module can input the ambient sound, and obtain the sound signal played by the vehicle from the ambient sound, and identify the content of the sound signal through sound recognition, and then determine the identification information of the sound signal according to the content of the sound signal, and play the corresponding voice prompt information to the user according to the identification information.

[0115] Referring to the foregoing, the preset audio information or the preset information list are all pre-configured. It is understandable that the sound signal, the sound signal type, etc. in the preset audio information or the preset information list are related to the functional domain components, the vehicle-mounted applications, etc. Therefore, the identification, description information, etc. of the sound signal, the sound signal type in the preset audio information or the preset information list can be updated based on the update of the functional domain components, the update of the vehicle-mounted applications, etc., wherein the update of the identification information can indicate that the form of the sound signal playback, the sound signal, etc. has changed, for example, from a high-frequency sound signal to a low-frequency sound signal, from a single play to a periodic loop play, from a single-frequency sound signal to music, etc.

[0116] Alternatively, the preset audio information or the preset information list can also be updated according to the user's settings. For example, the smart cockpit domain (such as the vehicle cockpit) can provide the user with an interface for setting the sound signal, on which the user can set the corresponding sound signal for specific abnormalities, faults or sound signal types, for example, in the case where the front passenger seat belt is not fastened, the user can select ringtone 1 as the corresponding alarm sound; in the case of power battery failure, the user can select ringtone 2 as the corresponding alarm sound; for the alarm type sound signal, the user can select ringtone 3 as the corresponding prompt sound, etc. Among them, it can be understood that ringtone 1, ringtone 2 and ringtone 3, etc., respectively correspond to different identification information, and the vehicle can update the preset audio information or the preset information list based on the user's selection, so that the identification information corresponding to the "front passenger seat belt is not fastened" alarm sound, power battery failure alarm sound, alarm type sound signal, etc. in the preset audio information or the preset information list matches the ringtone selected by the user.

[0117] In some possible application scenarios, if the audio output module simultaneously receives multiple sound signals and identification information of the sound signals that need to be played on the cockpit speakers, the audio output module can control the cockpit speakers to play a mixture of the multiple sound signals. Among them, the audio output module can obtain the description information corresponding to the different sound signals from the preset audio information or the preset information list according to the identification information of the different sound signals, and then obtain the priority information, sound signal level, etc. in the description information. Then, when the audio output module controls the cockpit speakers to play multiple sound signals, it controls the volume of the sound signals of different priorities accordingly. For example, the volume of the sound signal with the highest priority is greater than the volume of the sound signals with other priorities.

[0118] Alternatively, when the cockpit domain speaker is playing a sound signal, the audio output module receives a sound signal with a higher priority and the identification information of the sound signal. In this case, the audio output module can also control the cockpit speaker to pause the sound signal currently being played and play the sound signal with a higher priority. When the sound signal with a higher priority is played or the fault, abnormality, etc. corresponding to the sound signal are processed, the audio output module can control the cockpit speaker to continue playing the sound signal that was previously paused.

[0119] In the above embodiments, the sound signal is played in the functional domain where the sound event is generated or in the smart cockpit domain as an example. In some other possible application scenarios, if the functional domain where the sound event is generated does not include a speaker, the sound signal corresponding to the sound event can also be played in other functional domains other than the cockpit. For example, if the chassis domain does not include a speaker, then the sound signal corresponding to the sound event from the chassis domain can be set to be played by the safety domain speaker, that is, the sound position of the sound signal corresponding to the sound event is the safety domain speaker. In this application scenario, the smart cockpit domain (such as the vehicle cockpit) can determine the sound position of the sound signal after receiving the identification information of the sound signal. If the sound position of the sound signal is neither in the smart cockpit domain (such as the vehicle cockpit) nor in the functional domain that sends the identification information, then the smart cockpit domain (such as the vehicle cockpit) will forward the identification information to the functional domain corresponding to the sound position, and the controller or event monitoring module of the functional domain will control the speaker of the functional domain to play the corresponding sound signal.

[0120] As can be seen from the above content, in the above-mentioned sound signal processing method, the vehicle obtains identification information corresponding to the sound signal, wherein the sound signal may come from an on-board application in the smart cockpit domain (such as the vehicle cockpit) or a vehicle component other than the smart cockpit domain (such as the vehicle cockpit) (such as other functions and vehicle components), and the identification information is used to distinguish sound signals of different functions, effects or types. The vehicle then plays the sound signal, and determines the source information of the played sound signal based on the identification information of the sound signal and the preset audio information, wherein the preset audio information includes the corresponding relationship between the identification information of the sound signal and the description information.

[0121] The sound signals that can be played in the vehicle are pre-configured with corresponding identification information, and the vehicle can detect sound signals from multiple sources, such as from vehicle applications, from vehicle components, etc. Moreover, based on the correspondence between the sound signal and the identification information, the sources of multiple sound signals can be identified. The vehicle can determine the source of the sound signal (i.e., what kind of fault or situation the sound signal is used to indicate) through the identification information of the sound signal and the preset audio information. In this way, the source of the sound signal can be determined without the need for sound recognition, thereby eliminating the interference of noise and more accurately determining the function of the sound signal and the fault or situation indicated.

[0122] In addition, corresponding identification information is established for multiple sound signals. Through interaction with the user, the voice prompt information can be more clearly and accurately determined based on the identification information, providing the user with the source information of the sound signal, thereby improving the user's interaction experience with the vehicle. Moreover, detecting sound signals based on identification information can also make the detection of sound signals clearer, and it is also easier to detect the key sound signals that the user is concerned about from the acquired sound signals.

[0123] In some possible application scenarios, if the user wants to control the sound signal played by the vehicle through voice commands, there is no need to say which sound or sounds the vehicle is currently playing. The vehicle can determine the source of the audio based on the identification information of the sound signal being played, and then determine the corresponding sound signal and control the sound signal. In this way, the user does not need to know which sound or sounds the vehicle is currently playing, which improves the user's experience of interacting with the vehicle.

[0124] In addition, since the above method in the embodiment of the present application does not need to identify the content of the sound signal to determine the source of the sound signal, it will not increase the computing load of sound recognition, and there is no need to train the sound recognition algorithm, thereby reducing the time for algorithm maintenance and allowing users to use the voice recognition function on the vehicle (such as the in-vehicle voice assistant) more conveniently. If the speaker that plays the sound signal is set outside the vehicle, since the vehicle has obtained the identification information of the sound signal, when the user speaks a voice command for the sound signal, the above method in the embodiment of the present application can also accurately determine the source of the sound signal through the identification information, thereby avoiding the problem of being unable to identify the external sound signal of the vehicle through sound recognition.

[0125] The above-mentioned sound signal processing method may specifically include two parts: sound signal playing and user interaction. Among them, the sound signal playing part may be Figure 4 The following content is used as an example to illustrate. Figure 4 As shown, the sound signal playing part of the sound signal processing method may include an implementation part in a vehicle cockpit, and an implementation part in a target functional domain other than the vehicle cockpit.

[0126] The above method implemented in the target functional domain may include the following steps S401-S403.

[0127] S401: The target function domain generates a first sound event, determines a first sound signal corresponding to the first sound event, and sends identification information of the first sound signal to a vehicle cabin.

[0128] The first sound event generated by the above-mentioned target functional domain may come from the vehicle components of the target functional domain, for example, the main driver's seat belt, the co-driver's seat belt, etc. in the safety domain, the power battery, the engine, etc. in the power domain, the turn signal, the door, etc. in the body domain. When the vehicle components are abnormal, fail, or the working state changes, the vehicle components will trigger the sound event, for example, the power battery will trigger the sound event when the power battery fails, the door will trigger the sound event when the door is not closed, and the main driver's seat belt will trigger the sound event when the main driver's seat belt is not fastened.

[0129] In some embodiments, each sound event is configured with a corresponding sound signal (also referred to as a vehicle sound signal), and each sound signal is configured with corresponding identification information, and further, the sound event may include the identification information of the sound signal corresponding to the sound event. The identification information is used to distinguish sound signals of different functions, and the identification information between different sound signals is different. In addition, each sound signal also includes corresponding description information, and the description information is used to describe one or more of the source, type, priority, name, sound location, cause, and playback method of the sound signal. In addition, the identification information of each sound signal corresponds one-to-one to the corresponding description information, or has a corresponding relationship, and the identification information and description information of each sound signal are stored in the preset audio information or the preset information list.

[0130] Exemplarily, the following table 1 is a preset information list for storing identification information and description information of each sound signal. In the list, the function domain, sound signal name, sound signal identification, sound signal description, sound signal level and sound position of the first row all represent the description information of the sound signal. Among them, the function domain represents the specific source of the sound signal, for example, including the power domain, chassis domain, safety domain, body domain, vehicle cockpit, etc.; the sound signal description of the first row is used to describe the cause of the sound signal, the way the sound signal is played, etc. In addition, the sound signal description can also be used to describe the corresponding sound event; the sound signal level of the first row represents the priority of the sound signal, and the sound signal level can represent the playback order, importance and / or playback method of the sound signal. Some of the contents in the following table are explained as follows: controller area network (CAN), antilock brake system (ABS), electric vehicle low speed warning sound system (AVAS), electronic stability program (ESP), advanced driving assistance system (ADAS).

[0131] Table 1

[0132]

[0133]

[0134] When the first sound event occurs in the target functional domain, the target functional domain will obtain the first sound signal corresponding to the first sound event, and obtain the identification information of the first sound signal according to the pre-configured preset audio information or preset information list. In some embodiments, the target functional domain can determine the first sound signal corresponding to the first sound event according to the "sound signal description" and other contents in the preset audio information or preset information list. Alternatively, in other embodiments, the target functional domain can also determine the corresponding first sound signal according to the identification information included in the first sound event, wherein the identification information included in the first sound event is the identification information of the first sound signal.

[0135] S402: The target function domain determines a sound source position of the first sound signal according to identification information of the first sound signal.

[0136] In some embodiments, the target function domain may obtain description information of the first sound signal from preset audio information or a preset information list according to identification information of the first sound signal, and determine the sound source position of the first sound signal according to the description information.

[0137] According to the aforementioned Table 1, the sound position of the first sound signal can be a functional domain speaker or a cockpit speaker. When the target functional domain does not include a speaker or does not have the function of playing a sound signal, the sound signal of the target functional domain can be played by speakers of other functional domains (including the vehicle cockpit), so as to ensure that when each vehicle component has an abnormality, failure or working state change, the corresponding prompt sound or alarm sound can be played in time to remind the user to handle it in time.

[0138] Also, it can be understood that, regardless of whether the first sound signal is played in the current target functional domain, the target functional domain needs to send the identification information of the first sound signal to the vehicle cockpit, so that the vehicle cockpit can save the identification information of each sound signal played by the vehicle, providing a more convenient way to obtain prompt information for subsequent user interaction with the vehicle.

[0139] S403: When the sound source of the first sound signal is the speaker of the target functional domain, the target functional domain controls the speaker of the current functional domain to play the first sound signal.

[0140] Exemplarily, when the target functional domain is the power domain, if the sound emission position of the first sound signal is the power domain speaker, the power domain controls the power domain speaker to play the first sound signal; or, when the target functional domain is the chassis domain, if the sound emission position of the first sound signal is the chassis domain speaker, the chassis domain controls the chassis domain speaker to play the first sound signal.

[0141] In the above-mentioned method of S401-S403, the target functional domain can send the identification information of the sound signal corresponding to the sound event generated by the functional domain to the vehicle cockpit, and when the sound signal corresponding to the sound event needs to be played in the target functional domain, the target functional domain can also control the speaker of the functional domain to play the sound signal. Thereby, the vehicle cockpit collects the identification information of the prompt sound (or alarm sound) of all functional domains, so that the vehicle cockpit plays the role of overall control; in addition, since the speakers of each functional domain can be set on different components, that is, they can be set at different positions of the vehicle, the prompt sound (or alarm sound) of the vehicle can be played at any position of the vehicle, so that the reminder method for the abnormality, fault or working status change of the vehicle can be more flexible, which is convenient for users to understand the abnormality, fault or working status of the vehicle in time.

[0142] Still see Figure 4 As shown, the above method implemented in the vehicle cockpit may include the following steps S404-S407.

[0143] S404: The vehicle cockpit obtains identification information corresponding to the vehicle sound signal.

[0144] The vehicle sound signal may come from a vehicle cabin (eg, a second sound signal) or from a target functional domain (eg, a first sound signal).

[0145] When the vehicle sound signal comes from the vehicle cockpit, the sound event corresponding to the vehicle sound signal may come from the vehicle component of the vehicle cockpit or the vehicle-mounted application of the vehicle cockpit. When the vehicle component of the vehicle cockpit is abnormal, fails or the working state changes, the vehicle component will trigger a sound event (such as a second sound event), and the vehicle cockpit will detect the sound event, or the vehicle cockpit will receive a second message from the vehicle component, and the second message includes relevant information of the vehicle sound signal corresponding to the second sound event, such as information for indicating the vehicle sound signal, or identification information of the vehicle sound signal, etc. The vehicle cockpit obtains the corresponding vehicle sound signal and the identification information of the vehicle sound signal according to the sound event or the second message, etc. When the vehicle-mounted application of the vehicle cockpit needs to issue a prompt or play a sound signal, the vehicle-mounted application will also trigger a sound event, and the vehicle cockpit will detect the sound event (such as a third sound event), or the vehicle cockpit will receive a first message from the vehicle-mounted application, and the first message includes relevant information of the vehicle sound signal corresponding to the third sound event, such as information for indicating the vehicle sound signal, or identification information of the vehicle sound signal, etc. The vehicle cockpit obtains the corresponding vehicle sound signal and identification information of the vehicle sound signal according to the sound event or the first message.

[0146] In some embodiments, each sound event from an in-vehicle application in a vehicle cabin is configured with a corresponding vehicle sound signal, and each vehicle sound signal is configured with corresponding identification information, and further, the sound event may include the identification information of the vehicle sound signal corresponding to the sound event. The identification information is used to distinguish different vehicle sound signals, and the identification information between different vehicle sound signals is different. In addition, each vehicle sound signal also includes corresponding description information, and the description information is used to describe one or more of the source, type, priority, name, sound location, cause, and playback method of the vehicle sound signal. And, the identification information of each vehicle sound signal corresponds one-to-one to the corresponding description information, or has a corresponding relationship, and the identification information and description information of each vehicle sound signal are stored in the preset audio information or the preset information list.

[0147] Exemplarily, Table 2 below is a preset information list for storing identification information and description information of each vehicle sound signal corresponding to the vehicle-mounted application. In this list, the sound signal type, sound signal name, sound signal identification, sound signal description, priority and sound position in the first row all represent the description information of the sound signal. Among them, the smaller the priority value, the higher the priority; the sound signal description in the first row is used to describe the cause of the sound signal, the way the sound signal is played, etc. In addition, the sound signal description can also be used to describe the corresponding sound event. Some of the contents in the table below are explained as follows: emergency call (E-CALL), breakdown call (B-CALL).

[0148] Table 2

[0149]

[0150] S405: The vehicle cockpit determines description information of the vehicle sound signal from preset audio information according to the identification information of the vehicle sound signal.

[0151] Among them, the preset audio information may include the contents of the aforementioned Tables 1 and 2. Since Tables 1 and 2 include identification information and description information of vehicle sound signals, the vehicle cabin can determine which specific vehicle sound signal it is from Table 1 or Table 2 based on the identification information of the vehicle sound signal, and further obtain the description information of the vehicle sound signal.

[0152] S406: The vehicle cockpit determines the sound source position of the vehicle sound signal according to the description information of the vehicle sound signal. If the sound source position is the cockpit speaker, the vehicle cockpit controls the speaker of the functional domain to play the vehicle sound signal.

[0153] It is understandable that each vehicle sound signal is pre-configured with a corresponding sound source position. Regardless of whether it is generated by the cabin speaker, the vehicle cabin will obtain the identification information of the vehicle sound signal. For vehicle sound signals whose sound source position is the cabin speaker, in order to ensure that users can receive prompts, alarms or music in a timely manner, the vehicle cabin will control the cabin speaker to play the vehicle sound signal. For vehicle sound signals whose sound source position is not the cabin speaker, the vehicle cabin will not control the cabin speaker to play.

[0154] Exemplarily, if the vehicle cockpit determines that the sound source of the first vehicle sound signal is the instrument speaker, the vehicle cockpit will not control the cockpit speaker to play the first vehicle sound signal; if the vehicle cockpit determines that the sound source of the second vehicle sound signal is the cockpit speaker, the vehicle cockpit will control the cockpit speaker to play the second vehicle sound signal.

[0155] S407: The vehicle cockpit determines source information of the vehicle sound signal to be played according to the identification information of the vehicle sound signal and the preset audio information.

[0156] The preset audio information is a correspondence between the identification information and description information of the pre-configured vehicle sound signal, and the vehicle cockpit can obtain the description information of the vehicle sound signal from the preset audio information according to the identification information of the vehicle sound signal, and determine the source information of the vehicle sound signal according to the description information. Exemplarily, the source of the vehicle sound signal can be determined according to the type and name of the vehicle sound signal, such as if the name of the vehicle sound signal is "power battery fault indicator light", then it can be determined that the source information of the vehicle sound signal is the power battery, and the specific function is to indicate that the power battery is faulty.

[0157] In the above-mentioned method of S404-S407, the vehicle cockpit can obtain the identification information of the vehicle sound signal corresponding to the sound event generated by the functional domain, and can also obtain the identification information of the vehicle sound signal corresponding to the sound event generated by other functional domains. Thus, the vehicle cockpit can collect the identification information of the prompt sound (or alarm sound) of multiple functional domains, so that the vehicle cockpit can play the role of overall control; in addition, when other functional domains cannot play the vehicle sound signal, the vehicle cockpit can also play the vehicle sound signal of other functional domains, so that users can understand the abnormality, fault, working status, etc. of the vehicle in a timely manner.

[0158] In addition, the vehicle cockpit can determine the source of the vehicle sound signal (i.e., what kind of fault or situation the sound signal is used to indicate) through the identification information of the vehicle sound signal and the preset audio information. The source of the vehicle sound signal can be determined without the need for sound recognition, thereby eliminating noise interference and more accurately determining the function of the vehicle sound signal and the fault or situation it indicates.

[0159] In some embodiments, the vehicle cockpit may obtain identification information of the vehicle sound signal when the vehicle plays the vehicle sound signal or after the vehicle plays the vehicle sound signal, or the vehicle cockpit may also obtain identification information of the vehicle sound signal before the vehicle plays the vehicle sound signal.

[0160] And, in other embodiments, regardless of whether the vehicle sound signal is played, the vehicle cockpit can obtain the vehicle sound signal through the aforementioned message and other methods. When the vehicle sound signal is played, the vehicle cockpit can also detect the played vehicle sound signal in the ambient sound by identifying the ambient sound, and obtain the identification information corresponding to the vehicle sound signal by identifying the content of the vehicle sound signal. Thus, the vehicle can obtain the vehicle sound signal in a variety of ways, improve the accuracy of picking up or obtaining the sound signal, and more accurately obtain the sound signal that the user wants to know or want to operate.

[0161] The above embodiments describe how to implement the sound signal playing part in the above sound signal processing method. When the vehicle sound signal is played by the vehicle (such as the cockpit speaker or the speaker of the target functional domain) or after it is played, the user can also interact with the vehicle cockpit and operate the vehicle sound signal that is currently being played or has been played.

[0162] Based on this, the user interaction part in the above-mentioned sound signal processing method can be Figure 5 The following content is used as an example to illustrate. Figure 5 As shown, the user interaction part of the sound signal processing method can be implemented in a vehicle cockpit, and can specifically include the following steps S501-S504.

[0163] S501: The vehicle cockpit receives a first voice input operation from a user.

[0164] Among them, the first voice input operation may include a user inputting a first voice input instruction into a vehicle cabin, and, exemplarily, the first voice input instruction may be used to inquire about the source information of a vehicle sound signal being played, for example, the user says "what is this sound", "what is playing now".

[0165] In some embodiments, the vehicle cockpit can pick up the voice or voice commands of the user in the cockpit through an intelligent voice assistant, and identify based on the user's voice or voice commands whether the user wants to operate the vehicle sound signal currently playing or the vehicle sound signal that has already been played.

[0166] If the user wants to operate the vehicle sound signal that is being played, the vehicle cockpit continues to execute the following step S502.

[0167] In some possible application scenarios, the vehicle cockpit can obtain the vehicle sound signal and the identification information of the vehicle sound signal after the above-mentioned vehicle sound signal starts to play. At the same time, the vehicle cockpit can also obtain the start time of the vehicle sound signal. Alternatively, in other possible application scenarios, the vehicle cockpit can also obtain the identification information of the vehicle sound signal after the sound event occurs and before the corresponding vehicle sound signal is played. Then, when the vehicle sound signal starts to play, the vehicle cockpit obtains the start time of the vehicle sound signal.

[0168] In addition, in some possible application scenarios, when the vehicle sound signal finishes playing, the vehicle cockpit can also obtain the end time of the playback of the vehicle sound signal; or, the vehicle cockpit can also determine the playback mode of the vehicle sound signal (such as loop, periodic playback, etc.) based on preset audio information or the description information of the vehicle sound signal in a preset information list, thereby determining the end time of the playback of the vehicle sound signal.

[0169] S502: In response to the first voice input operation, the vehicle cockpit plays a first voice prompt message according to the identification information of the corresponding vehicle sound signal.

[0170] In other embodiments, after obtaining the identification information of the vehicle sound signal, the vehicle cockpit can obtain the description information according to the identification information, and determine the source information of the vehicle sound signal according to the description information. Therefore, the vehicle cockpit can respond to the first voice input operation, and after determining the corresponding vehicle sound signal, play the first voice prompt information corresponding to the vehicle sound signal.

[0171] Among them, the first voice prompt information includes the source information of the vehicle sound signal, for example, the vehicle cabin plays "This is the music sound", "This is the reminder sound for not fastening the seat belt", "This is the reminder sound for power battery failure", etc.

[0172] Regardless of whether the vehicle sound signal is played on the cockpit speaker, the vehicle cockpit will obtain the identification information of the vehicle sound signal, and may also obtain the start time and end time of the vehicle sound signal. Therefore, the vehicle cockpit will obtain the identification information of the vehicle sound signal being played from all the received identification information. It can be understood that the above-mentioned vehicle sound signal being played can represent a vehicle sound signal that has not been played to the end at the current moment.

[0173] In some embodiments, the vehicle cockpit can play the first voice prompt information in the current functional domain, or control the target functional domain to play the first voice prompt information. Alternatively, the vehicle cockpit controls the vehicle display screen to display the text content corresponding to the first voice prompt information while the cockpit speaker and / or the speaker of the target functional domain play the first voice prompt information.

[0174] For example, Figure 6 As shown, the vehicle cockpit can display text content such as "This is a reminder tone for not fastening the seat belt" on the central control screen (or display screen); or, Figure 7 As shown, the vehicle cockpit can play audio content such as "This is the reminder sound for not fastening the seat belt" through the cockpit speakers or the speakers of the target functional domain; alternatively, the vehicle cockpit can display the text content "This is the reminder sound for not fastening the seat belt" on the central control screen (or display screen) while playing the audio content "This is the reminder sound for not fastening the seat belt" through the cockpit speakers or the speakers of the target functional domain.

[0175] S503: The vehicle cockpit receives a second voice input operation from the user.

[0176] Among them, the second voice input operation may include the user inputting a second voice input instruction into the vehicle cabin, and, exemplarily, the second voice input instruction is used to instruct the control of the vehicle sound signal being played, for example, the user says "turn off this sound", "how to turn off this sound", etc.

[0177] In some embodiments, the vehicle cockpit can pick up the voice or voice commands of the user in the cockpit through an intelligent voice assistant, and identify the specific operation the user wants to control based on the user's voice or voice commands, such as turning off the sound, controlling the vehicle cockpit to play fault-clearing guidance, etc.

[0178] S504: The vehicle cockpit responds to the second voice input operation by performing a control operation on the vehicle sound signal according to source information of the vehicle sound signal being played.

[0179] The control operation includes turning off the vehicle sound signal and / or playing the fault elimination guidance corresponding to the vehicle sound signal. For example, when the user says "turn off this sound", the vehicle cockpit turns off the power battery fault prompt sound being played; when the user says "how to turn off this sound", the vehicle cockpit plays the fault elimination guidance of "please fasten your seat belts".

[0180] In some possible application scenarios, after the vehicle sound signal is successfully turned off, the vehicle cockpit will also play voice prompt information, such as Figure 5 In S505, a voice prompt message such as "the sound has been turned off" is displayed to prompt the user that the turning off operation has been completed.

[0181] In the above methods S501-S504, the vehicle cockpit interacts with the user through voice to obtain the user's voice commands. When the user wants to operate the vehicle sound signal being played by the vehicle, the vehicle cockpit can determine the content of the vehicle sound signal being played without relying on real-time sound collection, but instead relies on the pre-configured identification information of the vehicle sound signal played by the vehicle to determine the source information of the vehicle sound signal, thereby providing the user with prompt information for prompting the source information of the vehicle sound signal, solving the user's needs or helping the user to perform corresponding operations. When there is environmental noise, the above sound signal processing method will not cause misidentification, and can more accurately determine the content of the vehicle sound signal and provide more accurate prompt information.

[0182] Alternatively, the user interaction part of the sound signal processing method implemented in the vehicle cabin may also include the following steps S601-S605.

[0183] S601. The vehicle cockpit stores identification information of the played vehicle sound signal.

[0184] The played vehicle sound signal may be played by a cockpit speaker or a speaker of a target functional domain. The vehicle cockpit receives and stores the identification information of the vehicle sound signal. In some possible application scenarios, the played vehicle sound signal may represent the vehicle sound signal played most recently by the vehicle, or may represent the vehicle sound signal played by the vehicle within a period of time in the past, or may represent the vehicle sound signal played by the vehicle at a certain moment in the past.

[0185] S602: After the vehicle sound signal is played, the vehicle cockpit receives a third voice input operation from the user.

[0186] Among them, the third voice input operation may include the user inputting a third voice input instruction into the vehicle cabin, and, exemplarily, the third voice input instruction is used to inquire about the source information of the played vehicle sound signal, for example, the user asks "what sound was just played", "what sound was played at 12:30 today".

[0187] In some embodiments, the vehicle cockpit can pick up the voice or voice command of the user in the cockpit through an intelligent voice assistant, that is, the third voice input command. In other embodiments, the vehicle cockpit can also pick up the voice or voice command of the user in the cockpit through an intelligent voice assistant within a preset time after the vehicle sound signal ends, that is, the third voice input command. Afterwards, the vehicle cockpit identifies whether the user wants to operate the vehicle sound signal currently being played or the vehicle sound signal that has been played based on the user's voice or voice command. If the user wants to operate the vehicle sound signal that has been played, the vehicle cockpit continues to execute the following S603.

[0188] Regardless of whether the vehicle sound signal is played on the cabin speakers, the vehicle cockpit will obtain the identification information of the vehicle sound signal, and may also obtain the start time and end time of the vehicle sound signal. Therefore, the vehicle cockpit will obtain the identification information of the most recently played vehicle sound signal, the identification information of the vehicle sound signal played within a period of time in the past, and the identification information of the vehicle sound signal played at a certain moment in the past from all the identification information received.

[0189] S603: In response to the third voice input operation, the vehicle cockpit determines the source information of the played vehicle sound signal according to the saved identification information of the played vehicle sound signal and the preset audio information, and plays the second voice prompt information.

[0190] Among them, the second voice prompt information includes the source information of the vehicle sound signal that has been played, for example, the vehicle cabin plays "the sound just played was music", "the sound played at 12:30 today was a reminder sound for not fastening the seat belt", etc.

[0191] S604: The vehicle cockpit receives a fourth voice input operation from the user.

[0192] Among them, the fourth voice input operation may include a user inputting a fourth voice input instruction into a vehicle cabin, and, exemplarily, the fourth voice input instruction is used to instruct control of a played vehicle sound signal, for example, the user says "turn off this sound", "how to turn off this sound", etc.

[0193] S605: The vehicle cockpit responds to the fourth voice input operation by performing a control operation on the played vehicle sound signal according to the source information of the played vehicle sound signal.

[0194] The control operation includes turning off the vehicle sound signal that has been played and / or playing the fault elimination guidance corresponding to the vehicle sound signal that has been played. For example, when the vehicle sound signal that has been played indicates a power battery fault, if the user says "turn off this sound", the vehicle cockpit can control this prompt sound to be permanently turned off in the future; or, when the vehicle sound signal that has been played indicates that the seat belt is not fastened, if the user says "how to turn off this sound", the vehicle cockpit can play the fault elimination guidance of "please fasten your seat belt".

[0195] In some possible application scenarios, some vehicle sound signals can be turned off permanently or for a period of time. When the user says "turn off this sound", the vehicle cockpit can continue to play voice prompts, such as "Do you want to turn it off permanently?", "How long do you want to turn it off for?", "Do you want to turn off the sound only for this time?", etc. After that, the user can further speak voice commands to the vehicle cockpit according to their needs, thereby instructing the vehicle cockpit to permanently turn off the vehicle sound signal being played, prohibit the vehicle sound signal from being played for a period of time, turn off the vehicle sound signal being played only for this time, etc.

[0196] In the above methods S601-S605, the vehicle cockpit can perform voice interaction with the user and obtain the user's voice command. When the user wants to operate the vehicle sound signal that has been played by the vehicle, the vehicle cockpit can still obtain the identification information corresponding to the vehicle sound signal that has been played, and determine the source information of the vehicle sound signal based on the identification information, thereby providing the user with prompt information for prompting the source information of the vehicle sound signal, solving the user's needs or helping the user to perform corresponding operations.

[0197] In some cases, a vehicle can play multiple vehicle sound signals at the same time, and the multiple vehicle sound signals can come from the same vehicle cockpit or other target functional domains, or the multiple vehicle sound signals can come from different functional domains (including the vehicle cockpit and other target functional domains), that is, the multiple vehicle sound signals can be played simultaneously by the cockpit speakers, or by the same target functional domain speakers. That is, the above-mentioned vehicle sound signals played by the vehicle can include multiple ones, so that the vehicle cockpit can also obtain the identification information of multiple vehicle sound signals at the same time.

[0198] Based on this, in some embodiments, when the vehicle plays multiple vehicle sound signals at the same time, the vehicle cockpit can play a third voice prompt message in response to the user's above-mentioned first voice input operation, wherein the third voice prompt message is used to indicate the source information corresponding to the multiple vehicle sound signals respectively. For example, there are three vehicle sound signals played by the vehicle. If the user asks "What is this sound", the third voice prompt message played in the vehicle cockpit can be "This is the sound of music, the reminder sound of not fastening the seat belt, and the reminder sound of power battery failure."

[0199] In other embodiments, when the vehicle plays a plurality of the above-mentioned vehicle sound signals, the vehicle cockpit may also receive the above-mentioned second voice input operation, and in response to the second voice input operation, play the inquiry information corresponding to the plurality of vehicle sound signals respectively according to the source information corresponding to the plurality of vehicle sound signals respectively. The inquiry information is used to inquire whether to perform a control operation on the vehicle sound signal corresponding to the inquiry information. For example, there are three vehicle sound signals played by the vehicle, and the third voice prompt information played includes "This is the sound of music, the reminder tone of not fastening the seat belt, and the reminder tone of power battery failure". If the user says "Turn off this sound", the inquiry information played in sequence in the vehicle cockpit may be "Do you want to turn off the music", "Do you want to turn off the reminder tone of not fastening the seat belt", "Do you want to turn off the reminder tone of power battery failure".

[0200] And, within the preset time after playing the inquiry information, the vehicle cockpit receives the fifth voice input operation of the user, and in response to the fifth voice input operation, controls the vehicle sound signal corresponding to the inquiry information according to the source information of the vehicle sound signal corresponding to the inquiry information. For example, the vehicle cockpit plays "Do you want to turn off the music?" and receives the fifth voice input operation within 5 seconds. If it is received, the music is turned off; if the fifth voice input operation is not received within 5 seconds, it continues to play "Do you want to turn off the reminder sound of not wearing a seat belt?" and receives the fifth voice input operation within 5 seconds. If it is received, the reminder sound of not wearing a seat belt is turned off; if the fifth voice input operation is not received within 5 seconds, it continues to play "Do you want to turn off the reminder sound of power battery failure?" and receives the fifth voice input operation within 5 seconds. If it is received, the reminder sound of power battery failure is turned off. If it is not received, no vehicle sound signal will be controlled. Among them, the fifth voice input operation includes the operation of the user inputting the fifth voice input instruction, and the fifth voice input instruction is used to instruct the control operation of the vehicle sound signal corresponding to the inquiry information. For example, the user says "yes" in response to the "Do you want to turn off the music" played in the vehicle cockpit, then the music is controlled to be turned off; or the user can also say "how to turn off this sound" in response to the "Do you want to turn off the reminder sound for not fastening your seat belts" played in the vehicle cockpit, thereby controlling the vehicle cockpit to play the fault removal guidance of "Please fasten your seat belts".

[0201] Alternatively, the vehicle cockpit may reproduce the corresponding vehicle sound signal while playing the inquiry information in sequence, so as to prompt the user which vehicle sound signal needs to be controlled, and confirm whether the user wants to control the vehicle sound signal. For example, while playing "Do you want to turn off the music?", a relatively low volume of music is played; while playing "Do you want to turn off the reminder tone of not wearing seat belts?", a relatively low volume of the reminder tone of not wearing seat belts is played; while playing "Do you want to turn off the reminder tone of power battery failure?", a relatively low volume of the reminder tone of power battery failure is played.

[0202] In the above embodiment, when the vehicle is playing multiple vehicle sound signals at the same time, if the user wants to know what function the vehicle sound signal has, the vehicle cockpit can play the voice prompt information corresponding to each vehicle sound signal in turn, so that the user can clearly understand which vehicle sound signals are currently being played at the same time, and it is convenient for the user to select the vehicle sound signal that he wants to control. Afterwards, after the user speaks a voice command to control the vehicle sound signal, the vehicle cockpit will ask the user in turn which vehicle sound signal he wants to control, so that the vehicle sound signal that the user wants to control can be determined more accurately among the multiple vehicle sound signals.

[0203] In addition, among the vehicle sound signals that have been played, there may be multiple vehicle sound signals that were played simultaneously at historical moments. In this case, if the vehicle sound signal that the user inquires about includes multiple signals, the vehicle cabin may also refer to the contents of the above-mentioned embodiment to play the prompt information of each vehicle sound signal in sequence, as well as the inquiry information corresponding to each vehicle sound signal.

[0204] In some embodiments, the above-mentioned preset audio information or preset information list can be maintained by a developer or a technician, who configures corresponding identification information and description information for each vehicle sound signal, and then uploads the preset audio information or preset information list to a cloud device, server, etc. The vehicle cockpit can obtain the preset audio information or preset information list from a cloud device, server, etc. After the vehicle components of the functional domain are updated and the in-vehicle applications are updated, the developer or technician also updates the identification information, description information, etc. of the vehicle sound signal in the preset audio information or preset information list, and uploads the updated preset audio information to a cloud device, server, etc. The vehicle cockpit can obtain the updated preset audio information or preset information list from a cloud device, server, etc.

[0205] Alternatively, in some other embodiments, the preset audio information or the preset information list may also be set by the user. Figure 8As shown, the user can set the corresponding prompt tone or alarm tone for each abnormality, fault, working state change, vehicle sound signal corresponding to the vehicle application, etc. through the setting page displayed on the central control screen (or display screen) of the vehicle cockpit. For example, in the case of unfastened seat belts, the user can select ringtone 1 as the corresponding prompt tone; in the case of power battery failure, the user can select ringtone 2 as the corresponding prompt tone; for the vehicle sound signal from application 1 that serves as a prompt (such as prompting that there is an unread message), the user can select ringtone 3 as the corresponding prompt tone, etc. If the user does not select, the default ringtone is used as the prompt tone for each abnormality, working state change, vehicle sound signal corresponding to the vehicle application, etc. Among them, ringtone 1, ringtone 2 and ringtone 3, etc., respectively correspond to different identification information.

[0206] After the user completes the selection, he can click the "Confirm" control on the settings page, so that the vehicle cabin will save the user's settings in the preset audio information in response to the user's operation, that is, the vehicle sound signal identification information corresponding to the situation where the co-driver's seat belt is not fastened is set to the identification information corresponding to identification ringtone 1, the vehicle sound signal identification information corresponding to the power battery failure is set to the identification information corresponding to ringtone 2, and the identification information corresponding to the alarm vehicle sound signal is set to the identification information corresponding to ringtone 3.

[0207] In addition, after the preset audio information is set, the user can also Figure 8 The settings page shown changes the prompt tone or alarm tone of the vehicle sound signal corresponding to the abnormality, fault, working state change, and vehicle application. For example, in the case where the co-pilot seat belt is not fastened, the user can change the current corresponding ringtone 1 to ringtone 4; in the case of power battery failure, the user can change the current corresponding ringtone 2 to ringtone 5; for the alarm type vehicle sound signal, the user can change the current corresponding ringtone 3 to ringtone 6. Among them, ringtone 4, ringtone 5 and ringtone 6, etc., also correspond to different identification information respectively. The vehicle cockpit will also respond to the user's operation and update the preset audio information, that is, the vehicle sound signal identification information corresponding to the case where the co-pilot seat belt is not fastened is updated to the identification information corresponding to ringtone 4, the vehicle sound signal identification information corresponding to the power battery failure is updated to the identification information corresponding to ringtone 5, and the identification information corresponding to the alarm type vehicle sound signal is updated to the identification information corresponding to ringtone 6.

[0208] In the above implementation, the preset audio information or preset information list can be stored locally in the vehicle, and the preset audio information or preset information list can be set and updated through the vehicle cockpit. In some other embodiments, the preset audio information or preset information list can also be stored on a cloud device, and the vehicle cockpit sends the user's setting information for the preset audio information or preset information list to the cloud device, and the cloud device completes the setting and updating of the preset audio information or preset information list. After the preset audio information or preset information list is set or updated, the vehicle cockpit obtains the corresponding preset audio information or preset information list from the cloud device.

[0209] In some embodiments, the above-mentioned vehicle sound signal may also come from a call application in the vehicle cockpit. Then, in response to the above-mentioned first voice input operation, the vehicle cockpit plays the first voice prompt information of "This is an incoming call ringtone". After receiving the prompt information, the user can continue to interact with the voice assistant in the vehicle cockpit and speak a second voice command, wherein the second voice command may also instruct to answer or hang up the call. Also, after answering the call, the vehicle cockpit may control the cockpit speaker to play the voice content after the call is connected. It can be understood that the above-mentioned "incoming call" may not only represent the functions provided by the call application, but also in some other embodiments, may represent the functions provided by media applications, social applications, etc.

[0210] In some possible application scenarios, the vehicle cockpit can also play a voice prompt message after turning off the playing music (or vehicle sound signal) or hanging up the call, thereby reminding the user that the vehicle sound signal has been turned off or the call has been hung up.

[0211] In other possible application scenarios, if the user does not handle the abnormality or fault, the corresponding vehicle sound signal may not be turned off. In this case, even if the user controls the vehicle sound signal to be turned off through voice commands, the turning-off operation will not be successfully executed. Based on this, if the vehicle sound signal is not turned off successfully, the vehicle cockpit will also play voice prompt information, such as Figure 5 In S506, the user is prompted that the vehicle sound signal cannot be turned off and an abnormal situation needs to be resolved, such as the prompt information "Please fasten your seat belt", "Reduce the speed", etc. Further, the vehicle cockpit can also determine the prompt information according to the description information of the vehicle sound signal.

[0212] In the above implementation, the user can directly complete the rapid control of the vehicle sound signal through voice commands, or the user can solve anomalies, faults, etc. according to the guidance played in the vehicle cabin (such as prompt information, etc.), making the user's control of vehicle sound signals and handling of faults more convenient.

[0213] In addition, the user can also use pronouns to achieve voice interaction with the vehicle, and the intelligent voice assistant can also accurately determine the vehicle sound signal that the user wants to operate based on the pronouns, which can also improve the user's interactive experience with the intelligent voice assistant. Among them, the above-mentioned first voice input operation may include inputting a pronoun for referring to the vehicle sound signal being played and / or a pronoun for referring to the current moment, for example, "this", "this", "now", "currently", etc. The above-mentioned third voice input operation may include inputting a pronoun for referring to the vehicle sound signal that has been played and / or a pronoun for referring to a historical moment, for example, "just now", "just now", "previous", "previous", "before", "XX hours XX minutes", "XX points XX minutes", etc.

[0214] In some embodiments, when the vehicle cabin is playing music through the cabin speakers, the vehicle cabin can also respond to the user's voice commands to query and play relevant information of the music, such as the song title, singer, etc., thereby realizing functions such as "identifying songs by listening to them".

[0215] In some embodiments, the above-mentioned vehicle cockpit can also be associated with some safety functions or safety applications on the vehicle. When the vehicle cockpit plays a reminder sound related to user safety, if the user does not respond or does not resolve the abnormal situation, that is, the vehicle cockpit does not recognize the user's voice content or voice commands, etc., then the vehicle cockpit will automatically call or send a message to the user's pre-saved contacts.

[0216] For example, the vehicle cabin is connected to the speed sensor of the safety domain, that is, it is related to the safe driving function. When the vehicle's driving speed is high and there is a driving safety risk, the cabin speaker or the safety domain speaker will play the corresponding speeding alarm sound. If the user does not reduce the speed within a period of time, the vehicle cabin will automatically call the emergency rescue number.

[0217] In some embodiments, after receiving the identification information of the vehicle sound signal, the vehicle cockpit can directly play the fourth voice prompt information, wherein the fourth voice prompt information can include the source information of the sound signal, so as to play the prompt information for the user without user interaction, thereby improving the user experience.

[0218] The embodiment of the present application also provides a sound signal processing method, which can be applied to the above-mentioned vehicle, and the vehicle includes the above-mentioned vehicle cabin and at least one vehicle component. Fig. 9 As shown, the sound signal processing method may include the following steps S901-S903.

[0219] S901. The vehicle receives a vehicle sound signal.

[0220] The vehicle sound signal comes from an on-board application in the vehicle cockpit and / or a vehicle component other than the vehicle cockpit.

[0221] For example, the vehicle may receive a first message from an in-vehicle application in a vehicle cabin, and determine the vehicle sound signal according to the first message, wherein the first message includes information related to the vehicle sound signal. Alternatively, the vehicle may receive a second message from a vehicle component, and determine the vehicle sound signal according to the second message, wherein the second message includes information related to the vehicle sound signal.

[0222] As another example, the vehicle may detect ambient sound of an environment in which the vehicle is located, and detect a vehicle sound signal from the ambient sound.

[0223] S902: The vehicle determines corresponding identification information according to the vehicle sound signal.

[0224] The identification information of the vehicle sound signal is used to distinguish vehicle sound signals of different functions, effects or types.

[0225] In some possible application scenarios, the identification information corresponding to the vehicle sound signal can be obtained from the vehicle cockpit in the vehicle. Among them, the functions that can be realized or the operations that can be performed by the vehicle cockpit can refer to the contents in the above implementation.

[0226] In some possible application scenarios, the vehicle sound signal can be played in the vehicle cockpit, in the target functional domain of the vehicle, or in both the vehicle cockpit and the target functional domain. Furthermore, when playing in the vehicle cockpit, the vehicle cockpit controls the cockpit speakers to play; when playing in the target functional domain, the target functional domain controls the speakers of the functional domain to play. The functions that can be realized or the operations that can be performed by the vehicle cockpit and the target functional domain can refer to the contents of the aforementioned embodiments.

[0227] S903: The vehicle responds to the user's first voice input operation and plays a first voice prompt message according to the identification information.

[0228] The first voice prompt information includes source information of the vehicle sound signal.

[0229] In some possible application scenarios, the source information of the vehicle sound signal played can be determined by the vehicle cabin in the vehicle. Among them, the functions that can be realized or the operations that can be performed by the vehicle sound signal can refer to the contents in the above implementation.

[0230] In the above-mentioned sound signal processing method, the vehicle can determine the source information of the vehicle sound signal through the identification information of the vehicle sound signal, and can determine the source information of the vehicle sound signal without using sound recognition, thereby eliminating the interference of noise and more accurately determining the type, function or effect of the vehicle sound signal.

[0231] In some other embodiments, the vehicle obtains description information of the vehicle sound signal from preset audio information according to the identification information of the vehicle sound signal, and determines the source information of the vehicle sound signal according to the description information of the vehicle sound signal. In some possible application scenarios, the vehicle cockpit can be used to achieve the purpose of determining the source of the vehicle sound signal, wherein the functions that can be realized or the operations that can be performed by the vehicle cockpit can refer to the contents of the aforementioned implementation.

[0232] In some other embodiments, the vehicle determines the sound source of the vehicle sound signal based on the identification information and preset audio information of the vehicle sound signal; if the vehicle sound signal is generated at the cockpit speaker, the vehicle controls the cockpit speaker to play the vehicle sound signal; if the vehicle sound signal is generated at other speakers corresponding to vehicle components other than the cockpit speaker, the vehicle controls the other speakers to play the vehicle sound signal. In some possible application scenarios, the cockpit speaker can be controlled by the vehicle cockpit to play the vehicle sound signal, and the target functional domain of the vehicle can control other speakers to play the vehicle sound signal, and the other speakers can be speakers in the target functional domain. Among them, the functions that can be realized by the vehicle cockpit and the target functional domain or the operations that can be performed can refer to the contents of the aforementioned embodiments.

[0233] In some other embodiments, the vehicle plays the first voice prompt information in response to receiving the first voice input operation of the user during the playback of the vehicle sound signal. In some possible application scenarios, the first voice input operation can be received by the vehicle cockpit and the first voice prompt information can be played, wherein the functions that can be implemented or the operations that can be performed by the vehicle cockpit can refer to the contents of the aforementioned implementation.

[0234] In some other embodiments, the vehicle controls the vehicle sound signal according to the source information of the vehicle sound signal being played in response to receiving the second voice input operation of the user. In some possible application scenarios, the second voice input operation can be received by the vehicle cockpit and the vehicle sound signal can be controlled. The functions or operations that can be performed by the vehicle cockpit can refer to the contents of the aforementioned implementation.

[0235] In some other embodiments, the vehicle saves the identification information of the vehicle sound signal that has been played; after the vehicle sound signal is played, in response to receiving a third voice input operation from the user, the source information of the vehicle sound signal that has been played is determined based on the saved identification information of the vehicle sound signal that has been played and the preset audio information, and the second voice prompt information is played. In some possible application scenarios, the vehicle cockpit can save the identification information of the vehicle sound signal, receive the third voice input operation, and play the second voice prompt information, wherein the functions that can be realized or the operations that can be performed by the vehicle cockpit can refer to the contents of the aforementioned implementation.

[0236] In some other embodiments, in response to receiving the fourth voice input operation of the user, the vehicle controls the vehicle sound signal that has been played according to the source information of the vehicle sound signal that has been played. In some possible application scenarios, the fourth voice input operation can be received by the vehicle cockpit and the vehicle sound signal can be controlled. The functions that can be realized or the operations that can be performed by the vehicle cockpit can refer to the contents of the aforementioned implementation.

[0237] In some other embodiments, when the vehicle plays multiple vehicle sound signals simultaneously, the vehicle plays a third voice prompt message in response to receiving the first voice input operation of the user. In some possible application scenarios, the first voice input operation can be received by the vehicle cockpit, and the third voice prompt message can be played. The functions that can be implemented or the operations that can be performed by the vehicle cockpit can refer to the contents of the aforementioned implementation.

[0238] In some other embodiments, in response to receiving the second voice input operation from the user, the vehicle plays the inquiry information corresponding to the multiple vehicle sound signals in sequence according to the source information corresponding to the multiple vehicle sound signals; then, within a preset time after playing the inquiry information, in response to receiving the fifth voice input operation from the user, the vehicle sound signal corresponding to the inquiry information is controlled according to the source information of the vehicle sound signal corresponding to the inquiry information. In some possible application scenarios, the vehicle cockpit can receive the second voice input operation, play the inquiry information, and control the vehicle sound signal, wherein the functions that can be realized or the operations that can be performed by the vehicle cockpit can refer to the contents of the aforementioned implementation.

[0239] In some other embodiments, the vehicle determines the source application and / or source component corresponding to the vehicle sound signal according to the identification information and preset audio information of the vehicle sound signal. In some possible application scenarios, the source application and / or source component corresponding to the vehicle sound signal can be determined by the vehicle cockpit, wherein the functions that can be implemented or the operations that can be performed by the vehicle cockpit can refer to the contents of the aforementioned implementation.

[0240] In some other embodiments, if the vehicle sound signal played by the cabin speaker includes at least two signals, the vehicle obtains the priority information in the description information corresponding to each vehicle sound signal; the vehicle controls the cabin speaker to play the vehicle sound signal with the highest priority at a volume greater than the volume of other vehicle sound signals; or, the cabin speaker is controlled to play the vehicle sound signal with the highest priority, pauses playing other vehicle sound signals, and controls the cabin speaker to continue playing other vehicle sound signals after the vehicle sound signal with the highest priority is played. And / or, if the vehicle sound signal played by other speakers includes at least two signals, the vehicle obtains the priority information in the description information corresponding to each vehicle sound signal; the vehicle controls the other speakers to play the vehicle sound signal with the highest priority at a volume greater than the volume of other vehicle sound signals; or, the other speakers are controlled to play the vehicle sound signal with the highest priority, pauses playing other vehicle sound signals, and controls the other speakers to continue playing other vehicle sound signals after the vehicle sound signal with the highest priority is played.

[0241] In some possible application scenarios, the vehicle cockpit may obtain the above priority information and control the cockpit speaker to play each vehicle sound signal, and / or the vehicle target functional domain may obtain the above priority information and control other speakers to play each vehicle sound signal, and the other speakers may be speakers in the target functional domain. The functions that can be realized by the vehicle cockpit and the target functional domain or the operations that can be performed may refer to the contents of the aforementioned embodiments.

[0242] In some other embodiments, while the vehicle controls the cockpit speaker or other speakers except the cockpit speaker to play the first voice prompt information, the vehicle controls the on-board display screen to display the text content corresponding to the first voice prompt information. In some possible application scenarios, the vehicle cockpit can control the cockpit speaker to play the audio content corresponding to the first voice prompt information and control the on-board display screen to display the text content corresponding to the first voice prompt information, and the vehicle's target functional domain can control other speakers to play the audio content corresponding to the first voice prompt information, and the other speakers can be speakers of the target functional domain. Among them, the functions that can be realized or the operations that can be performed by the vehicle cockpit and the target functional domain can refer to the contents of the aforementioned embodiments.

[0243] It can be understood that the functions that can be realized or the operations that can be performed by the above-mentioned vehicle are only some examples, and the functions that can be realized or the operations that can be performed by the vehicle cabin and the target functional domain in the aforementioned embodiments can all be regarded as functions that can be realized or the operations that can be performed by the vehicle.

[0244] In some schemes, multiple embodiments of the present application can be combined, and the combined scheme can be implemented. Optionally, some operations in the process of each method embodiment are optionally combined, and / or the order of some operations is optionally changed. In addition, the execution order between the steps of each process is only exemplary and does not constitute a restriction on the execution order between the steps. There can also be other execution orders between the steps. It is not intended to show that the execution order is the only order in which these operations can be performed. A person of ordinary skill in the art will think of a variety of ways to reorder the operations described in the embodiments of the present application. In addition, it should be noted that the process details involved in a certain embodiment of the present application are also applicable to other embodiments in a similar manner, or different embodiments can be used in combination.

[0245] In addition, some steps in the method embodiment may be equivalently replaced by other possible steps. Alternatively, some steps in the method embodiment may be optional and may be deleted in certain usage scenarios. Alternatively, other possible steps may be added to the method embodiment.

[0246] Furthermore, the various method embodiments may be implemented separately or in combination.

[0247] It is understandable that in order to achieve the above functions, the aforementioned vehicle includes hardware and / or software modules corresponding to the execution of each function. In combination with the algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware 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 in combination with the embodiments, but such implementation should not be considered to be beyond the scope of this application.

[0248] In this embodiment, the functional modules of the vehicle can be divided according to the above method example. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above integrated modules can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0249] The present application also provides a vehicle, such as Fig.10 As shown, the vehicle may include one or more processors 1001 , a memory 1002 , and a communication interface 1003 .

[0250] The memory 1002 and the communication interface 1003 are coupled to the processor 1001. For example, the memory 1002, the communication interface 1003 and the processor 1001 may be coupled together via a bus 1004.

[0251] The communication interface 1003 is used for data transmission with other devices. The memory 1002 stores computer program code. The computer program code includes computer instructions. When the computer instructions are executed by the processor 1001, the vehicle executes the sound signal processing method in the embodiment of the present application.

[0252] Among them, the processor 1001 can be a processor or a controller, for example, a central processing unit (CPU), a general processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It can implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the present disclosure. The processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0253] The bus 1004 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus 1004 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.10 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0254] An embodiment of the present application also provides a computer-readable storage medium, in which a computer program code is stored. When the above-mentioned processor executes the computer program code, the vehicle executes the relevant method steps in the above-mentioned method embodiment.

[0255] The embodiment of the present application also provides a computer program product. When the computer program product is run on a computer, it enables the computer to execute the relevant method steps in the above method embodiment.

[0256] Among them, the vehicle, computer storage medium or computer program product provided in this application is used to execute the corresponding method provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method provided above, and will not be repeated here.

[0257] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned 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.

[0258] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0259] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0260] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0261] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0262] The above contents are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application shall be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A sound signal processing method, characterized in that: Applied to a vehicle, the method comprises: receiving a vehicle sound signal, the vehicle sound signal coming from an in-vehicle application in a vehicle cabin and / or a vehicle component other than the vehicle cabin; Determining corresponding identification information according to the vehicle sound signal; In response to a first voice input operation by the user, first voice prompt information is played according to the identification information, wherein the first voice prompt information includes source information of the vehicle sound signal.

2. The method according to claim 1, characterized in that The receiving of the vehicle sound signal comprises: Receiving a first message from an in-vehicle application in a vehicle cabin; the first message comprising information related to a vehicle sound signal; or A second message is received from a vehicle component; the second message includes information related to a vehicle acoustic signal.

3. The method according to claim 1 or 2, characterized in that: The receiving of the vehicle sound signal comprises: The ambient sound of the environment in which the vehicle is located is detected, and the vehicle sound signal is detected from the ambient sound.

4. The method according to any one of claims 1 to 3, characterized in that: The step of responding to the first voice input operation of the user and playing the first voice prompt information according to the identification information includes: In response to a first voice input operation by a user, obtaining description information of the vehicle sound signal corresponding to the identification information according to the identification information; the description information includes one or more of type information, sound location information, name information, and generation cause information of the vehicle sound signal; Play the first voice prompt information according to the description information of the vehicle sound signal.

5. The method according to claim 4, characterized in that There is a correspondence between the identification information and the description information of the vehicle sound signal, and the correspondence is pre-stored in the vehicle, or the correspondence is configured by the vehicle in response to a user's operation.

6. The method according to claim 4 or 5, characterized in that: The method further comprises: Determining a sound source position of the vehicle sound signal according to the description information of the vehicle sound signal; If the vehicle sound signal is generated at a cockpit speaker, controlling the cockpit speaker to play the vehicle sound signal; If the vehicle sound signal is generated by a speaker other than the cabin speaker, the other speaker is controlled to play the vehicle sound signal.

7. The method according to claim 6, characterized in that The user's first voice input operation includes inquiring about source information of the sound being played.

8. The method according to claim 6 or 7, characterized in that: The method further comprises: In response to a second voice input operation by the user, a control operation is performed on the vehicle sound signal being played based on source information of the vehicle sound signal being played; the second voice input operation is used to instruct control of the vehicle sound signal being played, and the control operation includes turning off the vehicle sound signal being played and / or playing a fault clearance guide corresponding to the vehicle sound signal being played.

9. The method according to any one of claims 6 to 8, characterized in that: The method further comprises: Saving identification information of vehicle sound signals that have been played; After the vehicle sound signal is played, in response to the user's third voice input operation, the source information of the played vehicle sound signal is determined based on the saved identification information of the played vehicle sound signal, and the second voice prompt information is played; the third voice input operation is used to inquire about the source information of the played vehicle sound signal, and the second voice prompt information includes the source information of the played vehicle sound signal.

10. The method according to claim 9, characterized in that The method further comprises: In response to a fourth voice input operation by the user, a control operation is performed on the played vehicle sound signal according to source information of the played vehicle sound signal; the fourth voice input operation is used to instruct the control of the played vehicle sound signal, and the control operation includes turning off the played vehicle sound signal and / or playing a fault clearance guidance corresponding to the played vehicle sound signal.

11. The method according to claim 6 or 7, characterized in that: The vehicle sound signal includes a plurality of sound signals, and the first voice prompt information is played according to the identification information in response to the first voice input operation of the user, including: When the cockpit speaker and / or the other speakers play the multiple sound signals simultaneously, in response to the user's first voice input operation, a third voice prompt information is played; the third voice prompt information includes source information corresponding to the multiple sound signals respectively.

12. The method according to claim 11, characterized in that The method further comprises: In response to the user's second voice input operation, playing the inquiry information corresponding to the multiple sound signals respectively according to the source information corresponding to the multiple sound signals respectively; the inquiry information is used to inquire whether to perform a control operation on the sound signal corresponding to the inquiry information; Within a preset time length after playing the inquiry information, in response to the user's fifth voice input operation, a control operation is performed on the sound signal corresponding to the inquiry information according to the source information of the sound signal corresponding to the inquiry information; the fifth voice input operation is used to instruct the control operation to be performed on the sound signal corresponding to the inquiry information.

13. The method according to claim 4, characterized in that The method further comprises: According to the description information of the vehicle sound signal, the source application and / or source component corresponding to the vehicle sound signal is determined; the first voice prompt information also includes the source application information and / or source component information of the vehicle sound signal.

14. The method according to any one of claims 6 to 13, characterized in that: The method further comprises: If the vehicle sound signal played by the cabin speaker includes at least two sound signals, obtaining priority information in the description information corresponding to each of the sound signals; Controlling the cockpit speaker to play the highest priority sound signal at a higher volume than other sound signals; or The cockpit speaker is controlled to play the sound signal with the highest priority, and the playing of other sound signals is paused. After the playing of the sound signal with the highest priority is completed, the cockpit speaker is controlled to continue playing other sound signals.

15. The method according to any one of claims 1 to 14, characterized in that: After determining the corresponding identification information according to the vehicle sound signal, the method further includes: Play a fourth voice prompt message; the fourth voice prompt message includes source information of the vehicle sound signal.

16. The method according to any one of claims 1 to 15, characterized in that: The first voice input operation includes inputting a pronoun referring to the vehicle sound signal being played and / or a pronoun used to refer to the current moment.

17. The method according to claim 9, characterized in that The third voice input operation includes inputting a pronoun for referring to a played vehicle sound signal and / or a pronoun for referring to a historical moment.

18. A vehicle, characterized in that: comprising a vehicle cabin and at least one vehicle component, the vehicle cabin being communicatively connected to the at least one vehicle component; The vehicle cockpit is used to receive a vehicle sound signal; the vehicle sound signal comes from an on-board application of the vehicle cockpit and / or the vehicle component; The vehicle cockpit is used to determine corresponding identification information according to the vehicle sound signal; The vehicle cockpit is also used to respond to a first voice input operation of the user and play a first voice prompt information according to the identification information, wherein the first voice prompt information includes source information of the vehicle sound signal.

19. The vehicle according to claim 18, characterized in that The vehicle cockpit is also used to receive a first message from an in-vehicle application; the first message includes information related to the vehicle sound signal; or, to receive a second message from a vehicle component; the second message includes information related to the vehicle sound signal.

20. The vehicle according to claim 18 or 19, characterized in that The vehicle cockpit is also used to detect the ambient sound of the environment in which the vehicle is located, and to detect the vehicle sound signal from the ambient sound.

21. The vehicle according to any one of claims 18-19, characterized in that: The vehicle cockpit is also used to respond to the user's first voice input operation, and obtain, according to the identification information, the description information of the vehicle sound signal corresponding to the identification information; the description information includes one or more of the type information, sound location information, name information, and cause information of the vehicle sound signal; and play the first voice prompt information according to the description information of the vehicle sound signal.

22. The vehicle according to claim 21, characterized in that There is a correspondence between the identification information and the description information of the vehicle sound signal, and the correspondence is pre-stored in the vehicle, or the correspondence is configured by the vehicle in response to a user's operation.

23. The vehicle according to claim 21 or 22, characterized in that The vehicle cockpit is further used to determine the sound source position of the vehicle sound signal according to the description information of the vehicle sound signal; if the source position of the vehicle sound signal is the cockpit speaker, the cockpit speaker is controlled to play the vehicle sound signal; if the source position of the vehicle sound signal is other speakers except the cockpit speaker, the other speakers are controlled to play the vehicle sound signal.

24. The vehicle according to claim 23, characterized in that The vehicle cockpit is also used to respond to a second voice input operation of the user and perform a control operation on the vehicle sound signal being played based on source information of the vehicle sound signal being played; the second voice input operation is used to instruct control of the vehicle sound signal being played, and the control operation includes turning off the vehicle sound signal being played and / or playing a fault clearance guidance corresponding to the vehicle sound signal being played.

25. A vehicle according to claim 23 or 24, characterised in that The vehicle cockpit is also used to save the identification information of the vehicle sound signal that has been played; after the vehicle sound signal is played, in response to the user's third voice input operation, the source information of the played vehicle sound signal is determined according to the saved identification information of the played vehicle sound signal, and the second voice prompt information is played; the third voice input operation is used to inquire about the source information of the played vehicle sound signal, and the second voice prompt information includes the source information of the played vehicle sound signal.

26. The vehicle according to claim 25, characterized in that The vehicle cockpit is also used to respond to a fourth voice input operation of the user and perform a control operation on the played vehicle sound signal according to source information of the played vehicle sound signal; the fourth voice input operation is used to instruct the control of the played vehicle sound signal, and the control operation includes turning off the played vehicle sound signal and / or playing a fault clearance guidance corresponding to the played vehicle sound signal.

27. The vehicle of claim 23, wherein: The vehicle sound signal includes multiple sound signals, and the vehicle cockpit is also used to play a third voice prompt information in response to a user's first voice input operation when the cockpit speaker and / or the other speakers play the multiple sound signals simultaneously; the third voice prompt information includes source information corresponding to the multiple sound signals respectively.

28. The vehicle according to claim 27, characterized in that The vehicle cockpit is also used to respond to a second voice input operation of the user, and play inquiry information corresponding to the multiple sound signals respectively according to the source information corresponding to the multiple sound signals; the inquiry information is used to inquire whether to perform a control operation on the sound signal corresponding to the inquiry information; within a preset time period after playing the inquiry information, in response to a fifth voice input operation of the user, a control operation is performed on the sound signal corresponding to the inquiry information according to the source information of the sound signal corresponding to the inquiry information; the fifth voice input operation is used to instruct to perform a control operation on the sound signal corresponding to the inquiry information.

29. The vehicle of claim 21, wherein: The vehicle cockpit is also used to determine the source application and / or source component corresponding to the vehicle sound signal based on the description information of the vehicle sound signal; the first voice prompt information also includes the source application information and / or source component information of the vehicle sound signal.

30. The vehicle according to any one of claims 23 to 29, characterized in that The vehicle cockpit is further configured to obtain priority information in the description information corresponding to each of the sound signals if the vehicle sound signal played by the cockpit speaker includes at least two sound signals; and control the cockpit speaker to play the sound signal with the highest priority at a volume greater than the volume of other sound signals; Alternatively, the cockpit speaker is controlled to play the sound signal with the highest priority and pause playing other sound signals; after the sound signal with the highest priority is finished playing, the cockpit speaker is controlled to continue playing other sound signals.

31. The vehicle according to any one of claims 18 to 30, characterized in that The vehicle cockpit is further used to play fourth voice prompt information after determining the identification information corresponding to the vehicle sound signal; the fourth voice prompt information includes source information of the vehicle sound signal.

32. A vehicle, characterized in that: It includes a memory and one or more processors; the memory is coupled to the processor; the memory stores computer program code, and the computer program code includes computer instructions. When the computer instructions are executed by the processor, the vehicle executes the sound signal processing method as described in any one of claims 1-17.

33. A computer-readable storage medium, characterized in that: The method comprises computer instructions, which, when executed on a vehicle, enable the vehicle to execute the sound signal processing method as claimed in any one of claims 1 to 17.

Images