Voice interaction method and apparatus, electronic device, storage medium and vehicle

Abstract

The present disclosure provides a voice interaction method and apparatus, an electronic device, a storage medium and a vehicle. The method comprises: acquiring a first voice generated in a first sound zone in a compartment in a sound zone locked mode, wherein the first sound zone is a sound zone for awakening a voice assistant; in response to the first voice triggering a multi-person interaction mode, acquiring a second voice generated in a second sound zone in the compartment, and determining a second intent of the second voice; and when determining that the second intent is correlated to a first intent, responding to the second intent, wherein the first intent is correlated to the first voice. When a sound zone is locked, an intent of a non-awakening user can be responded on the basis of the correlation between the second voice and the first voice, so that the technical effect of interaction between multiple persons and an in-vehicle infotainment system in a sound zone locked mode can be realized, thereby improving user experience.

Description

Voice interaction method, device, electronic device, storage medium, and vehicle

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to the Chinese patent application filed with the China Patent Office on August 29, 2023, with application number 202311100664.0 and application name “Voice Interaction Method, Device, Electronic Device, Storage Medium and Vehicle”, the entire contents of which are incorporated by reference into this application. Technical Field

[0003] The present disclosure relates to the field of intelligent vehicle technology, and is related to, but not limited to, a voice interaction method, device, electronic device, storage medium, and vehicle. Background Art

[0004] With the development of in-vehicle intelligent interactive systems, a voice zone locking function can be implemented. When a voice zone is locked, the car's voice assistant can only listen to the voice content in the voice zone where the person who woke up the car is located, and other voice zones cannot be recognized. For example, if the driver wakes up the voice assistant in the driver's voice zone to initiate a navigation request, the passenger cannot help choose the route by voice. For example, if the driver wakes up the voice assistant and says "turn on the seat heating", and the passenger also wants to turn on the seat heating, the passenger must wake up the voice assistant again and say "turn on the seat heating" and cannot directly say "I want it too". Therefore, when the voice zone is locked, if the voice of other users in the vehicle is related to the voice of the person who woke up the car, the car cannot respond to the voice of other users, thus affecting the user experience.

[0005] Summary of the Invention

[0006] The present disclosure proposes a voice interaction method, device, electronic device, storage medium and vehicle, aiming to solve one of the technical problems in the related art at least to a certain extent.

[0007] An embodiment of the first aspect of the present disclosure proposes a voice interaction method, including: obtaining a first voice generated in a first sound zone in a vehicle compartment in a sound zone lock mode; triggering a multi-person interaction mode in response to the first voice, obtaining a second voice generated in a second sound zone in the vehicle compartment, and determining a second intention of the second voice; and responding to the second intention when it is determined that the second intention is related to the first intention, wherein the first intention is related to the first voice.

[0008] An embodiment of the second aspect of the present disclosure proposes a voice interaction device, including: a first acquisition module, configured to acquire a first voice generated in a first sound zone in a vehicle compartment in a sound zone lock mode; a second acquisition module, configured to trigger a multi-person interaction mode in response to the first voice, acquire a second voice generated in a second sound zone in the vehicle compartment, and determine a second intention of the second voice; and a response module, configured to respond to the second intention when it is determined that the second intention is related to the first intention, wherein the first intention is related to the first voice.

[0009] An embodiment of the third aspect of the present disclosure proposes an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the voice interaction method of the embodiment of the present disclosure.

[0010] The fourth aspect of the present disclosure provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to execute the voice interaction method disclosed in the embodiment of the present disclosure.

[0011] A fifth embodiment of the present disclosure provides a vehicle, which includes an electronic device according to the first embodiment described above.

[0012] The sixth aspect of the present disclosure provides a computer program product, including computer-executable instructions or a computer program, which, when executed by a processor, implements the voice interaction method disclosed in the embodiment of the present disclosure.

[0013] In this embodiment, by obtaining the first voice generated in the first sound zone in the vehicle cabin in the sound zone locking mode, wherein the first sound zone is the sound zone for waking up the voice assistant, and triggering the multi-person interaction mode in response to the first voice, the second voice generated in the second sound zone in the vehicle cabin is obtained, and the second intention of the second voice is determined, and when it is judged that the second intention is related to the first intention, the second intention is responded to, wherein the first intention is related to the first voice, and when the sound zone is locked, the intention of not waking up the user can be responded to according to the correlation between the second voice and the first voice. Therefore, the technical effect of multi-person interaction with the vehicle computer in the sound zone locking mode can be achieved, thereby improving the user experience.

[0014] Additional aspects and advantages of the present disclosure will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The above and / or additional aspects and advantages of the present disclosure will become apparent and readily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0016] FIG1 is a flow chart of a voice interaction method according to an embodiment of the present disclosure;

[0017] FIG2 is a schematic diagram of a second intention recognition process provided according to an embodiment of the present disclosure;

[0018] FIG3 is a flow chart of a voice interaction method according to another embodiment of the present disclosure;

[0019] FIG4 is a schematic diagram of the overall process of multi-round multi-person voice interaction provided according to an embodiment of the present disclosure;

[0020] FIG5 is a schematic diagram of a voice interaction device according to another embodiment of the present disclosure;

[0021] FIG6 illustrates a block diagram of an exemplary electronic device suitable for implementing embodiments of the present disclosure. DETAILED DESCRIPTION

[0022] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features therein can be combined with each other in the absence of conflict.

[0023] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0024] It should be noted that the executor of the voice interaction method of this embodiment may be a voice interaction device, which may be implemented by software and / or hardware, and may be configured in an electronic device, which may include but is not limited to a terminal, a server, etc.

[0025] FIG1 is a flow chart of a voice interaction method according to an embodiment of the present disclosure. As shown in FIG1 , the method includes:

[0026] S101: Acquire a first voice generated in a first sound zone in a vehicle compartment in a sound zone locking mode.

[0027] Among them, when the car computer is in the sound zone lock mode, the sound zone where the user wakes up the voice assistant among the multiple sound zones in the car can be called the first sound zone, that is, the user wakes up the voice assistant in the first sound zone.

[0028] The voice generated by the user in the first voice zone can be called the first voice, and the first voice can be any voice, such as "turn on my seat heating function", "navigate to the mall", etc., without limitation.

[0029] In the embodiment of the present disclosure, the vehicle computer first obtains the first voice generated in the first sound zone, that is, the voice interaction method provided in this embodiment can be executed by the vehicle computer.

[0030] In an optional example, the cabin is divided into four sound zones, including the main driver's sound zone (sound zone 1), the co-driver's sound zone (sound zone 2), the rear left sound zone (sound zone 3), and the rear right sound zone (sound zone 4). The first sound zone of this embodiment can be any one of the four sound zones. For example, in the sound zone lock mode, user 1 wakes up the voice assistant in sound zone 1, and then sound zone 1 is used as the first sound zone.

[0031] S102: In response to the first voice triggering the multi-person interaction mode, a second voice generated in a second sound zone in the vehicle cabin is obtained, and a second intention of the second voice is determined.

[0032] As described in the background technology, when the sound zone is locked, the voice assistant only obtains the voice of the sound zone where the awakened person is located (ie, the first sound zone), and the voices of other sound zones cannot be recognized, thus affecting the user experience.

[0033] In view of this, after obtaining the first voice, the embodiment of the present disclosure further determines whether the intention of the first voice triggers the multi-person interaction mode. In the multi-person interaction mode of this embodiment, the voice assistant can also obtain voices generated in other sound zones.

[0034] Among them, the embodiment of the present disclosure can determine whether the first voice triggers the multi-person interaction mode in any possible way.

[0035] In some embodiments, interactive scenarios that can trigger the multi-person interaction mode can be pre-set, such as navigation, window control, seat control, and music control, without limitation. Furthermore, this embodiment can determine keywords for each scenario. For example, in the navigation scenario, the keyword can be "navigation," and in the window control scenario, the keyword can be "window." Furthermore, a mapping table can be constructed to record the multiple keywords that trigger the multi-person interaction mode. Furthermore, the vehicle computer in this embodiment can be configured with a pre-trained speech recognition model and a semantic recognition model. The speech recognition model can convert speech into corresponding text, while the semantic recognition model can identify the intent of the text. After acquiring a first speech, this embodiment can first acquire the mapping table. Furthermore, the speech recognition model can be used to convert the first speech into corresponding text, and the semantic recognition model can be used to identify the intent of the text. This intent can be referred to as the first intent, which is understood to be in text form. Furthermore, a determination is made as to whether the first intent (text) contains the keyword. If the keyword is present in the first intent, the multi-person interaction mode is triggered.

[0036] Among them, among the multiple sound zones in the car of this embodiment, except the sound zone where the person is awakened, the other sound zones can be called second sound zones, that is, the second sound zones of this embodiment include sound zone 2, sound zone 3 and sound zone 4.

[0037] The speech generated by the user in the second audio zone can be referred to as a second speech, and the second speech can be any speech content. In this embodiment, one second audio zone can generate the second speech, or multiple second audio zones can generate the second speech simultaneously, and one second audio zone can generate one or more second speech, without limitation.

[0038] For example, if user 2 speaks in sound zone 2 (second sound zone) in a car, the content of user 2's speech can be called the second voice; for another example, if user 2 speaks in sound zone 2 (second sound zone) in a car, and user 3 speaks in sound zone 3 (second sound zone) at the same time, the content of user 2 and user 3's speech can both be called the second voice.

[0039] In this embodiment, if the vehicle computer determines that the first voice has triggered the multi-person interaction mode, the vehicle computer can obtain the second voice in the second audio zone. Those skilled in the art will understand that in audio zone lock mode, only the voice activity detection (VAD) function of the audio zone where the wake-up person is located (the first audio zone) is enabled in the vehicle cabin, for example, the microphone is enabled, while the VAD function of other audio zones is disabled.

[0040] In some embodiments, when the multi-person interaction mode is triggered, the vehicle computer can turn on the voice activity detection function of all second sound zones in the vehicle to detect whether multiple second sound zones generate voice. If any second sound zone generates voice, the vehicle computer obtains the voice as the second voice.

[0041] In some other embodiments, when the multi-person interaction mode is triggered, in order to accurately obtain the second voice, the vehicle computer can selectively enable the voice activity detection function of part of the second sound zone in the vehicle.

[0042] For example, this embodiment can first detect the seating position information of users in the vehicle compartment. This seating position information is used to indicate the seating position of one or more users in the vehicle compartment. For example, the seating position information may include information about a user sitting in the driver's seat, a user sitting in the passenger seat, and a user sitting in the left rear seat. In some embodiments, this seating position information can be detected, for example, using a seat pressure sensor or an image recognition device installed in the vehicle compartment, without limitation.

[0043] Furthermore, this embodiment can, based on the seating position information, enable the voice activity detection function of the second sound zone where a user is sitting (turn on the microphone) to obtain the second voice generated in the second sound zone. For example, if the seating position information indicates that a user is sitting in the front passenger seat and a user is sitting in the left rear seat, this embodiment can enable the microphones of the front passenger seat (sound zone 2) and the left rear seat (sound zone 3). When the user in sound zone 2 (the second sound zone) and / or sound zone 3 (the second sound zone) generates a voice, the microphone in sound zone 2 and / or sound zone 3 can collect the voice as the second voice. If there is no user sitting in the right rear seat (sound zone 4), the microphone in sound zone 4 will not be enabled. Thus, this embodiment only enables the voice activity detection function of the second sound zone where someone is sitting, so the second voice can be accurately acquired and resources can be saved.

[0044] It should be noted that in the multi-person interaction mode, the voice activity detection function of the first voice zone is also turned on, that is, the voice assistant of this embodiment can also respond to the voice of the user in the first voice zone.

[0045] After acquiring the second speech, the disclosed embodiment further determines the intent (also referred to as semantics) of the second speech, which may be referred to as the second intent. The second intent may be any intent, such as opening a window, turning on heated seats, selecting a navigation route, chatting, and the like, without limitation.

[0046] Illustratively, after acquiring the second speech, this embodiment can first use the speech recognition model to convert the second speech into corresponding text, which can be referred to as the target text; further, the target text can be recognized using the semantic recognition model to determine the intent of the target text, that is, the second intent. Among them, after acquiring the second speech, this embodiment can also perform noise reduction, voice enhancement, and other processing on the second speech. It can be understood that the speech recognition model and semantic recognition model of this embodiment can be obtained by training based on any model, and this embodiment does not limit the training process.

[0047] In some embodiments, Figure 2 is a schematic diagram of the second intention recognition process provided according to an embodiment of the present disclosure. As shown in Figure 2, this embodiment configures an acoustic front-end module (i.e., for noise reduction, human voice enhancement, etc.), a speech recognition model, and a semantic recognition model for sound zone 1, sound zone 2, sound zone 3, and sound zone 4, respectively. That is to say, the speech generated by each sound zone can be processed separately by the acoustic front-end speech recognition model and the semantic recognition model configured for the sound zone, thereby realizing multi-channel speech recognition and multi-channel semantic interpretation.

[0048] For example, the voice (second voice) generated by the voice zone 2 can be collected by microphone 2 (voice activity detection function), and the voice can be further processed by the acoustic front end corresponding to the voice zone 2 to reduce noise and enhance human voice. The processed voice can be further processed by the voice recognition model corresponding to the voice zone 2 to obtain text (target text). The semantic recognition model corresponding to the voice zone 2 can be used to perform semantic understanding on the text to obtain the intention of the second voice (second intention). Therefore, when multiple voice zones generate voice at the same time, this embodiment can process the voice of each voice zone in parallel, thereby improving the efficiency of voice processing.

[0049] S103: If it is determined that the second intention is related to the first intention, respond to the second intention, wherein the first intention is related to the first voice.

[0050] That is to say, after determining the second intention of the second voice (opening the car window), this embodiment can determine the relevance of the second intention with the first intention. If it is determined that the second intention is related to the first intention, the vehicle computer can respond to the second intention, that is, control the opening of the car window; if the second intention is not related to the first intention, the vehicle computer can refuse to recognize the second intention and make no response.

[0051] Among them, the first intention of the embodiment of the present disclosure is related to the first voice.

[0052] In the embodiments of the present disclosure, the intent of the first speech can be used as the first intent. The first intent is determined in the same manner as the second intent, which will not be further described here. In other words, the embodiments of the present disclosure respond to the second intent if the second intent is related to the first intent of the first speech.

[0053] Whether the first intention is related to the second intention may be determined in any possible manner, and this is not limited.

[0054] In some embodiments, for example, whether the second intention is related to the first intention may be determined by calculating a cosine distance between the second intention and the first intention.

[0055] For example, if user 1 says "Turn on my seat heating" (i.e., the first voice) in voice zone 1 (the first voice zone), this embodiment can determine the first intention of the first voice, which is to turn on the seat heating. Subsequently, if user 2 says "seat heating" (the second voice) in voice zone 2 (the second voice zone), this embodiment can determine that the second intention of the second voice is also to turn on the seat heating. In this case, this embodiment can determine that the second intention is related to the first intention based on the cosine distance, and the vehicle computer can execute the second intention, i.e., turn on the seat heating function for user 2. If user 2 says "navigate to the mall" (the second voice) in voice zone 2 (the second voice zone), this embodiment can determine that the second intention of the second voice is navigation. In this case, this embodiment can determine that the second intention is unrelated to the first intention based on the cosine distance, and the vehicle computer will reject the second intention and make no response.

[0056] In some other embodiments, it is also possible to determine whether the second intention is the same as the first intention based on keywords of the second intention, where keywords include, for example, words such as "me too", "I want too", and "same" that indicate the same intention.

[0057] For example, user 1 says "Turn on my seat heating function" (i.e., the first voice) in voice zone 1 (first voice zone), then this embodiment can determine the first intention of the first voice, which is to turn on the seat heating; thereafter, if user 2 says "I want to turn it on too" (the second voice) in voice zone 2 (the second voice zone), then this embodiment can determine the second intention of the second voice. In this case, this embodiment can determine that the second intention is related to the first intention based on the keyword "I want it too", and the car computer executes the second intention.

[0058] In some other embodiments, when multiple second intentions corresponding to multiple second voices are related to the first intention, this example responds to the multiple second intentions in sequence according to the time sequence in which the multiple second voices are acquired.

[0059] For example, the time of obtaining the first voice is 12:00:00, and the first intention of the first voice is to turn on the seat heating; afterwards, for example, the second voice of voice zone 2 (second voice zone) obtained at 12:00:02 is "I want to turn it on too", and the second voice of voice zone 3 (second voice zone) obtained at 12:00:05 is "seat heating", then it is determined that the second intentions of the second voices in voice zone 2 and voice zone 3 are both related to the first intention. In this embodiment, according to the time order of obtaining the second voices in the two second voice zones, multiple second intentions are responded to in sequence, that is: first turn on the seat heating in voice zone 2, and then turn on the seat heating in voice zone 3.

[0060] In some embodiments, when it is determined that the second intention response is completed, the multi-person interaction mode is exited, that is, the voice assistant only receives the voice in the first voice zone. This can reduce the interference of other voice zones on the first voice zone.

[0061] In this embodiment, by obtaining the first voice generated in the first sound zone in the vehicle cabin in the sound zone locking mode, wherein the first sound zone is the sound zone for waking up the voice assistant, and triggering the multi-person interaction mode in response to the first voice, the second voice generated in the second sound zone in the vehicle cabin is obtained, and the second intention of the second voice is determined, and when it is judged that the second intention is related to the first intention, the second intention is responded to, wherein the first intention is related to the first voice, and when the sound zone is locked, the intention of not waking up the user can be responded to according to the correlation between the second voice and the first voice. Therefore, the technical effect of multi-person interaction with the vehicle computer in the sound zone locking mode can be achieved, thereby improving the user experience.

[0062] FIG3 is a flow chart of a voice interaction method according to another embodiment of the present disclosure. As shown in FIG3 , the method includes:

[0063] S301: Acquire a first voice generated in a first sound zone in a vehicle compartment in a sound zone locking mode.

[0064] The description of S301 refers to the above embodiment and will not be repeated here.

[0065] S302: In response to the first voice triggering the multi-person interaction mode, play prompt voices for multiple rounds of interaction related to the intention of the first voice.

[0066] In the disclosed embodiment, the first voice may trigger one or more rounds of interaction. For example, in a navigation scenario, multiple rounds of interaction are required, such as address selection and route selection. In this case, after the vehicle computer determines that the first voice triggers the multi-person interaction mode, it may play a prompt voice message for multiple rounds of interaction related to the intent of the first voice.

[0067] For example, a first voice message might be "Navigate to the supermarket," which triggers the multi-person interaction mode and is intended for navigation. In this case, the vehicle computer can play multiple navigation-related interaction prompts, each of which can be played sequentially. For example, the first prompt might be "We have found multiple supermarkets for you. Please select the number."

[0068] S303: Acquire a second voice generated in a second sound zone in the vehicle compartment, and determine a second intention of the second voice.

[0069] That is, after the prompt voice is broadcast, this embodiment activates the voice activity detection function of the second sound zone in the vehicle compartment to obtain the second voice generated in the second sound zone and determine the second intention of the second voice.

[0070] S304: If the second intention is related to the first intention of the prompt voice, respond to the second intention.

[0071] In this embodiment, the intent of the prompt voice associated with the first voice is considered the first intent. This means that this embodiment determines whether the second intent of the second voice is related to the first intent of the prompt voice. If so, the vehicle computer responds to the second intent. The method for determining the first intent of the prompt voice and determining relevance is similar to that of the above embodiment and will not be further described here.

[0072] For example, the above prompt voice is "We have found multiple supermarkets for you, please select the number", then the first intention is to ask which place to select; if the second voice is "the first place", then the second intention of the second voice is related to the first intention. In this case, the car computer can respond to the second intention, for example, broadcast the next round of prompt voice "Three routes were found for you, please select"; and if the second voice is "Turn on the seat heating", then the second intention is not related to the first intention. In this case, the car computer does not respond to the second intention, that is: it does not broadcast "Three routes were found for you, please select".

[0073] It is understandable that after the vehicle computer in this example broadcasts the next round of prompt voice, it continues to detect and activate the voice activity detection function of the second sound zone in the car to obtain the second voice generated in the second sound zone until multiple rounds of dialogue are completed and the sound zone lock mode is restored.

[0074] Therefore, the embodiment of the present disclosure can also determine the correlation between the prompt voice and the second voice, and thus achieve the technical effect of multi-person multi-round interaction in the sound zone locking mode under the guidance of the prompt voice, further improving the user experience.

[0075] In this embodiment, by acquiring a first voice generated in a first sound zone within the vehicle in the sound zone locked mode, wherein the first sound zone is the sound zone for waking up the voice assistant, and triggering a multi-person interaction mode in response to the first voice, acquiring a second voice generated in a second sound zone within the vehicle, determining a second intention of the second voice, and responding to the second intention when the second intention is determined to be related to the first intention, wherein the first intention is related to the first voice, it is possible to respond to the intention of not waking up the user based on the correlation between the second voice and the first voice when the sound zone is locked, thereby achieving the technical effect of multi-person interaction with the vehicle computer in the sound zone locked mode, thereby improving the user experience. In addition, the embodiment of the present disclosure can also determine the correlation between the prompt voice and the second voice, thereby achieving the technical effect of multi-person multi-round interaction in the sound zone locked mode under the guidance of the prompt voice, further improving the user experience.

[0076] In an optional example, FIG4 is a schematic diagram of the overall process of multi-round multi-person voice interaction provided according to an embodiment of the present disclosure. As shown in FIG4 , in the voice zone lock mode, the user in voice zone 1 first wakes up the voice assistant; further, the user in voice zone 1 says "Navigate to the mall" (first voice). In this case, it can be determined that the first voice triggers the multi-person interaction mode (i.e., multi-person voice transmission intention); further, the number of people is detected to determine that there are x people sitting in the car, and the microphone (mic) in the voice zone where x people are located is turned on to start multi-channel voice transmission, i.e., the second voice of multiple second voice zones is detected; further, the voice assistant replies "We have found multiple shopping malls for you, please select the number one" (i.e., prompt voice). Further, the user in voice zone 2 says "the first place" (second voice). In this In this case, it can be determined that the intention of the second voice is related to the intention of the broadcast voice, then the voice assistant can respond to the intention of the voice of the user in voice zone 2 and reply "3 paths found for you, please choose" (prompt voice). If the user in voice zone 3 is chatting with the user in voice zone 4 at this time, and it is detected that the speaking content is not a navigation multi-round intention, the voice will automatically refuse to be recognized; further, if it is detected that the user in voice zone 3 says "The first path, start navigation" (second voice), it can be determined that the second voice is related to the intention of the prompt voice, then respond to the second voice and reply "Okay, let's go"; in this case, the scene multi-round task is completed. In order to reduce interruptions, it automatically restores to listening only to the voice of the user in voice zone 1, and other voice zones are automatically blocked, that is: the voice zone lock mode is restored, and the entire process ends.

[0077] In order to implement the above embodiments, the present disclosure also proposes a voice interaction device.

[0078] FIG5 is a schematic diagram of a voice interaction device according to another embodiment of the present disclosure.

[0079] As shown in FIG5 , the voice interaction device 50 includes:

[0080] A first acquisition module 501 is configured to acquire a first voice generated in a first sound zone in a vehicle compartment in a sound zone locking mode;

[0081] A second acquisition module 502 is configured to, in response to the first voice triggering the multi-person interaction mode, acquire a second voice generated in a second sound zone in the vehicle compartment, and determine a second intention of the second voice; and

[0082] The response module 503 is configured to respond to the second intention when it is determined that the second intention is related to the first intention, wherein the first intention is related to the first voice.

[0083] In some embodiments, the voice interaction device 50 further includes: a detection module configured to detect the seating position information of the user in the vehicle; and an activation module configured to obtain a second voice generated in a second sound zone where the user is seated based on the seating position information.

[0084] In some embodiments, the second acquisition module 502 is further configured to: acquire a preset mapping table, wherein the mapping table records multiple keywords that trigger the multi-person interaction mode; and trigger the multi-person interaction mode in response to the first speech containing the keywords.

[0085] In some embodiments, the response module 503 is further configured to: respond to the second intent if the second intent is related to the first intent of the first speech.

[0086] In some embodiments, the voice interaction device 50 further includes: a playback module configured to play prompt voices of multiple rounds of interactions related to the intention of the first voice; and a response module 503 further configured to respond to the second intention when the second intention is related to the first intention of the prompt voice.

[0087] In some embodiments, the response module 503 is further configured to: when the multiple second intentions corresponding to the multiple second voices are related to the first intention, respond to the multiple second intentions in sequence according to the time sequence in which the multiple second voices are acquired.

[0088] In some embodiments, the second acquisition module 502 is further configured to: convert the second speech generated by each second sound zone into a target text through the speech recognition model configured for the second sound zone; and determine the second intention corresponding to the target text of the second sound zone through the semantic model configured for each second sound zone.

[0089] In some embodiments, the voice interaction device 50 further includes: a recovery module configured to exit the multi-person interaction mode when it is determined that the second intention response is completed.

[0090] In this embodiment, by obtaining the first voice generated in the first sound zone in the vehicle compartment in the sound zone locking mode, and triggering the multi-person interaction mode in response to the first voice, the second voice generated in the second sound zone in the vehicle compartment is obtained, and the second intention of the second voice is determined, and when it is judged that the second intention is related to the first intention, the second intention is responded to, wherein the first intention is related to the first voice, and when the sound zone is locked, the intention of the non-wake-up user can be responded to according to the correlation between the second voice and the first voice. Therefore, the technical effect of multi-person interaction with the vehicle computer in the sound zone locking mode can be achieved, thereby improving the user experience.

[0091] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0092] In order to implement the above embodiments, the present disclosure further proposes a computer program product. When the instruction processor in the computer program product is executed, the voice interaction method proposed in the above embodiments of the present disclosure is executed.

[0093] Figure 6 shows a block diagram of an exemplary electronic device suitable for implementing the embodiments of the present disclosure. The electronic device 12 shown in Figure 6 is only an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0094] 6 , electronic device 12 is implemented as a general-purpose computing device. Components of electronic device 12 may include, but are not limited to, one or more processors or processing units 16, system memory 28, and a bus 18 connecting various system components (including system memory 28 and processing unit 16).

[0095] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. Examples of these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnection (PCI) bus.

[0096] The electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 12, including volatile and non-volatile media, removable and non-removable media.

[0097] Memory 28 may include computer-readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Electronic device 12 may further include other removable / non-removable, volatile / non-volatile computer-readable storage media. By way of example only, storage system 34 may be configured to read and write to non-removable, non-volatile magnetic media (not shown in FIG. 6 , and commonly referred to as a "hard drive").

[0098] Although not shown in FIG6 , a disk drive for reading and writing to a removable non-volatile disk (e.g., a floppy disk) and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a Compact Disc Read Only Memory (CD-ROM), a Digital Video Disc Read Only Memory (DVD-ROM), or other optical media) can be provided. In these cases, each drive can be connected to the bus 18 via one or more data media interfaces. The memory 28 can include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of various embodiments of the present disclosure.

[0099] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may include an implementation of a network environment. Program modules 42 generally implement the functions and / or methods of the embodiments described herein.

[0100] The electronic device 12 can also communicate with one or more external devices 14 (e.g., a keyboard, pointing device, display 24, etc.), one or more devices that enable a user to interact with the electronic device 12, and / or any device that enables the electronic device 12 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). This communication can occur via an input / output (I / O) interface 22. Furthermore, the electronic device 12 can communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with other modules of the electronic device 12 via the bus 18. It should be understood that, although not shown, other hardware and / or software modules can be used in conjunction with the electronic device 12, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0101] The processing unit 16 executes various functional applications by running programs stored in the system memory 28, such as implementing the voice interaction method mentioned in the above embodiment.

[0102] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the following claims.

[0103] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

[0104] It should be noted that, in the description of this disclosure, the terms "first", "second", etc. are used for descriptive purposes only and should not be understood as indicating or implying relative importance. In addition, in the description of this disclosure, unless otherwise specified, the meaning of "plurality" is two or more.

[0105] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present disclosure includes additional implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present disclosure belong.

[0106] It should be understood that various parts of the present disclosure can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0107] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0108] In addition, the functional units in the various embodiments of the present disclosure may be integrated into a single processing module, or each unit may exist physically separately, or two or more units may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or in the form of software functional modules. If the integrated modules are implemented in the form of software functional modules and sold or used as independent products, they may also be stored in a computer-readable storage medium.

[0109] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0110] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in conjunction with that embodiment or example is included in at least one embodiment or example of the present disclosure. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0111] Although the embodiments of the present disclosure have been shown and described above, it is understood that the above embodiments are illustrative and are not to be construed as limitations on the present disclosure. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present disclosure. Industrial Applicability

[0112] By obtaining the first voice generated in the first sound zone in the car in the sound zone locking mode, wherein the first sound zone is the sound zone for waking up the voice assistant, and triggering the multi-person interaction mode in response to the first voice, obtaining the second voice generated in the second sound zone in the car, and determining the second intention of the second voice, and responding to the second intention when judging that the second intention is related to the first intention, wherein the first intention is related to the first voice, it is possible to respond to the intention of non-waking up the user according to the correlation between the second voice and the first voice when the sound zone is locked. Therefore, the technical effect of multi-person interaction with the vehicle computer in the sound zone locking mode can be achieved, thereby improving the user experience.

Claims

1. A voice interaction method, the method comprising: Acquire a first voice generated in a first sound zone in the vehicle compartment in the sound zone lock mode, wherein the first sound zone is a sound zone for waking up a voice assistant; In response to the first voice triggering a multi-person interaction mode, acquiring a second voice generated in a second sound zone in the vehicle compartment, and determining a second intention of the second voice; and In a case where it is determined that the second intention is related to the first intention, respond to the second intention, wherein the first intention is related to the first voice.

2. The method of claim 1, wherein: The obtaining of the second voice generated in the second sound zone in the vehicle compartment includes: Detecting the seating position information of the user in the vehicle compartment; and According to the seating position information, a second voice generated in the second sound zone where the user is seated is obtained.

3. The method of claim 1, wherein: The triggering of the multi-person interaction mode in response to the first voice comprises: Obtaining a preset mapping table, wherein the mapping table records a plurality of keywords that trigger the multi-person interaction mode; In response to the first intention of the first voice containing the keyword, the multi-person interaction mode is triggered.

4. The method of claim 1, wherein: The responding to the second intention when it is determined that the second intention is related to the first intention includes: In case the second intention is related to the first intention of the first voice, respond to the second intention.

5. The method of claim 1, wherein: Before acquiring the second voice generated in the second sound zone in the vehicle compartment, the method further includes: Playing prompt voices for multiple rounds of interactions related to the intent of the first voice; Furthermore, in a case where the second intent is related to the first intent, responding to the second intent includes: In case the second intention is related to the first intention of the prompt voice, respond to the second intention.

6. The method of claim 1, wherein: The responding to the second intention when it is determined that the second intention is related to the first intention includes: In the case that the multiple second intentions corresponding to the multiple second voices are related to the first intention, the multiple second intentions are responded to in sequence according to the time sequence in which the multiple second voices are acquired.

7. The method of claim 1, wherein: The determining the second intention of the second speech includes: Converting the second speech generated in the second sound zone into a target text through the speech recognition model configured in each second sound zone; and The second intention corresponding to the target text in the second sound zone is determined by using the semantic model configured for each of the second sound zones.

8. The method of claim 1, wherein: After responding to the second intention, the method further includes: When it is determined that the second intention response is completed, exit the multi-person interaction mode.

9. A voice interaction device, comprising: A first acquisition module is configured to acquire a first voice generated in a first sound zone in the vehicle compartment in a sound zone locking mode, wherein the first sound zone is a sound zone for waking up a voice assistant; A second acquisition module is configured to acquire a second voice generated in a second sound zone in the vehicle compartment in response to the first voice triggering a multi-person interaction mode, and determine a second intention of the second voice; and A response module is configured to respond to the second intention if it is determined that the second intention is related to the first intention, wherein the first intention is related to the first voice.

10. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 8.

11. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-8.

12. A vehicle comprising the electronic device according to claim 10.

13. A computer program product, comprising computer executable instructions or a computer program, wherein the computer executable instructions or the computer program, when executed by a processor, implements the voice interaction method described in any one of claims 1 to 8.

Images