Vehicle voice interaction method and device, electronic equipment and storage medium

Abstract

The invention relates to a vehicle voice interaction method and device, electronic equipment and a storage medium, voice data packets corresponding to at least two domain controllers in a vehicle are obtained, the voice data packets are data packets generated by the domain controllers according to user voice, and the voice data packets comprise sound intensity information and phase difference information; according to the sound intensity information and the phase difference information, sound area positioning is carried out, a target sound area is determined, an initial voice signal is extracted from a target voice data packet corresponding to the target sound area, the target voice data packet is a voice data packet generated by a target domain controller corresponding to the target sound area, and then an execution domain controller is determined based on the initial voice signal. According to the vehicle voice interaction method and device, the user voice is responded through the execution domain controller, the vehicle voice interaction result is obtained, the voice interaction response accuracy can be effectively improved, and the problem that in the prior art, the voice interaction response accuracy is low is solved.

Description

Technical Field

[0001] The present invention relates to the field of automobile technology, and in particular to a vehicle voice interaction method, device, electronic equipment and storage medium. Background Art

[0002] With the continuous development of vehicle technology, most vehicles nowadays are equipped with voice interaction functions in the vehicle cockpit in order to realize the intelligent cockpit. Voice interaction technology plays a vital role in the vehicle intelligent cockpit. However, the traditional in-vehicle voice interaction function mainly relies on the layout of a single or a small number of microphones. Under this layout, the in-vehicle voice interaction partition mostly relies on complex acoustic models and a large amount of computing resources, which makes it difficult to achieve a good balance between real-time and accuracy. Especially in multi-seat models such as large sports utility vehicles (SUV) or multi-purpose vehicles (MPV), voice signals between different seats are prone to interfere with each other, resulting in a high error rate in voice recognition and affecting the accuracy of voice interaction response. Summary of the invention

[0003] The present application provides a vehicle voice interaction method, device, electronic device and storage medium to solve the problem of low voice interaction response accuracy caused by mutual interference of voice signals between different seats in the existing related technology.

[0004] In a first aspect, the present application provides a vehicle voice interaction method, comprising:

[0005] Acquire voice data packets corresponding to at least two domain controllers in the vehicle, wherein the voice data packets are data packets generated by the domain controllers according to user voices, and the voice data packets contain sound intensity information and phase difference information;

[0006] Performing sound zone positioning according to the sound intensity information and the phase difference information to determine a target sound zone, where the target sound zone is the sound zone to which the user voice belongs;

[0007] Extracting an initial voice signal from a target voice data packet corresponding to the target voice zone, wherein the target voice data packet is a voice data packet generated by a target domain controller corresponding to the target voice zone;

[0008] Based on the initial voice signal, determining an execution domain controller;

[0009] The execution domain controller responds to the user voice and obtains the vehicle voice interaction result.

[0010] Optionally, performing sound zone positioning according to the sound intensity information and the phase difference information to determine a target sound zone includes:

[0011] Determining whether the phase difference information meets a preset phase difference condition;

[0012] In the case where the phase difference information meets the preset phase difference condition, determining whether the sound intensity information meets the preset sound intensity condition;

[0013] When the sound intensity information meets a preset sound intensity condition, determining the voice data packet corresponding to the sound intensity information as a target voice data packet;

[0014] The sound zone to which the target voice data packet belongs is determined as the target sound zone.

[0015] Optionally, performing sound zone positioning according to the sound intensity information and the phase difference information to determine a target sound zone includes:

[0016] Determining whether the sound intensity information meets a preset sound intensity condition;

[0017] In the case where the sound intensity information meets the preset sound intensity condition, determining whether the phase difference information meets the preset phase difference condition;

[0018] In a case where the phase difference information meets the preset phase difference condition, determining the voice data packet corresponding to the phase difference information as a target voice data packet;

[0019] The sound zone to which the target voice data packet belongs is determined as the target sound zone.

[0020] Optionally, determining whether the phase difference information meets a preset phase difference condition includes:

[0021] Determining a phase difference value of the phase difference information;

[0022] Determining whether the phase difference value is within a preset phase difference range;

[0023] When the phase difference value is within the preset phase difference range, determining that the phase difference information meets the preset phase difference condition;

[0024] When the phase difference value is not within the preset phase difference range, it is determined that the phase difference information does not meet the preset phase difference condition.

[0025] Optionally, determining whether the sound intensity information meets a preset sound intensity condition includes:

[0026] Determine a sound intensity value of each of the sound intensity information;

[0027] Determining whether the sound intensity value is a maximum sound intensity value;

[0028] When the sound intensity value is the maximum sound intensity value, determining that the sound intensity information meets the preset sound intensity condition;

[0029] When the sound intensity value is not the maximum sound intensity value, it is determined that the sound intensity information does not meet the preset sound intensity condition.

[0030] Optionally, determining an execution domain controller based on the initial voice signal includes:

[0031] Performing speech processing based on the initial speech signal to obtain target speech information;

[0032] Converting the target voice information into text to obtain target text information;

[0033] Extracting keywords from the target text information to obtain a keyword set;

[0034] The execution domain controller is determined according to the keyword set.

[0035] Optionally, extracting keywords from the target text information to obtain a keyword set includes:

[0036] Extracting keywords from the target text information to obtain at least one keyword;

[0037] Determine a keyword tag corresponding to the keyword;

[0038] The keyword set is generated according to the keywords and the keyword tags.

[0039] Optionally, determining the execution domain controller according to the keyword set includes:

[0040] Determining whether there is a directional word in the keyword set;

[0041] In the case that the directional word does not exist in the keyword set, determining the domain controller in the target pronunciation zone as the execution domain controller;

[0042] When the directional word exists in the keyword set, the domain controller corresponding to the directional word is determined as the execution domain controller.

[0043] Optionally, the acquiring of voice data packets corresponding to at least two domain controllers in the vehicle includes:

[0044] Acquiring, by the domain controller, the user voice collected by a sound receiving device in the vehicle;

[0045] According to the user voice acquired by each domain controller, the voice data packet corresponding to each domain controller is generated.

[0046] Optionally, the executing domain controller responds to the user voice to obtain a vehicle voice interaction result, including:

[0047] Generate a control instruction according to the keyword set corresponding to the user voice;

[0048] The control instruction is sent to the execution domain controller, and the execution domain controller performs a control operation in response to the control instruction to obtain control operation information;

[0049] The vehicle voice interaction result is generated according to the control operation information.

[0050] In a second aspect, the present application provides a vehicle voice interaction device, characterized in that it includes:

[0051] An acquisition module, used to acquire voice data packets corresponding to at least two domain controllers in the vehicle, wherein the voice data packets are data packets generated by the domain controller according to the user's voice, and the voice data packets contain sound intensity information and phase difference information;

[0052] A first determination module is used to perform sound zone positioning according to the sound intensity information and the phase difference information, and determine a target sound zone, where the target sound zone is the sound zone to which the user voice belongs;

[0053] An extraction module, used to extract an initial voice signal from a target voice data packet corresponding to the target voice zone, wherein the target voice data packet is a voice data packet generated by a target domain controller corresponding to the target voice zone;

[0054] A second determination module, configured to determine an execution domain controller based on the initial voice signal;

[0055] The response module is used to respond to the user voice through the execution domain controller to obtain the vehicle voice interaction result.

[0056] In a third aspect, an electronic device is provided, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0057] Memory, used to store computer programs;

[0058] The processor is used to implement the vehicle voice interaction method described in any one of the first aspects when executing the program stored in the memory.

[0059] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the vehicle voice interaction method as described in any one of the first aspects is implemented.

[0060] In a fifth aspect, a vehicle is provided, comprising the vehicle voice interaction device described in the second aspect.

[0061] The embodiment of the present application obtains voice data packets corresponding to at least two domain controllers in the vehicle, the voice data packets are data packets generated by the domain controller according to the user voice, and the voice data packets contain sound intensity information and phase difference information, so as to locate the sound zone according to the sound intensity information and the phase difference information, determine the target sound zone, the target sound zone is the sound zone to which the user voice belongs, and extract the initial voice signal from the target voice data packet corresponding to the target sound zone, the target voice data packet is the voice data packet generated by the target domain controller corresponding to the target sound zone, and then determine the execution domain controller based on the initial voice signal, respond to the user voice through the execution domain controller, and obtain the vehicle voice interaction result, thereby utilizing the sound intensity information and the phase difference information to locate the sound zone, and then adaptively determine the execution domain controller and respond, avoiding the problem of low accuracy of voice interaction response caused by mutual interference of voice signals between different seats in the existing related technology, and can effectively improve the accuracy of voice interaction response. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 A flow chart of a vehicle voice interaction method provided in an embodiment of the present application;

[0063] Figure 2 A schematic diagram of an application scenario of a vehicle voice interaction method provided in an embodiment of the present application;

[0064] Figure 3 A schematic diagram of another application scenario of a vehicle voice interaction method provided in an embodiment of the present application;

[0065] Figure 4 A schematic diagram of the structure of a vehicle voice interaction device provided in an embodiment of the present application;

[0066] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0067] The following will describe the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention, not for limiting the scope of protection of the present invention.

[0068] With the realization of intelligent vehicle cockpits, most users have become accustomed to controlling the vehicle through voice interaction in the vehicle, such as air conditioning adjustment, seat control, speaker control, etc., and the process of vehicle voice interaction in specific usage scenarios relies on the layout of a single or a small number of microphones. Under this layout, the voice interaction zoning in the vehicle mostly relies on complex acoustic models and a large amount of computing resources, that is, there is interference between voice signals between different seats, resulting in high difficulty in voice recognition; in addition, during specific voice interaction, there is often a need to control other areas. For example, when there is no one sitting in the back row, the front row occupants may want to turn off the air conditioning in the back row. At this time, due to the voice positioning in the front row, the voice can only control the front row air conditioning, and the rear row air conditioning cannot be directly controlled to turn off, that is, there is a problem of low flexibility in voice interaction.

[0069] In order to solve the problem of low accuracy of voice interaction response caused by mutual interference of voice signals between different seats in the existing related technology, the present application provides a vehicle voice interaction method, device, electronic device and storage medium, by obtaining voice data packets corresponding to at least two domain controllers in the vehicle, the voice data packets are data packets generated by the domain controller according to the user's voice, and the voice data packets contain sound intensity information and phase difference information, so as to locate the sound zone according to the sound intensity information and the phase difference information, determine the target sound zone, the target sound zone is the sound zone to which the user's voice belongs, and extract the initial voice signal from the target voice data packet corresponding to the target sound zone, the target voice data packet is the sound zone corresponding to the target sound zone, The voice data packet generated by the target domain controller determines the execution domain controller based on the initial voice signal. Therefore, compared with simple sound positioning, the present application can control different areas according to the initial voice signal by determining the matching execution domain controller, thereby improving the flexibility of voice interaction; then, the execution domain controller responds to the user's voice and obtains the vehicle voice interaction result, thereby utilizing the sound intensity information and phase difference information for sound zone positioning, and then adaptively determining the execution domain controller and responding, avoiding the problem of low accuracy of voice interaction response caused by mutual interference of voice signals between different seats in the existing related technology, and can effectively improve the accuracy of voice interaction response.

[0070] Figure 1A flow chart of a vehicle voice interaction method provided for an embodiment of the present application. This method can be applied to one or more electronic devices such as vehicles, clients, servers, etc. In addition, the execution subject of this method can be hardware or software. When the above-mentioned execution subject is hardware, the execution subject can be one or more of the above-mentioned electronic devices. For example, a single electronic device can execute this method, or multiple electronic devices can cooperate with each other to execute this method. When the above-mentioned execution subject is software, this method can be implemented as multiple software or software modules, or as a single software or software module. No specific limitation is made here.

[0071] like Figure 1 As shown, a vehicle voice interaction method provided by an embodiment of the present application may specifically include the following steps:

[0072] Step 110: Acquire voice data packets corresponding to at least two domain controllers in the vehicle. The voice data packets are data packets generated by the domain controllers according to user voices. The voice data packets contain sound intensity information and phase difference information.

[0073] Among them, the domain controller in this embodiment is a controller configured in the vehicle for controlling vehicle functions, and the voice data packet may be a data packet generated by the domain controller based on the user voice. The voice data packet may include but is not limited to sound intensity information and phase difference information. The user voice refers to the voice spoken by the user in the vehicle, and may also be the voice spoken by the user after saying the wake-up word, or the voice spoken by the user after turning on the voice collection function. This embodiment does not make specific limitations on this; the sound intensity information may indicate the information on the sound intensity corresponding to the user voice, and the phase difference information may indicate the phase difference of the user voice at each frequency point.

[0074] It should be noted that, in this embodiment, the domain controllers in the vehicle may include at least two, and the domain controllers may be configured according to the cabin division in the vehicle. For example, the vehicle cabin may be divided into four cabin areas: left front cabin, right front cabin, left rear cabin, and right rear cabin. At the same time, the four cabin areas correspond to a sound zone respectively, and each sound zone is equipped with a corresponding sound receiving device and a domain controller. Therefore, when a user speaks in the vehicle, each domain controller can collect the user's voice and generate a voice data packet based on it. Of course, the above division method is only an example for explanation. The specific division method can be adaptively adjusted according to needs and scenarios, and this embodiment does not make specific limitations on this.

[0075] Step 120: Perform voice zone positioning according to the sound intensity information and the phase difference information to determine a target voice zone, where the target voice zone is the voice zone to which the user's voice belongs.

[0076] Specifically, after obtaining the voice data packet corresponding to each domain controller, sound intensity information and phase difference information can be extracted from each voice data packet, so that sound zone positioning can be performed based on the sound intensity information and phase difference information to determine the target sound zone, where the target sound zone is the sound zone to which the user's voice belongs, wherein sound zone positioning refers to the process of determining the sound zone to which the user's voice currently belongs based on the sound intensity information and phase difference information, and the sound zone can be the area obtained by pre-dividing the vehicle cabin.

[0077] In one example, if Figure 2 As shown, the central computing unit can be the execution subject of the vehicle voice interaction method of the present application, and the vehicle cockpit can be divided into four cockpit areas: left front cockpit, right front cockpit, left rear cockpit, and right rear cockpit. At the same time, each of the four cockpit areas corresponds to a sound zone, such as Figure 2 As shown in the audio zone 1, audio zone 2, audio zone 3, and audio zone 4, each audio zone may be configured with a corresponding domain controller and a sound receiving device, so that the sound receiving device in each audio zone can collect voices, and the domain controller in each audio zone may generate a voice data packet according to the user voice collected by the sound receiving device in the audio zone. Of course, the division may be performed according to the requirements, and this embodiment does not specifically limit this.

[0078] In addition, in the present embodiment, the distance between the sound receiving devices is greater than the first preset distance and less than the second preset distance, and the first preset distance is less than the second preset distance. For example, the first preset distance is 0.3 meters and the second preset distance is 2 meters. The distance between the sound receiving devices greater than the first preset distance can reduce mutual interference between the sound receiving devices and improve positioning accuracy, while the distance between the sound receiving devices less than the second preset distance can ensure that the collected voice signals have sufficient phase difference information.

[0079] Step 130: extracting an initial voice signal from a target voice data packet corresponding to the target voice zone, where the target voice data packet is a voice data packet generated by a target domain controller corresponding to the target voice zone.

[0080] Specifically, after determining the target sound zone, the initial voice signal can be extracted from the target voice data packet corresponding to the target sound zone. The target voice data packet can represent the voice data packet generated by the target domain controller corresponding to the target sound zone, and the initial voice signal can represent the voice signal obtained based on the user voice collection, that is, each voice data packet can include but is not limited to sound intensity information, phase difference information and initial voice signal.

[0081] It can be seen that in this embodiment, the sound zone is located through the sound intensity information and the phase difference information to determine the target sound zone to which the user's voice belongs, and then the initial voice signal is extracted from the target voice data packet corresponding to the target sound zone, thereby obtaining the clearest initial voice signal of the user's voice. For example, when the vehicle cabin is divided into four cabin areas: the left front cabin, the right front cabin, the left rear cabin, and the right rear cabin, and the four cabin areas correspond to a sound zone respectively, the user makes an interactive voice with the vehicle in the right rear cabin. At this time, the voice collection method in the existing related technology is adopted, that is, a fixed single or a small number of microphones are used to collect the voice in the car. At this time, the collected voice may be unclear because the microphone is far away from the right rear cabin, or because of the interference of the communication sounds of other cabin occupants in the car, resulting in a problem of chaotic voice collection and difficulty in recognition. In this embodiment, By determining the target sound zone, it can be determined that the sound zone where the user emits interactive voice is the sound zone corresponding to the right rear cockpit. At this time, the target voice data packet generated by the domain controller corresponding to the right rear cockpit is obtained, and then the initial voice signal is extracted from the target voice data packet. Since the target voice data packet generated by the domain controller corresponding to the right rear cockpit is generated based on the user voice collected by the sound receiving device corresponding to the right rear cockpit, the initial voice signal in the target voice data packet is a signal containing the clearest user voice, thereby solving the problem of unclear voice collection due to the microphone being far away from the position where the user emits voice, and the problem of chaotic voice collection and difficulty in recognition due to interference from the voices of other cabin personnel. The voice signal collected at the position closest to the position where the user emits voice can be obtained, thereby greatly reducing the interference from the voices of other cabin personnel communicating, and achieving the purpose of obtaining the clearest initial voice signal of the user voice.

[0082] Step 140: Determine an execution domain controller based on the initial voice signal.

[0083] Specifically, after obtaining the initial voice signal, the execution domain controller can be determined based on the initial voice signal. The execution domain controller indicates the domain controller that needs to respond to and execute the operation corresponding to the user voice. Since multiple audio zones and domain controllers corresponding to the audio zones can be configured in the vehicle, the execution domain controller determined at this time can be the domain controller corresponding to the target audio zone, or it can be the domain controller corresponding to other audio zones outside the target audio zone. This embodiment does not make specific limitations on this.

[0084] It can be seen that in this embodiment, the domain controller corresponding to the target sound zone, or the domain controllers corresponding to other sound zones outside the target sound zone can be determined as the execution domain controller through the initial voice signal, thereby solving the problem of low flexibility of voice interaction in the related technology that the vehicle equipment at the location of the user's voice can only be controlled through voice positioning, such as the voice emitted in the front row can only control the front row air-conditioning, and the execution domain controller can be adaptively determined according to the initial voice signal, and the operation corresponding to the user voice can be executed through the domain controller response. For example, if the initial voice signal for controlling the rear row air-conditioning is emitted in the front row, the domain controller corresponding to the rear row can be determined as the execution domain controller. The rear row air-conditioning is controlled by the execution domain controller, thereby achieving the effect of improving the flexibility of voice interaction.

[0085] Step 150: The domain controller is executed to respond to the user's voice and obtain the vehicle voice interaction result.

[0086] Specifically, after determining the execution domain controller, the execution domain controller can be used to respond to the user voice and obtain the vehicle voice interaction result, where the response to the user voice can be the operation corresponding to the execution of the user voice, such as adjusting the air conditioner, adjusting the seat, etc., and the vehicle voice interaction result can represent the execution result of the execution domain controller, such as the execution completion result, the unable to execute result, the execution failure result, etc.

[0087] It can be seen that in this embodiment, by acquiring voice data packets corresponding to at least two domain controllers in the vehicle, the voice data packets are data packets generated by the domain controller according to the user voice, and the voice data packets contain sound intensity information and phase difference information, so as to perform sound zone positioning according to the sound intensity information and the phase difference information, determine the target sound zone, the target sound zone is the sound zone to which the user voice belongs, and extract the initial voice signal from the target voice data packet corresponding to the target sound zone, the target voice data packet is the voice data packet generated by the target domain controller corresponding to the target sound zone, and determine the execution domain controller based on the initial voice signal, which plays the role of determining the target sound zone through sound zone positioning, and obtaining the clearest initial voice signal of the user voice from the target voice data packet corresponding to the target sound zone; then, the execution domain controller responds to the user voice, obtains the vehicle voice interaction result, and thus determines the execution domain controller matched with the user voice, which can play the role of controlling different areas of different vehicles according to the initial voice signal, that is, the sound zone positioning is performed by using the sound intensity information and the phase difference information, and then the execution domain controller is adaptively determined and responded, which avoids the problem of low accuracy of voice interaction response caused by mutual interference of voice signals between different seats in the existing related technology, can effectively improve the accuracy of voice interaction response, and improve the flexibility of voice interaction.

[0088] In addition, in this embodiment, by determining the target sound zone to which the user voice belongs, the function of obtaining the clearest initial voice signal of the user voice is achieved, and the execution domain controller is determined to determine the execution domain controller that matches the user voice, thereby controlling different areas of the vehicle according to the initial voice signal; that is, the two aspects of intermediate user voice positioning and domain controller determination for responding to the user voice to perform operations in this application are executed separately. Compared with the existing related technology, the user positioning and the response to the user voice are combined for execution, which can achieve the effect of improving the accuracy and efficiency of voice interaction.

[0089] In the existing related technologies, in the process of locating the vehicle user's voice, positioning is usually based on the position of the microphone or the intensity of the user's voice. However, in the process of locating the microphone position or the intensity of the user's voice, it will be limited by other ambient sounds and the microphone's pickup ability. For example, the voices of other people communicating in the car, media sounds, and the short microphone pickup distance will affect the accuracy of user voice positioning, that is, there is a problem of low user voice positioning accuracy.

[0090] In an optional embodiment of the present application, sound zone positioning is performed based on sound intensity information and phase difference information to determine a target sound zone, which may specifically include the following sub-steps: determining whether the phase difference information meets a preset phase difference condition; if the phase difference information meets the preset phase difference condition, determining whether the sound intensity information meets the preset sound intensity condition; if the sound intensity information meets the preset sound intensity condition, determining the voice data packet corresponding to the sound intensity information as the target voice data packet; and determining the sound zone to which the target voice data packet belongs as the target sound zone.

[0091] In this embodiment, after extracting the sound intensity information and the phase difference information from the voice data packet, it can be determined whether the phase difference information meets the preset phase difference condition. The preset phase difference condition can represent a pre-configured condition for determining whether the phase difference information meets the requirement. The preset phase difference condition can be a pre-configured phase difference range, a phase difference threshold, and other conditions. If the phase difference information does not meet the preset phase difference condition, there is no need to perform subsequent steps. If the phase difference information meets the preset phase difference condition, it can be determined whether the sound intensity information meets the preset sound intensity condition. The preset sound intensity condition can represent a pre-configured condition for determining whether the sound intensity information meets the requirement. The preset sound intensity condition can be a pre-configured sound intensity condition. range, sound intensity threshold and other conditions. When the sound intensity information meets the preset sound intensity conditions, there is no need to execute subsequent steps. When the sound intensity information meets the preset sound intensity conditions, the voice data packet corresponding to the sound intensity information can be determined as the target voice data packet, and the sound zone to which the target voice data packet belongs can be determined as the target sound zone. Specifically, the target domain controller corresponding to the target voice data packet can be determined. The target domain controller can be the domain controller that generates the target voice data. According to the pre-configured sound zone division information, the sound zone to which the target domain controller belongs is determined as the target sound zone, and the pre-configured sound zone division information can represent information including the corresponding division relationship between the sound zone and the domain controller.

[0092] In addition, since the present embodiment may include voice data packets generated by multiple domain controllers, that is, the aforementioned steps may be performed for the sound intensity information and phase difference information contained in each voice data packet, so as to perform sound zone positioning through the voice data packets generated by the domain controllers in multiple sound zones, and determine the target sound zone to which the user voice belongs. In the process of sound zone positioning, the sound intensity information and the phase difference information are combined for judgment and determination, which solves the problem of low accuracy of user voice positioning in the related art that positioning is performed only based on the position of the microphone or the intensity of the user voice, and can effectively improve the accuracy of user voice positioning.

[0093] In one example, in the process of using sound intensity information and phase difference information to locate the sound zone, the relationship between the phase difference information and the sound zone positioning is: when the sound wave propagates from the sound source to different positions, the user voice collected by different sound receiving devices will arrive at different sound receiving device positions at different times due to the difference in propagation paths, thereby generating a phase difference, and thus the phase difference information can be used to infer the position of the sound source; the specific sound zone positioning method can use an algorithm to process the measured phase difference information to estimate the arrival direction (including azimuth and pitch angle) and distance of the sound source relative to the sound receiving device. Common algorithms include methods based on relative delay estimation such as the GCC-PHAT (Generalized Cross Correlation-Phase Transform) algorithm, beamforming-based methods such as the Steered Response Power with Phase Transform (SRP-PHAT) algorithm, and signal subspace-based methods such as the Multiple Signal Classification (MUSIC) algorithm, etc., which are not specifically limited in this embodiment. Phase difference information can play a role in locating the sound zone. This is because the various sound receiving devices in the car are at a certain distance from each other. At this time, the result of the sound zone positioning is very likely to be located between the two sound zones. Therefore, in this embodiment, sound intensity information is also added for calibration, so that accurate positioning of the sound zone can be achieved. It should be noted that the accuracy of sound zone positioning can be greatly improved by performing sound zone positioning from the two dimensions of phase difference information or sound intensity information. If only phase difference information or sound intensity information (the difference between the two extreme values ​​is very small) is used, positioning errors may occur, or the sound zones cannot be clearly distinguished. For example, the sound zone is positioned using phase difference information, and the sound source is located in the left front and left rear areas. Combined with the strongest sound intensity information, it can be locked in the left rear, thereby effectively improving the accuracy of user voice positioning. Of course, the above division method is only an example for illustration. The specific division method can be adaptively adjusted according to needs and scenarios, and this embodiment does not make specific limitations on this.

[0094] In an optional embodiment of the present application, sound zone positioning is performed based on sound intensity information and phase difference information to determine a target sound zone, which may specifically include the following sub-steps: determining whether the sound intensity information meets a preset sound intensity condition; if the sound intensity information meets the preset sound intensity condition, determining whether the phase difference information meets the preset phase difference condition; if the phase difference information meets the preset phase difference condition, determining the voice data packet corresponding to the phase difference information as the target voice data packet; and determining the sound zone to which the target voice data packet belongs as the target sound zone.

[0095] In this embodiment, after extracting the sound intensity information and the phase difference information from the voice data packet, it can be determined whether the sound intensity information meets the preset sound intensity condition. The preset sound intensity condition can represent a pre-configured condition for determining whether the sound intensity information meets the requirement. The preset sound intensity condition can be a pre-configured sound intensity range, a sound intensity threshold, and other conditions. If the sound intensity information does not meet the preset sound intensity condition, then there is no need to perform subsequent steps. If the sound intensity information meets the preset sound intensity condition, then it can be determined whether the phase difference information meets the preset phase difference condition. The preset phase difference condition can represent a pre-configured condition for determining whether the phase difference information meets the requirement. The preset phase difference condition can be a pre-configured condition for determining whether the phase difference information meets the requirement. The configured phase difference range, phase difference threshold and other conditions, when the phase difference information meets the preset phase difference conditions, there is no need to execute subsequent steps; and when the phase difference information meets the preset phase difference conditions, the voice data packet corresponding to the phase difference information can be determined as the target voice data packet, and the sound zone to which the target voice data packet belongs can be determined as the target sound zone, specifically, the target domain controller corresponding to the target voice data packet can be determined, the target domain controller can be the domain controller that generates the target voice data, and according to the pre-configured sound zone division information, the sound zone to which the target domain controller belongs is determined as the target sound zone, and the pre-configured sound zone division information can represent information containing the corresponding division relationship between the sound zone and the domain controller.

[0096] In addition, since the present embodiment may include voice data packets generated by multiple domain controllers, the aforementioned steps may be performed for the phase difference information and sound intensity information contained in each voice data packet, thereby performing sound zone positioning through the voice data packets generated by the domain controllers in multiple sound zones, and determining the target sound zone to which the user's voice belongs. In the process of sound zone positioning, the phase difference information and the sound intensity information are combined for judgment and determination, which solves the problem of low accuracy of user voice positioning in the related art that positioning is performed only based on the position of the microphone or the intensity of the user's voice, and can effectively improve the accuracy of user voice positioning.

[0097] In an optional embodiment of the present application, determining whether the phase difference information meets the preset phase difference condition may specifically include the following sub-steps: determining the phase difference value of the phase difference information; judging whether the phase difference value is within the preset phase difference range; if the phase difference value is within the preset phase difference range, determining that the phase difference information meets the preset phase difference condition; if the phase difference value is not within the preset phase difference range, determining that the phase difference information does not meet the preset phase difference condition.

[0098] In this embodiment, in the process of determining whether the phase difference information meets the preset phase difference condition, the phase difference value of the phase difference information can be determined. The phase difference value can represent the phase difference of the user voice at each frequency point. Then, it can be determined whether the phase difference value is within the preset phase difference range. The preset phase difference range represents a pre-configured phase difference range that meets the requirements. When the phase difference value is within the preset phase difference range, it means that the current phase difference information meets the preset requirements. At this time, it can be determined that the phase difference information meets the preset phase difference condition. When the phase difference value is not within the preset phase difference range, it means that the current phase difference information does not meet the preset requirements. At this time, it can be determined that the phase difference information does not meet the preset phase difference condition.

[0099] In addition, in addition to determining whether the phase difference information meets the preset phase difference conditions through a preset phase difference range, other methods may be used to determine whether the phase difference information meets the preset phase difference conditions, such as a neural network model, a prediction algorithm, other pre-configured phase difference reference information, etc. This embodiment does not make any specific limitations on this.

[0100] In an optional embodiment of the present application, determining whether the sound intensity information meets the preset sound intensity condition may specifically include the following sub-steps: determining the sound intensity value of each sound intensity information; judging whether the sound intensity value is the maximum sound intensity value; if the sound intensity value is the maximum sound intensity value, determining that the sound intensity information meets the preset sound intensity condition; if the sound intensity value is not the maximum sound intensity value, determining that the sound intensity information does not meet the preset sound intensity condition.

[0101] In this embodiment, in the process of determining whether the sound intensity information meets the preset sound intensity condition, the sound intensity value of each sound intensity information can be determined, and the sound intensity value can represent the sound intensity of the user's voice. Then, it can be determined that the sound intensity value is the maximum sound intensity value. The maximum sound intensity value indicates that there is no sound intensity value greater than the sound intensity value. When the sound intensity value is the maximum sound intensity value, it means that the current sound intensity information meets the preset requirements. At this time, it can be determined that the sound intensity information meets the maximum sound intensity value condition. When the sound intensity value is not the maximum sound intensity value, it means that the current sound intensity information does not meet the preset requirements. At this time, it can be determined that the sound intensity information does not meet the maximum sound intensity value condition. The specific method of determining whether the sound intensity value is the maximum sound intensity value can be determined by traversal comparison, function model, etc., and this embodiment does not make specific limitations on this.

[0102] In addition, in addition to determining whether the sound intensity information meets the preset sound intensity conditions through the maximum sound intensity value, other methods may be used to determine whether the sound intensity information meets the preset sound intensity conditions, such as a neural network model, a prediction algorithm, other pre-configured sound intensity reference information, etc., wherein other pre-configured sound intensity reference information may be a sound intensity range, a sound intensity threshold, etc., which is not specifically limited in this embodiment.

[0103] In an optional implementation of the present application, an execution domain controller is determined based on an initial voice signal, which may specifically include the following sub-steps: performing voice processing based on the initial voice signal to obtain target voice information; converting the target voice information into text to obtain target text information; extracting keywords from the target text information to obtain a keyword set; and determining an execution domain controller based on the keyword set.

[0104] In this embodiment, after obtaining the initial voice signal, voice processing can be performed based on the initial voice signal to obtain target voice information, wherein the voice processing can include but is not limited to denoising, endpoint detection, elimination, anti-aliasing filtering, voice enhancement and other processing, and the target voice information indicates that the voice processing is completed to obtain clear and clean voice information, so that the target voice information can be converted into text to obtain target text information, and the target text information can represent the text information contained in the target voice information. The text conversion method can be a neural network model, a speech recognition algorithm and the like, and this embodiment does not make specific limitations on this; thereby, keywords can be extracted from the target text information to obtain a keyword set, and the keyword set represents a set of keywords extracted from the target text information, and keyword extraction can be word segmentation, part-of-speech tagging, keyword matching and other processing of the text corresponding to the target text information, and the specific implementation can use convolutional neural network (CNN), deep neural network (DNN), recurrent neural network (RNN) and the like to extract keywords; and then the execution domain controller can be determined based on the keyword set.

[0105] In an optional implementation of the present application, keyword extraction is performed on the target text information to obtain a keyword set, which may specifically include the following sub-steps: keyword extraction is performed on the target text information to obtain at least one keyword; determining the keyword tag corresponding to the keyword; and generating a keyword set based on the keywords and keyword tags.

[0106] In this embodiment, during the keyword extraction process, keyword extraction can be performed on the target text information to obtain at least one keyword. The keyword extraction can be to extract characters, words, etc. in the target text information that meet pre-configured keyword conditions. The pre-configured keyword conditions can be a keyword library or a keyword judgment strategy, etc. This embodiment does not make specific limitations on this; thereby, the keyword tag corresponding to the keyword can be determined, and the keyword tag represents a tag obtained by classifying the keyword. The tag can be pre-configured, and specifically can include but is not limited to directional word tags, noun tags, verb tags, operation tags, etc.; and then a keyword set can be generated based on the keywords and keyword tags. Specifically, all keywords and their corresponding keyword tags can be integrated to generate a keyword set.

[0107] In the existing related technologies, when performing vehicle voice interaction to control the execution of related functions, the execution functions are usually controlled by a pre-configured domain controller. At this time, there is a problem of low flexibility in voice interaction. For example, when the user needs to control the needs of other areas, such as when there is no one sitting in the back row, the front row passengers may want to turn off the air conditioning in the back row. At this time, due to the voice positioning in the front row, the voice can only control the front row air conditioning, and cannot directly control the turn off of the back row air conditioning, that is, there is a problem of low flexibility in voice interaction.

[0108] In an optional implementation of the present application, the execution domain controller is determined based on a keyword set, which may specifically include the following sub-steps: determining whether there is a directional word in the keyword set; if there is no directional word in the keyword set, determining the domain controller in the target sound area as the execution domain controller; if there is a directional word in the keyword set, determining the domain controller corresponding to the directional word as the execution domain controller.

[0109] In this embodiment, in the process of determining the execution domain controller, it can be determined whether there is a directional word in the keyword set. The directional word refers to a word used to describe the location where the operation needs to be performed, such as left rear, right rear, co-pilot seat, etc. If there is no directional word in the keyword set, there is no need to consider controlling other areas. The domain controller in the target sound zone can be directly determined as the execution domain controller. If there is a directional word in the keyword set, it means that other areas outside the target sound zone need to be controlled at this time. At this time, the domain controller corresponding to the directional word can be determined as the execution domain controller. For example, when the directional word is left rear, the domain controller corresponding to the left rear position can be determined as the execution domain controller.

[0110] It can be seen that in the process of determining the execution domain controller based on the keyword set in this embodiment, different strategies for determining the execution domain controller can be adopted by determining whether there is a directional word in the keyword set, that is, to satisfy the user in different situations and determine a domain controller that meets the user's needs as the execution domain controller. For example, when the user says "lower the air-conditioning temperature" in the co-pilot area, the sound zone where the co-pilot area is located can be determined as the target sound zone through sound zone positioning. However, there is no directional word in the keyword set, which means that the user does not need to adjust the air-conditioning temperature in other areas. At this time, the domain controller corresponding to the target sound zone can be directly used as the execution domain controller, and the air-conditioning temperature of the co-pilot area can be controlled through the execution domain controller; and when the user says "lower the air-conditioning temperature" in the co-pilot area The user says "lower the air-conditioning temperature in the right rear row" in the domain. At this time, the sound zone where the co-pilot area is located can be determined as the target sound zone through sound zone positioning, and the directional word "right rear" exists in the keyword set, indicating that the user needs to adjust the air-conditioning temperature in other sound zones outside the target sound zone. At this time, the domain controller corresponding to the sound zone to which the right rear belongs can be used as the execution domain controller, and then the air-conditioning temperature in the sound zone to which the right rear belongs can be controlled by the execution domain controller; thereby solving the problem of low flexibility of voice interaction in related technologies, and being able to adaptively determine the accurate execution domain controller according to whether there is a directional word in the user's voice keyword set, thereby accurately controlling the vehicle control at the corresponding position through the domain controller, and effectively improving the flexibility of voice interaction.

[0111] In an optional implementation of the present application, obtaining voice data packets corresponding to at least two domain controllers in a vehicle may specifically include the following sub-steps: obtaining user voices collected by a sound receiving device in the vehicle through the domain controller; and generating voice data packets corresponding to each domain controller based on the user voices obtained by each domain controller.

[0112] In this embodiment, in the process of obtaining voice data corresponding to at least two domain controllers in the vehicle, the user voice collected by the sound receiving device in the vehicle can be obtained through the domain controller. That is, after the sound receiving device collects the user voice, the user voice can be sent to the domain controller, so that a voice data packet corresponding to each domain controller can be generated based on the user voice obtained by each domain controller. Specifically, the domain controller can calculate the sound intensity of the received user voice to obtain sound intensity information, and the phase difference of the user voice at each frequency point to obtain phase difference information, and use the initial voice signal, sound intensity information and phase difference information as the voice data packet.

[0113] In an optional implementation of the present application, a vehicle voice interaction result is obtained by responding to the user voice through the execution domain controller, which may specifically include the following sub-steps: generating a control instruction based on a keyword set corresponding to the user voice; sending the control instruction to the execution domain controller, and the execution domain controller performs a control operation in response to the control instruction to obtain control operation information; and generating a vehicle voice interaction result based on the control operation information.

[0114] In this embodiment, in the process of responding to the user voice through the execution domain controller to obtain the vehicle voice interaction result, a control instruction can be generated based on the keyword set corresponding to the user voice. The control instruction represents an instruction for controlling the execution domain controller to perform an operation corresponding to the user voice. The control instruction can be sent to the execution domain controller so that the execution domain controller performs a control operation in response to the control instruction to obtain control operation information. The control operation information represents the specific control operation status of the execution domain controller, such as the control operation completed, the control operation in progress, the control operation abnormality, etc., and then the vehicle voice interaction result is generated based on the control operation information.

[0115] In one example, if Figure 3 As shown, the central computing unit can be the executor of the vehicle voice interaction method of the present application. According to the keyword set corresponding to the user voice, the generated control instruction is an instruction to lower the air-conditioning temperature. When the execution domain controller receives the control instruction to lower the air-conditioning temperature, it can determine the execution mechanism corresponding to the control instruction. The execution structure can be the air-conditioning, ambient light, seat, etc. in the area where the execution controller is located. Then the execution domain controller can control the execution mechanism to execute the control operation corresponding to the control instruction, that is, it can control the air-conditioning actuator to lower the air-conditioning temperature.

[0116] like Figure 4 As shown, the present application also discloses an embodiment, providing a vehicle voice interaction device, including:

[0117] An acquisition module 410 is used to acquire voice data packets corresponding to at least two domain controllers in the vehicle, wherein the voice data packets are data packets generated by the domain controllers according to user voices, and the voice data packets contain sound intensity information and phase difference information;

[0118] A first determination module 420 is used to perform sound zone positioning according to the sound intensity information and the phase difference information, and determine a target sound zone, where the target sound zone is the sound zone to which the user voice belongs;

[0119] An extraction module 430 is used to extract an initial voice signal from a target voice data packet corresponding to the target voice zone, wherein the target voice data packet is a voice data packet generated by a target domain controller corresponding to the target voice zone;

[0120] A second determination module 440 is used to determine an execution domain controller based on the initial voice signal;

[0121] The response module 450 is used to respond to the user voice through the execution domain controller to obtain the vehicle voice interaction result.

[0122] In an optional implementation of the present application, the first determining module 420 may include:

[0123] A first determining unit, configured to determine whether the phase difference information meets a preset phase difference condition;

[0124] A second determining unit, configured to determine whether the sound intensity information meets a preset sound intensity condition when the phase difference information meets the preset phase difference condition;

[0125] A third determining unit, configured to determine the voice data packet corresponding to the voice intensity information as a target voice data packet if the voice intensity information meets a preset voice intensity condition;

[0126] The fourth determining unit is configured to determine the sound zone to which the target voice data packet belongs as the target sound zone.

[0127] In an optional implementation of the present application, the first determining module 420 may include:

[0128] A fifth determining unit, configured to determine whether the sound intensity information meets a preset sound intensity condition;

[0129] A sixth determining unit, configured to determine whether the phase difference information meets a preset phase difference condition when the sound intensity information meets a preset sound intensity condition;

[0130] A seventh determining unit, configured to determine the voice data packet corresponding to the phase difference information as a target voice data packet when the phase difference information meets the preset phase difference condition;

[0131] The eighth determining unit is configured to determine the sound zone to which the target voice data packet belongs as the target sound zone.

[0132] In an optional implementation of the present application, the first determining unit or the sixth determining unit includes:

[0133] A first determining subunit, used to determine a phase difference value of the phase difference information;

[0134] A first judging subunit, used to judge whether the phase difference value is within a preset phase difference range;

[0135] A second determining subunit, configured to determine, when the phase difference value is within the preset phase difference range, that the phase difference information meets a preset phase difference condition;

[0136] The third determining subunit is configured to determine, when the phase difference value is not within the preset phase difference range, that the phase difference information does not meet the preset phase difference condition.

[0137] In an optional implementation of the present application, the second determining unit or the fifth determining unit includes:

[0138] A fourth determining subunit, configured to determine a sound intensity value of each piece of the sound intensity information;

[0139] A second judging subunit, configured to judge whether the sound intensity value is a maximum sound intensity value;

[0140] a fifth determining subunit, configured to determine, when the sound intensity value is the maximum sound intensity value, that the sound intensity information meets the preset sound intensity condition;

[0141] The sixth determining subunit is configured to determine, when the sound intensity value is not the maximum sound intensity value, that the sound intensity information does not meet the preset sound intensity condition.

[0142] In an optional implementation of the present application, the second determining module 440 may include:

[0143] A speech processing unit, used for performing speech processing based on the initial speech signal to obtain target speech information;

[0144] A text conversion unit, used for converting the target voice information into text to obtain target text information;

[0145] A keyword extraction unit, used to extract keywords from the target text information to obtain a keyword set;

[0146] The sixth determination unit is used to determine the execution domain controller according to the keyword set.

[0147] In an optional implementation of the present application, the keyword extraction unit may include:

[0148] A keyword extraction subunit, used to extract keywords from the target text information to obtain at least one keyword;

[0149] A seventh determining subunit, configured to determine a keyword tag corresponding to the keyword;

[0150] A generating subunit is used to generate the keyword set according to the keywords and the keyword tags.

[0151] In an optional implementation of the present application, the sixth determining unit may include:

[0152] An eighth determination subunit is used to determine whether there is a directional word in the keyword set;

[0153] A ninth determination subunit, configured to determine the domain controller in the target pronunciation zone as the execution domain controller when the directional word does not exist in the keyword set;

[0154] The tenth determining subunit is used to determine the domain controller corresponding to the directional word as the execution domain controller when the directional word exists in the keyword set.

[0155] In an optional implementation of the present application, the acquisition module 410 may include:

[0156] an acquisition unit, configured to acquire, through the domain controller, the user voice collected by a sound receiving device in the vehicle;

[0157] The first generating unit is used to generate the voice data packet corresponding to each domain controller according to the user voice acquired by each domain controller.

[0158] In an optional implementation of the present application, the response module 450 may include:

[0159] A second generating unit, configured to generate a control instruction according to a keyword set corresponding to the user voice;

[0160] A response unit, configured to send the control instruction to the execution domain controller, and the execution domain controller executes a control operation in response to the control instruction to obtain control operation information;

[0161] The third generating unit is used to generate the vehicle voice interaction result according to the control operation information.

[0162] The implementation process of the functions and effects of each module in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, which will not be repeated here.

[0163] like Figure 5 As shown, an embodiment of the present application provides an electronic device, including a processor 510, a communication interface 520, a memory 550 and a communication bus 540, wherein the processor 510, the communication interface 520, and the memory 550 communicate with each other through the communication bus 540.

[0164] Memory 550, for storing computer programs;

[0165] In one embodiment of the present application, the processor 510 is used to execute the program stored in the memory 550 to implement the vehicle voice interaction control method provided by any of the aforementioned method embodiments, by acquiring voice data packets corresponding to at least two domain controllers in the vehicle, the voice data packets are data packets generated by the domain controller according to the user voice, and the voice data packets contain sound intensity information and phase difference information, so as to locate the sound zone according to the sound intensity information and the phase difference information, determine the target sound zone, the target sound zone is the sound zone to which the user voice belongs, and extract the initial voice signal from the target voice data packet corresponding to the target sound zone, the target voice data packet is the voice data packet generated by the target domain controller corresponding to the target sound zone, and determine the execution domain based on the initial voice signal. The controller determines the target sound zone through sound zone positioning, and obtains the clearest initial voice signal of the user's voice from the target voice data packet corresponding to the target sound zone; then responds to the user's voice through the execution domain controller, obtains the vehicle voice interaction result, and thus determines the execution domain controller that matches the user's voice, which can control different areas of the vehicle according to the initial voice signal, that is, it uses the sound intensity information and phase difference information to locate the sound zone, and then adaptively determines the execution domain controller and responds, avoiding the problem of low accuracy of voice interaction response caused by mutual interference of voice signals between different seats in the existing related technology, and can effectively improve the accuracy of voice interaction response, as well as improve the flexibility of voice interaction.

[0166] The embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of the vehicle voice interaction method provided in any of the aforementioned method embodiments are implemented, by acquiring voice data packets corresponding to at least two domain controllers in the vehicle, the voice data packets being data packets generated by the domain controllers according to user voices, the voice data packets containing sound intensity information and phase difference information, so as to locate the sound zone according to the sound intensity information and the phase difference information, determine the target sound zone, the target sound zone being the sound zone to which the user voice belongs, and extracting an initial voice signal from a target voice data packet corresponding to the target sound zone, the target voice data packet being a voice data packet generated by the target domain controller corresponding to the target sound zone, based on the initial voice signal , determine the execution domain controller, which plays a role in determining the target sound zone through sound zone positioning, and obtaining the clearest initial voice signal of the user's voice from the target voice data packet corresponding to the target sound zone; then, through the execution domain controller, respond to the user's voice, and obtain the vehicle voice interaction result, so as to determine the execution domain controller matching the user's voice, which can play the role of controlling different areas of the vehicle according to the initial voice signal, that is, using the sound intensity information and phase difference information to locate the sound zone, and then adaptively determine the execution domain controller and respond, avoiding the problem of low accuracy of voice interaction response caused by mutual interference of voice signals between different seats in the existing related technology, and can effectively improve the accuracy of voice interaction response, as well as improve the flexibility of voice interaction.

[0167] An embodiment of the present application provides a vehicle, comprising the vehicle voice interaction device described in the aforementioned embodiment.

[0168] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0169] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0170] It should be understood that the terms used herein are only for the purpose of describing specific example embodiments and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0171] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A vehicle voice interaction method, characterized in that: include: Acquire voice data packets corresponding to at least two domain controllers in the vehicle, wherein the voice data packets are data packets generated by the domain controllers according to user voices, and the voice data packets contain sound intensity information and phase difference information; Performing sound zone positioning according to the sound intensity information and the phase difference information to determine a target sound zone, where the target sound zone is the sound zone to which the user voice belongs; Extracting an initial voice signal from a target voice data packet corresponding to the target voice zone, wherein the target voice data packet is a voice data packet generated by a target domain controller corresponding to the target voice zone; Based on the initial voice signal, determining an execution domain controller; The execution domain controller responds to the user voice and obtains the vehicle voice interaction result.

2. The vehicle voice interaction method according to claim 1, characterized in that: The performing of sound zone positioning according to the sound intensity information and the phase difference information to determine the target sound zone includes: Determining whether the phase difference information meets a preset phase difference condition; In the case where the phase difference information meets the preset phase difference condition, determining whether the sound intensity information meets the preset sound intensity condition; When the sound intensity information meets a preset sound intensity condition, determining the voice data packet corresponding to the sound intensity information as a target voice data packet; The sound zone to which the target voice data packet belongs is determined as the target sound zone.

3. The vehicle voice interaction method according to claim 1, characterized in that: The performing of sound zone positioning according to the sound intensity information and the phase difference information to determine the target sound zone includes: Determining whether the sound intensity information meets a preset sound intensity condition; In the case where the sound intensity information meets the preset sound intensity condition, determining whether the phase difference information meets the preset phase difference condition; In a case where the phase difference information meets the preset phase difference condition, determining the voice data packet corresponding to the phase difference information as a target voice data packet; The sound zone to which the target voice data packet belongs is determined as the target sound zone.

4. The vehicle voice interaction method according to claim 2 or 3, characterized in that: The determining whether the sound intensity information meets a preset sound intensity condition includes: Determine a sound intensity value of each of the sound intensity information; Determining whether the sound intensity value is a maximum sound intensity value; When the sound intensity value is the maximum sound intensity value, determining that the sound intensity information meets the preset sound intensity condition; When the sound intensity value is not the maximum sound intensity value, it is determined that the sound intensity information does not meet the preset sound intensity condition.

5. The vehicle voice interaction method according to claim 1, characterized in that: The step of determining the execution domain controller based on the initial voice signal includes: Performing speech processing based on the initial speech signal to obtain target speech information; Converting the target voice information into text to obtain target text information; Extracting keywords from the target text information to obtain a keyword set; The execution domain controller is determined according to the keyword set.

6. The vehicle voice interaction method according to claim 5, characterized in that: The step of extracting keywords from the target text information to obtain a keyword set includes: Extracting keywords from the target text information to obtain at least one keyword; Determine a keyword tag corresponding to the keyword; The keyword set is generated according to the keywords and the keyword tags.

7. The vehicle voice interaction method according to claim 5, characterized in that: The determining the execution domain controller according to the keyword set includes: Determining whether there is a directional word in the keyword set; In the case that the directional word does not exist in the keyword set, determining the domain controller in the target pronunciation zone as the execution domain controller; When the directional word exists in the keyword set, the domain controller corresponding to the directional word is determined as the execution domain controller.

8. The vehicle voice interaction method according to claim 1, characterized in that: The obtaining of voice data packets corresponding to at least two domain controllers in the vehicle includes: Acquiring, by the domain controller, the user voice collected by a sound receiving device in the vehicle; According to the user voice acquired by each domain controller, the voice data packet corresponding to each domain controller is generated.

9. The vehicle voice interaction method according to claim 1, characterized in that: The executing domain controller responds to the user voice to obtain a vehicle voice interaction result, including: Generate a control instruction according to the keyword set corresponding to the user voice; The control instruction is sent to the execution domain controller, and the execution domain controller performs a control operation in response to the control instruction to obtain control operation information; The vehicle voice interaction result is generated according to the control operation information.

10. A vehicle voice interaction device, characterized in that: include: An acquisition module, used to acquire voice data packets corresponding to at least two domain controllers in the vehicle, wherein the voice data packets are data packets generated by the domain controller according to the user's voice, and the voice data packets contain sound intensity information and phase difference information; A first determination module is used to perform sound zone positioning according to the sound intensity information and the phase difference information, and determine a target sound zone, where the target sound zone is the sound zone to which the user voice belongs; An extraction module, used to extract an initial voice signal from a target voice data packet corresponding to the target voice zone, wherein the target voice data packet is a voice data packet generated by a target domain controller corresponding to the target voice zone; A second determination module, configured to determine an execution domain controller based on the initial voice signal; The response module is used to respond to the user voice through the execution domain controller to obtain the vehicle voice interaction result.

11. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; The processor is used to implement the vehicle voice interaction method described in any one of claims 1-9 when executing the program stored in the memory.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the vehicle voice interaction method as described in any one of claims 1 to 9 is implemented.

13. A vehicle, characterized in that: The vehicle voice interaction device comprising claim 10.

Images