Voice interaction method, electronic device and storage medium

Abstract

The present invention discloses a voice interaction method, an electronic device and a storage medium. In the method, voice data is acquired; based on the semantic content corresponding to the voice data, a target dialogue skill matching the semantic content is determined from a preset dialogue skill set; the dialogue skill set includes a first dialogue skill for releasing the audio focus of a terminal device and a second dialogue skill for seizing the audio focus of the terminal device; based on the target dialogue skill, a voice interaction operation is performed. Thus, the voice skill interaction that best matches the current semantic environment is achieved, without the need to perform hardware coding on the terminal based on a single skill, reducing development costs, and making it easier for different manufacturers to customize personalized skills for diverse scenarios.

Description

Technical Field

[0001] The present invention belongs to the technical field of audio processing, and in particular relates to a voice interaction method, electronic equipment and storage medium. Background Art

[0002] With the continuous development of voice technology, people's requirements for personalized configuration of voice interaction are also increasing.

[0003] At present, the voice interaction skills of devices usually adopt multi-round context inheritance, that is, directly setting multiple rounds of states in a certain field, covering the same semantic slots, and accumulating different semantic slots. The next action will be triggered only after the required semantic slots are filled.

[0004] Take a scenario with multiple rounds of context inheritance as an example:

[0005] “User: “Navigate to Beijing”;

[0006] System: Find multiple addresses in Beijing for you, which one do you want to go to (multi-round status);

[0007] User: First;

[0008] System: Navigating to Beijing Station for you, confirm or cancel? (Multiple rounds)

[0009] User: OK;

[0010] System: Navigate to Beijing Station for you. "

[0011] The above multi-round state requires context inheritance, and in this strong multi-round state, the terminal device needs to seize the audio focus and cannot play background sounds such as music until the navigation task is completed.

[0012] However, some interaction scenarios do not require strong context inheritance of multi-round states. For example, when users use audio-visual functions, the audio focus needs to be released and the device needs to directly play the music specified by the user. In the face of these types of interaction scenarios, the current common practice is to uniformly use multi-round dialogue skills and hard-code the audio focus release on the terminal. Although this can quickly solve the problem, it is difficult to customize and increases development costs.

[0013] The industry has not yet provided a better solution to the above problems. Summary of the invention

[0014] The embodiments of the present invention provide a voice interaction method, an electronic device and a storage medium, which are used to solve at least one of the above-mentioned technical problems.

[0015] In a first aspect, an embodiment of the present invention provides a voice interaction method, comprising: acquiring voice data; based on the semantic content corresponding to the voice data, determining a target dialogue skill that matches the semantic content from a preset dialogue skill set; the dialogue skill set includes a first dialogue skill for releasing the audio focus of a device and a second dialogue skill for seizing the audio focus of the device; and based on the target dialogue skill, performing a voice interaction operation.

[0016] In a second aspect, an embodiment of the present invention provides 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 perform the steps of the above method.

[0017] In a third aspect, an embodiment of the present invention provides a storage medium, in which one or more programs including execution instructions are stored, and the execution instructions can be read and executed by an electronic device (including but not limited to a computer, a server, or a network device, etc.) to execute the steps of the above-mentioned method of the present invention.

[0018] In a fourth aspect, an embodiment of the present invention further provides a computer program product, wherein the computer program product comprises a computer program stored on a storage medium, wherein the computer program comprises program instructions, and when the program instructions are executed by a computer, the computer executes the steps of the above method.

[0019] The beneficial effects of the embodiments of the present invention are:

[0020] Through the embodiments of the present invention, when a user performs human-computer voice interaction on a terminal device, the user's voice semantics can be parsed and the dialogue skill that best matches the semantics can be called from multiple skills to perform voice interaction operations. Thus, the voice skill interaction that best matches the current semantic environment is achieved, and there is no need to perform hardware coding on the terminal based on a single skill, which reduces development costs and makes it easier for different manufacturers to customize personalized skills for diverse scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 A flowchart of an example of a voice interaction method according to an embodiment of the present invention is shown;

[0023] Figure 2 Shows Figure 1 A flowchart of an example of a specific operation process of step 120;

[0024] Figure 3 A flowchart of an example of a voice interaction method according to an embodiment of the present invention is shown;

[0025] Figure 4 A flowchart of an example of a voice interaction method according to an embodiment of the present invention is shown;

[0026] Figure 5 It is a schematic structural diagram of an embodiment of an electronic device of the present invention. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0028] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other.

[0029] The present invention may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communications network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0030] In the present invention, "module", "system" and the like refer to related entities applied to computers, such as hardware, a combination of hardware and software, software or software in execution, etc. In detail, for example, an element can be, but is not limited to, a process, a processor, an object, an executable element, an execution thread, a program and / or a computer running on a processor. In addition, an application program or a script program, a server running on a server can be an element. One or more elements can be in the process and / or thread of execution, and an element can be localized on a computer and / or distributed between two or more computers, and can be operated by various computer-readable media. An element can also communicate by a local and / or remote process according to a signal with one or more data packets, for example, a signal from a local system, another element interacting in a distributed system, and / or a signal of data interacting with other systems through a signal on a network of the Internet.

[0031] Finally, it should be noted that, in this article, the terms "include" and "comprise" include not only those elements, but also other elements not explicitly listed, or elements inherent to such processes, methods, articles or equipment. In the absence of further restrictions, the elements defined by the sentence "include..." do not exclude the existence of other identical elements in the process, method, article or equipment that includes the elements.

[0032] Figure 1 The flowchart of an example of the voice interaction method according to the embodiment of the present invention is shown. The execution subject of the method of the embodiment of the present invention can be a cloud server dedicated to providing voice service support, or it can be integrated in the terminal device to realize various device voice functions.

[0033] like Figure 1 As shown, in step 110, voice data is acquired. Specifically, the terminal device may collect voice data through an audio collection module, or the server may receive voice data from the terminal device, and both are within the scope of implementation of the embodiment of the present invention.

[0034] In step 120, based on the semantic content corresponding to the voice data, a target dialogue skill matching the semantic content is determined from a preset dialogue skill set. Here, the dialogue skill set includes a first dialogue skill for releasing the audio focus of the terminal device and a second dialogue skill for seizing the audio focus of the terminal device.

[0035] In step 130 , a voice interaction operation is performed based on the target dialogue skill.

[0036] Regarding the implementation details of the above step 110, the process of acquiring voice data can be triggered based on the voice wake-up function of the device. Specifically, the system can collect the first ambient audio based on the terminal device, identify whether the first ambient audio contains the wake-up keyword, and when the ambient audio contains the wake-up keyword, collect the second ambient audio corresponding to the preset time period, and when the second ambient audio contains a real human voice component, determine the voice data based on the second ambient audio. In this way, the voice interaction function is triggered only when the ambient audio meets the voice wake-up condition, avoiding false triggering of the system, and effectively saving system resource consumption.

[0037] In an embodiment of the present invention, multiple dialogue skills are pre-deployed, and different dialogue skills have differentiated control methods for the audio focus of the terminal device, which can meet the personalized needs of different business scenarios, and there is no need to perform differentiated configuration for different scenarios based on a single skill.

[0038] Figure 2 Shows Figure 1 A flowchart of an example of the specific operation process of step 120 in FIG.

[0039] like Figure 2 As shown, in step 210, the text content corresponding to the voice data is identified.

[0040] In step 220, semantic content corresponding to the text content is parsed, and a target speech scene matching the semantic content is determined.

[0041] In step 230, a target dialogue skill is determined from a preset dialogue skill set according to the target speech scenario.

[0042] Through the embodiments of the present invention, the semantics of the text content are classified into corresponding target scenarios, and matching skills are determined from the dialogue skill set based on the scenarios, thereby achieving adaptation of personalized voice interaction skills for different scenarios.

[0043] In some business scenarios, users can personalize the adaptation skills for different scenarios to meet the personalized needs of different manufacturers. Specifically, the system can first detect whether there is a scenario skill customization request, for example, the scenario skill customization operation is triggered by the user. When there is a scenario skill customization request, the customized scenario and the corresponding customized skill information for the dialogue skill set are received, and then the customized scenario and the customized skill information are associated. Through the embodiment of the present invention, users can customize the relationship between scenarios and skills, and realize personalized skill customization for different business scenarios. The operation is convenient and no hard coding operation is required.

[0044] In some examples of embodiments of the present invention, the first dialogue skill for releasing the audio focus of the terminal device can also be divided into two categories, namely, a single-round dialogue skill for stopping monitoring the user's voice, and a weak multi-round skill for continuously monitoring the user's voice within a set time period. Here, the single-round dialogue skill is generally more suitable for one-way device control scenarios, such as "turn on the air conditioner", and the system does not need to perform multiple rounds of voice interaction operations with the user. In addition, based on the weak multi-round skill, the terminal device can continuously monitor the user's voice within a set time period, such as "please play music". At this time, the system controls the terminal device to release the audio focus and play music, and monitors whether there are valid instructions in a short time.

[0045] Specifically, regarding the implementation details of the above step 130, when the target dialogue skill is a single-round dialogue skill, based on the single-round dialogue skill, the response data for the voice data is determined, and then the voice interaction operation is performed based on the response data, and the audio focus is released, and the monitoring of voice instructions is stopped.

[0046] On the other hand, when the target dialogue skill is a weak multi-round dialogue skill, the response data for the voice data is determined based on the weak multi-round dialogue skill. In addition, voice interaction operations are performed based on the response data, and the audio focus is released, and whether there are valid audio instructions is continuously monitored within a set time period. If a valid audio instruction is detected, a voice interaction operation is performed according to the valid audio instruction, voice data, and response data. If no valid audio instruction is detected, stop monitoring the voice instruction. Therefore, when using weak multi-round dialogue skills for voice interaction, the audio focus can be released, allowing the terminal to use the audio of other applications for broadcasting, and detect user voice instructions in a short time to achieve multiple broadcasts.

[0047] In some examples, the weak multi-round skill is associated with a video playback scenario.

[0048] The following will take voice song request as an example to describe the audio and video playback scenario:

[0049] “User: I want to listen to Andy Lau’s “The Days We Walked Together”;

[0050] System: Play Andy Lau's "The Days We Have Gone Together" for you; (enter full-duplex delayed listening state, at this time the audio focus needs to be released, and the device needs to play the specified music directly)

[0051] User: Change to Jacky Cheung's song;

[0052] System: Play Jacky Cheung's "The Days We Have Gone Together" for you. (Entering full-duplex delayed listening state, the audio focus needs to be released at this time, and the device needs to play the specified music directly)"

[0053] In the embodiment of the present invention, weak multi-round skills are used to support the audio and video playback scene, meeting the voice interaction requirements of the audio and video playback scene. In addition, users can achieve this through scene skill customization without hard-coding adaptation for skills, which greatly reduces the difficulty of skill customization.

[0054] It should be understood that both the second skill (also known as the strong multi-round skill) and the weak multi-round skill are voice interaction skills that require context inheritance, and their interactive experience on the device side is different in different fields or scenarios.

[0055] Figure 3 A flowchart of an example of a voice interaction method according to an embodiment of the present invention is shown.

[0056] like Figure 3 As shown, full-duplex voice interaction is divided into different states, and the concepts of maintaining monitoring and maintaining context state are also separated.

[0057] Referring to the "not awakened" state in the figure, it corresponds to two situations: first, the device is not awakened; second, no valid instructions are given within a certain period of time in the multi-round state or delayed listening state, at which time the device switches to the not awakened state, and the commonly used delayed listening time is 30s.

[0058] Reference Figure 3 The "wake-up state" in the text box corresponds to the situation where the device is woken up by voice (for example, the voice says: Hello Xiaochi). When the device is just woken up, it enters the multi-round state by default.

[0059] Reference Figure 3 The "multi-round" state in the figure corresponds to the following situation: after the device wakes up, the voice triggers a multi-round skill statement, and the multi-round skill returns to maintain the context and continues to listen. At this time, it enters the multi-round state (for example, the scene is: navigating to Beijing, the system answers: I found multiple addresses in Beijing for you, which one do you want to go to?).

[0060] Reference Figure 3 There are two corresponding situations in the "delayed listening" state: first, after the device wakes up, a single skill statement or a multi-round skill statement is triggered, the multi-round skill returns to maintain the context, and the listening state is turned off, then the delayed listening state is entered; second, the state switches from the multi-round state to the delayed listening state, such as when the multi-round skill context ends, the delayed listening state is entered after the monitoring is turned off.

[0061] It should be noted that all logic for entering the delayed listening state is that the skill returns to the closed listening state. After entering this state, audio-visual skill context inheritance can also be achieved.

[0062] In addition, for audio-visual skills, the terminal devices currently have hard-coded logic, and the cloud maintains the audio-visual skills for multiple rounds. Later, it was found that such customization is too non-universal and not conducive to large-scale replicable solutions.

[0063] In the embodiment of the present invention, two states, namely, maintaining context state and maintaining monitoring, are abstracted through the cloud, and the two states are combined with full-duplex state switching to reorganize the state transfer process.

[0064] Through the embodiments of the present invention, the cloud distinguishes between audio-visual multi-round skills (i.e., weak multi-round skills) and common multi-round skills (i.e., strong multi-round skills). Based on the above design, all skill configurations are completed in the cloud, and the terminal device does not need to be hard-coded, which can achieve large-scale replicability of the solution in full-duplex state.

[0065] Figure 4 A flowchart of an example of a voice interaction method according to an embodiment of the present invention is shown.

[0066] like Figure 4 As shown, after the vehicle-mounted terminal device is voice-awakened, it starts to receive audio input.

[0067] Next, after the audio passes through VAD (Voice Activity Detection), the valid audio is sent for recognition to obtain the audio recognition result.

[0068] Next, the recognition results are semantically understood to obtain multiple skill semantic parsing results, namely semantic decoding results (for example, recognition algorithm based on nbest).

[0069] Next, the semantic results are routed through the central control DM (Dialog Management) to select the best skill.

[0070] Next, after selecting the optimal skill, the skill DM is scheduled to obtain the result of the skill DM, including NLG feedback or action for the current input.

[0071] Next, if the skill returned by the skill DM is a strong multi-round skill, that is, keep multi-round and keep monitoring, the vehicle terminal device enters the multi-round state, the radio continues to receive the sound, and the audio focus is not released.

[0072] Next, if the skill returned by the skill DM is a single-round skill or a weak multi-round skill, the vehicle-mounted terminal device enters a delayed listening state. If the returned skill is a single-round skill, that is, multi-rounds are turned off and monitoring is turned off. If it is a weak multi-round skill, that is, multi-rounds are maintained and monitoring is turned off. The cloud also returns a delayed listening status flag to the client. At this time, the cloud is context-maintaining and the monitoring state ends. At this time, the vehicle-mounted terminal device releases the audio focus.

[0073] Next, the session timeout timer is started from the beginning of the interaction with the system. If there is a valid DM return within the session timeout range, the session timeout timer is updated at this time. If the current vehicle terminal is playing a synthesized sound, the session timeout timer is also updated. After there is no valid input and no valid return for a period of time, the system ends the interaction.

[0074] Through the embodiments of the present invention, the customization of multi-round skills in different scenarios is realized. For example, for strong multi-round skills such as navigation, the audio focus is not released during the multi-round; in addition, for weak multi-round skills such as music / video, the audio focus is released during the weak multi-round, and music, video, etc. can be played. In this way, the voice solution can be quickly and scalably expanded.

[0075] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of combined actions, but those skilled in the art should be aware that the present invention is not limited by the described order of actions, because according to the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention. In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0076] In some embodiments, an embodiment of the present invention provides a non-volatile computer-readable storage medium, which stores one or more programs including execution instructions, and the execution instructions can be read and executed by an electronic device (including but not limited to a computer, a server, or a network device, etc.) to execute any of the above-mentioned voice-based device inventory methods of the present invention.

[0077] In some embodiments, an embodiment of the present invention further provides a computer program product, which includes a computer program stored on a non-volatile computer-readable storage medium, and the computer program includes program instructions, which, when executed by a computer, cause the computer to execute any of the above-mentioned voice-based device inventory methods.

[0078] In some embodiments, an embodiment of the present invention also provides 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 perform a voice interaction method.

[0079] Figure 5is a schematic diagram of the hardware structure of an electronic device for executing a voice interaction method provided by another embodiment of the present invention, such as Figure 5 As shown, the device includes:

[0080] One or more processors 510 and memory 520, Figure 5 A processor 510 is taken as an example.

[0081] The device for executing the voice interaction method may further include: an input device 530 and an output device 540 .

[0082] The processor 510, the memory 520, the input device 530 and the output device 540 may be connected via a bus or other means. Figure 5 The example of connecting through bus is taken in the following.

[0083] The memory 520 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions / modules corresponding to the voice interaction method in the embodiment of the present invention. The processor 510 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory 520, that is, the voice interaction method in the above method embodiment is implemented.

[0084] The memory 520 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the voice interaction device, etc. In addition, the memory 520 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 520 may optionally include a memory remotely arranged relative to the processor 510, and these remote memories may be connected to the audio synthesis device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0085] The input device 530 can receive input digital or character information and generate signals related to user settings and function control of the audio synthesis device. The output device 540 can include a display device such as a display screen.

[0086] The one or more modules are stored in the memory 520, and when executed by the one or more processors 510, the voice interaction method in any of the above method embodiments is executed.

[0087] The above product can execute the method provided by the embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not described in detail in this embodiment, please refer to the method provided by the embodiment of the present invention.

[0088] The electronic devices of the embodiments of the present invention exist in various forms, including but not limited to:

[0089] (1) Mobile communication equipment: This type of equipment is characterized by having mobile communication functions and its main purpose is to provide voice and data communications. This type of terminal includes: smart phones, multimedia phones, functional phones, and low-end phones.

[0090] (2) Ultra-mobile personal computer devices: These devices belong to the category of personal computers, have computing and processing functions, and generally also have mobile Internet access features. These terminals include: PDA, MID and UMPC devices, etc.

[0091] (3) Portable entertainment devices: These devices can display and play multimedia content. They include audio and video players, handheld game consoles, e-books, smart toys, and portable car navigation devices.

[0092] (4) Other onboard electronic devices with data interaction functions, such as on-board devices installed in vehicles.

[0093] 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.

[0094] 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.

[0095] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A voice interaction method, comprising: Get voice data; Based on the semantic content corresponding to the speech data, determining a target dialogue skill that matches the semantic content from a preset dialogue skill set; The dialogue skill set includes a first dialogue skill for releasing the audio focus of the terminal device and a second dialogue skill for seizing the audio focus of the terminal device; wherein, when the audio focus is seized, the terminal device cannot play audio; Based on the target dialogue skill, a voice interaction operation is performed; the target dialogue skill includes any one of the following: a single-round dialogue skill, a weak multi-round dialogue skill, and a strong multi-round dialogue skill; During the voice interaction process based on the strong multi-round dialogue skill, the terminal device cannot play audio, and During the voice interaction process based on the single-round dialogue skill or the weak multi-round dialogue skill, the terminal device can play audio.

2. The method according to claim 1, wherein: The determining, based on the semantic content corresponding to the voice data, a target dialogue skill matching the semantics from a preset dialogue skill set includes: Identifying text content corresponding to the voice data; Parsing semantic content corresponding to the text content, and determining a target speech scene matching the semantic content; According to the target voice scenario, a target dialogue skill is determined from a preset dialogue skill set.

3. The method according to claim 2, wherein: The method further comprises: Detect whether there is a scenario skill customization request; When there is a scenario skill customization request, receiving a customization scenario and corresponding customization skill information for the dialog skill set; The customized scenario and the customized skill information are associated.

4. The method according to claim 1, wherein: The first dialogue skill includes a single-round dialogue skill for stopping monitoring the user's voice, and a weak multi-round skill for continuously monitoring the user's voice within a set time period.

5. The method according to claim 4, wherein: When the target dialogue skill is a single-round dialogue skill, The performing of the voice interaction operation based on the target dialogue skill includes: Determining response data for the voice data based on the single-round dialogue skill; A voice interaction operation is performed based on the response data, and the audio focus is released, and the monitoring of the voice command is stopped.

6. The method according to claim 4, wherein: When the target dialogue skill is a weak multi-round dialogue skill, The performing of the voice interaction operation based on the target dialogue skill includes: Determining response data for the voice data based on the weak multi-turn dialogue skill; Execute the voice interaction operation based on the response data, release the audio focus, and continuously monitor whether there is a valid audio instruction within a set time period; If a valid audio instruction is detected, performing a voice interaction operation according to the valid audio instruction, the voice data and the response data; and If no valid audio command is detected, the system stops monitoring the voice command.

7. The method according to claim 4, wherein: The weak multi-round skill is associated with the audio and video playback scene.

8. The method according to any one of claims 1 to 7, wherein: The acquiring of voice data comprises: Based on the terminal device, collecting the first environment audio; Identify whether the first ambient audio contains a wake-up keyword; When the ambient audio contains a wake-up keyword, collecting a second ambient audio corresponding to a preset time period; When the second environmental audio includes a real human voice component, voice data is determined based on the second environmental audio.

9. 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 perform the steps of the method described in any one of claims 1 to 8.

10. A storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 8 are implemented.

Images