Voice question answering method and electronic equipment

Abstract

The invention provides a voice question answering method and electronic equipment. The voice question-answering method comprises the following steps: determining a mute state of a first application in a conference process; obtaining a first input audio stream according to the mute state of the first application in the conference process; generating a first question and answer result based on the first input audio stream; the first question-answer result is presented in a text or voice mode; and outputting the first question-answer result.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electronics, and in particular to a voice question and answer method and an electronic device. BACKGROUND

[0002] Most conference systems support core conference functions such as audio and video communication and screen sharing, but still have deficiencies in instant information acquisition during a conference. If a participant encounters a difficult problem during a conference, the participant usually needs to interrupt the listening and manually switch to other applications to query. This not only distracts attention, but also destroys the continuity of the conference, resulting in reduced efficiency.

[0003] Related technologies have a text question and answer function built in a conference system, and a user can perform a text query in a conference interface. However, in a conference environment mainly using voice communication, requiring the user to stop and type input still causes an interruption in interaction. This is particularly inconvenient for participants in a mobile scenario or multitasking. Therefore, there is an urgent need for a new interaction method to improve the above problems. SUMMARY

[0004] Therefore, the embodiments of the present application provide at least a voice question and answer method and an electronic device.

[0005] The technical solutions of the embodiments of the present application are implemented as follows: In a first aspect, the embodiments of the present application provide a voice question and answer method, which comprises the following steps: determining a mute state of a first application during a conference process; acquiring a first input audio stream according to the mute state of the first application during the conference process; generating a first question and answer result based on the first input audio stream; the first question and answer result is presented in a text or voice manner; outputting the first question and answer result.

[0006] In a second aspect, the embodiments of the present application provide an electronic device, which comprises a processor. The processor is configured to determine a mute state of a first application during a conference process; acquire a first input audio stream according to the mute state of the first application during the conference process; generate a first question and answer result based on the first input audio stream; the first question and answer result is presented in a text or voice manner; and output the first question and answer result.

[0007] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, but not limiting the technical solutions of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0008] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with this application and, together with the specification, serve to explain the technical solutions of this application.

[0009] Figure 1 A schematic diagram of the implementation process of a voice question-and-answer method provided in this application embodiment. Figure One ; Figure 2 A schematic diagram of the implementation process of a voice question-and-answer method provided in this application embodiment. Figure Two ; Figure 3 A schematic diagram of the implementation process of a voice question-and-answer method provided in this application embodiment. Figure Three ; Figure 4 A schematic diagram of the implementation process of a voice question-and-answer method provided in this application embodiment. Figure Four ; Figure 5 A schematic diagram of the composition structure of an electronic device provided in an embodiment of this application; Figure 6 This is a schematic diagram of a hardware entity of an electronic device in an embodiment of this application. Detailed Implementation

[0010] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application are further described in detail below with reference to the accompanying drawings and embodiments. The described embodiments should not be regarded as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0011] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0012] The terms “first / second / third” are used merely to distinguish similar objects and do not represent a specific ordering of objects. It is understood that “first / second / third” may be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0013] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. The terminology used herein is for descriptive purposes only and is not intended to limit the scope of this application.

[0014] To address the problems in the related technologies, this application provides a voice question-and-answer method that can be applied to electronic devices. For example, the electronic devices include, but are not limited to, smartphones, tablets, wearable devices, personal computers (PCs), netbooks, etc. The implementation of this application is not fixed or limited.

[0015] Figure 1 A schematic diagram of the implementation process of a voice question-and-answer method provided in this application embodiment. Figure One ,like Figure 1 As shown, this voice question-and-answer method can be implemented through steps S101-S104: S101. Determine the mute status of the first application during the meeting.

[0016] Here, the first application is conferencing applications, such as Zoom, Microsoft Teams, and Webex. The mute state indicates whether other participants can hear the user during the meeting.

[0017] If other participants cannot hear the user's voice during the meeting, the first application will be muted. If other participants can hear the user's voice during the meeting, the first application will be unmute.

[0018] By detecting the muted state of the first application during the meeting, it can be determined whether to provide the user with a voice Q&A function based on the muted state of the first application during the meeting.

[0019] S102. Obtain the first input audio stream based on the mute state of the first application during the meeting.

[0020] Here, the first input audio stream includes the audio stream of the user's input query.

[0021] In some examples, the process of obtaining the first input audio stream based on the mute state of the first application during the meeting may include: obtaining the first input audio stream when the first application is muted during the meeting; and not responding to the first input audio stream when the first application is not muted during the meeting.

[0022] For example, when the first application is in the middle of a meeting, if the user clicks the mute button on the meeting interface of the first application, the app will be muted, and the first input audio stream can be obtained. The first input audio stream may include the user's query audio stream, and a response can then be made based on the first input audio stream.

[0023] By acquiring the first input audio stream while in a muted state, it is ensured that the entire Q&A process will not affect the normal progress of the meeting, while improving the privacy of voice Q&A and the user experience.

[0024] S103. Generate the first question and answer result based on the first input audio stream.

[0025] The first question and answer result is presented in text or voice format.

[0026] For example, the first question-and-answer result can be presented as plain text, or it can be converted into speech through a text-to-speech (TTS) model and presented as speech.

[0027] In some examples, the process of generating a first question-and-answer result based on a first input audio stream may include: converting the first input audio stream into a first query text, then inputting the first query text into a question-and-answer model to obtain the first question-and-answer result corresponding to the first query text. The first question-and-answer result output by the question-and-answer model can be either text or speech.

[0028] Presenting the initial question-and-answer results in text or voice format can meet user needs in different scenarios. For example, in noisy environments, text output makes the results clearer and easier to read. In quiet environments, voice output makes the results more intuitive and convenient. These methods enhance the flexibility and practicality of voice-based question-and-answer systems.

[0029] S104. Output the first question and answer result.

[0030] Here, outputting the first question and answer result can mean presenting the generated first question and answer result to the user in a specified way.

[0031] For example, the system can automatically select the most appropriate output method to display the first question and answer result based on user settings or the electronic device's judgment. For instance, if other participants are speaking during the meeting, the first question and answer result will be displayed in text format. If no other participants are speaking, the first question and answer result will be displayed in audio format.

[0032] By adopting flexible and diverse output methods, users can efficiently obtain the information they need without interrupting the meeting, achieving deep integration of voice question-and-answer methods with the meeting system, thereby significantly improving meeting efficiency and user experience.

[0033] In the embodiments of the present application, by detecting whether the first application is in the mute state and conducting a question-and-answer session in the mute state, seamless connection between voice question-and-answer and the meeting is achieved. The multitasking ability of the electronic device during the meeting is improved, and the interactivity and intelligent level of the meeting are enhanced.

[0034] In some examples, the voice question-and-answer method further includes: S1011. Before determining the mute state of the first application during the meeting, receive the first inquiry event of the user during the meeting.

[0035] Alternatively, after determining the mute state of the first application during the meeting, receive the first inquiry event of the user during the meeting.

[0036] Alternatively, during the process of determining the mute state of the first application during the meeting, receive the first inquiry event of the user during the meeting; the first inquiry event is used to trigger the acquisition of the first input audio stream.

[0037] In some examples, the first inquiry event is used to trigger the acquisition of the user's inquiry audio stream. The first inquiry event can serve as an interaction entry, enabling the user to trigger the voice question-and-answer function without interrupting the meeting process.

[0038] Exemplarily, the first inquiry event can be triggered by the user through voice or text instructions during the meeting; for example, the first inquiry event is triggered by the user's voice instruction, and the voice instruction can be: "Please answer this question, or help me check the content of this question, etc.". The first inquiry event can also be triggered by keywords. For example, when the electronic device detects the keyword "Xiaoyi Xiaoyi", the first inquiry event is triggered.

[0039] In the embodiments of the present application, the first inquiry event can occur before determining the mute state of the first application during the meeting, can also occur after determining the mute state of the first application during the meeting, or occur simultaneously with determining the mute state of the first application during the meeting. The present application does not limit the occurrence timing of the first inquiry event.

[0040] When the reception of the first inquiry event occurs before determining the mute state of the first application during the meeting, the user's intention can be captured in advance, so that the question-and-answer process can be quickly entered, the response speed of the whole process can be improved, and the user experience can be improved accordingly.

[0041] When the reception of the first inquiry event occurs after determining the mute state of the first application during the meeting, it can be ensured that the voice question-and-answer is only enabled when the user actively selects the mute state, avoiding the accidental activation of the voice question-and-answer in the non-mute state, which may cause interference to the normal meeting communication.

[0042] Upon receiving the first query event, the system simultaneously determines the mute status of the first application during the meeting, allowing for the preparation of voice responses even before the mute status is definitively confirmed. Receiving the user's first query event and preparing voice responses in advance during the mute status determination process accelerates response time, improves system efficiency, and ultimately meets the user's need for immediate feedback.

[0043] In this embodiment of the application, flexible and efficient voice question and answer is achieved by setting multiple times for receiving the first inquiry event (i.e. before, during and after confirmation of the silent state).

[0044] Figure 2 A schematic diagram of the implementation process of a voice question-and-answer method provided in this application embodiment. Figure Two ,like Figure 2 As shown, step S101 determines the mute state of the first application during the meeting, including: S201. In response to the operation that triggers the startup of the second application, the second application executes the startup process.

[0045] In some examples, the action that triggers the launch of the second application may include a user's click, voice command, or keyboard shortcut. For instance, on the system desktop of an electronic device, a user can launch the second application by clicking its icon with a mouse or using a keyboard shortcut. Exemplarily, the second application could be a voice question-and-answer application or a meeting assistant application; that is, the second application can be a standalone third-party application. Of course, the second application can also be a voice question-and-answer unit or a meeting assistant unit within a meeting application; that is, the second application is a functional unit within the meeting application.

[0046] Upon receiving a startup command, the second application's startup process may include: responding to the startup command by performing operations such as initialization configuration, loading the model, and establishing a connection. After completing the startup process, the second application can run normally and interact with other applications on the electronic device. For example, the second application can interact with the first application on the electronic device. Only after the second application successfully starts can the first application's mute status be checked and its voice question-and-answer function be executed.

[0047] S202. After the second application is launched, the second application determines the mute status of the first application during the meeting.

[0048] In some examples, the first and second applications are two independent applications. After the second application starts successfully, it can detect whether the first application is muted during the meeting. Then, based on the muted status of the first application during the meeting, it determines whether to respond to user-inputted audio streams.

[0049] In this embodiment, after the second application is launched, it can take over the audio stream of the user's input question while the first application is in a muted state, thereby realizing voice question and answer. Through this method, users do not need to manually switch between multiple applications to acquire question and answer knowledge, improving the ease of operation and meeting experience for meeting participants.

[0050] In other embodiments, determining the mute state of the conference application during the conference further includes: in response to an operation that triggers the launch of the first application, the first application executes a launch process; after the first application is launched, the voice question-and-answer unit of the first application determines the mute state of the first application during the conference.

[0051] For example, the action that triggers the launch of the first application may include a user's click, voice command, or keyboard shortcut. For instance, on the system desktop of an electronic device, a user can launch the first application by clicking its icon with a mouse or by using a keyboard shortcut.

[0052] The muted state of the first application during the meeting can be determined by the voice question-and-answer unit within the first application. The voice question-and-answer unit can be an auxiliary function module integrated into the meeting application. This unit is used to determine the muted state of the first application during the meeting; and based on the muted state of the first application during the meeting, to obtain the first input audio stream; and then, based on the first input audio stream, to generate and output the first question-and-answer result.

[0053] The meeting application uses a voice Q&A unit to determine if it is muted. When the application is not muted, the Q&A unit does not respond to user-inputted audio messages to avoid disrupting the meeting flow. However, when the application is muted, the Q&A unit can respond to user-inputted audio messages to answer questions. The entire process requires no manual user intervention, achieving an automated and intelligent meeting interaction experience.

[0054] Figure 3 A schematic diagram of the implementation process of a voice question-and-answer method provided in this application embodiment. Figure Three ,like Figure 3 As shown, step S101 determines the mute state of the first application during the meeting, including: S301. Obtain the input audio stream from the microphone and the output audio stream from the first application.

[0055] In some examples, microphone input audio stream refers to the audio stream that a user inputs to an electronic device system through a microphone.

[0056] The output audio stream of the first application refers to the audio stream that the first application sends to speakers or headphones, which is usually the sound content heard by other participants in the meeting.

[0057] The electronic device can simultaneously acquire the input audio stream from the microphone and the output audio stream from the first application, and compare the input audio stream from the microphone and the output audio stream from the first application to determine the muted state of the first application during the meeting.

[0058] In some examples, the microphone's input audio stream and the first application's output audio stream can be captured by a second application using the Windows API.

[0059] S302. Compare the input audio stream of the microphone with the output audio stream of the first application to determine the muted state of the first application during the meeting.

[0060] In some examples, the process of determining whether a first application is muted during a meeting by comparing the microphone's input audio stream and the first application's output audio stream may include: a second application in an electronic device comparing the similarity, energy difference, and spectral differences between the microphone's input audio stream and the first application's output audio stream to obtain a comparison result; and determining the first application's muted state during the meeting based on the comparison result. For example, when the microphone's input audio stream contains obvious content while the first application's output audio stream is empty, it can be determined that the first application is muted.

[0061] By comparing the input audio stream from the microphone with the output audio stream from the first application, it's possible to identify whether the first application is muted without relying on a mute interface. Then, based on the recognition result, it automatically switches to voice question-and-answer mode. This improves the user experience and reduces manual switching.

[0062] Figure 4 A schematic diagram of the implementation process of a voice question-and-answer method provided in this application embodiment. Figure Four ,like Figure 4 As shown, step S101 determines the mute state of the first application during the meeting, including: S401. Determine the microphone status in the first application interface.

[0063] The microphone status is used to indicate whether the microphone input function is turned on or off when the user is using the first application.

[0064] In some examples, microphone status can be obtained in several ways, such as by calling the API provided by the first application to read whether the microphone is currently on or off. Alternatively, the microphone status can be determined by detecting elements in the first application's interface. After determining the microphone status, the muting state of the first application during the meeting can be determined based on the microphone status.

[0065] S402. Determine the mute state of the first application during the meeting based on the microphone status in the first application interface.

[0066] In some examples, if the microphone in the first application interface is detected as being on, it indicates that the first application is not muted during the meeting. If the microphone in the first application interface is detected as being off, it indicates that the first application is muted during the meeting.

[0067] Upon detecting that the first application is muted during the meeting, the system switches to voice Q&A mode to answer user-input audio queries. By detecting the microphone status to determine if the muted state is active, and then deciding whether to initiate the voice Q&A process based on the muted state, the system avoids users frequently switching windows or opening other applications to search or ask questions during the meeting, thus improving meeting efficiency and user experience.

[0068] In some examples, the process of determining the mute state of the first application during the meeting may also include: calling the mute interface of the first application to read the mute flag, and determining the mute state of the meeting application during the meeting based on the mute flag in the mute interface.

[0069] For example, the mute interface could be a programming interface (API) provided by the first application. The mute interface allows external programs to access the first application's internal state information, such as whether the first application has its microphone on or off. The mute flag can be identified using a Boolean value (true / false).

[0070] The process by which the second application reads the mute flag by calling the mute interface of the first application may include: obtaining a boolean value (true / false) through the mute interface of the first application, which indicates whether the first application is currently in a mute state.

[0071] After reading the mute flag, the mute status of the first application during the meeting can be determined based on the mute flag in the mute interface. For example, if the mute flag is true, the first application is confirmed to be mute during the meeting. If the mute flag is false, the first application is confirmed to be unmute during the meeting.

[0072] In some examples, the second application can periodically call the mute interface through a polling mechanism to ensure that it can promptly capture changes in the mute state of the first application. Alternatively, an event listening mechanism can be used, whereby the first application proactively notifies the second application of changes in the mute state, thereby improving response speed and accuracy.

[0073] In this embodiment, the mute flag is read by calling the mute interface of the first application, and the mute state during the meeting is identified based on the mute flag. This allows for accurate judgment of the mute state, thereby intelligently controlling the activation and deactivation of the voice question-and-answer function, and ultimately improving the convenience of knowledge acquisition.

[0074] In some examples, obtaining the first input audio stream in step S102 includes: Step S1021: Acquire the first input audio stream through the microphone.

[0075] The first input audio stream includes an inquiry audio stream from the user and a conference audio stream from the first application.

[0076] Generally, when the first application is muted, it will no longer acquire audio streams through the microphone. However, during this process, the microphone remains on, so the second application can still capture the first input audio stream through the microphone.

[0077] In some examples, when the first application is muted, the second application can capture and process the user's input audio stream via a microphone.

[0078] During a normal meeting, the first application can output the meeting audio stream through its speakers. Therefore, the microphone can capture not only the user's input audio stream but also the meeting audio stream output by the first application. The second application, also using its microphone, can simultaneously capture both the user's input audio stream and the meeting audio stream output by the first application. Subsequently, the second application can use both the user's input audio stream and the first application's meeting audio stream to provide a knowledge-based answer, improving the accuracy of the first application's response.

[0079] In some examples, the process of acquiring the first input audio stream via a microphone can also be: the voice question-and-answer unit in the first application acquires the first input audio stream via a microphone.

[0080] Normally, when the first application is muted during a meeting, it will no longer actively access the microphone. However, when the first application includes a voice Q&A unit, the voice Q&A unit can continuously monitor the muted state of the first application during the meeting. When it detects that the first application is muted, the voice Q&A unit can access the microphone to obtain the first input audio stream because the microphone hardware unit is still on.

[0081] In this embodiment of the application, by acquiring the audio stream of the user's inquiry and the audio stream of the meeting from the first application, more reference information can be provided for the subsequent generation of the first question and answer result, thereby further improving the output accuracy of the first question and answer result.

[0082] In some examples, step S103 generates a first question-and-answer result based on the first input audio stream, including: Step S1031: Input the audio stream of the user's inquiry and the audio stream of the meeting from the first application into the question-answering model to obtain the first question-answering result.

[0083] Here, the question-answering model generates a first question-answer result based on the user's query audio stream and the conference audio stream from the first application. The conference audio stream can be used to provide contextual information, helping the question-answering model to more accurately understand the user's input query audio stream and generate the first question-answer result corresponding to the query audio stream.

[0084] In some examples, the process of inputting an audio stream of a user's inquiry and a conference audio stream from a first application into a question-answering model to obtain a first question-answering result may include: a second application inputting an audio stream of a user's inquiry and a conference audio stream from a first application into a question-answering model to obtain a first question-answering result.

[0085] Specifically, the second application inputs the user's query audio stream and the conference audio stream from the first application into the question-answering model. The question-answering model identifies and semantically analyzes the content of the first input audio stream, and combines it with the conference audio stream from the first application to generate the first question-answering result.

[0086] For example, the user-input query audio stream is used to instruct the user to ask how to configure firewall rules. The question-and-answer model will generate a first question-and-answer result based on the meeting audio stream output by the first application and the query audio stream. The first question-and-answer result indicates the configuration suggestions for firewall rules.

[0087] In other examples, the process of inputting the user's query audio stream and the conference audio stream from the first application into the question-answering model to obtain the first question-answering result can also be as follows: the voice question-answering unit in the first application inputs the user's query audio stream and the conference audio stream from the first application into the question-answering model to obtain the first question-answering result.

[0088] In some examples, question-answering models can be implemented using various architectures, such as Transformer-based models (e.g., BERT, T5), or multimodal models integrating speech recognition and natural language understanding. Furthermore, question-answering models can support generating first-response results in multiple output formats, such as text-based or speech-based results, thus adapting to different use cases.

[0089] In this embodiment of the application, by jointly inputting the user's inquiry audio stream and the conference audio stream into the question-answering model, the question-answering model can more comprehensively understand the user's intent based on the complete context, thereby improving the accuracy and practicality of the answer.

[0090] In some examples, step S104 outputs the first question-and-answer result, including: Step S1041: The second application calls the speaker to play the first question and answer result.

[0091] Alternatively, the second application displays the results of the first question and answer.

[0092] After the second application obtains the first question-and-answer result, the first question-and-answer result can be output in various ways. For example, the first question-and-answer result can be played out as speech through a speaker, or the first question-and-answer result can be displayed as text.

[0093] When the first Q&A result is displayed in text form, it can be shown in a specific area of ​​the second application's interface, such as a sidebar or floating window, to ensure that it does not interfere with the normal progress of the meeting.

[0094] In this embodiment, two output methods for the first question-and-answer result are provided (playing the first question-and-answer result through a speaker and displaying the first question-and-answer result). Users can flexibly choose between these two methods according to their actual needs. Using these two output methods allows for adaptation to different usage scenarios in different environments, thereby improving the user experience and further enhancing the intelligence and functionality of the conference system.

[0095] In some embodiments, the process of outputting the first question-and-answer result may further include: determining the volume value of the output audio stream of the first application; playing the first question-and-answer result if the volume value of the output audio stream of the first application is less than or equal to a threshold; and displaying a first interface if the volume value of the output audio stream of the first application is greater than the threshold, wherein the first interface is used to display the first question-and-answer result.

[0096] The output audio stream of the first application can be the audio stream played by the first application through a hardware output device in its current running state. The volume value is used to represent the sound intensity of the output audio stream of the first application, and the volume value can be expressed in decibels (dB) or a normalized value (such as a value between 0 and 1).

[0097] The second application can determine the current communication status of the meeting by detecting the volume of the audio stream output by the first application. If the volume is close to zero, it means that several participants are not speaking; conversely, if the volume is high, it means that several participants are speaking normally.

[0098] In some examples, the output audio stream of the first application can be obtained by calling an audio API (e.g., the Windows Core Audio API) or an open interface of the conferencing system (such as the Teams SDK), and the volume value of the output audio stream of the first application can be calculated. Alternatively, the volume value of the output audio stream of the first application can also be obtained by performing a Fourier transform or energy detection on the output audio stream of the first application.

[0099] When the second application detects that the volume of the audio stream output by the first application is less than or equal to a threshold (i.e., a preset mute threshold), it indicates that the current environment is relatively quiet. In this case, the first question-and-answer result can be played through the speaker, allowing the user to receive the answer without looking at the screen. This way, the second application can more intuitively display the first question-and-answer result through playback without interfering with the meeting, thus improving user satisfaction.

[0100] When the second application detects that the volume of the audio stream output by the first application exceeds a threshold, it indicates that a participant is speaking during the meeting. To prevent privacy leaks or disruptions to other participants due to playback, the first Q&A result can be displayed as text on the first interface. This maintains the availability of the Q&A function while balancing meeting efficiency and user needs. The first interface is a display screen for showing the first Q&A result. It can be part of the display screen of the first or second application, or it can be a separate pop-up window specifically for displaying the first Q&A result.

[0101] By dynamically selecting the output method of the first question and answer result based on the volume value of the output audio stream of the first application, it is possible to ensure that the result feedback is given in a reasonable way using either playback or text in different meeting states. This can adapt to a variety of usage scenarios and significantly improve the user's meeting experience and interaction efficiency.

[0102] In some examples, step S104 outputs the first question-and-answer result, including: Step S1042: The second application sends the first question and answer result to the first application so that the first application can display the first question and answer result.

[0103] It is understandable that the first question-and-answer result can be output through the second application or through the first application. When the first question-and-answer result is output through the first application, the second application can send the obtained first question-and-answer result back to the first application. After receiving the first question-and-answer result, the first application will output the first question-and-answer result.

[0104] In some examples, the process of a second application sending a first question-and-answer result to a first application may include the second application sending the first question-and-answer result to the first application through API calls, shared memory mechanisms, or local message queues.

[0105] Furthermore, whether the first application is muted or not, the second application can still send the first question-and-answer result to the first application. Upon receiving the first question-and-answer result, the first application can directly output it, allowing the user to see or hear the result without switching windows. This avoids frequent software changes and improves operational efficiency and user experience.

[0106] In this embodiment, after the second application generates the first question-and-answer result, the first question-and-answer result can be sent to the first application and displayed on the interface of the first application. This avoids users switching back and forth between multiple applications, thus maintaining the continuity of the meeting and further improving user experience and work efficiency.

[0107] Figure 5 This is a schematic diagram of the composition structure of an electronic device provided in an embodiment of this application, such as... Figure 5 As shown, the electronic device 500 includes a determining module 501, an acquiring module 502, a generating module 503, and an output module 504; wherein, The determination module 501 is used to determine the mute status of the first application during the meeting.

[0108] The acquisition module 502 is used to acquire the first input audio stream based on the mute state of the first application during the meeting.

[0109] The generation module 503 is used to generate a first question-and-answer result based on the first input audio stream; the first question-and-answer result is presented in text or voice format.

[0110] Output module 504 is used to output the first question and answer result.

[0111] In some embodiments, the determining module 501 is further configured to, in response to an operation that triggers the launch of the second application, execute a launch process; after the second application is launched, the second application determines the mute state of the first application during the meeting.

[0112] In some embodiments, the output module 504 is further configured to have the second application call the speaker to play the first question-and-answer result; or, the second application displays the first question-and-answer result.

[0113] In some embodiments, the output module 504 is further configured to send a first question-and-answer result from the second application to the first application, so that the first application displays the first question-and-answer result.

[0114] In some embodiments, the acquisition module 502 is further configured to acquire a first input audio stream via a microphone; the first input audio stream includes an inquiry audio stream from the user and a conference audio stream from the first application.

[0115] In some embodiments, the generation module 503 is further configured to input the query audio stream from the user and the conference audio stream from the first application into the question-answering model to obtain a first question-answering result.

[0116] In some embodiments, the determining module 501 is further configured to receive a first query event from the user during the meeting before determining that the first application is in a mute state during the meeting; or, after determining that the first application is in a mute state during the meeting, receive the first query event from the user during the meeting; or, during the process of determining that the first application is in a mute state during the meeting, receive the first query event from the user during the meeting; the first query event is used to trigger the acquisition of the first input audio stream.

[0117] In some embodiments, the determining module 501 is further configured to acquire the input audio stream of the microphone and the output audio stream of the first application; compare the input audio stream of the microphone and the output audio stream of the first application to determine the muted state of the first application during the meeting.

[0118] In some embodiments, the determining module 501 is further configured to determine the microphone status in the first application interface; and determine the mute status of the first application during the meeting based on the microphone status in the first application interface.

[0119] The descriptions of the apparatus embodiments above are similar to those of the method embodiments above, and have similar beneficial effects. In some embodiments, the functions or modules included in the apparatus provided in this application can be used to perform the methods described in the method embodiments above. For technical details not disclosed in the apparatus embodiments of this application, please refer to the descriptions of the method embodiments of this application for understanding.

[0120] It should be noted that, in the embodiments of this application, if the above-mentioned voice question-and-answer method is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiments of this application, or the part that contributes to the related technology, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, mobile hard drives, read-only memory (ROM), magnetic disks, or optical disks. Thus, the embodiments of this application are not limited to any specific hardware, software, or firmware, or any combination of hardware, software, and firmware.

[0121] This application provides a computer device including a memory and a processor. The memory stores a computer program that can run on the processor. When the processor executes the program, it implements some or all of the steps in the above-described method.

[0122] This application provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements some or all of the steps in the above-described method. The computer-readable storage medium can be transient or non-transient.

[0123] This application provides a computer program including computer-readable code. When the computer-readable code is run in a computer device, the processor in the computer device performs some or all of the steps in the above-described method.

[0124] This application provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program. When the computer program is read and executed by a computer, it implements some or all of the steps in the above-described method. This computer program product can be implemented specifically through hardware, software, or a combination thereof. In some embodiments, the computer program product is specifically embodied as a computer storage medium; in other embodiments, the computer program product is specifically embodied as a software product, such as a software development kit (SDK), etc.

[0125] It should be noted that the descriptions of the various embodiments above tend to emphasize the differences between them, while their similarities or commonalities can be referred to interchangeably. The descriptions of the above embodiments of the device, storage medium, computer program, and computer program product are similar to the descriptions of the above method embodiments and have similar beneficial effects. For technical details not disclosed in the embodiments of the device, storage medium, computer program, and computer program product of this application, please refer to the descriptions of the method embodiments of this application for understanding.

[0126] Figure 6 This is a schematic diagram of a hardware entity of an electronic device in an embodiment of this application, such as... Figure 6 As shown, the hardware entity of the electronic device 600 includes: a processor 601, a communication interface 602, and a memory 603. Wherein: The processor 601 typically controls the overall operation of the electronic device 600, which may be to implement the voice question-and-answer method provided in the embodiments of this application.

[0127] The communication interface 602 enables the electronic device 600 to communicate with other terminals or servers via a network.

[0128] The memory 603 is configured to store instructions and applications executable by the processor 601, and can also cache data to be processed or already processed (e.g., image data, audio data, voice communication data, and video communication data) in the processor 601 and various modules in the electronic device 600. It can be implemented using flash memory or random access memory (RAM). Data transfer between the processor 601, the communication interface 602, and the memory 603 can be performed via bus 604.

[0129] This application provides a computer storage medium storing one or more programs that can be executed by one or more processors to implement the steps of the voice question-and-answer method as described in any of the above embodiments.

[0130] It should be noted that the descriptions of the storage medium and device embodiments above are similar to the descriptions of the method embodiments above, and have similar beneficial effects. For technical details not disclosed in the storage medium and device embodiments of this application, please refer to the descriptions of the method embodiments of this application for understanding.

[0131] The aforementioned processor can be at least one of the following: Application Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), Central Processing Unit (CPU), Controller, Microcontroller, and Microprocessor. It is understood that other electronic devices can also implement the functions of the aforementioned processor, and this application does not specifically limit the specific implementation.

[0132] The aforementioned computer storage media / memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM), etc.; or it can be various terminals that include one or any combination of the above-mentioned memories, such as mobile phones, computers, tablet devices, personal digital assistants, etc.

[0133] It should be understood that the phrase "one embodiment" or "an embodiment" throughout the specification means that a specific feature, structure, or characteristic related to the embodiment is included in at least one embodiment of this application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It should be understood that in the various embodiments of this application, the sequence numbers of the above steps / processes do not imply a sequential order of execution; the execution order of each step / process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application. The sequence numbers of the above embodiments of this application are merely descriptive and do not represent the superiority or inferiority of the embodiments.

[0134] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0135] The above are merely embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1.A voice question and answer method, the method comprising: determining a mute state of a first application during a conference; acquiring a first input audio stream according to the mute state of the first application during the conference; generating a first question and answer result based on the first input audio stream; presenting the first question and answer result in text or voice; outputting the first question and answer result. 2.The method of claim 1, wherein the determining the mute state of the first application during the conference comprises: in response to an operation triggering a second application to start, the second application executing a start procedure; after the second application starts, the second application determining the mute state of the first application during the conference. 3.The method of claim 1, wherein the outputting the first question and answer result comprises: the second application calling a speaker to play the first question and answer result; or the second application displaying the first question and answer result. 4.The method of claim 1, wherein the outputting the first question and answer result comprises: the second application sending the first question and answer result to the first application, so that the first application displays the first question and answer result. 5.The method of claim 1, wherein the acquiring the first input audio stream comprises: acquiring the first input audio stream through a microphone; wherein the first input audio stream comprises a query audio stream from a user and a conference audio stream from the first application. 6.The method of claim 5, wherein the generating the first question and answer result based on the first input audio stream comprises: inputting the query audio stream from the user and the conference audio stream from the first application into a question and answer model to obtain the first question and answer result. 7.The method of claim 1 or 2, further comprising: receiving the first query event of the user during the conference before determining the mute state of the first application during the conference; or receiving the first query event of the user during the conference after determining the mute state of the first application during the conference; or receiving the first query event of the user during the conference during the determination of the mute state of the first application during the conference; wherein the first query event is used to trigger the acquiring the first input audio stream. 8.The method of any one of claims 1-6, wherein the determining the mute state of the first application during the conference comprises: acquiring an input audio stream of a microphone and an output audio stream of the first application; and comparing the input audio stream of the microphone and the output audio stream of the first application to determine the mute state of the first application during the conference. 9.The method of any one of claims 1-6, wherein the determining the mute state of the first application during the conference comprises: determining a microphone state in an interface of the first application; and determining the mute state of the first application during the conference according to the microphone state in the interface of the first application. the electronic device comprising: ​ ​ ​ ​ ​ ​ 10. An electronic device, comprising: ​ A processor is configured to determine a mute state of a first application during a conference, acquire a first input audio stream according to the mute state of the first application during the conference, generate a first question and answer result based on the first input audio stream, present the first question and answer result in a text or voice manner, and output the first question and answer result.

Images