Voice interaction method, device, computer equipment and storage medium

Abstract

This application relates to a voice interaction method, apparatus, computer device, and storage medium. The method is executed on a voice interaction device connected to a terminal, comprising: when the terminal plays application audio (with user voice masked) generated by a first user account in an interaction room of the application; acquiring first user voice matched with the first user account; transmitting the first user voice to a target device corresponding to a second user account in the interaction room; the first user voice being played by the target device; playing second user voice responded to by the target device in response to the first user voice; and matching the second user voice with a second user account. This method can reduce interference between application audio and user voice, improving the voice interaction effect.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a voice interaction method, apparatus, computer device, and storage medium. Background Technology

[0002] With the development of computer technology, various terminal applications have emerged, such as multiplayer game applications, live streaming applications, and social applications. Users can interact through these applications, such as playing games and engaging in audio and video interaction, which not only facilitates people's work but also enriches their lives and entertainment.

[0003] When users interact through terminal applications, they can use various interaction methods such as text interaction and voice interaction. However, during voice interaction, the voices of users can easily overlap with the application's own audio, such as the application's background music, which can interfere with the voice interaction and reduce the effectiveness of the voice interaction. Summary of the Invention

[0004] Therefore, it is necessary to provide a voice interaction method, device, computer equipment, and storage medium that can reduce interference between application audio and user voice and improve the voice interaction effect, in order to address the above-mentioned technical problems.

[0005] A voice interaction method, executed on a voice interaction device connected to a terminal, the method comprising:

[0006] When the terminal plays application audio generated by the first user account in the application's interactive room, which has the user's voice blocked, the first user's voice that is collected and matches the first user account is obtained.

[0007] The first user's voice is transmitted to the target device corresponding to the second user account in the interactive room; the first user's voice is used for playback by the target device.

[0008] The target device responds to the second user's voice in response to the first user's voice; the second user's voice matches the second user's account.

[0009] In one embodiment, transmitting first user voice to a target device corresponding to a second user account in the interactive room includes:

[0010] Send the first user voice to the server; the first user voice is also used to instruct the server to determine the target device corresponding to the second user account in the interactive room, and forward the first user voice to the target device corresponding to the second user account.

[0011] A voice interaction device is applied to a voice interaction device connected to a terminal, the device comprising:

[0012] The first user voice acquisition module is used to acquire the first user voice that matches the first user account when the terminal plays application audio generated by the first user account in the application's interactive room, which has masked the user's voice.

[0013] The first user voice transmission module is used to transmit the first user's voice to the target device corresponding to the second user account in the interactive room; the first user's voice is used for playback by the target device.

[0014] The second user voice playback module is used to play the second user voice that the target device responds to in response to the first user voice; the second user voice is matched with the second user account.

[0015] A computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program performing the following steps:

[0016] When the terminal plays application audio generated by the first user account in the application's interactive room, which has the user's voice blocked, the first user's voice that is collected and matches the first user account is obtained.

[0017] The first user's voice is transmitted to the target device corresponding to the second user account in the interactive room; the first user's voice is used for playback by the target device.

[0018] The target device responds to the second user's voice in response to the first user's voice; the second user's voice matches the second user's account.

[0019] A computer-readable storage medium having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0020] When the terminal plays application audio generated by the first user account in the application's interactive room, which has the user's voice blocked, the first user's voice that is collected and matches the first user account is obtained.

[0021] The first user's voice is transmitted to the target device corresponding to the second user account in the interactive room; the first user's voice is used for playback by the target device.

[0022] The target device responds to the second user's voice in response to the first user's voice; the second user's voice matches the second user's account.

[0023] The aforementioned voice interaction method, apparatus, computer equipment, and storage medium, when the terminal plays application audio (with user voice masked) generated by the first user account in the application's interaction room, the voice interaction device connected to the terminal sends the first user's voice matching the first user account to the target device corresponding to the second user account in the interaction room. The target device then plays the second user's voice matching the second user account, responding to the first user's voice. This allows users to interact with each other within the application through the voice interaction device connected to the terminal. During the voice interaction, the application audio (with user voice masked) generated by the first user account in the application's interaction room is played by the terminal, while the user voices used for voice interaction between users are transmitted and played through the voice interaction device connected to the terminal. Playing application audio and user voices from different sound sources through different devices reduces interference between them and improves the effectiveness of the voice interaction.

[0024] A voice interaction method, executed on a terminal connected to a voice interaction device, the method comprising:

[0025] In response to the triggered network configuration operation, display the network configuration result of the voice interaction device through the network configuration operation;

[0026] When the network configuration result is successful, in response to the interactive room joining operation triggered in the application, the room joining result of the interactive room joining operation specified by the interactive room joining operation is displayed.

[0027] When the room joining result indicates that the room joining was successful, and the voice interaction device plays the user voices of the first user account and the second user account in the interactive room during the voice interaction process, the application audio generated by the first user account, which masks the user voice, is played.

[0028] A voice interaction device, applied to a terminal connected to a voice interaction device, the device comprising:

[0029] The network distribution module is used to respond to triggered network distribution operations and display the network distribution results of the voice interaction device through the network distribution operation.

[0030] The room join module is used to respond to the interactive room join operation triggered in the application when the network configuration result is successful, and display the room join result of the interactive room join operation specified by the interactive room join operation.

[0031] The application audio playback module is used to play application audio generated by the first user account (with the user's voice masked) when the room joining result indicates that the room has been successfully joined and the voice interaction device plays the user voices of the first user account and the second user account in the interactive room during the voice interaction process.

[0032] A computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program performing the following steps:

[0033] In response to the triggered network configuration operation, display the network configuration result of the voice interaction device through the network configuration operation;

[0034] When the network configuration result is successful, in response to the interactive room joining operation triggered in the application, the room joining result of the interactive room joining operation specified by the interactive room joining operation is displayed.

[0035] When the room joining result indicates that the room joining was successful, and the voice interaction device plays the user voices of the first user account and the second user account in the interactive room during the voice interaction process, the application audio generated by the first user account, which masks the user voice, is played.

[0036] A computer-readable storage medium having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0037] In response to the triggered network configuration operation, display the network configuration result of the voice interaction device through the network configuration operation;

[0038] When the network configuration result is successful, in response to the interactive room joining operation triggered in the application, the room joining result of the interactive room joining operation specified by the interactive room joining operation is displayed.

[0039] When the room joining result indicates that the room joining was successful, and the voice interaction device plays the user voices of the first user account and the second user account in the interactive room during the voice interaction process, the application audio generated by the first user account, which masks the user voice, is played.

[0040] In the aforementioned voice interaction method, apparatus, computer equipment, and storage medium, when the terminal responds to a triggered network configuration operation and displays the network configuration result of the voice interaction device as successful, it responds to a triggered interactive room joining operation. When the displayed room joining result indicates successful room joining, and the voice interaction device plays the user voices of the first and second user accounts during the voice interaction process in the interactive room, the terminal plays the application audio generated by the first user account, which masks the user voice. Thus, voice interaction between users in the application is achieved through the voice interaction device connected to the terminal. During the voice interaction process, the user voices interacting between users are transmitted and played through the voice interaction device connected to the terminal, while the application audio generated by the first user account in the interactive room, which masks the user voice, is played by the terminal. This allows application audio from different sound sources and user voices to be played through different devices, reducing interference between the application audio and user voices and improving the voice interaction effect.

[0041] A voice interaction method, the method comprising:

[0042] Send application audio generated by the first user account in the application's interactive room, with the user's voice masked, to the terminal, and receive the first user's voice uploaded by the voice interaction device connected to the terminal, which matches the first user account;

[0043] Based on the room information of the interactive room, determine the target device identifier corresponding to the second user account in the interactive room;

[0044] The first user's voice is sent to the target device corresponding to the target device identifier; the first user's voice is used for playback by the target device.

[0045] Receive the second user's voice response from the target device in response to the first user's voice; the second user's voice matches the second user's account.

[0046] The second user's voice is sent to the voice interaction device; the second user's voice is used for playback by the voice interaction device.

[0047] A voice interaction device, the device comprising:

[0048] The first user voice receiving module is used to send application audio generated by the first user account in the application's interactive room, which has masked the user's voice, to the terminal, and to receive the first user voice uploaded by the voice interaction device connected to the terminal that matches the first user account.

[0049] The target device identifier determination module is used to determine the target device identifier corresponding to the second user account in the interactive room based on the room information of the interactive room;

[0050] The first user voice forwarding module is used to send the first user's voice to the target device corresponding to the target device identifier; the first user's voice is used for playback by the target device.

[0051] The second user voice receiving module is used to receive the second user voice feedback from the target device in response to the first user voice; the second user voice is matched with the second user account.

[0052] The second user voice forwarding module is used to send the second user's voice to the voice interaction device; the second user's voice is used for playback by the voice interaction device.

[0053] A computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program performing the following steps:

[0054] Send application audio generated by the first user account in the application's interactive room, with the user's voice masked, to the terminal, and receive the first user's voice uploaded by the voice interaction device connected to the terminal, which matches the first user account;

[0055] Based on the room information of the interactive room, determine the target device identifier corresponding to the second user account in the interactive room;

[0056] The first user's voice is sent to the target device corresponding to the target device identifier; the first user's voice is used for playback by the target device.

[0057] Receive the second user's voice response from the target device in response to the first user's voice; the second user's voice matches the second user's account.

[0058] The second user's voice is sent to the voice interaction device; the second user's voice is used for playback by the voice interaction device.

[0059] A computer-readable storage medium having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0060] Send application audio generated by the first user account in the application's interactive room, with the user's voice masked, to the terminal, and receive the first user's voice uploaded by the voice interaction device connected to the terminal, which matches the first user account;

[0061] Based on the room information of the interactive room, determine the target device identifier corresponding to the second user account in the interactive room;

[0062] The first user's voice is sent to the target device corresponding to the target device identifier; the first user's voice is used for playback by the target device.

[0063] Receive the second user's voice response from the target device in response to the first user's voice; the second user's voice matches the second user's account.

[0064] The second user's voice is sent to the voice interaction device; the second user's voice is used for playback by the voice interaction device.

[0065] The aforementioned voice interaction method, apparatus, computer device, and storage medium send application audio (with user voice masked) generated by a first user account in the application's interaction room to the terminal for playback. Based on the room information, a target device identifier corresponding to a second user account in the interaction room is determined. The first user voice, uploaded by a voice interaction device connected to the terminal and matching the first user account, is sent to the target device corresponding to the target device identifier. The second user voice, responded to by the target device in response to the first user voice, is then sent to the voice interaction device for playback. Thus, voice interaction within the application is achieved through the voice interaction device connected to the terminal. During voice interaction, the application audio (with user voice masked) generated by the first user account in the application's interaction room is played by the terminal, while the user voices used for voice interaction between users are transmitted and played through the voice interaction device connected to the terminal. Playing application audio and user voices from different sound sources through different devices reduces interference between them and improves the effectiveness of voice interaction. Attached Figure Description

[0066] Figure 1 This is a diagram illustrating the application environment of a voice interaction method in one embodiment;

[0067] Figure 2 This is a flowchart illustrating a voice interaction method in one embodiment;

[0068] Figure 3 This is a diagram illustrating the application environment of the voice interaction method in another embodiment;

[0069] Figure 4 This is a diagram illustrating the application environment of the voice interaction method in yet another embodiment;

[0070] Figure 5 This is a schematic diagram illustrating the application of an interruption interaction prompt audio in one embodiment.

[0071] Figure 6 This is a flowchart illustrating the process of creating an interactive room in one embodiment;

[0072] Figure 7 This is a flowchart illustrating the voice interaction method in another embodiment;

[0073] Figure 8 This is a flowchart illustrating the voice interaction method in yet another embodiment;

[0074] Figure 9 This is a structural block diagram of a voice interaction method application system in one embodiment;

[0075] Figure 10 This is a schematic diagram of a structure in one embodiment where the speaker voice channel and the game voice channel are separated;

[0076] Figure 11 This is a schematic diagram illustrating the separate playback of game music and player voice in one embodiment;

[0077] Figure 12 This is a timing diagram of a voice interaction method in one embodiment;

[0078] Figure 13 This is a schematic diagram illustrating how a server records speaker addresses in one embodiment;

[0079] Figure 14 This is a schematic diagram illustrating how the server records the speaker address and the bound room in one embodiment;

[0080] Figure 15 This is a schematic diagram illustrating the server deleting the speaker address and bound room record in one embodiment;

[0081] Figure 16 This is a structural block diagram of a voice interaction device in one embodiment;

[0082] Figure 17 This is a structural block diagram of the voice interaction device in another embodiment;

[0083] Figure 18 This is a structural block diagram of the voice interaction device in yet another embodiment;

[0084] Figure 19 This is an internal structural diagram of a computer device in one embodiment;

[0085] Figure 20 This is a diagram of the internal structure of a computer device in another embodiment. Detailed Implementation

[0086] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0087] The voice interaction method provided in this application can be applied to, for example... Figure 1In the application environment shown, terminal 102 and voice interaction device 104 communicate with server 106 via a network. Voice interaction device 104 is connected to terminal 102, and target device 108 is connected to server 106 via a network. The voice interaction method provided in this application is executed on the voice interaction device. When terminal 102 plays application audio generated by the interaction of the first user account in the application's interaction room (with user voice masked), voice interaction device 104 connected to terminal 102 sends the first user voice matching the first user account to target device 108 corresponding to the second user account in the interaction room via server 106. Target device 108 then plays the second user voice matching the second user account, which is the response from target device 108 to the first user voice. Thus, voice interaction in the application is realized through voice interaction device 104 connected to terminal 102.

[0088] In another embodiment, the voice interaction method provided in this application can be applied to, for example, Figure 1 In the application environment shown, the operation is executed on terminal 102. When terminal 102 responds to the triggered network configuration operation and displays the network configuration result returned by server 106 to voice interaction device 104 as successful, terminal 102 responds to the triggered interactive room joining operation. When the room joining result returned by server 106 indicates that the room has been successfully joined, and voice interaction device 104 plays the user voices of the first user account and the second user account in the interactive room during the voice interaction process, terminal 102 plays the application audio generated by the interaction through the first user account, which has masked the user voice. Thus, the user's voice interaction in the application is realized through voice interaction device 104 connected to terminal 102.

[0089] In yet another embodiment, the voice interaction method provided in this application can be applied to, for example, Figure 1 In the application environment shown, the server 106 sends application audio (with user voice masked) generated by the interaction of the first user account in the application's interactive room to the terminal 102 for playback. The server 106 determines the target device identifier corresponding to the second user account in the interactive room based on the room information, and sends the first user voice, which matches the first user account and is uploaded by the voice interaction device 104 connected to the terminal 102, to the target device 108 corresponding to the target device identifier. The server 106 also sends the second user voice, which is fed back by the target device 108 in response to the first user voice, to the voice interaction device 104 for playback. Thus, the user's voice interaction in the application is realized through the voice interaction device 104 connected to the terminal 102.

[0090] The terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, in-vehicle devices, and portable wearable devices. The voice interaction device 104 can be various devices capable of voice interaction, such as speakers, tablets, in-vehicle devices with voice interaction functions, and portable wearable devices. The server 106 can be implemented using a standalone server or a server cluster composed of multiple servers. The target device 108 can be various personal computers, laptops, smartphones, tablets, in-vehicle devices, speakers, and portable wearable devices.

[0091] In one embodiment, such as Figure 2 As shown, a voice interaction method is provided, which can be applied to... Figure 1 Taking a voice interaction device connected to a terminal as an example, the explanation includes the following steps:

[0092] Step 202: When the terminal plays application audio generated by the first user account in the application's interactive room, which has the user's voice blocked, the collected first user voice that matches the first user account is acquired.

[0093] Voice interaction is a human-computer interaction technology that allows users to interact with computers by speaking to obtain information and services. In some scenarios, voice interaction can make human-computer interaction simpler and more natural. Voice interaction devices possess voice interaction capabilities, enabling human-computer interaction. For example, users can send commands via voice to control the computer to perform corresponding tasks. Voice interaction devices have the function of capturing and playing audio. They can also enable dialogue between users; for example, user A and user B can have a real-time voice conversation through a voice interaction device with an established communication connection. In specific applications, voice interaction devices can be smart speakers or other electronic devices that support voice interaction, such as tablets, in-vehicle devices, or portable wearable devices.

[0094] An application refers to a computer program that runs on a terminal. An application is a computer program designed to perform one or more specific tasks. It runs in user mode, can interact with the user, and has a visual user interface. Each application runs in an independent process and has its own address space; the boundary between different applications is called the process boundary. Specifically, applications can be various types, such as social applications, media applications, and game applications. An interactive room is a platform established based on an application for users to interact and communicate. Interactive rooms typically have corresponding group chats. Users can join an interactive room and communicate via text or voice within the corresponding group chat. In practice, users can trigger the creation of an interactive room within the application and add relevant users to it. Users within the interactive room can communicate; for example, in a game application, users in the interactive room can communicate within the game to collaborate.

[0095] The first user account is the user account logged in on the client application of the terminal. This first user account can interact within the application or interactive room, generating application audio that masks the user's voice. The application audio masks the user's voice; that is, it does not include the voices of other users interacting in the interactive room. The application audio can include audio generated during the application's operation, such as background music and sound effects in a game application, or sound effects and background music in a live streaming application. The first user's voice is matched with the first user account and is the user's voice generated during the interaction corresponding to that account. This first user's voice can be captured by the terminal or a voice interaction device. Specifically, if the first user's voice is directly captured by the voice interaction device, the device can directly process it for subsequent interactive actions; if the first user's voice is captured by the terminal, the terminal can send it to the voice interaction device for further interactive processing.

[0096] The voice interaction method utilizes a voice interaction device connected to a terminal. Users can add this device to an application's interaction room via an installed application. This allows users in the interaction room to separate audio tracks between the terminal and the voice interaction device, enabling voice interaction. Specifically, when the terminal connected to the voice interaction device plays application audio (with user voice masked) generated by the interaction of the first user account within the application's interaction room (e.g., background music or game sound effects generated by the first user account's game interactions), the voice interaction device acquires the first user's voice matched by the first user account. This can be achieved directly through the voice interaction device's voice acquisition.

[0097] Step 204: Transmit the first user's voice to the target device corresponding to the second user account in the interactive room; the first user's voice is used for playback by the target device.

[0098] The second user account is the user account that interacts with the first user account in the interactive room. The second user account can log in on applications on other terminals. The target device is the device corresponding to the second user account for voice interaction. Specifically, the target device can be the terminal corresponding to the second user account, or a voice interaction device connected to the terminal. The target device can play various audio files corresponding to the second user account, such as application audio and user voice.

[0099] Specifically, after obtaining the first user's voice matching the first user account, the voice interaction device transmits the first user's voice to the target device corresponding to the second user account in the interaction room, thereby allowing the first user's voice to be played on the target device. For example, when the target device corresponding to the second user account is the terminal logged into the second user account, the first user's voice can be played on the terminal corresponding to the second user account; if the target device corresponding to the second user account is also a voice interaction device connected to the terminal logged into the second user account, then the first user's voice can be played on the voice interaction device corresponding to the second user account. In a specific implementation, the voice interaction device can send the obtained first user's voice to a server, so that the server can transmit the first user's voice to the target device corresponding to the second user account in the interaction room. For example, the server can determine the target device corresponding to the second user account in the interaction room based on the room information, thereby transmitting the first user's voice to the target device corresponding to the second user account in the interaction room.

[0100] Step 206: Play the second user's voice as a response from the first user's voice to the target device; the second user's voice matches the second user's account.

[0101] The second user voice is the user voice feedback from the second user account. This second user voice can be captured by the target device corresponding to the second user account and transmitted to the voice interaction device corresponding to the first user account. Specifically, after the voice interaction device transmits the first user voice to the target device corresponding to the second user account, the voice interaction device receives the second user voice feedback from the target device in response to the first user voice, which matches the second user account. For example, this could be a reply from the user corresponding to the second user account to the first user voice. The voice interaction device plays this second user voice, thereby realizing voice interaction between the first and second user accounts in the application's interactive room.

[0102] In a specific implementation, after the target device corresponding to the second user account plays the first user voice transmitted by the server and sent by the voice interaction device, the user corresponding to the second user account can provide feedback on the first user voice and generate a second user voice. The target device, such as a terminal or the voice interaction device corresponding to the second user account, collects the second user voice and sends it to the server, so that the server can feed back the second user voice to the voice interaction device, and the voice interaction device can play the second user voice received from the server.

[0103] In the aforementioned voice interaction method, when the terminal plays application audio (with user voice masked) generated by the first user account in the application's interaction room, the voice interaction device connected to the terminal sends the first user's voice, matching the first user account, to the target device corresponding to the second user account in the interaction room. The target device then plays the second user's voice, matching the second user account, in response to the first user's voice. This allows users to interact with each other within the application through the voice interaction device connected to the terminal. During the voice interaction, the application audio (with user voice masked) generated by the first user account in the application's interaction room is played by the terminal, while the user voices used for voice interaction between users are transmitted and played through the voice interaction device connected to the terminal. Playing application audio and user voices from different sound sources through different devices reduces interference between them and improves the effectiveness of the voice interaction.

[0104] In one embodiment, the first user's voice is collected by a voice interaction device; the target device is a voice interaction device corresponding to the second user account and connected to the terminal corresponding to the second user account; the second user's voice is collected by the voice interaction device corresponding to the second user account.

[0105] In this embodiment, the first user voice is collected by a voice interaction device connected to the terminal. Specifically, the user corresponding to the first user account can speak to the voice interaction device connected to the terminal, and the voice interaction device collects the first user voice emitted by the user corresponding to the first user account. The target device corresponding to the second user account is the voice interaction device corresponding to the second user account, and it is connected to the terminal corresponding to the second user account. Specifically, the second user account is logged in on another terminal, and the terminal corresponding to the second user account is connected to another voice interaction device. The voice interaction device corresponding to the second user account can collect voice and play audio. Further, the second user voice is collected by the voice interaction device corresponding to the second user account. For example, the user corresponding to the second user account can speak to the voice interaction device connected to the terminal, and the voice interaction device corresponding to the second user account collects the second user voice emitted by the user corresponding to the second user account.

[0106] In a specific application, such as Figure 3 As shown, a first user logs into the game application on a first terminal using a first user account and joins the interactive room of the game application. The first terminal is connected to a first voice interaction device. A second user logs into the game application on a second terminal using a second user account and joins the interactive room of the game application associated with the first user account. The second terminal is connected to a second voice interaction device. The first user can interact with the game on the first terminal and speak to the first voice interaction device. The first terminal plays application audio generated by the first user through the first user account in the game application, with the user's voice muted, including game background music and game sound effects. The first voice interaction device collects the first user's voice and sends it to the second voice interaction device corresponding to the second user account in the interactive room. Specifically, the first user's voice is first sent to the server, which then forwards it to the second voice interaction device corresponding to the second user account. The second voice interaction device then plays the received first user's voice. The second user can interact with the game on the second terminal. The second terminal plays application audio generated by the second user through the second user account in the game application with the user's voice muted. The second user can speak to the second voice interaction device. The second voice interaction device collects the second user's voice and sends the second user's voice to the first voice interaction device corresponding to the first user account in the interaction room, so that the first voice interaction device can play the second user's voice. In this way, voice interaction between users in the application interaction room is realized through the collaboration of the terminal and the voice interaction device.

[0107] In this embodiment, the acquisition and playback of user voices for each user in the application interaction room are implemented by corresponding voice interaction devices. The application audio, which shields user voices, is played by the terminal. This allows application audio from different sound sources and user voices to be played through different devices, which can reduce interference between application audio and user voices and improve the effect of voice interaction. Moreover, by not having the terminal perform voice acquisition and playback, the terminal's resource usage can be freed up, and the application running efficiency of the terminal can be improved.

[0108] In one embodiment, the voice interaction method further includes: when a third user account without a corresponding voice interaction device exists in the interaction room, when a user voice matching any user account with a corresponding voice interaction device is triggered in the interaction room, the user voice is blocked for the third user account; wherein the user account includes at least one of a first user account and a second user account; and the user voice includes at least one of a first user voice and a second user voice.

[0109] The third user account refers to a user account that does not have a corresponding voice interaction device. That is, the third user account is not configured with a corresponding voice interaction device and cannot achieve voice interaction between users through the voice interaction device. Therefore, the user's voice can be muted from the voice interaction device for this third user account. The user account includes at least one of the first user account and the second user account; the user's voice includes at least one of the first user voice and the second user voice. Specifically, the user voice corresponds to the user account. When the user account is the first user account, the user voice is the first user voice matching the first user account; when the user account is the second user account, the user voice is the first user voice matching the second user account.

[0110] Specifically, if a third user account exists in the interactive room without a corresponding voice interaction device, it indicates that in addition to user accounts using voice interaction devices, there are also user accounts that do not use voice interaction devices. Therefore, when a user's voice matching any user account with a corresponding voice interaction device is triggered in the interactive room, the voice of the third user account is blocked. In a specific application, such as... Figure 4 The interactive room contains a first user account, a second user account, and a third user account. The first user account corresponds to a first terminal connected to a first voice interaction device, and the second user account corresponds to a second terminal connected to a second voice interaction device. The first, second, and third terminals are interconnected for application interaction, such as multiplayer online game interaction. The first and second user accounts can interact via voice interaction devices, and the user voice during this interaction is blocked from the third user account; that is, the third user account cannot access the user voice during the interaction between the first and second user accounts.

[0111] In this embodiment, by blocking the voice of third-party user accounts that do not have corresponding voice interaction devices, the privacy of voice interactions between user accounts that use voice interaction devices can be ensured, and the security of user voices during voice interaction can be improved.

[0112] In one embodiment, restrictions can also be placed on user accounts within the application's interactive room. For example, the interactive room can be established based on the voice interaction device of each user account. That is, each user account joins the interactive room through the corresponding voice interaction device, while user accounts without a corresponding voice interaction device cannot join the interactive room. This ensures that all user accounts in the application's interactive room have the corresponding voice interaction device, and all user accounts in the interactive room can perform voice interaction through the voice interaction device. This ensures that the content of voice interaction through the voice interaction device is not known to user accounts without a corresponding voice interaction device, thereby improving the security of user voice during voice interaction through the voice interaction device.

[0113] In one embodiment, the target device is a terminal that is not connected to a voice interaction device corresponding to the second user account, and the second user's voice is directly collected by the terminal corresponding to the second user account.

[0114] Specifically, the target device corresponding to the second user account is a terminal that is not connected to a voice interaction device. That is, the second user account directly collects and processes user voice data through a terminal that is not connected to a voice interaction device. In practice, in the interactive room, the second user account interacting with the first user account via voice interaction can also interact with the first user account via a terminal that is not connected to a voice interaction device.

[0115] In practice, the first user account in the interactive room interacts via voice through a voice interaction device connected to a corresponding terminal. The second user account, also interacting with the first user account, may or may not have a voice interaction device connected to a corresponding terminal. When the second user account has a voice interaction device connected to a corresponding terminal, it interacts via the same device as the first user account. However, when the second user account does not have a voice interaction device connected to a corresponding terminal, it can directly interact via its own terminal, that is, it interacts with the first user account's voice interaction device through the terminal corresponding to the second user account.

[0116] In this embodiment, when the second user account does not have a voice interaction device connected to the corresponding terminal, the second user account can directly interact with the terminal corresponding to the first user account through the voice interaction device corresponding to the first user account, thereby expanding the application scenarios of voice interaction and ensuring the communication effect of voice interaction.

[0117] In one embodiment, the voice interaction method further includes: when an interaction prompt is triggered, playing an interaction prompt audio that provides interaction prompts for the first user account in the application.

[0118] Interactive prompts are prompts that are generated during application operation and interact with the user within the application. Different applications correspond to different interactive prompts. For example, in game applications, interactive prompts can include information such as situational analysis for both sides and the user's character status. Different trigger conditions can be set for interactive prompts. When the corresponding trigger conditions are met, the voice interaction device can emit corresponding interactive prompt audio to provide feedback to the user. For example, when the application's running time meets the trigger condition, an interactive prompt audio can be used to prompt the user. Specifically, in a live streaming application, when a user watches a particular streamer for a preset duration, the interactive prompt condition is met, and the voice interaction device can provide an interactive prompt audio, such as playing the audio "Follow the streamer and you won't get lost!" to prompt the user to follow the streamer.

[0119] In practical implementation, different interactive prompt audios can correspond to different interactive prompt triggering conditions. These triggering conditions can be preset according to the actual needs of the application and can also be flexibly configured by the user. Specifically, the server can monitor the interaction status of the first user account in the application. If the interactive prompt triggering conditions are met, an interactive prompt is triggered. The server queries the interactive prompt audio corresponding to the triggering conditions and sends the audio to the voice interaction device for playback.

[0120] Furthermore, playing the second user voice as a response from the target device to the first user voice includes: when the target device receives the second user voice as a response to the first user voice, stopping the playback of the interactive prompt audio and playing the second user voice.

[0121] When the voice interaction device is playing interactive prompt audio to prompt the first user account's interaction in the application, if the voice interaction device receives a second user voice response from the target device in response to the first user's voice, the voice interaction device will interrupt the playback of the interactive prompt audio and play the received second user voice, thereby realizing the timely playback of the user's voice during the voice interaction process.

[0122] Specifically, when an interactive prompt is triggered, the voice interaction device acquires and plays the interactive prompt audio for the first user account's interaction within the application. If the voice interaction device receives a second user voice response from the target device corresponding to the second user account, the device stops playing the interactive prompt audio and plays the second user voice matched to the second user account. In practice, when the second user voice response from the target device is received and played, and the interactive prompt audio playback stops, the playback can be directly terminated, indicating the current interactive prompt audio playback is complete, and monitoring for new interactive prompts can continue. Alternatively, the playback can be interrupted, meaning the interactive prompt audio continues playing after the second user voice playback ends. Furthermore, if the first user account triggers a voice interaction while the voice interaction device is playing the interactive prompt audio, such as when the voice interaction device receives a voice message from the user corresponding to the first user account, the voice interaction device also stops playing the interactive prompt audio and acquires the first user voice message from the user corresponding to the first user account for subsequent voice interaction processing.

[0123] In a specific application, such as Figure 5 As shown, when a user logs into their first user account on the terminal and interacts, such as during a game, if an interactive prompt is triggered, the voice interaction device plays a system prompt voice, such as "The economies of both sides are currently similar, please develop steadily...", to prompt the user to continue the game. While the voice interaction device is playing the interactive prompt audio, if it receives a second user voice response from the target device in response to the first user's voice, the voice interaction device stops playing the interactive prompt audio and plays the received second user voice, such as the voice message "Come to the mid lane!" sent by user account Zhang San in the interactive room.

[0124] In this embodiment, an interactive prompt audio is played through a voice interaction device connected to the terminal to provide interactive prompts for the first user account in the application. In addition to enabling voice interaction between users through the voice interaction device, the interactive prompt audio is also played through the voice interaction device to provide interactive prompts for the user, which can improve the interactive processing efficiency of the user application.

[0125] In one embodiment, the voice interaction method further includes: in response to an interactive room joining operation triggered on the terminal, playing a joining prompt audio for the interactive room specified by the joining operation.

[0126] The interactive room joining operation refers to the action of joining an interactive room within the application. This operation is triggered by the user on the terminal, such as by the user clicking the room joining control on the terminal interface. The room joining notification audio is an audio message indicating the result of joining the room, such as a sound effect or voice message indicating that the room has been successfully joined, thus providing a notification to the user.

[0127] Specifically, the voice interaction device responds to the user's interactive room joining operation triggered on the terminal. For example, if the user triggers the room joining control on the terminal interface, thereby triggering the interactive room joining operation, the voice interaction device obtains the room joining prompt audio and plays the room joining prompt audio of the interactive room specified by the interactive room joining operation. For example, by playing a joining success sound effect, the user is prompted that the interactive room has been successfully joined. Voice interaction can be carried out in the interactive room based on the voice interaction device.

[0128] Furthermore, in response to an interactive room exit operation triggered on the terminal, an exit prompt audio for the interactive room specified by the exit operation is played.

[0129] The interactive room exit operation refers to the action of leaving an interactive room within the application. This operation is triggered by the user on the terminal, such as by the user clicking the room exit control on the terminal interface. The room exit prompt audio is an audio message indicating the result of the room exit, such as a sound effect or voice indicating a successful room exit, thus providing a notification to the user.

[0130] Specifically, the voice interaction device responds to the user's interactive room exit operation triggered on the terminal. For example, if the user triggers the room exit control on the terminal interface, thereby triggering the interactive room exit operation, the voice interaction device obtains the exit room prompt audio and plays the exit room prompt audio, such as by playing an exit success sound effect to prompt the user that the interactive room has been successfully exited.

[0131] In this embodiment, users can trigger an operation to join or leave an interactive room on the terminal to join the application's interactive room for voice interaction, or leave the interactive room. This allows application audio and user voice from different sound sources to be played through different devices, reducing interference between application audio and user voice and improving the effect of voice interaction.

[0132] In one embodiment, the voice interaction method further includes: receiving a room join instruction generated based on an interactive room join operation sent by a terminal; generating a room join request according to the room join instruction; using the room join request to request to join an interactive room of the application; sending the room join request to a server and receiving a room join prompt audio from the server.

[0133] The interactive room joining operation refers to the process of joining an interactive room within the application. This operation is triggered by the user on the terminal, such as by the user clicking the room join control on the terminal interface. After triggering the interactive room joining operation, the terminal generates a corresponding room join command and sends it to the voice interaction device connected to the terminal, instructing the voice interaction device to join the corresponding interactive room. The room join request is a request message generated by the voice interaction device based on the room join command sent by the terminal. The room join request can carry information about the room to be joined specified in the room join command, as well as the account information of the first user account. It can also carry information about the voice interaction device itself, such as the device identification information, so that the server can add the first user account to the application's interactive room. The room join notification audio is an audio message indicating the result of joining the room, such as a sound effect or voice message indicating successful room joining, thus providing a notification to the user.

[0134] Specifically, the voice interaction device receives a room-joining command sent by the terminal. This command is generated based on an interactive room-joining operation triggered by the user on the terminal. The terminal then sends the room-joining command generated from this operation to the voice interaction device. Upon receiving the command, the voice interaction device generates a room-joining request. This request requests joining an interactive room within the application. The voice interaction device sends the request to the server, requesting that the server join the corresponding interactive room. Upon receiving the request, the server adds the corresponding first user account and voice interaction device to the interactive room, allowing the user of the first user account to interact with other users via voice through the voice interaction device. While the server processes the room-joining request, it obtains the corresponding result, generates a room-joining prompt audio, and sends this audio back to the voice interaction device to indicate the room-joining result. In addition, the server can also simultaneously send the room joining result back to the terminal to display the room joining result on the terminal. This allows users to know the room joining result through a visual interface on the terminal, and they can also know the room joining result by listening to the room joining prompt audio played by the voice interaction device.

[0135] In this embodiment, the voice interaction device generates a corresponding room join request based on the room join instruction sent by the terminal, sends the room join request to the server to request to join the corresponding interactive room, and plays the room join prompt audio fed back by the server. Thus, the user can realize the joining process of the first user account and the interactive room of the voice interaction device through terminal operation. In this way, voice interaction processing can be carried out in collaboration between the voice interaction device and the terminal, which can reduce the interference between application audio and user voice and improve the effect of voice interaction.

[0136] In one embodiment, generating a room join request based on a room join instruction includes: extracting the account information of the first user account and the interactive room identifier of the room to be joined from the room join instruction; and generating a room join request based on the account information of the first user account, the interactive room identifier, and the device identifier information of the voice interaction device.

[0137] The account information includes identifying details such as account number, username, user ID (Identity Document), linked mobile phone number, linked ID card number, linked social media account, or linked email address. The interactive room identifier is the information for the interactive room to be joined, such as the room ID, room address, and room name. The device identifier is the device information for the voice interaction device, used to identify each voice interaction device; specifically, it can include the device name, device address, device number, and other identifying information.

[0138] Specifically, after receiving a room-joining instruction generated by the terminal based on the interactive room-joining operation, the voice interaction device extracts the account information of the first user account and the interactive room identifier of the room to be joined from the room-joining instruction. For example, the voice interaction device can extract the account information of the first user account and the interactive room identifier of the room to be joined from the account field and room identifier field in the room-joining instruction. Further, the voice interaction device determines its own device identification information, such as its own IP (Internet Protocol) address information. Based on the obtained account information of the first user account, the interactive room identifier, and the device identification information of the voice interaction device, the voice interaction device generates a room-joining request. This room-joining request is used to request to join the application's interactive room.

[0139] In this embodiment, the voice interaction device generates a room join request based on the account information of the first user account and the interactive room identifier of the room to be joined carried in the room join instruction sent by the terminal, as well as the device identifier information of the voice interaction device itself. Thus, the first user account and the voice interaction device can be added to the corresponding interactive room through the room join request. This allows the voice interaction device and the terminal to work together to perform voice interaction processing, which can reduce the interference between application audio and user voice and improve the effect of voice interaction.

[0140] In one embodiment, the voice interaction method further includes: receiving a room exit instruction generated based on an interactive room exit operation sent by a terminal; generating a room exit request based on the room exit instruction; the room exit request being used to request to exit the interactive room of the application; sending the room exit request to a server and receiving an exit room prompt audio from the server.

[0141] The interactive room exit operation is the action to leave an interactive room within the application. This operation is triggered by the user on the terminal, such as by the user clicking the room exit control on the terminal interface. After triggering the exit operation, the terminal generates a corresponding room exit command and sends it to the voice interaction device connected to the terminal, instructing the voice interaction device to exit the corresponding interactive room. The room exit request is a request message generated by the voice interaction device based on the room exit command sent by the terminal. The room exit request can carry information about the room to be exited specified in the room exit command, the account information of the first user account, and information about the voice interaction device itself, such as the device identification information, so that the server can cause the first user account to exit the application's interactive room. The room exit prompt audio is the audio indicating the room exit result, such as a sound effect or voice indicating a successful room exit, thus providing a notification to the user.

[0142] Specifically, the voice interaction device receives a room exit command sent by the terminal. This command is generated based on an interactive room exit operation triggered by the user on the terminal. The terminal then sends the generated room exit command to the voice interaction device. Upon receiving the command, the voice interaction device generates a room exit request to request exit from the application's interactive room. This request is sent to the server, requesting the server to exit the corresponding interactive room. Upon receiving the request, the server removes the corresponding first user account and the voice interaction device from the room. While the server processes the room exit based on the request, it obtains the exit result, generates a corresponding exit prompt audio, and sends this audio back to the voice interaction device to indicate the exit result. Additionally, the server can simultaneously send the exit result back to the terminal for display. Users can then view the exit result visually on the terminal and listen to the exit prompt audio played by the voice interaction device.

[0143] In this embodiment, the voice interaction device generates a corresponding room exit request based on the room exit command sent by the terminal, sends the room exit request to the server to request to exit the corresponding interactive room, and plays the exit room prompt audio fed back by the server. Thus, the user can quickly exit the interactive room through terminal operation, improving the processing efficiency of voice interaction.

[0144] In one embodiment, such as Figure 6 As shown, the voice interaction method also includes the processing of creating an interactive room, specifically including:

[0145] Step 602: When the connection with the server is successful, receive the interactive room creation instruction sent by the terminal.

[0146] The interactive room creation command is sent by the terminal and is used to create interactive rooms within the application. Specifically, the interactive room creation command can be generated based on an interactive room creation operation triggered on the terminal, such as when a user triggers a room creation control on the terminal interface, thereby triggering the interactive room creation operation.

[0147] Specifically, when a voice interaction device successfully connects to the server, it can create an interactive room based on the interactive room creation command sent by the terminal. If the voice interaction device is not connected to the server, it cannot interact with the server, and the server cannot forward the user's voice in the interactive room, meaning that voice interaction processing based on the voice interaction device cannot be achieved.

[0148] Step 604: Generate an interactive room creation request based on the interactive room creation instruction; the interactive room creation request is used to request the server to create an interactive room according to the interactive room creation request.

[0149] The interactive room creation request is a request message generated by the voice interaction device based on the interactive room creation instruction sent by the terminal. The interactive room creation request can carry information about the room to be created and the account information of the first user account, as well as information about the voice interaction device itself, such as the device identification information of the voice interaction device, so that the server can create an interactive room that meets the requirements according to the interactive room creation request.

[0150] Specifically, after receiving an interactive room creation instruction, the voice interaction device further generates an interactive room creation request based on the instruction. This request is used to request the server to create an interactive room according to the request. In practice, the interactive room creation request may carry the account information of the first user account, the interactive room identifier of the room to be created, and the device identifier information of the voice interaction device itself. The server can then create the corresponding interactive room based on the interactive room creation request.

[0151] Step 606: Send an interactive room creation request to the server and play an audio prompt indicating the room creation result from the server.

[0152] The voice interaction device sends an interactive room creation request to the server, requesting the server to create an interactive room according to the request. Upon receiving the request, the server creates the corresponding interactive room, allowing users within the room to interact with other users via voice through the voice interaction device. After processing the room creation request, the server obtains the room creation result, generates a corresponding audio prompt, and sends this audio prompt back to the voice interaction device to indicate the room creation result. Additionally, the server can simultaneously send the room creation result back to the terminal for display. Users can then view the room creation result through a visual interface on the terminal and by listening to the audio prompt indicating the result played by the voice interaction device.

[0153] In this embodiment, the voice interaction device generates a corresponding interactive room creation request based on the interactive room creation instruction sent by the terminal, sends the interactive room creation request to the server to request the server to create an interactive room according to the interactive room creation request, and receives and plays the prompt audio indicating the room creation result from the server. This allows users who join the interactive room to perform voice interaction processing through the collaborative voice interaction device and the terminal, which can reduce the interference between application audio and user voice and improve the effect of voice interaction.

[0154] In one embodiment, before receiving the interactive room creation instruction sent by the terminal when a successful connection with the server is established, the method further includes: receiving a network configuration instruction sent by the terminal; generating a network configuration request based on the network configuration instruction and the device identification information of the voice interaction device; using the network configuration request to request the voice interaction device to establish a connection with the server; sending the network configuration request to the server and playing a prompt audio message from the server indicating the network configuration result.

[0155] The network configuration command is a command sent by the terminal to perform network configuration processing on the voice interaction device. Specifically, it may include network configuration information such as the local area network account password. Network configuration processing refers to establishing a connection between the voice interaction device and the server. After successful connection establishment, the voice interaction device and the server can communicate. The network configuration request carries the network configuration command information and the device identification information of the voice interaction device to be configured. The network configuration request is used to request the voice interaction device to establish a connection with the server. The device identification information of the voice interaction device is the device information used to identify each voice interaction device, specifically including various identification information such as the device name, device address, and device number. The prompt audio indicating the network configuration result is the audio that prompts the voice interaction device about the network configuration result, such as a sound effect or voice indicating successful network configuration, thus prompting the user.

[0156] Specifically, when the voice interaction device is not connected to the server, it receives a network configuration command from the terminal. This command is generated based on a network configuration operation triggered by the user on the terminal, which then sends the generated command to the voice interaction device. Upon receiving the command, the device generates a network configuration request to request a connection between itself and the server. The device sends this request to the server, requesting a connection between them. The server, upon receiving the request, establishes a connection based on it. While the server processes the configuration based on the request, it obtains the configuration result, generates a corresponding audio prompt, and sends this prompt back to the device to indicate the configuration result. In addition, the server can also simultaneously feed back the network configuration results to the terminal to display the network configuration results on the terminal. This allows users to learn about the network configuration results through a visual interface on the terminal. They can also learn about the network configuration results by listening to the prompt audio played by the voice interaction device. When the network configuration result is successful, the voice interaction device and the server can communicate. Specifically, this can be used to transmit and process user data generated during the voice interaction process in the interactive room.

[0157] In this embodiment, the voice interaction device generates a corresponding network configuration request based on the network configuration command sent by the terminal, sends the network configuration request to the server to request the establishment of a connection, and plays the prompt audio indicating the network configuration result fed back by the server. Thus, the user can realize the network configuration processing of the voice interaction device through the terminal operation. In this way, the voice interaction device and the terminal can work together to perform voice interaction processing, which can reduce the interference between application audio and user voice and improve the effect of voice interaction.

[0158] In one embodiment, transmitting a first user voice to a target device corresponding to a second user account in an interactive room includes: sending the first user voice to a server; the first user voice is further used to instruct the server to determine the target device corresponding to the second user account in the interactive room and to forward the first user voice to the target device corresponding to the second user account.

[0159] After obtaining a first user voice message matching a first user account, the voice interaction device transmits the first user voice message to the target device corresponding to a second user account in the interaction room, so that the target device corresponding to the second user account can play the first user voice message. Specifically, after obtaining the first user voice message matching the first user account, the voice interaction device sends the first user voice message to the server. After receiving the first user voice message, the server determines the target device corresponding to the second user account in the interaction room and forwards the first user voice message to the target device corresponding to the second user account. In a specific implementation, after receiving the first user voice message sent by the voice interaction device, the server can determine the room information of the interaction room where the first user account is located, and determine the second user accounts in the interaction room based on the room information, further determine the target devices corresponding to each second user account in the interaction room, and forward the first user voice message to the target device corresponding to the second user account.

[0160] In this embodiment, the server forwards the first user's voice obtained by the voice interaction device to the target device corresponding to the second user account in the interaction room, thereby realizing voice interaction between users in the interaction room based on the voice interaction device. This enables the separation of user voice and application audio between users in the interaction room. By coordinating voice interaction processing between the voice interaction device and the terminal, the interference between application audio and user voice can be reduced, thereby improving the effect of voice interaction.

[0161] In one embodiment, the voice interaction method further includes: receiving interactive prompt audio sent by a server for a first user account to interact in the application; and generating a stop playback command for controlling the cessation of playback of the interactive prompt audio when receiving a second user voice from the server in response to the first user's voice from the target device.

[0162] Interactive prompts are prompts made during application operation, and different applications correspond to different interactive prompts. When an interactive prompt is triggered, the server sends an interactive prompt audio to the voice interaction device. This audio is used to provide interactive prompts for the first user account within the application, and the voice interaction device plays the received audio. Further, when the voice interaction device receives a second user voice response from the server, indicating the target device's response to the first user's voice, the voice interaction device needs to stop playing the interactive prompt audio and instead play the second user's voice. Specifically, upon receiving the second user voice from the server, the voice interaction device generates a stop playback command. This command controls the cessation of interactive prompt audio playback, thereby stopping the playback of the interactive prompt audio and allowing the second user's voice to be played.

[0163] In this embodiment, an interactive prompt audio is played through a voice interaction device connected to the terminal to provide interactive prompts for the first user account in the application. In addition to enabling voice interaction between users through the voice interaction device, the interactive prompt audio is also played through the voice interaction device to provide interactive prompts for the user, which can improve the interactive processing efficiency of the user application.

[0164] In one embodiment, such as Figure 7 As shown, a voice interaction method is provided, which can be applied to... Figure 1 Taking a terminal connected to a voice interaction device as an example, the explanation includes the following steps:

[0165] Step 702: In response to the triggered network configuration operation, display the network configuration result of the voice interaction device through the network configuration operation.

[0166] When the voice interaction device is not connected to the server, the user needs to perform network configuration processing on the voice interaction device to establish a connection between the voice interaction device and the server. The user can trigger the network configuration operation on the terminal, such as by clicking the network configuration control on the terminal interface. When the network configuration is completed, the network configuration result of the network configuration processing of the voice interaction device through the network configuration operation is displayed.

[0167] Specifically, a user can trigger a network configuration operation for a voice-interactive device on the terminal, sending the generated network configuration command to the voice-interactive device. Upon receiving the command, the voice-interactive device generates a network configuration request, which requests a connection between the device and the server. The voice-interactive device then sends this request to the server, requesting a connection between the two. Upon receiving the request, the server establishes a connection with the device. After processing the network configuration based on the request, the server obtains the corresponding configuration result and sends it back to the terminal, which then displays the received result.

[0168] Step 704: When the network configuration result is successful, in response to the interactive room joining operation triggered in the application, display the room joining result of the interactive room specified by the interactive room joining operation.

[0169] The interactive room joining operation refers to the operation of joining an interactive room in the application. The interactive room joining operation is triggered by the user on the terminal, such as when the user triggers the room joining control in the terminal interface, thereby triggering the interactive room joining operation.

[0170] Specifically, when the terminal displays a successful network configuration result, the terminal responds to the user's interactive room joining operation triggered in the application by generating a room joining instruction corresponding to the interactive room joining operation. The terminal sends the room joining instruction to the voice interaction device. After receiving the room joining instruction, the voice interaction device further generates a room joining request based on the room joining instruction. The room joining request is used to request joining the interactive room of the application. The voice interaction device sends the room joining request to the server to request the server to join the corresponding interactive room of the application. After receiving the room joining request, the server adds the corresponding first user account and voice interaction device to the interactive room based on the room joining request, so that the user corresponding to the first user account can interact with other users in the interactive room through the voice interaction device. After the server processes the room joining based on the room joining request, it obtains the corresponding room joining result and feeds the room joining result back to the terminal. After receiving the room joining result fed back by the server, the terminal displays it on the interface.

[0171] Step 706: When the room joining result indicates that the room has been successfully joined, and the voice interaction device plays the user voices of the first user account and the second user account in the interactive room during the voice interaction process, the application audio generated by the first user account, which has masked the user voice, is played.

[0172] In this interactive room, the voice messages of the first and second user accounts during the voice interaction are played by the voice interaction device, while the application audio generated by the first user account (with user voice masked) is played directly by the terminal. The application audio masks user voice; that is, it does not include the voice messages of the users in the interactive room during the interaction. However, the application audio can include audio generated during application operation, such as background music and sound effects in game applications, or sound effects and background music in live streaming applications.

[0173] Specifically, the room joining result displayed on the terminal indicates that the room joining was successful, that is, the first user account has successfully joined the interactive room of the application, and when the voice interaction device corresponding to the first user account plays the user voice of the first user account and the second user account in the interactive room during the voice interaction process, the terminal plays the application audio generated by the interaction of the first user account, which has masked the user voice, so that the application audio and user voice from different sound sources are played through different devices.

[0174] In the aforementioned voice interaction method, when the terminal responds to a triggered network configuration operation and displays a successful network configuration result on the voice interaction device, it responds to a triggered interactive room joining operation. When the displayed room joining result indicates successful room joining, and the voice interaction device plays the user voices of the first and second user accounts during the voice interaction process in the interactive room, the terminal plays the application audio generated by the first user account, which masks the user voice. This allows users to interact with each other in the application through the voice interaction device connected to the terminal. During the voice interaction process, the user voices interacting between users are transmitted and played through the voice interaction device connected to the terminal, while the application audio generated by the first user account in the application's interactive room, which masks the user voice, is played by the terminal. This allows application audio from different sound sources and user voices to be played through different devices, reducing interference between the application audio and user voices and improving the effectiveness of voice interaction.

[0175] In one embodiment, the voice interaction method further includes processing for creating an interactive room. Specifically, a user can trigger an interactive room creation operation on the terminal, such as by triggering a room creation control on the terminal interface. The terminal generates an interactive room creation instruction based on the user-triggered interactive room creation operation and sends the instruction to the voice interaction device, which can then perform interactive room creation processing based on the instruction sent by the terminal.

[0176] Furthermore, after receiving the interactive room creation instruction, the voice interaction device generates an interactive room creation request based on the instruction. This request requests the server to create an interactive room according to the request. Specifically, the interactive room creation request may carry the account information of the first user account, the interactive room identifier of the room to be created, and the device identifier information of the voice interaction device itself. The server can then create the corresponding interactive room based on the request. The voice interaction device sends the interactive room creation request to the server, requesting the server to create the interactive room according to the request. Upon receiving the request, the server creates the corresponding interactive room based on the request, enabling users in the interactive room to interact with other users via voice through the voice interaction device. After the server processes the room creation based on the request, it obtains the corresponding room creation result and feeds it back to the terminal for display. Users can then view the room creation result on the terminal through a visual interface and by listening to an audio prompt indicating the result played by the voice interaction device.

[0177] In one embodiment, the voice interaction method further includes processing for exiting the interactive room. Specifically, the user can trigger an interactive room exit operation on the terminal, such as by triggering a room exit control on the terminal interface. The terminal generates a room exit command based on the user-triggered interactive room exit operation and sends the room exit command to the voice interaction device, which can then process the interactive room exit according to the room exit command sent by the terminal.

[0178] Furthermore, after receiving a room exit command, the voice interaction device generates a room exit request based on the command. This request is used to request exit from the application's interactive room. The voice interaction device sends the room exit request to the server, requesting the server to exit the corresponding interactive room. Upon receiving the room exit request, the server removes the corresponding first user account and voice interaction device from the interactive room. After the server processes the room exit based on the request, it obtains the corresponding room exit result and sends it back to the terminal for display. Users can then view the room exit result on the terminal through a visual interface and by listening to the exit prompt audio played by the voice interaction device.

[0179] In one embodiment, such as Figure 8 As shown, a voice interaction method is provided, which can be applied to... Figure 1 Taking a server connected to both the terminal and the voice interaction device as an example, the explanation includes the following steps:

[0180] Step 802: Send application audio (with user voice masked) generated by the first user account in the application's interactive room to the terminal, and receive the first user voice (matching the first user account) uploaded by the voice interaction device connected to the terminal.

[0181] The application can be any type of application, such as a social application, a media application, or a game application. An interactive room is a platform established based on the application for users to interact and communicate. Interactive rooms typically have corresponding group chats, where users can join and communicate via text or voice in the corresponding group chat. Application audio excludes user voice recordings; that is, it does not include the voices of users interacting within the interactive room. Application audio can include audio generated during application operation, such as background music and sound effects in game applications, and sound effects and background music in live streaming applications.

[0182] Specifically, the server is connected to both the terminal and the voice interaction device. The server sends the application audio (with user voice masked) generated by the interaction of the first user account in the application's interactive room to the terminal, and receives the first user voice, which matches the first user account, uploaded by the voice interaction device connected to the terminal. The first user voice, matched with the first user account, is the user voice generated by the user corresponding to the first user account during the interaction. The first user voice can be captured by the terminal or the voice interaction device.

[0183] Step 804: Based on the room information of the interactive room, determine the target device identifier corresponding to the second user account in the interactive room.

[0184] The room information refers to information related to the interactive room, which may include, but is not limited to, the room name, room identifier, room number, and room member information. The target device identifier is the identification information of the target device corresponding to the second user account, such as the device name, device number, and device address. The target device is the device corresponding to the second user account for voice interaction; specifically, the target device can be the terminal corresponding to the second user account or a voice interaction device connected to the terminal. The target device can play various audio files corresponding to the second user account, such as application audio and user voice.

[0185] Specifically, the server obtains the room information of the interactive room where the first user account is located. For example, it can query the corresponding room information based on the room identifier of the interactive room. Based on the room information of the interactive room, it determines the target device identifier corresponding to the second user account in the interactive room. Specifically, it can extract room member information from the room information, determine the device information of each member based on the room member information, and thus obtain the target device identifier corresponding to the second user account.

[0186] Step 806: Send the first user voice to the target device corresponding to the target device identifier; the first user voice is used for playback by the target device.

[0187] After determining the target device identifier corresponding to the second user account in the interactive room, the server sends the first user's voice to the target device corresponding to the target device identifier, thereby enabling the first user's voice to be played on the target device. For example, when the target device corresponding to the second user account is the terminal logged into the second user account, the first user's voice can be played on the terminal corresponding to the second user account; if the target device corresponding to the second user account is also a voice interaction device, and this voice interaction device is connected to the terminal logged into the second user account, then the first user's voice can be played on the voice interaction device corresponding to the second user account.

[0188] Step 808: Receive the second user voice response from the target device in response to the first user voice; the second user voice matches the second user account.

[0189] The second user voice is the user voice feedback from the second user account. This second user voice can be collected by the target device corresponding to the second user account and transmitted to the server. Specifically, after the server transmits the first user voice to the target device corresponding to the second user account, the server receives the second user voice feedback from the target device that matches the second user account, such as a reply voice from the user corresponding to the second user account in response to the first user voice.

[0190] Step 810: Send the second user's voice to the voice interaction device; the second user's voice is used for playback by the voice interaction device.

[0191] After receiving the second user's voice response from the target device in response to the first user's voice, the server sends the second user's voice to the voice interaction device so that the second user's voice can be played on the voice interaction device, thereby realizing voice interaction between the first user account and the second user account in the application's interactive room.

[0192] In the aforementioned voice interaction method, application audio (with user voice masked) generated by the first user account in the application's interaction room is sent to the terminal for playback. Based on the room information, a target device identifier corresponding to the second user account in the interaction room is determined. The first user voice, uploaded by the voice interaction device connected to the terminal and matching the first user account, is sent to the target device corresponding to the target device identifier. The second user voice, responded to by the target device in response to the first user voice, is then sent to the voice interaction device for playback. Thus, voice interaction within the application is achieved through the voice interaction device connected to the terminal. During voice interaction, the application audio (with user voice masked) generated by the first user account in the application's interaction room is played by the terminal, while the user voices used for voice interaction between users are transmitted and played through the voice interaction device connected to the terminal. Playing application audio and user voices from different sound sources through different devices reduces interference between them and improves the effectiveness of voice interaction.

[0193] In one embodiment, the voice interaction method further includes: receiving an interactive room creation request uploaded by a voice interaction device; creating an interactive room according to the interactive room creation request and obtaining a room creation result; and returning the room creation result to the terminal and the voice interaction device.

[0194] The interactive room creation request is used to request the server to create an interactive room according to the request. This request is generated by the voice interaction device based on the interactive room creation instruction sent by the terminal. The interactive room creation instruction is generated by the terminal based on the user-triggered interactive room creation operation. Specifically, the terminal generates an interactive room creation instruction based on the user-triggered operation and sends it to the voice interaction device. The voice interaction device then sends a further generated interactive room creation request based on the instruction to the server, requesting the server to create the interactive room according to the request.

[0195] Specifically, when the server receives an interactive room creation request uploaded by the voice interaction device, the server creates the interactive room according to the request, such as according to the room size, room name, and room permissions set in the request, and obtains the room creation result. The server returns the room creation result to the terminal and the voice interaction device. In a specific implementation, the server can directly return the room creation result to the terminal for visual display; in addition, the server can also generate a corresponding audio prompt indicating the room creation result and send the audio prompt to the voice interaction device for playback, thereby ensuring that the user can learn about the room creation result through a visual interface on the terminal, and also learn about the room creation result by listening to the audio prompt played by the voice interaction device.

[0196] This application also provides an application scenario in which the above-described voice interaction method is applied. Specifically, the voice interaction method is applied in this scenario as follows:

[0197] In multiplayer online battle arena (MOBA) games, players often communicate via voice chat in group chat rooms for collaborative gameplay. These group chat rooms serve as interactive spaces within the game application, allowing players to communicate through text, voice, and other means. However, currently in MOBA games, the audio channel of the running terminal (such as a smartphone) is often exclusively used by game music or other background music. Since player conversations in the group chat room are still transmitted and played through the game application's running terminal, this audio channel, which includes both game music and user voice, causes crosstalk. This affects the playback quality of the game music and the effectiveness of user voice interaction.

[0198] For competitive games, terminal performance is crucial to players. Network speed, battery consumption, heat dissipation, and terminal memory directly affect game smoothness and response time. Embedding voice communication within the game consumes network bandwidth and terminal memory, significantly increases battery consumption, and can even cause the terminal to overheat, directly impacting the user's gaming experience. The voice interaction method in this embodiment is applied to a smart speaker connected to the terminal running the game application, allowing players to interact via voice. Furthermore, the smart speaker can provide real-time updates on the game status on the running terminal, such as match information. Figure 9 As shown, in the voice interaction method of this embodiment, the terminal is connected to a smart speaker. The terminal plays game music from the game application, while the smart speaker plays the player's voice in the group chat room. Compared to the traditional method where the terminal directly plays both the voice interaction method described in this embodiment and the player's voice in the group chat room, this embodiment separates the game music from the player's voice, allowing them to be played separately by the terminal and the smart speaker. This reduces the terminal's memory usage and power consumption, and improves the terminal's network response speed.

[0199] Currently, voice communication in multiplayer online battle arena (MOBA) games typically relies on temporarily forming group chat rooms with teammates within the game. For example, in games like Honor of Kings or survival games, a team is usually matched with five players. However, if there are two players, such as a couple, and the team size is less than five, the game system will randomly match other players to join. These new players are strangers to the two players in the actual team. Therefore, creating a private group chat room is not possible on the game itself, and if voice communication is enabled, the conversation will be overheard by other unfamiliar players. The voice interaction method provided in this embodiment, however, allows for... Figure 10 As shown, five players log into the game application through five different terminals. Players 1-5 correspond to terminals 1-5 respectively. Terminals 1, 2, and 3 do not have smart speakers, while terminals 4 and 5 can establish a speaker voice channel for voice communication through a smart speaker. Unlike the game voice channel that all five players are connected to, the speaker voice channel established between terminals 4 and 5 cannot be accessed by terminals 1, 2, and 3, thus enabling private group chat between terminals 4 and 5.

[0200] Furthermore, for multiplayer online battle games, game music is also a necessary element to significantly enhance game immersion. For example, survival games require players to listen for footsteps to determine enemy locations. If group chat is enabled, ambient noise from other players will severely interfere with players' ability to hear the original game audio. However, in the voice interaction method provided in this embodiment, such as... Figure 11As shown, the game music is played directly by the terminal, while the player voice communication between players is played by a smart speaker connected to the terminal. The voice interaction separates the game music and player voice in the game application. The player voice of other players in the group chat room and the original game sound come from two different sound sources, which greatly reduces the interference of other players' ambient noise to players and improves the effect of voice interaction.

[0201] Specifically, such as Figure 12 As shown, the user triggers a network configuration operation on the terminal. The terminal generates a corresponding network configuration command based on the operation and sends it to the smart speaker. The smart speaker generates a network configuration request based on the command and sends it to the server. The server processes the network configuration request and sends a successful configuration message back to the smart speaker. After successful configuration, the server records the smart speaker's IP address, which serves as the smart speaker's unique identifier. Subsequently, the user sends a voice command to the smart speaker to create a group chat room. The smart speaker requests room creation from the server, and upon successful creation, the server returns the room's unique identifier, the room ID. The user then issues a room-joining command to the smart speaker, such as "join room1." The smart speaker requests to join the room from the server. After successfully joining the room, the server can identify the IP addresses of all smart speakers in room1. When a user in the room sends a voice message through a smart speaker, the server forwards this message to other smart speakers with the same IP address in the room, which then automatically play it for the user.

[0202] Furthermore, such as Figure 13 As shown, before use, the smart speaker connects to the internet and the server, registering the speaker's IP address with the server. The server's database can record the IP address of each player's corresponding smart speaker, and the server uses this IP address to push voice messages to each player's corresponding smart speaker. Figure 13 In the database, the server records the IP addresses of the smart speakers corresponding to players A, B, C, and D.

[0203] Furthermore, to ensure that group chat rooms are limited to users within the group and messages are not pushed to other users, a group chat room ID needs to be created. Smart speakers used by users participating in the group chat must be bound to this room ID, and this information is recorded on the server. Only smart speakers bound to this room ID can communicate with each other in the group chat; smart speakers not bound to this room ID will not receive group chat messages. Figure 14As shown, players A, B, and C have all joined the group chat room 1. The smart speakers associated with players A, B, and C are all bound to room 1, while player D's smart speaker is not bound to room 1. Players A, B, and C can interact via voice through their smart speakers in room 1, while player D cannot access this voice dialogue channel and therefore cannot know the content of the voice conversation. Furthermore, after all speakers are bound to room IDs, when player A sends a message to the server through their speaker, the server finds that player A's speaker is bound to room 1, then queries the smart speakers bound to room 1, and pushes the voice message through the IP addresses of other users' speakers, thus pushing the voice message to the smart speakers associated with the other players in the group chat room.

[0204] Furthermore, such as Figure 15 As shown, after player C's speaker sends a request to leave the room to the server, the server deletes the roomid bound to IP_C. At this time, if player A sends a voice message through the corresponding smart speaker, the server will query other smart speakers with the same roomid bound to player A's smart speaker and push the voice message to the corresponding smart speaker, thus realizing the push of voice messages.

[0205] The voice interaction method provided in this embodiment can transmit voice messages without relying on third-party social accounts, but only using the IP address of the smart speaker device as the communication ID; moreover, the user voice generated during voice interaction does not occupy the terminal's audio channel, which can assist the user in voice communication when the terminal is occupied, thereby improving the voice communication effect.

[0206] It should be understood that, although Figure 2 , 6 The steps in flowcharts -8 and 12 are shown sequentially as indicated by the arrows; however, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order in which these steps are performed, and they can be executed in other orders. Furthermore, Figure 2 , 6 - At least some of the steps in -8 and 12 may include multiple steps or multiple stages, which are not necessarily completed at the same time, but may be executed at different times, and the execution order of these steps or stages is not necessarily sequential, but may be executed in turn or alternately with other steps or at least some of the steps or stages in other steps.

[0207] In one embodiment, such as Figure 16As shown, a voice interaction device 1600 is provided, applied to a voice interaction device connected to a terminal. This device can be a software module, a hardware module, or a combination of both as part of a computer device. Specifically, the device includes: a first user voice acquisition module 1602, a first user voice transmission module 1604, and a second user voice playback module 1606, wherein:

[0208] The first user voice acquisition module 1602 is used to acquire the first user voice that matches the first user account when the terminal plays application audio generated by the first user account in the application's interactive room, which has masked the user's voice.

[0209] The first user voice transmission module 1604 is used to transmit the first user's voice to the target device corresponding to the second user account in the interactive room; the first user's voice is used for playback by the target device.

[0210] The second user voice playback module 1606 is used to play the second user voice that the target device responds to in response to the first user voice; the second user voice is matched with the second user account.

[0211] In one embodiment, the first user's voice is collected by a voice interaction device; the target device is a voice interaction device corresponding to the second user account, which is connected to the terminal corresponding to the second user account; the second user's voice is collected by the voice interaction device corresponding to the second user account.

[0212] In one embodiment, the system further includes a blocking processing module, configured to block user voice for the third user account when a user voice matching any user account with a corresponding voice interaction device is triggered in the interactive room, provided that a third user account without a corresponding voice interaction device exists in the interactive room; wherein the user account includes at least one of a first user account and a second user account; and the user voice includes at least one of a first user voice and a second user voice.

[0213] In one embodiment, the target device is a terminal that is not connected to a voice interaction device corresponding to the second user account, and the second user's voice is directly collected by the terminal corresponding to the second user account.

[0214] In one embodiment, the system further includes an interactive prompt playback module, configured to play interactive prompt audio for the first user account in the application when an interactive prompt is triggered; and a second user voice playback module 1606, configured to stop playing the interactive prompt audio and play the second user voice when the target device responds to the second user voice.

[0215] In one embodiment, the system further includes a room joining module and a room exit module; wherein: the room joining module is configured to play a room joining prompt audio for the interactive room specified by the interactive room joining operation triggered on the terminal; the room exit module is configured to play a room exit prompt audio for the interactive room exit specified by the interactive room exit operation triggered on the terminal.

[0216] In one embodiment, the application further includes a join instruction receiving module, a join request obtaining module, and a join request processing module; wherein: the join instruction receiving module is used to receive a room join instruction generated based on the interactive room join operation sent by the terminal; the join request obtaining module is used to generate a room join request according to the room join instruction; the room join request is used to request to join the interactive room of the application; the join request processing module is used to send the room join request to the server and receive the room join prompt audio from the server.

[0217] In one embodiment, the join request acquisition module includes an instruction parsing module and a request generation module; wherein: the instruction parsing module is used to extract the account information of the first user account and the interactive room identifier of the room to be joined from the room join instruction; the request generation module is used to generate a room join request based on the account information of the first user account, the interactive room identifier and the device identifier information of the voice interaction device.

[0218] In one embodiment, the application further includes an exit instruction receiving module, an exit request obtaining module, and an exit request processing module; wherein: the exit instruction receiving module is used to receive a room exit instruction generated by the terminal based on the interactive room exit operation; the exit request obtaining module is used to generate a room exit request based on the room exit instruction; the room exit request is used to request to exit the interactive room of the application; and the exit request processing module is used to send the room exit request to the server and receive the exit room prompt audio from the server.

[0219] In one embodiment, the system further includes a creation instruction receiving module, a creation request obtaining module, and a creation request processing module; wherein: the creation instruction receiving module is used to receive an interactive room creation instruction sent by the terminal when a successful connection with the server is established; the creation request obtaining module is used to generate an interactive room creation request based on the interactive room creation instruction; the interactive room creation request is used to request the server to create an interactive room according to the interactive room creation request; and the creation request processing module is used to send the interactive room creation request to the server and play a prompt audio indicating the room creation result fed back by the server.

[0220] In one embodiment, the system further includes a network distribution instruction receiving module, a network distribution request obtaining module, and a network distribution request processing module; wherein: the network distribution instruction receiving module is used to receive network distribution instructions sent by the terminal; the network distribution request obtaining module is used to generate a network distribution request based on the network distribution instruction and the device identification information of the voice interaction device; the network distribution request is used to request the voice interaction device to establish a connection with the server; and the network distribution request processing module is used to send the network distribution request to the server and play a prompt audio indicating the network distribution result fed back by the server.

[0221] In one embodiment, the first user voice transmission module 1604 is further configured to send a first user voice to the server; the first user voice is further configured to instruct the server to determine the target device corresponding to the second user account in the interactive room, and to forward the first user voice to the target device corresponding to the second user account.

[0222] In one embodiment, the system further includes a prompt audio receiving module and a stop command generating module; wherein: the prompt audio receiving module is used to receive interactive prompt audio sent by the server for the first user account to interact with the application; the stop command generating module is used to generate a stop playback command to control the stopping of playback of the interactive prompt audio when it receives a second user voice response from the target device in response to the first user's voice sent by the server.

[0223] In one embodiment, such as Figure 17 As shown, a voice interaction device 1700 is provided, applied to a terminal connected to a voice interaction device. This device can be a software module, a hardware module, or a combination of both, integrated into a computer device. Specifically, the device includes: a network configuration module 1702, a room joining module 1704, and an application audio playback module 1706, wherein:

[0224] The network distribution module 1702 is used to respond to the triggered network distribution operation and display the network distribution result of the voice interaction device through the network distribution operation;

[0225] The room joining module 1704 is used to display the room joining result of the interactive room joining operation triggered in the application when the network configuration result is successful.

[0226] The application audio playback module 1706 is used to play application audio generated by the first user account that masks the user's voice when the room joining result indicates that the room has been successfully joined and the voice interaction device plays the user voice of the first user account and the second user account in the interactive room during the voice interaction process.

[0227] In one embodiment, such as Figure 18As shown, a voice interaction device 1800 is provided. This device can be a software module, a hardware module, or a combination of both as part of a computer device. Specifically, the device includes: a first user voice receiving module 1802, a target device identifier determination module 1804, a first user voice forwarding module 1806, a second user voice receiving module 1808, and a second user voice forwarding module 1810, wherein:

[0228] The first user voice receiving module 1802 is used to send application audio generated by the first user account in the application's interactive room, which has masked the user's voice, to the terminal, and to receive the first user voice uploaded by the voice interaction device connected to the terminal that matches the first user account.

[0229] The target device identifier determination module 1804 is used to determine the target device identifier corresponding to the second user account in the interactive room based on the room information of the interactive room;

[0230] The first user voice forwarding module 1806 is used to send the first user voice to the target device corresponding to the target device identifier; the first user voice is used for playback by the target device.

[0231] The second user voice receiving module 1808 is used to receive the second user voice feedback from the target device in response to the first user voice; the second user voice is matched with the second user account.

[0232] The second user voice forwarding module 1810 is used to send the second user's voice to the voice interaction device; the second user's voice is used for playback by the voice interaction device.

[0233] In one embodiment, the system further includes a creation request receiving module, a room creation module, and a creation result feedback module; wherein: the creation request receiving module is used to receive an interactive room creation request uploaded by the voice interaction device; the room creation module is used to create an interactive room according to the interactive room creation request and obtain a room creation result; and the creation result feedback module is used to return the room creation result to the terminal and the voice interaction device.

[0234] For specific limitations regarding the voice interaction device, please refer to the limitations on the voice interaction method above, which will not be repeated here. Each module in the aforementioned voice interaction device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in the computer device in hardware form, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0235] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 19As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores data. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements a voice interaction method.

[0236] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 20 As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a voice interaction method. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0237] Those skilled in the art will understand that Figure 19 and Figure 20 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0238] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0239] In one embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0240] In one embodiment, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and executes the computer instructions, causing the computer device to perform the steps in the above method embodiments.

[0241] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0242] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0243] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A voice interaction method, characterized in that, The method, performed on a voice interaction device connected to a terminal, includes: Receive the network configuration command sent by the terminal; A network distribution request is generated based on the network distribution command and the device identification information of the voice interaction device; The network configuration request is sent to the server, and a prompt audio indicating the network configuration result is played in response to the server; the network configuration request is used to request the voice interaction device to establish a connection with the server; When a successful connection is established with the server, the terminal sends an interactive room creation command. An interactive room creation request is generated according to the interactive room creation instruction; the interactive room creation request carries information about the room to be created, the account information of the first user account, and the device identification information of the voice interaction device; the interactive room creation request is used to request the server to create an interactive room according to the interactive room creation request. Send the interactive room creation request to the server and play the audio prompt indicating the room creation result from the server. When the terminal plays application audio generated by the first user account in the interactive room of the application, with the user's voice masked, the first user's voice that matches the first user account is acquired; the first user's voice is acquired by the voice interaction device; the interactive room is a platform for interactive communication established based on the application; the application audio does not include the voice during the interaction process in the interactive room; The first user voice is sent to the server; the first user voice is used to instruct the server to determine the room information of the interactive room, determine the second user account in the interactive room based on the room information, determine the target device corresponding to the second user account, and forward the first user voice to the target device corresponding to the second user account; the first user voice is used for playback by the target device; the target device is a voice interaction device corresponding to the second user account and is connected to the terminal corresponding to the second user account. Play the second user voice that the target device responds to in response to the first user voice; the second user voice is matched with the second user account; the second user voice is collected by the voice interaction device corresponding to the second user account.

2. The method according to claim 1, characterized in that, The method further includes: If a third user account without a corresponding voice interaction device exists in the interactive room, when a user voice that matches any user account with a corresponding voice interaction device is triggered in the interactive room, the user voice of the third user account is blocked. The user account includes at least one of the first user account and the second user account; the user voice includes at least one of the first user voice and the second user voice.

3. The method according to claim 1, characterized in that, The target device is a terminal that is not connected to a voice interaction device corresponding to the second user account, and the second user's voice is directly collected by the terminal corresponding to the second user account.

4. The method according to claim 1, characterized in that, The method further includes: When an interactive prompt is triggered, play the interactive prompt audio for the first user account in the application; Playing the second user voice feedback from the target device in response to the first user voice includes: When the target device responds to the second user's voice in response to the first user's voice, the interactive prompt audio is stopped, and the second user's voice is played.

5. The method according to any one of claims 1 to 4, characterized in that, The method further includes: In response to the interactive room joining operation triggered on the terminal, play the joining room prompt audio of the interactive room joining operation specified by the interactive room joining operation; In response to an interactive room exit operation triggered on the terminal, an exit prompt audio for exiting the interactive room specified by the interactive room exit operation is played.

6. The method according to claim 5, characterized in that, The method further includes: Receive the room join instruction generated by the interactive room join operation sent by the terminal; A room join request is generated based on the room join instruction; the room join request is used to request to join an interactive room of the application; Send the room join request to the server and receive the room join prompt audio from the server.

7. The method according to claim 6, characterized in that, The step of generating a room join request based on the room join instruction includes: Extract the account information of the first user account and the interactive room identifier of the room to be joined from the room join instruction; A room join request is generated based on the account information of the first user account, the interactive room identifier, and the device identifier information of the voice interaction device.

8. The method according to claim 5, characterized in that, The method further includes: Receive the room exit command generated by the interactive room exit operation sent by the terminal; A room exit request is generated based on the room exit instruction; the room exit request is used to request to exit the interactive room of the application; Send the room exit request to the server and receive the room exit prompt audio from the server.

9. The method according to claim 4, characterized in that, The method further includes: Receive interactive prompt audio sent by the server for the first user account to interact with in the application; When the server receives a second user voice response from the target device in response to the first user voice, a stop playback command is generated to control the cessation of playback of the interactive prompt audio.

10. A voice interaction method, characterized in that, The method, performed on a terminal connected to a voice interaction device, includes: In response to a triggered network configuration operation, a network configuration instruction generated based on the network configuration operation is sent to the voice interaction device, and the network configuration result of the network configuration processing performed on the voice interaction device through the network configuration operation is displayed; the network configuration instruction is used to instruct the voice interaction device to generate a network configuration request based on the network configuration instruction and the device identification information of the voice interaction device, send the network configuration request to the server, and play a prompt audio indicating the network configuration result fed back by the server; the network configuration request is used to request the voice interaction device to establish a connection with the server; When the voice interaction device successfully connects to the server, an interactive room creation command is sent to the voice interaction device. This command instructs the voice interaction device to generate an interactive room creation request, send the request to the server, and play a prompt audio message from the server indicating the room creation result. The interactive room creation request carries information about the room to be created, the account information of the first user account, and the device identification information of the voice interaction device. The request requests the server to create the interactive room according to the command. When the network configuration result is successful, in response to an interactive room joining operation triggered in the application, the room joining result for joining the interactive room specified by the interactive room joining operation is displayed. When the room joining result indicates that the room joining was successful, and the voice interaction device plays the user voice of the first user account and the second user account in the interactive room during the voice interaction process, the application audio generated by the first user account with the user voice muted is played. During the voice interaction, the first user voice matched by the first user account is collected by the voice interaction device and sent to the server by the voice interaction device; the first user voice is used to instruct the server to determine the room information of the interaction room, determine the second user account in the interaction room based on the room information, determine the voice interaction device corresponding to the second user account, and forward the first user voice to the voice interaction device corresponding to the second user account; the second user voice matched by the second user account is collected by the voice interaction device corresponding to the second user account; the interaction room is a platform for interactive communication established based on the application; the application audio does not include the voice during the interaction process in the interaction room.

11. A voice interaction method, characterized in that, Executed on a server, the method includes: The system receives a network configuration request sent by a voice interaction device and establishes a connection between the voice interaction device and the server based on the network configuration request. The network configuration request is generated by the voice interaction device based on a network configuration instruction and the device identification information of the voice interaction device. The network configuration instruction is sent from the terminal to the voice interaction device. The system receives an interactive room creation request uploaded by the voice interaction device; creates an interactive room according to the interactive room creation request, and obtains a room creation result; returns the room creation result to the terminal and the voice interaction device; the interactive room creation request is generated by the voice interaction device according to the interactive room creation instruction, and the interactive room creation request carries information about the room to be created, account information of the first user account, and device identification information of the voice interaction device; the interactive room creation instruction is sent by the terminal to the voice interaction device. The system sends application audio (with user voice masked) generated by the first user account in the interactive room of the application to the terminal, and receives first user voice uploaded by the voice interaction device connected to the terminal that matches the first user account; the first user voice is collected by the voice interaction device; the interactive room is a platform for interactive communication established based on the application; the application audio does not include voice during the interaction process in the interactive room; Based on the room information of the interactive room, the target device identifier corresponding to the second user account in the interactive room is determined; The first user voice is sent to the target device corresponding to the target device identifier; the first user voice is used for playback by the target device; the target device is a voice interaction device corresponding to the second user account and is connected to the terminal corresponding to the second user account. The target device receives a second user voice response in response to the first user voice; the second user voice is matched with the second user account; the second user voice is collected by the voice interaction device corresponding to the second user account. The second user's voice is sent to the voice interaction device; the second user's voice is used for playback by the voice interaction device.

12. A voice interaction device, characterized in that, The device is used in a voice interaction device connected to a terminal, the device comprising: A network distribution instruction receiving module is used to receive network distribution instructions sent by the terminal; The network distribution request acquisition module is used to generate a network distribution request based on the network distribution command and the device identification information of the voice interaction device; The network configuration request processing module is used to send the network configuration request to the server and play a prompt audio indicating the network configuration result fed back by the server; the network configuration request is used to request the voice interaction device to establish a connection with the server. A command receiving module is created to receive the interactive room creation command sent by the terminal when a successful connection with the server is established. A request creation module is used to generate an interactive room creation request according to the interactive room creation instruction; the interactive room creation request carries information about the room to be created, account information of the first user account, and device identification information of the voice interaction device; the interactive room creation request is used to request the server to create an interactive room according to the interactive room creation request. Create a request processing module, which is used to send the interactive room creation request to the server and play the prompt audio from the server indicating the room creation result; The first user voice acquisition module is used to acquire the first user voice that matches the first user account when the terminal plays application audio generated by the first user account in the interaction room of the application, which has the user voice masked; the first user voice is acquired by the voice interaction device; the interaction room is a platform for interactive communication established based on the application; the application audio does not include the voice in the interaction room during the interaction process; A first user voice transmission module is used to send the first user voice to the server; the first user voice is used to instruct the server to determine the room information of the interactive room, determine the second user account in the interactive room according to the room information, determine the target device corresponding to the second user account, and forward the first user voice to the target device corresponding to the second user account; the first user voice is used for playback by the target device; the target device is a voice interaction device corresponding to the second user account and is connected to the terminal corresponding to the second user account. The second user voice playback module is used to play the second user voice that the target device responds to in response to the first user voice; the second user voice is matched with the second user account; the second user voice is collected by the voice interaction device corresponding to the second user account.

13. The apparatus according to claim 12, characterized in that, The device further includes: The blocking module is used to block the user voice of the third user account when a user voice that matches any user account with a corresponding voice interaction device is triggered in the interactive room, in the case where there is a third user account in the interactive room that does not have a corresponding voice interaction device. The user account includes at least one of the first user account and the second user account; the user voice includes at least one of the first user voice and the second user voice.

14. The apparatus according to claim 12, characterized in that, The target device is a terminal that is not connected to a voice interaction device corresponding to the second user account, and the second user's voice is directly collected by the terminal corresponding to the second user account.

15. The apparatus according to claim 12, characterized in that, The device further includes: An interactive prompt playback module is used to play interactive prompt audio for the first user account in the application when an interactive prompt is triggered. The second user voice playback module is further configured to stop playing the interactive prompt audio and play the second user voice when the target device responds to the second user voice in response to the first user voice.

16. The apparatus according to any one of claims 12 to 15, characterized in that, The device further includes: The room joining module is used to respond to an interactive room joining operation triggered on the terminal by playing a room joining prompt audio for joining the interactive room specified by the interactive room joining operation; The room exit module is used to respond to an interactive room exit operation triggered on the terminal by playing an exit prompt audio for leaving the interactive room specified by the interactive room exit operation.

17. The apparatus according to claim 16, characterized in that, The device further includes: A room join instruction receiving module is used to receive a room join instruction generated based on the interactive room join operation sent by the terminal; The join request acquisition module is used to generate a room join request based on the room join instruction; the room join request is used to request to join the interactive room of the application; The request processing module is used to send the room join request to the server and receive the room join prompt audio from the server.

18. The apparatus according to claim 17, characterized in that, The join request acquisition module is further configured to extract the account information of the first user account and the interactive room identifier of the room to be joined from the room join instruction; and generate a room join request based on the account information of the first user account, the interactive room identifier and the device identifier information of the voice interaction device.

19. The apparatus according to claim 16, characterized in that, The device further includes: The exit instruction receiving module is used to receive the room exit instruction generated by the terminal based on the interactive room exit operation; The exit request acquisition module is used to generate a room exit request based on the room exit instruction; the room exit request is used to request to exit the interactive room of the application; The exit request processing module is used to send the room exit request to the server and receive the exit room prompt audio from the server.

20. The apparatus according to claim 15, characterized in that, The device further includes: The audio prompt receiving module is used to receive interactive prompt audio sent by the server for the first user account to interact with the application. The stop instruction generation module is used to generate a stop playback instruction to control the stopping of the interactive prompt audio when it receives a second user voice response from the target device in response to the first user voice sent by the server.

21. A voice interaction device, characterized in that, A device for use in a terminal connected to a voice interaction device, the device comprising: The network configuration module is used to respond to a triggered network configuration operation by sending a network configuration command generated based on the network configuration operation to the voice interaction device, and displaying the network configuration result of the network configuration processing performed on the voice interaction device through the network configuration operation; the network configuration command is used to instruct the voice interaction device to generate a network configuration request based on the network configuration command and the device identification information of the voice interaction device, send the network configuration request to the server, and play a prompt audio indicating the network configuration result fed back by the server; the network configuration request is used to request the voice interaction device to establish a connection with the server; The device is further configured to send an interactive room creation instruction to the voice interaction device when the voice interaction device successfully connects to the server. The interactive room creation instruction instructs the voice interaction device to generate an interactive room creation request according to the instruction, send the interactive room creation request to the server, and play a prompt audio from the server indicating the room creation result. The interactive room creation request carries information about the room to be created, account information of the first user account, and device identification information of the voice interaction device. The interactive room creation request is used to request the server to create an interactive room according to the interactive room creation request. The room joining module is used to display the room joining result of joining the interactive room specified by the interactive room joining operation triggered in the application when the network configuration result is successful. An application audio playback module is used to play application audio generated by the first user account (with user voice masked) when the room joining result indicates successful room joining and the voice interaction device plays user voices of the first user account and the second user account during the voice interaction process in the interactive room. During the voice interaction process, the first user voice matched by the first user account is collected by the voice interaction device and sent to the server by the voice interaction device. The first user voice is used to instruct the server to determine the room information of the interactive room, determine the second user account in the interactive room based on the room information, determine the voice interaction device corresponding to the second user account, and forward the first user voice to the voice interaction device corresponding to the second user account. The second user voice matched by the second user account is collected by the voice interaction device corresponding to the second user account. The interactive room is a platform for interactive communication established based on the application. The application audio does not include the voices generated during the interaction process in the interactive room.

22. A voice interaction device, characterized in that, The device includes: The device is used to receive a network configuration request sent by a voice interaction device, and establish a connection between the voice interaction device and the server based on the network configuration request; the network configuration request is generated by the voice interaction device based on a network configuration instruction and the device identification information of the voice interaction device, and the network configuration instruction is sent by the terminal to the voice interaction device; A request receiving module is created to receive an interactive room creation request uploaded by the voice interaction device. The interactive room creation request is generated by the voice interaction device according to the interactive room creation instruction. The interactive room creation request carries information about the room to be created, the account information of the first user account, and the device identification information of the voice interaction device. The interactive room creation instruction is sent by the terminal to the voice interaction device. The room creation module is used to create an interactive room according to the interactive room creation request and obtain the room creation result. A result feedback module is created to return the room creation result to the terminal and the voice interaction device; The first user voice receiving module is used to send application audio (with user voice masked) generated by the first user account in the interactive room of the application to the terminal, and to receive the first user voice uploaded by the voice interaction device connected to the terminal that matches the first user account; the first user voice is collected by the voice interaction device; the interactive room is a platform for interactive communication established based on the application; the application audio does not include the voice during the interaction process in the interactive room; The target device identifier determination module is used to determine the target device identifier corresponding to the second user account in the interactive room based on the room information of the interactive room; the target device is a voice interaction device corresponding to the second user account and connected to the terminal corresponding to the second user account. A first user voice forwarding module is used to send the first user voice to the target device corresponding to the target device identifier; the first user voice is used for playback by the target device. The second user voice receiving module is used to receive the second user voice fed back by the target device in response to the first user voice; the second user voice is matched with the second user account; the second user voice is collected by the voice interaction device corresponding to the second user account. The second user voice forwarding module is used to send the second user voice to the voice interaction device; the second user voice is used for playback by the voice interaction device.

23. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 11.

24. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 11.

25. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 11.

Images