Voice interaction method, device, equipment, medium and product

Abstract

The embodiment of the invention discloses a voice interaction method, device and equipment, a medium and a product, which can be applied to the technical field of data processing. The method comprises the steps that an interaction entrance is displayed in a comment display page in a manner of being associated with a first voice comment, and the first voice comment belongs to a preset content type; in response to a trigger operation for the interaction entrance, displaying a voice input page, the voice input page being used for indicating at least one of content associated with the first voice comment, user information issuing the first voice comment, and target associated content having a target association relationship with the first voice comment; inputting a second voice comment through the voice input page; and in response to release of the second voice comment, displaying the second voice comment and a target association relationship between the second voice comment and the first voice comment. By adopting the method and the device, the interaction richness of the first voice comment and the comment display page can be improved, so that the interaction effect of the first voice comment and the comment display page can be improved.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to voice interaction methods, apparatus, devices, media and products. Background Technology

[0002] With the rapid development of internet technology and the diversification of information dissemination channels, users' participation in and interaction with online content has increased significantly. As a core interactive carrier connecting content creators and users, the comment function is becoming increasingly important.

[0003] In existing technologies, traditional comment interaction methods are mostly limited to basic interactive operations such as replying and liking, which makes the interaction methods relatively simple and affects the interactive effect of the comment display page. Summary of the Invention

[0004] This application provides a voice interaction method, apparatus, device, medium, and product that can improve the interactivity of a first voice comment, thereby improving the interactivity of the comment display page. Through rich interactive methods, the interactive effect of the first voice comment can be improved, thereby improving the interactive effect of the comment display page.

[0005] On one hand, embodiments of this application disclose a voice interaction method, characterized in that the method includes: An interactive entry point is displayed on the comment display page in association with the first voice comment, which belongs to the pre-defined content type; In response to a trigger operation on the interactive entry point, a voice input page corresponding to the first voice comment is displayed. The voice input page is used to indicate at least one of the following: content associated with the first voice comment, user information of the user who posted the first voice comment, and target associated content that has a target association relationship with the first voice comment. Enter a second voice comment via the voice input page; In response to the publication of the second voice comment, the second voice comment and the target association between the second voice comment and the first voice comment are displayed in the comment display area where the first voice comment is located. The second voice comment belongs to a predetermined content type.

[0006] On one hand, embodiments of this application disclose a voice interaction method, characterized in that the method includes: The target audio playback entry is displayed in association with the audio comment on the comment display page. The audio comment is a pre-defined content type. In response to a trigger operation targeting the target audio playback entry, the target audio content is played. The target audio content is obtained based on an audio comment and / or at least one sub-audio comment under the audio comment. Any sub-audio comment in the at least one sub-audio comment has a target association relationship with the audio comment or other sub-audio comments under the audio comment. Any sub-audio comment belongs to a predetermined content type.

[0007] On one hand, embodiments of this application disclose a voice interaction device, characterized in that the device includes: The display module is used to display the interactive entry point associated with the first voice comment on the comment display page. The first voice comment belongs to a predetermined content type. The display module is also used to respond to a trigger operation on the interactive entry point and display a voice input page corresponding to the first voice comment. The voice input page is used to indicate at least one of the following: content associated with the first voice comment, user information of the user who published the first voice comment, and target associated content that has a target association relationship with the first voice comment. The input module is used to input a second voice comment via the voice input page; The display module is also used to respond to the publication of a second voice comment by displaying the second voice comment in the comment display area where the first voice comment is located, as well as the target association between the second voice comment and the first voice comment, wherein the second voice comment belongs to a predetermined content type.

[0008] On one hand, embodiments of this application disclose a voice interaction device, characterized in that the device includes: The display module is used to display the target audio playback entry in association with the audio comment on the comment display page. The audio comment belongs to a predefined content type. The playback module is used to play the target audio content in response to a trigger operation on the target audio playback entry. The target audio content is obtained based on the audio comment and / or at least one sub-audio comment under the audio comment. Any sub-audio comment in the at least one sub-audio comment has a target association relationship with the audio comment or other sub-audio comments under the audio comment. Any sub-audio comment belongs to a predetermined content type.

[0009] One embodiment of this application provides a computer device, including a memory and a processor; the memory is connected to the processor, the memory is used to store a computer program, and the processor is used to invoke the computer program so that the computer device performs the method provided in any of the above embodiments.

[0010] One aspect of this application provides a computer-readable storage medium storing a computer program adapted to be loaded and executed by a processor, so that a computer device having a processor performs the method provided in any of the above aspects.

[0011] One aspect of this application provides a computer program product, which includes a computer program stored in a computer-readable storage medium. The computer program is adapted to be read and executed by a processor so that a computer device having a processor performs the method provided in any of the above aspects.

[0012] In this embodiment, a computer device can display an interactive entry point associated with a first voice comment on a comment display page. The first voice comment belongs to a predetermined content type. In response to a trigger operation on the interactive entry point, a voice input page corresponding to the first voice comment can be displayed. The voice input page is used to indicate at least one of the following: content associated with the first voice comment, user information of the user who published the first voice comment, and target associated content that has a target association relationship with the first voice comment. A second voice comment is entered via the voice input page. In response to publishing the second voice comment, the second voice comment and the target association relationship between the second and first voice comments can be displayed in the comment display area where the first voice comment is located. The second voice comment belongs to a predetermined content type. As can be seen from the above, this embodiment provides a novel interactive entry point for a first voice comment belonging to a predetermined content type. Through this interactive entry point, new interactions with the first voice comment can be achieved. Clearly, this embodiment adds new interactive methods for the first voice comment, which can improve the richness of the first voice comment's interaction, thereby improving the richness of the interaction on the comment display page where the first voice comment is located. Through rich interactive methods, the interactive effect of the first voice comment can be improved, thereby improving the interactive effect of the comment display page. Attached Figure Description

[0013] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 This is a schematic diagram of the structure of a voice interaction system provided in an embodiment of this application; Figure 2 This is a schematic diagram of a voice interaction scenario provided in an embodiment of this application. Figure 1 ; Figure 3This is a schematic diagram of a voice interaction scenario provided in an embodiment of this application. Figure 2 ; Figure 4 This is a flowchart illustrating a voice interaction method provided in an embodiment of this application. Figure 1 ; Figure 5 This is a schematic diagram of a voice interaction scenario provided in an embodiment of this application. Figure 3 ; Figure 6 This is a schematic diagram of a voice interaction scenario provided in an embodiment of this application. Figure 4 ; Figure 7 This is a schematic diagram of a voice interaction scenario provided in an embodiment of this application. Figure 5 ; Figure 8 This is a schematic diagram of a voice interaction scenario provided in an embodiment of this application. Figure 6 ; Figure 9 This is a schematic diagram of a voice interaction scenario provided in an embodiment of this application. Figure 7 ; Figure 10 This is a schematic diagram of a voice interaction scenario provided in an embodiment of this application. Figure 8 ; Figure 11 This is a flowchart illustrating a voice interaction method provided in an embodiment of this application. Figure 2 ; Figure 12 This is a schematic diagram of a voice interaction scenario provided in an embodiment of this application. Figure 9 ; Figure 13 This is a schematic diagram of a voice interaction scenario provided in an embodiment of this application. Figure 10 ; Figure 14 This is a schematic diagram of a voice interaction scenario provided in an embodiment of this application. Figure 10 one; Figure 15 This is a schematic diagram of a voice interaction scenario provided in an embodiment of this application. Figure 10 two; Figure 16 This is an interactive flowchart of a voice interaction method provided in an embodiment of this application; Figure 17 This is a flowchart illustrating a voice interaction method provided in an embodiment of this application. Figure 3 ; Figure 18 This is a schematic diagram of a voice interaction scenario provided in an embodiment of this application. Figure 10 three; Figure 19 This is a schematic diagram of the structure of a voice interaction device provided in an embodiment of this application. Figure 1 ; Figure 20 This is a schematic diagram of the structure of a voice interaction device provided in an embodiment of this application. Figure 2 ; Figure 21 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0015] The technical solutions in the embodiments of this application will now be described with reference to the accompanying drawings.

[0016] The following are explanations of some key terms used in this application: "In response to" indicates the state in which a corresponding event occurs or a condition is met. The timing of subsequent actions performed in response to this event or condition is not necessarily strongly correlated with the time when the event occurs or the condition is met. For example, in some cases, subsequent actions may be performed immediately when the event occurs or the condition is met; while in other cases, subsequent actions may be performed some time after the event occurs or the condition is met.

[0017] Triggered operations refer to actions performed on information (such as controls) provided by a computer device. These operations send corresponding instructions to the computer device, triggering it to execute the next task. The next task triggered by different triggered operations on different information can all be pre-programmed. These triggered operations can be performed manually by the user; for example, clicks, double-clicks, long presses, and swipes performed by the user on content displayed on the computer screen are all triggered operations. In some cases, these triggered operations can also be executed by the computer device based on a pre-defined program.

[0018] Published content: This refers to content information that users publish in advance or in real-time on the content platform. It can include text, images, audio, and video, and is therefore also called multimedia content. It can be displayed in the form of notes, articles, video files, video streams, etc. The specific content information included in published content can be adjusted accordingly for different scenarios, and the content information in the published content can be determined by the publisher.

[0019] The comment display page can be understood as a page used to display comments (including voice comments). The comment display page can also show interactive information about the comments, such as the number of views, likes, and favorites.

[0020] Comments can be understood as comment data on published content. In this embodiment, comments mainly include voice comments, also known as audio comments. Voice comments can be understood as comment data that can be presented in audio format. Optionally, voice comments can also be combined with at least one of text comments, image comments, and emoticon comments to form multimodal comments.

[0021] Please see Figure 1 , Figure 1 This is a schematic diagram of the structure of a voice interaction system provided in an embodiment of this application. Figure 1 As shown, the voice interaction system may include terminal devices (such as device 11a, device 12a, and device 13a) and server 100a. It is understood that... Figure 1 The number of terminal devices and servers shown is merely illustrative; any number of terminal devices and servers can be used as needed. Terminal devices (such as devices 11a, 12a, and 13a) can communicate with servers via a network (i.e., through a medium that provides a communication link via wired, wireless communication links, or fiber optic cables, etc.) to transmit data.

[0022] It is understood that a client can run on the terminal device (such as device 12a), which can be a program providing local services to the user (also known as the business object or operation object). Server 100a can be the server corresponding to the client, and a program running on server 100a can provide resources, service data, and other services to the client. It is understood that the client running on the terminal device can be any type of client, such as a social client, an instant messaging client (e.g., a conferencing client), an entertainment client (e.g., a live streaming client), a multimedia client (e.g., a video client), an information client (e.g., a news client), a shopping client, or any other multimedia client with voice content interaction capabilities. The specific type of application client is not limited here.

[0023] A client, also known as an application client, business client, etc., allows users to log in with an account and post or interact with voice comments. For example, the client running on device 11a corresponding to user U1 can log in with account ZH1, and then retrieve comment data for the posted content from the server and display it on device 11a.

[0024] It is understood that terminal devices (such as device 11a) may include, but are not limited to, mobile phones, computers, smart voice interaction devices, smart home appliances, vehicle terminals, aircraft, smart speakers, etc., without limitation. The server 100a may be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms, without limitation.

[0025] Please see Figure 2 , Figure 2 This is a schematic diagram of a voice interaction scenario provided in an embodiment of this application. Figure 1 The implementation of this voice interaction scenario can be performed on the terminal device, or it can be performed between the terminal device and the server; no limitation is made here. For ease of description and understanding, this application embodiment uses the terminal device as an example, that is, the terminal device is used as a computer device. The terminal device can be one of the aforementioned... Figure 1 Any one of the terminal devices in the corresponding embodiment.

[0026] like Figure 2 As shown, the terminal device can display a comment display page 20a of the published content. This embodiment does not limit the published content and can determine it according to the actual application scenario. The terminal device displays comment data on the comment display page 20a. This embodiment does not limit the content modality of the comment data and can include at least one of images, audio, and text. Figure 2 Example comment display page 20a includes 7 comments, with 2 independent comments currently displayed. These are the comment data displayed in comment display area 201d (hereinafter referred to as the first comment data for ease of description) and the comment data displayed in comment display area 202d (hereinafter referred to as the second comment data for ease of description).

[0027] Figure 2 The first comment data in the example was posted by a user named "ai". This first comment data is a multimodal comment, including text comments, such as... Figure 2 The example "Let's sing a song together" also includes voice commentary 201a. Figure 2 Example voice comment 201a is a 4-second song clip, and the comment display page 20a can display this information, such as... Figure 2 The example shown is voice recognition prompt 203a, namely... Figure 2The displayed message "Singing detected" is converted to text using the voice comment 201a. The text content is as follows: Figure 2 Example: "Unforgettable xx, unforgettable xx".

[0028] Figure 2 The second set of comment data in the example was also posted by a user named "ai". This second set of comment data is a multimodal comment, including text comments, such as... Figure 2 The example "Wishing everyone eternal happiness" also includes voice commentary 201b. Figure 2 Example voice comment 201b is a 4-second song clip, and the comment display page 20a can display this information, such as... Figure 2 The example shown is voice recognition prompt 203b, namely... Figure 2 The displayed message "Singing detected" is the text content of the voice comment 201b after being converted to text. Figure 2 Example of "New Year xx".

[0029] In this embodiment, the first voice comment refers to a voice comment on the comment display page that belongs to a predetermined content type (which can be a voice comment at any level, such as a first-level voice comment or a second-level voice comment). The predetermined content type refers to a pre-set content type. This embodiment does not limit the predetermined content type and can pre-set it according to the needs of the actual application scenario, including but not limited to song content types, poetry content types, idiom content types, local language content types (such as Cantonese, English, etc.), and story content types. If the predetermined content type is a song content type, then the first voice comment in this embodiment refers to a voice comment on the comment display page that belongs to the song content type, such as... Figure 2 Example voice commentary 201a and voice commentary 201b, in other words, Figure 2 Both voice comments 201a and 201b in the examples can be used as the first voice comment. If the predetermined content type is poetry, then the first voice comment in this embodiment refers to the voice comment on the comment display page that belongs to the poetry content type. For example, if the voice content of voice comment 2z is poetry (e.g., "The bright moonlight shines before my window"), then voice comment 2z can be used as the first voice comment in this embodiment. If the predetermined content type is idiom, then the first voice comment in this embodiment refers to the voice comment on the comment display page that belongs to the idiom content type. For example, if the voice content of voice comment 2x is an idiom (e.g., "completely clean"), then voice comment 2x can be used as the first voice comment in this embodiment.

[0030] For ease of understanding and description, this application sets the predetermined content type as song content type. If the predetermined content type is other content type, such as the poetry content type, idiom content type, local language content type, story content type, etc. in the example above, the specific implementation method can be found in the following description of song content type.

[0031] It is understood that when voice comment 201a and voice comment 201b are used as the first voice comment, the subsequent processing of both by the terminal device and the user's operation on both are the same. Therefore, this application embodiment uses voice comment 201a as the first voice comment for detailed description. For the specific implementation of other voice comments belonging to the predetermined content type in actual application scenarios, please refer to the description of voice comment 201a, which will not be repeated here.

[0032] Since voice commentary 201a belongs to the pre-defined content type ( Figure 2 as well as Figure 3 All content types are set to song content type), and the terminal device can display the interactive entry 202a in association with the voice comment 201a (which serves as a first voice comment) on the comment display page 20a, such as Figure 2 The example of the continue singing entry does not limit the association between the voice comment 201a and the interactive entry 202a in this embodiment of the application. It can be set according to the actual application scenario. Any entry or control that triggers the continue singing of the voice comment 201a can be called the interactive entry 202a.

[0033] Understandable, Figures 2-3 The interfaces and controls shown in the accompanying drawings described below are merely some reference forms. In actual business scenarios, developers can design according to product requirements. This application embodiment does not limit the specific form of the interfaces and controls involved. For example, when the predetermined content type is idiom content, the interactive entry in this application embodiment can be presented as "idiom chain" on the product; when the predetermined content type is poetry content, the interactive entry in this application embodiment can be presented as "poetry chain" on the product; when the predetermined content type is story content, the interactive entry in this application embodiment can be presented as "story chain".

[0034] In response to the trigger operation of the interactive entry 202a, the terminal device displays the voice input page 20c corresponding to the first voice comment. This application embodiment does not limit the relationship between the comment display page 20a and the voice input page 20c. It can be set according to the actual application scenario, including but not limited to the comment display page 20a and the voice input page 20c being two independent pages, the voice input page 20c being a floating page on the comment display page 20a, and the voice input page 20c being superimposed on the comment display page 20a.

[0035] The terminal device displays the voice input control 201c on the voice input page 20c; please refer to the following: Figure 2 as well as Figure 3 , Figure 3 This is a schematic diagram of a voice interaction scenario provided in an embodiment of this application. Figure 2 .like Figure 2 as well as Figure 3 As shown, in response to a trigger operation on the voice input control 201c, the terminal device records a voice comment 202c and displays the recorded voice comment 202c on the voice input page 20c. This embodiment of the application will not provide a detailed description of the voice comment 202c recording process; please refer to the following text. Figure 4 The description of step S103 in the corresponding embodiment.

[0036] Please see again. Figure 3 The user corresponding to the terminal device performs a posting operation on the voice comment 202c, for example, the user corresponding to the terminal device triggers... Figure 3 In the example of the sending control 203c, the terminal device responds to the publishing operation for the voice comment 202c, in the voice comment 201a ( Figure 2 as well as Figure 3 In the comment display area 201d where the first voice comment example is voice comment 201a), the voice comment 202c used to sing along to voice comment 201a is displayed. Figure 3 Let's take the user's account name in the client as an example, corresponding to the terminal device, as Az.

[0037] In this embodiment of the application, the second voice comment refers to interaction with the first voice comment. Figure 2 as well as Figure 3 Taking singing in response as an example, in practical applications it can be voice comments for interactive activities such as singing in response. Therefore, the second voice comment can be understood as a sub-voice comment of the first voice comment. For example, if the first voice comment is a level one comment, then the second voice comment is a level two comment; if the first voice comment is a level two comment, then the second voice comment is a level three comment.

[0038] In practical applications, the second voice comment can be a song used to sing along with the first voice comment; that is, the second voice comment also belongs to the predetermined content type, such as... Figure 3 The example voice comment 202c is a song, so the terminal device can display this information on the comment display page, such as... Figure 3 The example shown is voice recognition prompt 204c, which is... Figure 3 The displayed message "Singing detected" indicates that the voice comment 202c has been converted from speech to text, and the text content is as follows: Figure 3 Example of "regardless of the day...".

[0039] In practical applications, the second voice comment can also be a simple description used to respond to the first voice comment. In this case, the second voice comment does not belong to the predetermined content type. A simple description refers to a description made by a user with the main purpose of stating facts, expressing opinions, and sharing experiences, using everyday and colloquial language. Its biggest difference from the first voice comment is that it does not have a melody.

[0040] As described above, this application embodiment provides a novel interactive entry point for the first voice comment belonging to a predetermined content type. Through this interactive entry point, the user can sing along to the first voice comment. Obviously, this application embodiment adds new interactive methods to the first voice comment, which can improve the interactivity of the first voice comment and, consequently, improve the interactivity of the comment display page where the first voice comment is located. Through rich interactive methods, the interactive effect of the first voice comment can be improved, thereby improving the interactive effect of the comment display page.

[0041] It should be noted that all user data collected in this application is collected with the user's consent and authorization, and the collection, use, and processing of related user data must comply with the relevant laws, regulations, and standards of the relevant regions. All content involved in the application (such as voice comments, including but not limited to songs, poems, idioms, and stories) is copyrighted. For example, this application can display prompts before and during the collection of user data to inform the user that their data is being collected. This ensures that the application only begins the steps to collect user data after receiving confirmation from the user regarding the prompt; otherwise (i.e., without receiving confirmation from the user), the steps to collect user data end, meaning no user data is collected. Furthermore, the text content in the examples of this application's embodiments is generated after converting the voice comments into text.

[0042] It is understood that the above scenarios are merely examples and do not constitute a limitation on the application scenarios of the technical solutions provided in the embodiments of this application. The technical solutions of this application can also be applied to other scenarios. For example, as those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0043] Based on the above description, this application proposes a voice interaction method. Please refer to [link to relevant documentation]. Figure 4 , Figure 4 This is a flowchart illustrating a voice interaction method provided in an embodiment of this application. Figure 1 This method can be executed by a computer device, which can be a terminal device (such as the one mentioned above). Figure 1 (Device 11a in the text). The voice interaction method may include the following steps S101-S104.

[0044] S101. Display an interactive entry point associated with the first voice comment on the comment display page. The first voice comment belongs to the pre-defined content type.

[0045] Specifically, the comment display page shows the comment data for published content. Published content can be text and image content (referred to as text and image content), video content (referred to as video content), live content (referred to as live content, i.e., content that includes live images), and live stream content (referred to as live stream content), etc. As mentioned above... Figure 2 As shown in the example, the comment display page can be a subpage of the content display page. The content display page is used to display the published content. This content display page can show detailed information about the published content and also display interactive controls for the published content, such as... Figure 2 The comment control 401a, comment control 402a, like control 403a, favorite control 404a, and comment display control 405a are included.

[0046] The comment display page 20a can display the account information of the interactive accounts (including the accounts that post comments and the accounts that interact with the comments), such as the account avatar and account name. The displayed account information can be all or part of the account information of the interactive account.

[0047] The recognition process for the first voice comment can be performed by the terminal device or by the server (such as the one mentioned above). Figure 1The method described in 100a) can be executed by the terminal device and the server together. This application does not limit the method for recognizing the first voice comment, nor does it limit the method itself. This includes, but is not limited to, the extraction of acoustic and semantic features, and the analysis of the extracted multi-dimensional features, such as multimodal analysis using acoustic and semantic models, to determine that the first voice comment belongs to a predetermined content type. It is understood that the recognition process for all voice comments on the comment display page is the same.

[0048] The display location, display format, and display conditions of the interactive entry point can be set according to the actual application scenario. For ease of explanation and understanding, [the following is a simplified explanation]. Figure 2 Taking interactive entry 202a as an example, the display conditions of interactive entry 202a include, but are not limited to, the following: 1. When the voice comment 201a is not triggered by the user, the terminal device can hide and display the interaction entry 202a in the comment display page 20a. In response to the triggering operation of the voice comment 201a, while playing the voice comment 201a, the interaction entry 202a is displayed in association with the voice comment 201a in the comment display page 20a.

[0049] 2. When the voice comment 201a has been triggered by the user, the interaction entry 202a can be fixedly displayed on the comment display page 20a.

[0050] 3. When the comment voice 201a is triggered by the user, the interaction entry 202a is displayed on the comment display page 20a for a preset display duration (e.g., 1 minute). If the interaction entry 202a is retried within the preset display duration, the terminal device executes step S102 and re-timing the display duration of the interaction entry 202a. If the display duration of the interaction entry 202a reaches the preset display duration, i.e., it is not retried within the preset display duration, the terminal device cancels the display of the interaction entry 202a. It can be understood that the conditions for re-displaying the interaction entry 202a are the same as those for display condition 1 above.

[0051] 4. When the comment voice 201a has been triggered by the user and the user completes the interaction with the comment voice 201a (e.g., sing along), the interaction entry 202a is canceled. It is understood that the conditions for the redisplay of the interaction entry 202a are the same as the display condition 1 above.

[0052] For ease of understanding, this application embodiment uses song content type as an example to define the content type. It is understood that the comment display page may include one or more first voice comments; please refer to [the relevant documentation / reference]. Figure 5 , Figure 5 This is a schematic diagram of a voice interaction scenario provided in an embodiment of this application. Figure 3 .like Figure 5As shown, the comment display page 20a includes voice comments 201a and 201b, both of which belong to a predetermined content type. At this time, the terminal device can display an interaction entry 202a associated with voice comment 201a and an interaction entry 40b associated with voice comment 201b on the comment display page 20a. Figure 5 The interactive entry 40b is presented as an example of a "Keep Singing" entry.

[0053] S102. In response to a trigger operation on the interactive entry point, a voice input page corresponding to the first voice comment is displayed. The voice input page is used to indicate at least one of the following: content associated with the first voice comment, user information of the user who published the first voice comment, and target associated content that has a target association relationship with the first voice comment.

[0054] Specifically, it can be understood that the user who publishes the content (hereinafter referred to as the content publishing user for ease of distinction) can trigger an interactive entry point to respond to the first voice comment, for example... Figure 5 The content publisher is user with the account name "ai". This user published a piece of content (also known as multimedia content) and used the voice comment function on comment page 20a to add a voice comment to their own post, such as... Figure 5 Examples of voice commentary 201a and voice commentary 201b. Subsequently, the content publishing user (i.e....) Figure 5 The example AI user performs a sing-along action on their own posted voice comment 201b, specifically by triggering... Figure 5 If the interactive entry 40b is triggered, the terminal device will display the voice input page for the voice comment 201b in response to the trigger operation of the interactive entry 40b.

[0055] Unlike content publishers, browsing users can also trigger an interactive entry point to respond to the first voice comment, such as... Figure 2 as well as Figure 3 The example given is for Az users, who are different from ai users. Please refer to the above text for the implementation process of this scenario. Figures 2-3 The descriptions in the corresponding embodiments are not repeated here.

[0056] The first audio comment can be posted by a publishing account (the account that published the content; for clarity, this will be referred to as the content publishing account below) or by a browsing user's (not the content publishing user) browsing account. Users who respond to the first audio comment can be either the content publishing user or the browsing user. In other words, the participants in the process of publishing the first audio comment and the participants in the process of responding to it can overlap.

[0057] S103. Enter a second voice comment via the voice input page.

[0058] Specifically, in response to a continuous press operation on the voice input control on the voice input page, the last x seconds of the voice content in the first voice comment are played, where x is a positive number; in response to the completion of the playback of the last x seconds of the voice content, voice content is started to be recorded on the voice input page until the press operation on the voice input control is canceled, and the voice content recorded on the voice input page is identified as the second voice comment; the second voice comment is displayed on the voice input page.

[0059] The specific process of playing the last x seconds of voice content in the first voice comment in response to a continuous press operation on the voice input control on the voice input page may include: displaying a guidance start prompt and the corresponding text content of the last x seconds of voice content in the first voice comment on the voice input page in response to a continuous press operation on the voice input control on the voice input page, the guidance start prompt including a guidance progress bar; sequentially highlighting the guidance progress bar; starting to play the last x seconds of voice content in response to the completion of the highlighting of the guidance progress bar, and updating the guidance start prompt to a guidance playback prompt; and sequentially highlighting the continuously displayed text content in response to the playback progress of the last x seconds of voice content.

[0060] This application does not limit the operation method of triggering the voice input control. It can be set according to the actual application scenario. One feasible operation method of triggering the voice input control is to continuously press the voice input control. Another feasible operation method of triggering the voice input control is to trigger the voice input control for the first time to indicate that the last x seconds of the voice content in the first voice comment will start playing, and after the last x seconds of the voice content in the first voice comment has finished playing, the voice content will start recording. The second time the voice input control is triggered, it indicates that the voice content recording is complete. Therefore, the terminal device determines the recorded voice content as the second voice comment.

[0061] Please see also Figure 6 , Figure 6 This is a schematic diagram of a voice interaction scenario provided in an embodiment of this application. Figure 4 .like Figure 6As shown, the terminal device displays the voice input control 201c on the voice input page 20c, and can display prompts associated with the voice input control 201c, such as... Figure 6 The example in the text is "Press and hold to continue singing". If the user of the terminal device continuously presses the voice input control 201c, the terminal device can respond to the continuous press operation on the voice input control 201c by displaying a guided start prompt message and the text content corresponding to the last x seconds of the voice content in the first voice comment on the voice input page 20c. In addition, the voice input page 20c can also display interactive prompt messages, such as... Figure 6 The message says, "You can continue singing after the song finishes playing; please keep pressing and holding."

[0062] The guidance start prompt information includes a guidance progress bar 401c and guidance prompt text 402c, such as... Figure 6 The example in the text is "The intro is about to play." For ease of understanding, the first voice commentary example here is... Figure 2 In the voice comment 201a, the text content 403c corresponding to the last x seconds of the voice content in voice comment 201a is exemplified as "Unforgettable xx, unforgettable xx". The length x of the guiding voice can be set according to the actual application scenario; it is an adjustable parameter that can be preset by the application client or made available to the user corresponding to the application client. Therefore, the user corresponding to the application client can set the value of x according to their needs. For example, if x is set to 4 seconds, the guiding voice is the last 4 seconds of the voice content in the first voice comment. If the playback duration of the first voice comment exceeds 4 seconds, such as 8 seconds, the terminal device plays the last 4 seconds of the 8-second voice content; if the playback duration of the first voice comment is equal to or less than 4 seconds, such as 3 seconds, the terminal device plays the 3-second voice content.

[0063] Please participate again. Figure 6 The voice input page 20c displays a guidance progress bar 401c, which has a prompting effect. The terminal device displays the guidance progress bar 401c in an orderly manner. Please refer to [the documentation / reference]. Figure 7 , Figure 7 This is a schematic diagram of a voice interaction scenario provided in an embodiment of this application. Figure 5 .like Figure 7 As shown, the terminal device first starts from the beginning of the guide progress bar (e.g., Figure 7 The progress bar (as shown in 404c) will begin to highlight, and the progress bar will be highlighted sequentially until the end of the progress bar, as shown in 404c. Figure 7 The progress bar in the guide is shown in 405c. It is important to emphasize that... Figures 6-8 The example scenario requires the user of the terminal device to continuously press the voice input control 201c.

[0064] Once the progress bar is fully highlighted, the terminal device will respond by playing the last x seconds of audio content. Please refer to [link / reference]. Figure 8 , Figure 8 This is a schematic diagram of a voice interaction scenario provided in an embodiment of this application. Figure 6 .like Figure 8 As shown, when the terminal device starts playing the last x seconds of audio content, the guidance start prompt message is updated to guidance playback prompt message 406c, specifically by canceling the display of the guidance progress bar. Figure 6 The example guide text 402c is updated to guide playback information 406c, as shown below. Figure 8 The example shown is "Playing the previous song". During the above description, text content 403c remains displayed. The terminal device responds to the playback progress of the last x seconds of the audio content by sequentially highlighting the continuously displayed text content 403c. Specifically, it first highlights the text content 403c from its starting point, then highlights it according to the playback progress, such as... Figure 8 As shown in text content 407c, when the last x seconds of audio content finishes playing, the terminal device also completes the highlighting of the text content.

[0065] This application does not limit the method of highlighting, but can be set according to the actual application scenario, including but not limited to making the highlighted text bold, or making the color of the highlighted text and image different from the non-highlighted parts, or making the highlighted parts animated.

[0066] Please see again. Figure 8 Upon completion of the last x seconds of voice content playback, the terminal device begins recording voice content on the voice input page 20c. Specifically, the user corresponding to the terminal device sings along to the first voice comment, for example, the first voice comment is "Unforgettable xx, unforgettable xx", which is the first two lines of a song. The user then sings the last two lines, for example, "Regardless of the weather...". When the user finishes singing (singing along), the continuous pressing of the voice input control 201c is canceled. The terminal device, in response to the cancellation of the pressing operation on the singing input control, identifies the voice content recorded on the voice input page 20c as voice comment 202c and displays voice comment 202c on the voice input page 20c. It can also display the voice duration of voice comment 202c, such as... Figure 8 The example is 4 seconds.

[0067] In summary, the content output on the voice input page associated with the first voice comment includes the last x seconds of the first voice comment's audio content and the corresponding text content. If the predetermined content type is a song content type, then in scenarios where the application client possesses song copyrights, the content associated with the first voice comment may also include the song's accompaniment.

[0068] The user information for posting the first voice comment includes at least one of the user's avatar and username; the target association matches the predetermined content type. When the predetermined content type is a song, the target association can be a singing relationship. When the predetermined content type is a poem, idiom, story, etc., the target association can be a chain relationship.

[0069] The target-related content that has a target association relationship with the first voice comment can include the content that follows. For example, when the target association relationship is a singing relay relationship, the content that follows can be at least one of the lyrics of the song being sung or the accompaniment of the song being sung; for example, when the target association relationship is a chain relationship, the content that follows can be poems, idioms, local language content, stories, etc.

[0070] S104. In response to publishing the second voice comment, the second voice comment and the target association between the second voice comment and the first voice comment are displayed in the comment display area where the first voice comment is located. The second voice comment belongs to a predetermined content type.

[0071] Specifically, the voice input page includes a delete control and a send control for the second voice comment; if a trigger operation is performed on the delete control, the second voice comment is deleted on the voice input page; if a trigger operation is performed on the send control, the second voice comment is published; in response to the successful publication of the second voice comment, the second voice comment and the target association relationship between the second voice comment and the first voice comment are displayed in the comment display area where the first voice comment is located.

[0072] Please see again. Figure 8 The terminal device can display a delete control 40d for the voice comment 202c and a send control 203c on the voice input page 20c. If the user corresponding to the terminal device triggers the delete control 40d, the terminal device responds to the trigger operation of the delete control 40d by deleting the voice comment 202c on the voice input page 20c. At this time, the voice input page 20c can be restored to its previous state. Figure 6 On the voice input page 20c, the user corresponding to the terminal device can exit the current singing or resume singing the first voice comment. If the user resumes singing the first voice comment, the terminal device will execute step S103 again.

[0073] If the user corresponding to the terminal device triggers the sending control 203c, the terminal device responds to the triggering operation of the sending control 203c by publishing a voice comment 202c. Another feasible implementation is as follows: The terminal device packages the voice comment 202c and the account information used to represent the user corresponding to the terminal device into a voice comment interaction request. The account information sent by the terminal device to the server includes an account identifier, and optionally, the account information may also include at least one of the following: account name and account avatar.

[0074] The terminal device sends a voice comment interaction request to the server. Upon receiving the request, the server obtains the voice comment 202c. Based on the account information, it determines the target audience for the voice comment 202c. This target audience information includes the account name, account avatar, posting time, posting location, and interactive controls for the voice comment 202c, including but not limited to like and comment controls. The server then encapsulates the voice comment 202c and the target audience information into comment data and publishes the comment data.

[0075] This step may further include: displaying a published notification message for the second voice comment on the comment display page; and canceling the display of the published notification message if the display duration exceeds a display duration threshold.

[0076] Please see also Figure 9 , Figure 9 This is a schematic diagram of a voice interaction scenario provided in an embodiment of this application. Figure 7 .like Figure 9 As shown, when voice comment 202c is successfully published, the terminal device responds by displaying a published notification message 40e for voice comment 202c on the comment display page 20a. Figure 9 The example shows the "Comment Published" notification message. There are several ways to cancel the display of the published notification message 40e. One possible method is as follows: The terminal device counts the display duration of the published notification message 40e. If the display duration exceeds a preset display duration threshold (e.g., 3 seconds), the published notification message 40e is canceled. Another possible method is as follows: The terminal device displays a close control associated with the published notification message 40e on the comment display page 20a. This close control is used to cancel the display of the published notification message 40e. If the user who posted the voice comment 202c triggers the close control, the terminal device responds to the trigger operation of the close control and cancels the display of the published notification message 40e.

[0077] Simultaneously, in response to the successful publication of the voice comment 202c, the terminal device displays the comment display area 201d of the comment display page 20a for the first voice comment ( Figure 9 (Taking voice comment 201a as an example) the voice comment 202c that follows the singing. The comment data 40f, including voice comment 202c, can also include text comment 401f input by the user corresponding to the terminal device, such as... Figure 9 The example in the text is "I'll sing the second line".

[0078] like Figure 9 As shown, unlike regular replies and comments, comment data 40f highlights the target relationship between voice comments 201a and 202c, such as... Figure 9 The bolded "singing back" indicates that user Az interacted with user ai's voice comment 201a by singing back.

[0079] The second voice comment can be a song used to sing along with the first voice comment; that is, the second voice comment also belongs to the predetermined content type, such as... Figure 9 The example voice comment 202c is a song, so the terminal device can display this information on the comment display page 20a, such as... Figure 9 The example shown is voice recognition prompt 204c, which is... Figure 9 The displayed message "Singing detected" is converted to text by the voice comment 202c. The text content is as follows: Figure 9 Example of "regardless of the day...".

[0080] In practical applications, the second voice comment can also be a simple description used to respond to the first voice comment. In this case, the second voice comment does not belong to the predetermined content type. A simple description refers to a description made by a user with the main purpose of stating facts, expressing opinions, or sharing experiences, using everyday, colloquial language. Its biggest difference from the first voice comment is that it lacks melody. Based on this, if the user corresponding to the terminal device triggers the second voice comment, the terminal device will respond to the triggering operation by playing the second voice comment, but will not provide an interactive entry point.

[0081] The above example uses a first-level voice comment to illustrate the first-level voice comment, for example... Figure 9 The following is an example of a Level 2 voice commentary, specifically from the 201a version of the audio commentary section. Please participate in the audio commentary section as well. Figure 10 , Figure 10 This is a schematic diagram of a voice interaction scenario provided in an embodiment of this application. Figure 8 .like Figure 10As shown, voice comment 202c belongs to the song content type (which can be a predetermined content type). In this application embodiment, the voice comment for the singing-along interaction can include not only the voice comment published by the account that initiated the singing-along (i.e., the first-level voice comment), but also the voice comment generated by singing along to the first-level voice comment (which can be understood as a continuation voice comment or a sub-voice comment), for example... Figure 10 Voice commentary 201a, as a Level 1 voice commentary, belongs to the predefined content type; for example... Figure 10 Voice comment 202c, as a continuation of voice comment, belongs to the pre-defined content type, therefore... Figure 10 The example voice comment 202c can also serve as the first voice comment in the embodiments of this application.

[0082] In response to a trigger operation on voice comment 202c, the terminal device displays an interaction entry 402f for voice comment 202c on the comment display page 20a. Interaction entry 202a is associated with voice comment 201a, and interaction entry 402f is associated with voice comment 202c. However, interaction entry 202a and interaction entry 402f have the same function: both initiate a sing-along event for the associated voice comment. Therefore, the voice interaction process after the terminal device responds to a trigger operation on interaction entry 402f is the same as the voice interaction process after the terminal device responds to a trigger operation on interaction entry 202a. The only difference is that after the terminal device responds to a trigger operation on interaction entry 202a, it responds to a sing-along event for voice comment 201a, while after the terminal device responds to a trigger operation on interaction entry 402f, it responds to a sing-along event for voice comment 202c.

[0083] Therefore, after the terminal device responds to the singing / replying process of the voice comment 202c via the interactive entry 402f, the comment data 40g can be displayed in the comment display area 201d of the comment display page 20a. The voice comment 402g in the comment data 40g is a 4-second song used to sing / reply to the voice comment 202c. The comment data 40g may also include the text comment 401g input by the user corresponding to the terminal device, such as... Figure 10 The example in the text is "Then I'll sing the third line, hee hee." It's understandable that the generation process of the 40g comment data is related to... Figures 6-9 The generation process is the same as that of the voice comment 202c example in the example.

[0084] like Figure 10 As shown, unlike regular replies and comments, comment data 40g highlights the target relationship between voice comment 202c and voice comment 402g, such as... Figure 10The bolded "reply" indicates that user AI is interacting with user Az's voice comment 202c by singing along. Similarly, when voice comment 402g belongs to a pre-defined content type, the terminal device can also display an interactive entry associated with voice comment 402g. Figure 10 Three voice comments are given as examples: voice comment 201a (a first-level comment), voice comment 202c (a second-level comment) obtained by singing along to voice comment 201a, and voice comment 402g (a third-level comment) obtained by singing along to voice comment 202c.

[0085] Figure 10 Example voice comment 201a is the account that initiated the comment (i.e. Figure 10 In the example, if a user (AI) posts a voice comment, then all voice comments in the comment display area 201d where voice comment 201a is located, which are used for singing along, are associated with voice comment 201a, such as the aforementioned voice comment 202c and voice comment 402g.

[0086] The above process can be understood as follows: the first user publishes the first voice comment through the first terminal; the second user, through the interactive entry point associated with the first voice comment provided by the second terminal, responds to the first voice comment and publishes the second voice comment; subsequently, the third user, through the interactive entry point associated with the second voice comment provided by the third terminal, responds to the second voice comment and publishes the third voice comment, and so on. Subsequently, users continuously respond to the published voice comments (including the first, second, and third voice comments mentioned above) through the interactive entry points associated with voice comments provided by the client, thus forming a set of voice comments generated through the responding method. This set of voice comments includes the first, second, and third voice comments mentioned above, and each voice comment in the set belongs to a predetermined content type.

[0087] In practical applications, the first user, second user, and third user mentioned above can be different users, or some users can be the same. For example, the first user and the third user are the same user, or all three users can be the same user. Similarly, the first terminal, second terminal, and third terminal mentioned above can be different terminals (by default, the logged-in accounts are different), or some terminals can be the same. For example, the first terminal and the third terminal are the same terminal (by default, they are logged into the same account), or all three terminals can be the same terminal (by default, they are logged into the same account).

[0088] This application embodiment, through an interactive entry point associated with the first voice comment, helps users better interact with the voice comment (e.g., sing along, play a chain song) without increasing the complexity of the function. When a user participates in singing along with the first voice comment, this application embodiment plays the end of the x-second segment of the first voice comment they are singing, helping the user to start singing more easily. Therefore, it can improve the rhythmic correlation and coordination between the two voice comments, thereby improving the content quality of the second voice comment. As can be seen from the above, this application embodiment provides a brand-new interactive entry point for the first voice comment. Through this interactive entry point, users can sing along with the first voice comment. By adding new interactive methods to the first voice comment, the interactivity of the first voice comment can be improved, thereby improving the interactivity of the comment display page where the first voice comment is located. Through rich interactive methods, the interactive effect of the first voice comment can be improved, thereby improving the interactive effect of the comment display page.

[0089] Please see Figure 11 , Figure 11 This is a flowchart illustrating a voice interaction method provided in an embodiment of this application. Figure 2 This method can be executed by a computer device, which can be a terminal device (such as the one mentioned above). Figure 1 (Device 11a in the text). The voice interaction method may include the following steps S201-S207.

[0090] S201. Display an interactive entry point associated with the first voice comment on the comment display page. The first voice comment belongs to the pre-defined content type.

[0091] S202, in response to a trigger operation on the interactive entry point, display a voice input page corresponding to the first voice comment, the voice input page being used to indicate at least one of the following: content associated with the first voice comment, user information of the user who posted the first voice comment, and target associated content that has a target association relationship with the first voice comment.

[0092] S203. Enter a second voice comment via the voice input page.

[0093] S204. In response to publishing the second voice comment, the second voice comment and the target association between the second voice comment and the first voice comment are displayed in the comment display area where the first voice comment is located. The second voice comment belongs to a predetermined content type.

[0094] For details on the implementation of steps S201-S204, please refer to the above text. Figure 4 The descriptions of steps S101-S104 in the corresponding embodiments will not be repeated here.

[0095] S205. On the comment display page, target text content is displayed in association with the first voice comment, and a voice description label is displayed in association with the target text content. The target text content is used to represent the first voice comment.

[0096] Specifically, the target text content refers to the text generated after processing the first voice comment into text. Please refer to [link / reference]. Figure 10 Voice comment 201a belongs to the song content type in the predetermined content types. Therefore, voice comment 201a can be a first voice comment, and its corresponding target text content is as follows: Figure 10 The example song text "Unforgettable xx, unforgettable xx" can have its associated voice description tags updated, as detailed in the description of step S206 below. Figure 10 The example, associated with Voice Comments 201a, displays a voice description label that is a voice recognition prompt, which is "recognized as singing" following the text content "Unforgettable xx, unforgettable xx".

[0097] Similarly, Figure 10 Voice comment 202c belongs to the song content type in the predefined content types. Therefore, voice comment 202c can be a first voice comment, and its corresponding target text content is as follows: Figure 10 Example song text: "Regardless of..." Figure 10 The example associated with voice comment 202c displays a voice description label as voice recognition prompt information 204c, which reads "Singing detected".

[0098] Similarly, Figure 10 The voice comment 402g belongs to the song content type in the predefined content type. Therefore, voice comment 402g can be a first voice comment, and its corresponding target text content is as follows: Figure 10 Example song text: "World..." Figure 10 The example, associated with voice comment 402g, displays a voice description label as voice recognition prompt information 404g, which reads "Singing was detected".

[0099] S206. In response to publishing a sub-voice comment of the first voice comment, update the voice description tag associated with the target text content to indicate the target voice playback entry and / or the relevant statistical information of the target voice content. The target voice content is obtained based on the first voice comment and / or at least one sub-voice comment under the first voice comment. Any sub-voice comment in the at least one sub-voice comment has a target association relationship with the first voice comment or other sub-voice comments under the first voice comment. Any sub-voice comment belongs to a predetermined content type.

[0100] Specifically, the target speech content includes multiple speech segments arranged in sequence. The first speech segment in the multiple speech segments corresponds to the first speech comment. The remaining speech segments in the multiple speech segments, excluding the first speech segment, are obtained based on at least one sub-speech comment under the first speech comment.

[0101] The process of generating the remaining audio segments in the target audio content, excluding the first audio segment, includes: determining the sub-audio comments at each level from the at least one sub-audio comment under the first audio comment; determining at least one target sub-audio comment from each level from the sub-audio comments based on at least one of the sub-audio comments' interaction value, quality value, and relevance to the currently logged-in user account; and obtaining the remaining audio segments in the target audio content, excluding the first audio segment, based on the order between levels and at least one target sub-audio comment in each level.

[0102] Please see again. Figure 10 , Figure 10 The example provides three voice comments: voice comment 201a, voice comment 202c (a follow-up to voice comment 201a), and voice comment 402g (a follow-up to voice comment 202c). Voice comment 201a is a level 1 voice comment (referred to as a level 1 voice comment). Voice comment 202c is a sub-voice comment of voice comment 201a, and is a level 2 voice comment (referred to as a level 2 voice comment). Voice comment 402g is a sub-voice comment of voice comment 202c, and therefore also a sub-voice comment of voice comment 201a, and is a level 3 voice comment (referred to as a level 3 voice comment).

[0103] For ease of description and understanding, this step will be described using the first voice comment as voice comment 201a. Assume... Figure 10 The example comment display area 201d includes a total of 8 voice comments belonging to the song content type within the predefined content types. Please refer to all of them. Figure 12 , Figure 12 This is a schematic diagram of a voice interaction scenario provided in an embodiment of this application. Figure 9 .like Figure 12 As shown, the eight voice comments are voice comment 201a, voice comment 202c, voice comment 402g, and... Figure 10The five undisplayed voice comments are voice comment 110, voice comment 111, voice comment 112, voice comment 113, and voice comment 114. The relationships between the eight voice comments are as follows: voice comment 201a is a first-level voice comment; voice comments 202c and 110 are second-level voice comments, used to respond to voice comment 201a, thus voice comments 202c and 110 are both sub-voice comments of voice comment 201a; voice comments 402g and 112 are third-level voice comments, used to respond to... Voice comment 202c, therefore voice comment 402g and voice comment 112 are both sub-voice comments of voice comment 202c, and also sub-voice comments of voice comment 201a; voice comment 114 is a level 4 voice comment used to respond to voice comment 402g, therefore voice comment 114 is also a sub-voice comment of voice comment 201a; voice comments 111 and voice comment 113 are level 3 voice comments used to respond to voice comment 110, therefore voice comments 111 and voice comment 113 are both sub-voice comments of voice comment 110, and also sub-voice comments of voice comment 201a.

[0104] by Figure 12 The example illustrates this: Voice comment 201a's first voice comment comprises seven sub-voice comments. From these seven sub-voice comments, the terminal device determines the following: Level 2 voice comments include voice comments 202c and 110; Level 3 voice comments include voice comments 402g, 112, 111, and 113; and Level 4 voice comments include voice comment 114. This application provides multiple dimensions of information to determine the target sub-voice comments for each level from the sub-voice comments at each level. These multiple dimensions include, but are not limited to, the interaction value, quality value, and correlation with the currently logged-in user account of the sub-voice comments.

[0105] The interactive methods of sub-voice comments may include at least one of replying, liking, playing, and new interactions proposed in this application (such as singing along, relaying, etc.). If multiple interactions are included, such as playing and singing along, the total number of plays and the number of singing along will be used as the interaction value of the sub-voice comment.

[0106] The quality score of a sub-voice comment includes two aspects. The first aspect is the lyrics quality score, which is calculated by combining the text content of the sub-voice comment with its corresponding parent voice comment (e.g., Figure 12The first aspect is the phonological quality value, which is determined by calculating the phonological correlation between the sub-voice comment 402g and its parent voice comment 202c. The second aspect is the rhythmic quality value, determined by calculating the phonological correlation between the sub-voice comment and its corresponding parent voice comment. The terminal device determines the quality value of the sub-voice comment using both the lyric quality value and the phonological quality value.

[0107] The correlation between sub-voice comments and the currently logged-in user account refers to whether the sub-voice comment was posted by the currently logged-in user account. Figure 10 For example, the user account logged into the terminal device is user account with the name Az. Voice comment 202c is entered by user account with the name Az. Therefore, the first correlation degree (e.g., value 1) representing that the sub-voice comment was published by the currently logged-in user account is determined as the correlation degree between voice comment 202c and user account with the name Az. Voice comment 402g is entered by user account with the name ai. Therefore, the second correlation degree (e.g., value 0) representing that the sub-voice comment was not published by the currently logged-in user account is determined as the correlation degree between voice comment 402g and user account with the name Az.

[0108] Please see again. Figure 12 The terminal device identifies voice comment 201a as the first voice segment. If the target sub-voice comment at each level is determined based on one dimension of the sub-voice comment, the terminal device obtains the evaluation priorities corresponding to multiple dimensions. The evaluation priorities corresponding to multiple dimensions can be set according to the needs of the actual application scenario. This step provides the following evaluation priority: the correlation between the sub-voice comment and the currently logged-in user account is greater than the interaction value of the sub-voice comment, and the interaction value of the sub-voice comment is greater than the quality value of the sub-voice comment.

[0109] Level 2 voice commentary includes voice commentary 202c and voice commentary 110. Voice commentary 202c is generated by the user account logged into the terminal device (e.g., ...). Figure 10 If a user account named Az (as shown in the example) enters and successfully publishes voice comment 110, and the voice comment 110 is also entered and successfully published by the currently logged-in user account, then the terminal device will identify both voice comment 202c and voice comment 110 as target sub-voice comments under the second level. Specifically, voice comment 202c and voice comment 110 will be processed into a chorus, and the chorus-processed voice segment will be identified as the second voice segment used to follow the first voice segment. If voice comment 110 is entered and successfully published by a user account different from the currently logged-in user account, then the terminal device will identify voice comment 202c as a target sub-voice comment under the second level. In other words, voice comment 202c is used to follow the first voice segment (i.e., voice comment 201a).

[0110] The three-level voice comments include voice comments 402g, 112, 111, and 113. If at least one of the four three-level voice comments (e.g., voice comment 111) is entered and successfully published by the currently logged-in user account, the terminal device will identify this at least one voice comment entered and successfully published by the currently logged-in user account as the target sub-voice comment under the three-level category. Specifically, this at least one voice comment will be processed into a chorus, and the resulting chorus segment will be used as the third segment to follow the second segment. If none of the four three-level voice comments is entered and successfully published by the currently logged-in user account, the terminal device will determine the target sub-voice comment under the three-level category based on the interaction values ​​corresponding to the four three-level voice comments. For example, if voice comment 111 has the highest interaction value among the four three-level voice comments, then voice comment 111 will be identified as the target sub-voice comment under the three-level category.

[0111] The Level 4 speech commentary includes only one speech commentary 114. Therefore, the terminal device can directly identify speech commentary 114 as the target sub-speech commentary under Level 4. Thus, the terminal device determines the target sub-speech commentary for each level, combined with... Figure 12 Examples are as follows: the first audio segment is audio comment 201a, the second is audio comment 202c, the third is audio comment 111, and the fourth is audio comment 114. In practical applications, a certain audio segment may be generated by merging multiple audio comments. One feasible way to generate the target audio content is as follows: concatenate the above four audio segments to obtain a song containing the above four audio segments; in other words, a song is composed of the above four audio segments, and the concatenated song is determined as the target audio content. Another feasible way to generate the target audio content is as follows: determine the above four audio comments as the target audio content.

[0112] If the target sub-voice comment at each level is determined based on multiple dimensions of sub-voice comments, such as the interaction value, quality value, and relevance to the currently logged-in user account, the terminal device obtains the evaluation weights corresponding to each dimension. These weights can be set according to the specific application scenario. This step provides the following evaluation weights: the relevance of the sub-voice comment to the currently logged-in user account has a weight of 0.4; the interaction value has a weight of 0.3; and the interaction value of a sub-voice comment is greater than its quality value has a weight of 0.3. The terminal device then performs a weighted fusion of the values ​​of these dimensions to obtain a total evaluation value. Based on this total evaluation value, at least one target sub-voice comment is determined for each level. Specifically, the sub-voice comment with the highest total evaluation value at each level is selected as the target sub-voice comment for that level. Subsequent processing is the same as described above and will not be repeated here.

[0113] It is important to emphasize that the target speech content can be updated or changed. For example, at least one sub-speech comment of the first speech comment at the first moment may be different from at least one sub-speech comment of the first speech comment at the second moment. This includes, but is not limited to, the following scenarios: 1. At the first moment, the first speech comment has 7 sub-speech comments. At the second moment, which is later than the first moment, the first speech comment has 5 additional sub-speech comments in addition to the above 7 sub-speech comments. In particular, the 5 additional sub-speech comments include sub-speech comments under additional levels. For example, the above 7 sub-speech comments are level 2, level 3, and level 4 speech comments, and the 5 additional sub-speech comments are level 2, level 3, and level 5 speech comments. At this time, the target speech content at the first moment includes 4 speech segments (because there are 4 levels), and the target speech content at the second moment includes 5 speech segments (because there are a total of 5 levels).

[0114] 2. At least one sub-voice comment of the first voice comment at the first moment and at least one sub-voice comment of the first voice comment at the second moment, which is later than the first moment, have different evaluation values ​​(including at least one of the interaction value, quality value, and relevance to the currently logged-in user account of the sub-voice comment). In this case, the target sub-voice comment may be different because the evaluation values ​​are different.

[0115] Furthermore, user 1 triggers the target audio playback entry displayed on terminal device 1 associated with the first audio comment, and terminal device 1 plays target audio content 1. User 2 triggers the target audio playback entry displayed on terminal device 2 associated with the first audio comment, and terminal device 2 plays target audio content 2. Target audio content 1 and target audio content 2 may be the same or different. For example, at least one sub-audio comment of the first audio comment may contain audio comments entered and published by user 1, but may not contain audio comments entered and published by user 2. In this case, target audio content 1 may contain audio comments entered and published by user 1, and target audio content 2 may or may not contain audio comments entered and published by user 1.

[0116] When the terminal device determines the target audio content, it updates the audio description tags associated with the target audio content to indicate the target audio playback entry point and / or relevant statistical information of the target audio content. Please also refer to... Figure 13 , Figure 13 This is a schematic diagram of a voice interaction scenario provided in an embodiment of this application. Figure 10 .like Figure 13 As shown, the terminal device updates the target text content (such as...). Figure 13 The example of "Unforgettable xx, unforgettable xx" is associated with voice description tags, specifically by separating the voice description tags from the voice recognition prompts (i.e., Figure 10 The example (which recognizes singing) is updated to the target voice playback entry 40z. The target voice playback entry 40z can display splicing prompts, such as... Figure 13 The example given is "Listen to 5 people sing along." Furthermore, in response to publishing a new sub-voice comment after the first voice comment, the terminal device can again update the voice description tags associated with the target text content; please refer to [link to related documentation]. Figure 14 , Figure 14 This is a schematic diagram of a voice interaction scenario provided in an embodiment of this application. Figure 10 1. For example Figure 14 As shown, voice comment 201a is a first voice comment. The terminal device displays the voice description tag of the target voice playback entry 40z in association with the target text content of voice comment 201a. In response to publishing voice comment 402g, the terminal device updates the voice description tag again, specifically by updating the voice description tag from the target voice playback entry 40z to the target voice playback entry 40p. The concatenation prompt information for the target voice playback entry 40p is as follows: Figure 14 The phrase "listen to 6 people sing in turn" appears in the text.

[0117] The above describes in detail the first voice comment posted by the account that initiated the singing (i.e. Figure 10In the example of voice comment 201a), the following describes a scenario where the first voice comment is a continuation of a voice comment. It can be understood that when a continuation voice comment (such as...) is used... Figure 14 When the voice description tag associated with the text content of the voice comment (202c) is a target voice playback entry point, the subsequent voice comments (such as...) Figure 14 The voice description tag associated with the text content of the voice commentary (201a) also serves as a target voice playback entry point. Please refer to [link / reference]. Figure 14 as well as Figure 15 , Figure 15 This is a schematic diagram of a voice interaction scenario provided in an embodiment of this application. Figure 10 2. For example Figure 15 As shown, voice comment 201a is a first voice comment, and voice comment 202c, which follows voice comment 201a, is another first voice comment. In response to the publication of the sub-voice comment with voice comment 202c as the first voice comment, the terminal device updates the text content of voice comment 202c (which is a target text content, such as...) Figure 14 The voice description tags associated with "regardless of the weather..." are specifically used to... Figure 14 The voice recognition prompt 204c (e.g., singing was detected) is updated to the target voice playback entry 405g. The target voice playback entry 405g can display concatenated prompt information, such as... Figure 15 The phrase "listen to 5 people sing in turn" appears in the text.

[0118] This application describes in detail the method for generating the target speech content, as illustrated below. Figure 17 The corresponding embodiments provide alternative methods for generating target speech content.

[0119] S207. In response to a trigger operation targeting the target audio playback entry, play the target audio content.

[0120] Specifically, in response to a trigger operation targeting the target audio playback entry, the target audio content is played via the player; in response to any audio content within the target audio content being played, the user information of the user who published the audio content is displayed in the player.

[0121] Please see again. Figure 13 The terminal device, in response to a trigger operation on the target audio playback entry 40z, displays player 40x. This embodiment does not limit the relationship between the display area of ​​player 40x and the comment display page 20a; it can be set according to the actual application scenario. Player 40x includes a playback control 401x. When the playback control 401x is in playback mode, the terminal device plays the target audio content. In this embodiment, the target audio content is a chorus song. Figure 13The example song for the singing contest is a 30-second song, sung by 5 users (in real-world scenarios, these 5 users may include the same user), where user AI is the first singer. The terminal device can close player 40x in response to a trigger action on the close control 402x.

[0122] In summary, when multiple people can sing along, this embodiment of the application will select the closest and higher-quality audio (voice) for splicing. Once the splicing is successful, an entry point for listening to the singing along will be added to the end of the text-to-text conversion of the voice comment from the initiating account and / or the singing-along account. This increases the user's sense of surprise and helps consumers hear the full amount of voice content, enhancing the immersive experience. As described above, this embodiment of the application provides a novel interactive entry point for the first voice comment. Through this interactive entry point, users can sing along to the first voice comment. By adding new interactive methods to the first voice comment, the interactivity of the first voice comment can be improved, thereby enhancing the interactivity of the comment display page where the first voice comment is located. The rich interactive methods improve the interactive effect of the first voice comment, and consequently, improve the interactive effect of the comment display page.

[0123] Please see Figure 16 , Figure 16 This is an interactive flowchart of a voice interaction method provided in an embodiment of this application. The method can be executed interactively by the aforementioned terminal device (e.g., device 11a) and server (e.g., server 100a), and the terminal device can run a client. The voice interaction method may include the following steps S301-S309.

[0124] S301. The server identifies the content type of the first voice comment. If the content type of the first voice comment is a predetermined content type, the server renders the interactive entry point of the first voice comment.

[0125] S302, The server sends an interactive entry point associated with the first voice comment to the client.

[0126] S303. The client displays an interactive entry point associated with the first voice comment on the comment display page.

[0127] S304. In response to the trigger operation for the interactive entry, the client displays the voice input page corresponding to the first voice comment.

[0128] S305, the client inputs a second voice comment via the voice input page.

[0129] S306. In response to the publish operation for the second voice comment, the client sends the second voice comment to the server.

[0130] S307. The server encapsulates the second voice comment and the information of the publishing object to obtain the comment data.

[0131] S308, The server publishes comment data to the client.

[0132] S309. The client displays a second voice comment in the comment display area where the first voice comment is located, which is used to continue the first voice comment.

[0133] As described above, this application provides a novel interactive entry point for the first voice comment. Through this interactive entry point, users can sing along to the first voice comment. By adding new interactive methods to the first voice comment, the interactivity of the first voice comment can be improved, thereby enhancing the interactivity of the comment display page where the first voice comment is located. The rich interactive methods can improve the interactive effect of the first voice comment, thereby enhancing the interactive effect of the comment display page.

[0134] Please see Figure 17 , Figure 17 This is a flowchart illustrating a voice interaction method provided in an embodiment of this application. Figure 3 This method can be executed by a computer device, which can be a terminal device (such as the one mentioned above). Figure 1 (Device 11a in the text). The voice interaction method may include the following steps S401-S402.

[0135] S401. Display the target audio playback entry in association with the audio comment on the comment display page. The audio comment belongs to the predefined content type.

[0136] Specifically, the above Figure 4 The corresponding embodiments mainly describe the user corresponding to the terminal device (hereinafter referred to as the interactive user) and voice comments belonging to a predetermined content type (including...). Figure 4 The scenario in the corresponding embodiment (the first voice comment and the second voice comment) involves interaction. Figure 11 The corresponding embodiments mainly describe scenarios where interactive users interact with voice comments belonging to a predetermined content type, and interactive users consume target voice content generated based on voice comments belonging to a predetermined content type.

[0137] Understandably, a user can participate in the following three scenarios: 1. Only interact with voice comments that belong to the pre-defined content type, such as singing along or playing a chain game. Figure 4 The corresponding embodiments mainly describe the first scenario.

[0138] 2. It allows users to interact with voice comments that fall under the pre-defined content type, and also consume the target voice content. Figure 11The corresponding embodiments mainly describe the second scenario.

[0139] 3. Consume only the target voice content. This application embodiment mainly describes the third scenario; therefore, the voice comments in this application embodiment are equivalent to those described above. Figure 11 The first voice comment in the corresponding embodiment.

[0140] S402. In response to a trigger operation targeting the target audio playback entry, play the target audio content, which is obtained based on an audio comment and / or at least one sub-audio comment under the audio comment. Any sub-audio comment in the at least one sub-audio comment has a target association relationship with the audio comment or other sub-audio comments under the audio comment, and any sub-audio comment belongs to a predetermined content type.

[0141] The process of determining the target speech content can be as follows: Based on the first speech comment and at least one sub-speech comment under the first speech comment, at least one candidate speech content is determined, and there is a target association relationship between every two adjacent speech comments in a candidate speech content; the target speech content is determined from the at least one candidate speech content.

[0142] The specific process of determining the target audio content from at least one candidate audio content may include: determining the target audio content from at least one candidate audio content based on at least one of the following: length, interaction value, quality value, and relevance to the currently logged-in user account.

[0143] Please see again. Figure 10 The terminal device displays the sequential audio comments in area 201d. Figure 10 The document provides a detailed example of three sequential voice comments, including voice comment 201a as the first voice comment, voice comment 202c which responds to voice comment 201a, and voice comment 402g which responds to voice comment 202c. Figure 12 Example voice comment 110 is obtained by singing along with voice comment 201a. Since both voice comment 202c and voice comment 110 are obtained by singing along with voice comment 201a, there is no singing along with voice comment 202c and voice comment 110. Since voice comment 402g is obtained by singing along with voice comment 202c, there is no sequential singing along with voice comment 402g and voice comment 110.

[0144] The terminal device counts the number of sequentially linked voice comments in the comment display area 201d. If the number reaches 'a', meaning there are 'a' voice comments in the comment display area 201d that have a sequentially linked relationship, then the terminal device concatenates these 'a' voice comments sequentially to obtain the target voice content. Here, the target voice content can be called the linked song. For example, if 'a' equals 3, then the terminal device... Figure 10 The example audio comments 201a, 202c, and 402g are concatenated in sequence to obtain a song where the first segment is the audio content of audio comment 201a, the second segment is the audio content of audio comment 202c, and the third segment is the audio content of audio comment 402g.

[0145] For ease of understanding and explanation, we will use 5 as an example here. In practical applications, when there are 5 voice comments in the comment display area that are sequentially linked, the number of voice comments included in that comment display area may be much greater than 5. For example, if the first user initiates a voice linking activity on the comment display page, then the first user's account can be understood as the initiating account, and the voice comment posted can be understood as the first-level voice comment or the main comment. Then, 5 second users link to the first-level voice comment, resulting in 5 second-level voice comments used to link to the first-level voice comment. For ease of explanation later, these 5 second-level voice comments will be referred to as second-level voice comment a1, second-level voice comment a2, second-level voice comment a3, second-level voice comment a4, and second-level voice comment a5, respectively.

[0146] Subsequently, six third-party users responded to the second-level voice comment a1 with their own singing, resulting in six third-level voice comments used to respond to the second-level voice comment a1. For ease of narration later, these six third-level voice comments will be referred to as third-level voice comment b1, third-level voice comment b2, third-level voice comment b3, third-level voice comment b4, third-level voice comment b5, and third-level voice comment b6. Clearly, at this point, the comment display area containing the first-level voice comment already contains 12 voice comments, far exceeding 5. However, the maximum length that can be sequentially sung is 3. For example, first-level voice comment a1, second-level voice comment a1, and third-level voice comment b1 still cannot be sequentially concatenated to obtain a song to sing along to.

[0147] Subsequently, four fourth users responded to the second-level voice comment a2, resulting in four third-level voice comments used to respond to it. For ease of narration later, these four third-level voice comments will be referred to as third-level voice comment c1, third-level voice comment c2, third-level voice comment c3, and third-level voice comment c4. At this point, the maximum length of the comment display area containing the first-level voice comment that can be responded to sequentially remains 3.

[0148] Based on the above, when the length of the sequentially singable audio comment in the comment display area where the first-level audio comment is located is 5, the comment display area includes far more than 5 audio comments. Therefore, the terminal device needs to filter out more relevant and higher-quality audio content from a large number of audio comments for splicing. The terminal device's filtering process can be as follows: Based on the first audio comment and at least one sub-audio comment under the first audio comment, at least one candidate audio content is determined, wherein the audio segment length of a candidate audio content is at least 'a', and there is a target association relationship between every two adjacent audio comments (in this case, an audio segment includes one audio comment). This application provides multiple dimensions of information to determine the target audio content from at least one candidate audio content based on multiple dimensions of information. The multiple dimensions of information include, but are not limited to, the length of the candidate audio content, the interaction value, the quality value, and the degree of association with the currently logged-in user account.

[0149] The length of a candidate audio content refers to the total number of audio segments included in the candidate audio content. For example, if the length of a candidate audio content is 5, it means that the candidate audio content includes 5 audio segments.

[0150] The interaction value of a candidate audio content is determined by the interaction values ​​of its constituent audio segments. For example, if a candidate audio content includes 5 audio segments, the interaction value of the candidate audio content is generated by using the interaction values ​​corresponding to each of the 5 audio segments. The process for determining the interaction value of a single audio segment is described above. Figure 11 The description of the interaction value of sub-voice comments in the corresponding embodiments will not be repeated here.

[0151] The quality value of a candidate speech content is determined by the quality values ​​of its constituent speech segments. For example, if a candidate speech content includes 5 speech segments, the quality value of the candidate speech content is generated by using the quality values ​​corresponding to each of the 5 speech segments. The process for determining the quality value of a single speech segment is described above. Figure 11 The description of the quality value of the sub-voice comment in the corresponding embodiments will not be repeated here.

[0152] The relevance of candidate audio content to the currently logged-in user account is determined by the relevance of each audio segment to the user account. For example, if a candidate audio content consists of 5 audio segments, the relevance of the candidate audio content to the currently logged-in user account is generated by calculating the relevance of each of the 5 audio segments to the user account. The process for determining the relevance of a single audio segment to the user account is detailed above. Figure 11 The description of the correlation between sub-voice comments and the currently logged-in user account in the corresponding embodiments will not be repeated here.

[0153] Specifically, in response to a trigger operation targeting the target audio playback entry, the target audio content is played via the player; in response to playing any audio segment within the target audio content, the user information of the user who published that audio segment is displayed in the player.

[0154] Specifically, in response to a trigger operation targeting the target audio playback entry, the target audio content is played via a player, which includes a playback progress bar and / or a text content area; in response to playback of any audio segment in the target audio content, the text content corresponding to the audio segment is displayed in the text content area of ​​the player, and / or, user information of at least one user corresponding to the audio segment is displayed or differentiated on the playback progress bar, the audio segment being obtained based on audio comments posted by at least one user, and the audio comments posted by at least one user being the same or similar.

[0155] One feasible implementation method is as follows: Please refer to [link / reference] Figure 13 as well as Figure 18 , Figure 18 This is a schematic diagram of a voice interaction scenario provided in an embodiment of this application. Figure 10 3. When a user triggers the target audio playback entry 40z, the terminal device responds to the trigger operation for the target audio playback entry and directly displays... Figure 18 The example player 407x plays the target audio content via player 407x.

[0156] Another feasible implementation method is described above. Figure 11 The description of step S207 in the corresponding embodiment will not be repeated here.

[0157] Please see also Figure 13 as well as Figure 18 The terminal device responds to the expansion operation of the player 40x. For example, if the user of the terminal device clicks on a blank area of ​​the player 40x, it will display... Figure 18 The example is a player 407x for playing songs. This application embodiment does not limit the relationship between the display page of player 407x and the comment display page; it can be set according to the actual application scenario.

[0158] Player 407x includes first voice commentary (such as...) Figure 13 The example audio comment 201a) is associated with the participant information, such as Figure 18 The example of 322 people singing together means that 322 people participated in the singing along with voice comment 201a, such as singing along with voice comment 201a or voice comment 202c. The voice comments located in the comment display area where voice comment 201a is located are all voice comments associated with voice comment 201a.

[0159] Player 407x includes initiating account information 408x for the initiating account, including... Figure 18 The example account avatar and account name "ai" also indicate that the account named "ai" initiated the song reply. Player 407x includes a playback progress bar 409x for the song to be replied to. The terminal device responds to the playback progress of the song by updating and displaying the song subtitles 403x in real time within player 407x. Figure 18 Example: The currently displayed song subtitle 403x is "Unforgettable xx, unforgettable xx". Figure 18 The example shows the first 9 seconds of the song being played, so the terminal device can identify the played area 404x in the playback progress bar 409x and highlight it. Furthermore, the terminal device can determine the playback area range of multiple audio segments within the playback progress bar 409x. Figure 18 The solid dots define the playback area of ​​a voice segment within the playback progress bar 409x. Specifically, the first and second solid dots above the playback progress bar 409x correspond to the playback area of ​​the first voice segment within 409x; the second and third solid dots above the playback progress bar 409x correspond to the playback area of ​​the second voice segment within 409x; and the third solid dot above the playback progress bar 409x... The first and fourth solid dots correspond to the range on the playback progress bar 409x, which is the playback area of ​​the third audio segment within the playback progress bar 409x; the fourth and fifth solid dots above the playback progress bar 409x correspond to the range on the playback progress bar 409x, which is the playback area of ​​the fourth audio segment within the playback progress bar 409x; the fifth solid dot above the playback progress bar 409x and the area below (behind) it correspond to the range on the playback progress bar 409x, which is the playback area of ​​the fifth audio segment within the playback progress bar 409x.

[0160] Furthermore, the terminal device displays the participant information for the corresponding audio segment in association with each playback area, such as... Figure 18 As shown, the system can display the account avatars and number of participants associated with each playback area. If the number of participants exceeds a threshold, the system selects the most popular participants from the large pool of candidates and displays either their account names or their account avatars. The terminal device... Figure 18 In the example, among the five playback area ranges, determine the target playback area range where the next song's playback progress is located, for example... Figure 18The example target playback area is the second playback area, and the information of the participating objects associated with the second playback area is highlighted.

[0161] As described above, this application provides a novel playback entry point for voice comments. Through this playback entry point, target voice content can be played. This target voice content includes not only the voice comment itself but also its sub-voice comments. By adding a new playback method to voice comments, the interactivity of voice comments can be improved, thereby enhancing the interactivity of the comment display page where the voice comments are located. Through rich interactive methods, the interactive effect of voice comments can be improved, which in turn enhances the interactive effect of the comment display page.

[0162] Please see Figure 19 , Figure 19 This is a schematic diagram of the structure of a voice interaction device provided in an embodiment of this application. Figure 1 .like Figure 19 As shown, the voice interaction device 1 can be a computer device (e.g., the one described above). Figure 1 A computer program (including program code) for device 11a), for example, the voice interaction device 1 is an application software; it is understood that the voice interaction device 1 can be used to execute corresponding steps in the voice interaction method provided in the embodiments of this application. Figure 19 As shown, the voice interaction device 1 may include a display module 11 and an input module 12.

[0163] Display module 11 is used to display an interactive entry associated with the first voice comment on the comment display page. The first voice comment belongs to a predetermined content type. The display module 11 is also configured to respond to a trigger operation on the interactive entry point by displaying a voice input page corresponding to the first voice comment. The voice input page is used to indicate at least one of the following: content associated with the first voice comment, user information of the user who published the first voice comment, and target associated content that has a target association relationship with the first voice comment. Input module 12 is used to input a second voice comment via the voice input page; The display module 11 is also used to respond to the publication of the second voice comment by displaying the second voice comment in the comment display area where the first voice comment is located, as well as the target association relationship between the second voice comment and the first voice comment, wherein the second voice comment belongs to a predetermined content type.

[0164] In one embodiment, the voice interaction device 1 further includes a playback module 13; Playback module 13 is specifically used for: On the comment display page, target text content is displayed in association with the first voice comment, and a voice description label is displayed in association with the target text content. The target text content is used to characterize the first voice comment. In response to the publication of a sub-voice comment of the first voice comment, update the voice description tag associated with the target text content to indicate the target voice playback entry and / or the relevant statistical information of the target voice content. The target voice content is obtained based on the first voice comment and / or at least one sub-voice comment under the first voice comment. Any sub-voice comment in the at least one sub-voice comment has a target association relationship with the first voice comment or other sub-voice comments under the first voice comment. Any sub-voice comment belongs to a predetermined content type. In response to a trigger operation targeting the target audio playback entry, the target audio content is played.

[0165] In one embodiment, the target speech content includes a plurality of speech segments arranged in sequence, wherein the first speech segment corresponds to a first speech comment, and the remaining speech segments other than the first speech segment are obtained based on at least one sub-speech comment under the first speech comment.

[0166] In one embodiment, at least one sub-voice comment under a first voice comment has a hierarchy; Playback module 13 is also specifically used for: In at least one sub-voice comment under the first voice comment, identify the sub-voice comments at each level; Based on at least one of the following: interaction value, quality value, and relevance to the currently logged-in user account of the sub-voice comment, determine at least one target sub-voice comment for each level. Based on the order between levels and at least one target sub-speech comment under each level, the remaining speech segments in the target speech content, excluding the first speech segment, are obtained.

[0167] In one embodiment, the playback module 13 is further specifically used for: Based on the first voice comment and at least one sub-voice comment under the first voice comment, at least one candidate voice content is determined, and there is a target association relationship between every two adjacent voice comments in a candidate voice content; Determine the target speech content from at least one candidate speech content.

[0168] In one embodiment, the playback module 13 is further specifically used for: The target audio content is determined from at least one candidate audio content based on at least one of the following: length, interaction value, quality value, and relevance to the currently logged-in user account.

[0169] In one embodiment, the playback module 13 is further specifically used for: In response to a trigger operation targeting the target audio playback entry, the target audio content is played via the player; In response to any audio segment played in the target audio content, the user information of the user who published the audio segment is displayed in the player.

[0170] In one embodiment, the playback module 13 is further specifically used for: In response to a trigger operation targeting the target audio playback entry, the target audio content is played via a player, which includes a playback progress bar and / or a text content area; In response to any audio segment played in the target audio content, the text content corresponding to the audio segment is displayed in the text content area of ​​the player, and / or, user information of at least one user corresponding to the audio segment is displayed or differentiated on the playback progress bar, the audio segment being obtained based on audio comments posted by at least one user, and the audio comments posted by at least one user being the same or similar.

[0171] As described above, this application embodiment provides a novel interactive entry point for the first voice comment belonging to a predetermined content type. Through this interactive entry point, interactions such as singing along to the first voice comment can be realized. Obviously, this application embodiment adds new interactive methods to the first voice comment, which can improve the interactivity of the first voice comment, and thus improve the interactivity of the comment display page where the first voice comment is located. Through rich interactive methods, the interactive effect of the first voice comment can be improved, and thus the interactive effect of the comment display page can be improved.

[0172] Please see Figure 20 , Figure 20 This is a schematic diagram of the structure of a voice interaction device provided in an embodiment of this application. Figure 2 .like Figure 20 As shown, the voice interaction device 2 can be a computer device (e.g., the one described above). Figure 1 A computer program (including program code) for device 11a), for example, the voice interaction device 2 is an application software; it is understood that the voice interaction device 2 can be used to execute corresponding steps in the voice interaction method provided in the embodiments of this application. Figure 20 As shown, the voice interaction device 2 may include a display module 21 and a playback module 22.

[0173] Display module 21 is used to display the target audio playback entry in association with the audio comment on the comment display page. The audio comment belongs to a predetermined content type. The playback module 22 is used to play target audio content in response to a trigger operation on the target audio playback entry. The target audio content is obtained based on audio comments and / or at least one sub-audio comment under the audio comments. Any sub-audio comment in the at least one sub-audio comment has a target association relationship with the audio comment or other sub-audio comments under the audio comment. Any sub-audio comment belongs to a predetermined content type.

[0174] As described above, this application provides a novel playback entry point for voice comments. Through this playback entry point, target voice content can be played. This target voice content includes not only the voice comment but also its sub-voice comments. By adding a new playback method to the voice comments, the interactivity of the voice comments can be improved, thereby enhancing the interactivity of the comment display page where the voice comments are located. Through rich interactive methods, the interactive effect of the voice comments can be improved, which in turn enhances the interactive effect of the comment display page.

[0175] Please see Figure 21 , Figure 21 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Figure 21 As shown, the computer device 1000 may include a processor 1001, a network interface 1004, and a memory 1005. Furthermore, the computer device 1000 may also include a user interface 1003 and at least one communication bus 1002. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen and a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be high-speed RAM or non-volatile memory, such as at least one disk storage device. Optionally, the memory 1005 may also be at least one storage device located remotely from the processor 1001. Figure 21 As shown, the memory 1005, which is a computer-readable storage medium, may include an operating system, a network communication module, a user interface module, and a device control application.

[0176] In such Figure 21In the computer device 1000 shown, the network interface 1004 provides network communication functionality; the user interface 1003 is mainly used to provide an input interface for the user; and the processor 1001 can be used to call the device control application stored in the memory 1005 to execute the voice interaction method described in any of the corresponding embodiments above, which will not be repeated here. Furthermore, the beneficial effects of using the same method will also not be repeated.

[0177] Furthermore, it should be noted that this application also provides a computer-readable storage medium storing a computer program adapted to be loaded and executed by a processor, so that a computer device having a processor performs the methods described in the preceding embodiments. Therefore, these will not be repeated here. Additionally, the beneficial effects of using the same method will also not be repeated. For technical details not disclosed in the embodiments of the computer-readable storage medium involved in this application, please refer to the description of the method embodiments of this application.

[0178] The aforementioned computer-readable storage medium can be the apparatus provided in any of the foregoing embodiments or the internal storage unit of the aforementioned computer device, such as the hard disk or memory of the computer device. The computer-readable storage medium can also be an external storage device of the computer device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., provided on the computer device. Furthermore, the computer-readable storage medium may include both internal storage units and external storage devices of the computer device. The computer-readable storage medium is used to store the computer program and other programs and data required by the computer device. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0179] Furthermore, it should be noted that this application also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. The computer program is adapted to be read and executed by a processor, so that a computer device having a processor performs the method provided in any of the corresponding embodiments described above. Additionally, the beneficial effects of using the same method will not be repeated here. For technical details not disclosed in the computer program product or computer program embodiments involved in this application, please refer to the description of the method embodiments of this application.

[0180] The terms "first," "second," etc., in the specification, claims, and drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the term "comprising," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or device that includes a series of steps or units is not limited to the listed steps or modules, but may optionally include steps or modules not listed, or may optionally include other step units inherent to these processes, methods, apparatuses, products, or devices.

[0181] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0182] The above-disclosed embodiments are merely preferred embodiments of this application and should not be construed as limiting the scope of this application. Therefore, any equivalent variations made in accordance with the claims of this application shall still fall within the scope of this application.

Claims

1. A voice interaction method, characterized in that, The method includes: An interactive entry point is displayed on the comment display page in association with the first voice comment, which belongs to a predetermined content type; In response to a trigger operation on the interactive entry point, a voice input page corresponding to the first voice comment is displayed. The voice input page is used to indicate at least one of the following: content associated with the first voice comment, user information of the user who published the first voice comment, and target associated content that has a target association relationship with the first voice comment. A second voice comment is recorded via the aforementioned voice input page; In response to the publication of the second voice comment, the second voice comment and the target association between the second voice comment and the first voice comment are displayed in the comment display area where the first voice comment is located, wherein the second voice comment belongs to the predetermined content type.

2. The method according to claim 1, characterized in that, The method further includes: On the comment display page, target text content is displayed in association with the first voice comment, and a voice description tag is displayed in association with the target text content, wherein the target text content is used to characterize the first voice comment; In response to the publication of a sub-voice comment of the first voice comment, the voice description tag associated with the target text content is updated to indicate the target voice playback entry and / or the relevant statistical information of the target voice content. The target voice content is obtained based on the first voice comment and / or at least one sub-voice comment under the first voice comment. Any sub-voice comment in the at least one sub-voice comment has a target association relationship with the first voice comment or other sub-voice comments under the first voice comment. Any sub-voice comment belongs to the predetermined content type. In response to a trigger operation targeting the target audio playback entry, the target audio content is played.

3. The method according to claim 2, characterized in that, The target speech content includes multiple speech segments arranged in sequence. The first speech segment in the multiple speech segments corresponds to the first speech comment. The remaining speech segments in the multiple speech segments, excluding the first speech segment, are obtained based on at least one sub-speech comment under the first speech comment.

4. The method according to claim 3, characterized in that, At least one sub-voice comment under the first voice comment has a hierarchy; The method further includes: In at least one sub-voice comment under the first voice comment, determine the sub-voice comments under each level; Based on at least one of the following: interaction value, quality value, and relevance to the currently logged-in user account of the sub-voice comment, determine at least one target sub-voice comment for each level. Based on the order between levels and at least one target sub-speech comment under each level, the remaining speech segments in the target speech content, excluding the first speech segment, are obtained.

5. The method according to claim 2, characterized in that, The method further includes: Based on the first voice comment and at least one sub-voice comment under the first voice comment, at least one candidate voice content is determined, and the target association relationship exists between every two adjacent voice comments in a candidate voice content. The target speech content is determined from the at least one candidate speech content.

6. The method according to claim 5, characterized in that, Determining the target speech content from the at least one candidate speech content includes: The target audio content is determined from the at least one candidate audio content based on at least one of the following: length, interaction value, quality value, and relevance to the currently logged-in user account.

7. The method according to claim 2, characterized in that, The step of playing the target audio content in response to a trigger operation on the target audio playback entry point includes: In response to a trigger operation targeting the target audio playback entry, the target audio content is played via the player; In response to playing any audio segment from the target audio content, the user information that published the audio segment is displayed in the player.

8. The method according to claim 2, characterized in that, The step of playing the target audio content in response to a trigger operation on the target audio playback entry point includes: In response to a trigger operation targeting the target audio playback entry, the target audio content is played via a player, the player including a playback progress bar and / or a text content area; In response to playback of any audio segment in the target audio content, the text content corresponding to the audio segment is displayed in the text content area of ​​the player, and / or, user information of at least one user corresponding to the audio segment is displayed or differentiated on the playback progress bar, the audio segment being obtained based on audio comments posted by the at least one user, the audio comments posted by the at least one user being the same or similar.

9. A voice interaction method, characterized in that, The method includes: The target audio playback entry is displayed in association with the audio comment on the comment display page, and the audio comment belongs to a predetermined content type; In response to a trigger operation targeting the target audio playback entry, the target audio content is played. The target audio content is obtained based on the audio comment and / or at least one sub-audio comment under the audio comment. Any sub-audio comment in the at least one sub-audio comment has a target association relationship with the audio comment or other sub-audio comments under the audio comment. Any sub-audio comment belongs to the predetermined content type.

10. The method according to claim 9, characterized in that, The step of playing the target audio content in response to a trigger operation on the target audio playback entry point includes: In response to a trigger operation targeting the target audio playback entry, the target audio content is played via the player; In response to playing any audio segment from the target audio content, the user information that published the audio segment is displayed in the player.

11. The method according to claim 9, characterized in that, The step of playing the target audio content in response to a trigger operation on the target audio playback entry point includes: In response to a trigger operation on the target audio playback entry, the target audio content is played via a player, the player including a playback progress bar and / or a text content area; In response to playback of any audio segment in the target audio content, the text content corresponding to the audio segment is displayed in the text content area of ​​the player, and / or, user information of at least one user corresponding to the audio segment is displayed or differentiated on the playback progress bar, the audio segment being obtained based on audio comments posted by the at least one user, the audio comments posted by the at least one user being the same or similar.

12. A voice interaction device, characterized in that, The device includes: The display module is used to display an interactive entry associated with the first voice comment on the comment display page, wherein the first voice comment belongs to a predetermined content type; The display module is further configured to respond to a trigger operation on the interactive entry point by displaying a voice input page corresponding to the first voice comment, wherein the voice input page is configured to indicate at least one of the following: content associated with the first voice comment, user information of the user who published the first voice comment, and target associated content that has a target association relationship with the first voice comment; The input module is used to input a second voice comment via the voice input page; The display module is further configured to, in response to the publication of the second voice comment, display the second voice comment and the target association between the second voice comment and the first voice comment in the comment display area where the first voice comment is located, wherein the second voice comment belongs to the predetermined content type.

13. A voice interaction device, characterized in that, The device includes: The display module is used to display the target audio playback entry in association with the audio comment on the comment display page, wherein the audio comment belongs to a predetermined content type; The playback module is used to play target audio content in response to a trigger operation on the target audio playback entry. The target audio content is obtained based on the audio comment and / or at least one sub-audio comment under the audio comment. Any sub-audio comment in the at least one sub-audio comment has a target association relationship with the audio comment or other sub-audio comments under the audio comment. Any sub-audio comment belongs to the predetermined content type.

14. A computer device, characterized in that, Including memory and processor; The memory is connected to the processor, the memory is used to store computer programs, and the processor is used to invoke the computer programs so that the computer device performs the method according to any one of claims 1-11.

15. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program adapted to be loaded and executed by a processor to cause a computer device having the processor to perform the method of any one of claims 1-11.

16. A computer program product, characterized in that, The computer program product includes a computer program stored in a computer-readable storage medium, the computer program being adapted to be read and executed by a processor to cause a computer device having the processor to perform the method of any one of claims 1-11.

Images