Methods, apparatuses, devices, and products for displaying information

Abstract

The present disclosure relates to methods, apparatuses, devices and products for displaying information. The method includes playing a first media content and displaying a first component on a first interface, the first media content including a first content in a first language. The method further includes playing a second media content in response to an operation on the first component, the second media content including a second content in a second language, the first content being generated based on semantic information of the second content.

Description

Technical Field

[0001] This article relates to the field of human-computer interaction, and more specifically to methods, apparatuses, devices and products for displaying information. Background Technology

[0002] With the rapid development of smart terminal devices, various terminal products have become deeply integrated into users' daily lives, serving as important platforms for social interaction, life, and work. Against this backdrop, various social media apps have emerged and rapidly gained popularity, becoming primary channels for users to share their lives, record their experiences, and convey their opinions. Users can conveniently access current events and media content on social platforms using smart terminal devices. The media content is diverse, encompassing text, images, video, audio, and emoticons. Summary of the Invention

[0003] In a first aspect of the examples presented herein, a method for displaying information is provided. The method includes playing first media content on a first interface and displaying a first component, the first media content including first content in a first language. The method also includes playing second media content in response to an operation on the first component, the second media content including second content in a second language, the first content being generated based on semantic information of the second content. In this way, the terminal device can display first content in a first language generated based on the semantic information of the second content in the second language, enabling the expansion of media content in different languages ​​and facilitating the presentation of high-quality multilingual media content. Furthermore, the terminal device can also provide users with a simple operation entry point for switching between the first and second media content through the first component, facilitating users' access to related multimedia content in different languages ​​and improving the user experience. In a second aspect of the examples herein, an apparatus for displaying information is provided. The apparatus includes a first display module configured to play first media content and display a first component on a first interface, the first media content including first content in a first language. The apparatus also includes a second display module configured to play second media content in response to an operation on the first component, the second media content including second content in a second language, the first content being generated based on semantic information of the second content. In this way, the terminal device can display first content in a first language generated based on the semantic information of the second content in a second language, enabling the expansion of media content in different languages ​​and facilitating the presentation of high-quality multilingual media content. Furthermore, the terminal device can provide users with a simple operation entry point for switching between the first and second media content through the first component, facilitating users' access to associated multimedia content in different languages ​​and improving the user experience.

[0004] In a third aspect of the examples herein, an electronic device is provided. This electronic device includes one or more processors; and a storage device for storing one or more programs, which, when executed by the one or more processors, enable the one or more processors to play first media content and display a first component on a first interface. The first media content includes first content in a first language. Then, the one or more processors can also, in response to an operation on the first component, play second media content, which includes second content in a second language, and the first content is generated based on semantic information of the second content. In this way, the terminal device can display first content in a first language generated based on the semantic information of the second content in a second language, enabling the expansion of media content in different languages ​​and facilitating the presentation of high-quality multilingual media content. Furthermore, the terminal device can also provide users with a simple operation entry point for switching between the first and second media content through the first component, facilitating users' access to associated multimedia content in different languages ​​and improving the user experience.

[0005] In a fourth aspect of the examples herein, a computer program product is provided. This computer program product is tangibly stored on a non-transitory computer-readable medium and includes machine-executable instructions that, when executed, enable a machine to play first media content and display a first component on a first interface. The first media content includes first content in a first language. The machine can then, in response to an operation on the first component, play second media content, which includes second content in a second language, and the first content is generated based on semantic information of the second content. In this way, a terminal device can display first content in a first language generated based on the semantic information of the second content in a second language, enabling the expansion of media content in different languages ​​and facilitating the presentation of high-quality multilingual media content. Furthermore, the terminal device can provide users with a simple operation entry point for switching between the first and second media content through the first component, facilitating access to associated multimedia content in different languages ​​and improving the user experience.

[0006] The summary section is provided to present the chosen concepts in a simplified form, which will be further described in the detailed description below. The summary section is not intended to identify key or principal features of the claimed subject matter, nor is it intended to limit the scope of the claimed subject matter. Attached Figure Description

[0007] The above and other features, advantages, and aspects of the examples herein will become more apparent when taken in conjunction with the accompanying drawings and the following detailed description. In the accompanying drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0008] Figure 1A schematic diagram of an example environment that can be implemented according to some of the examples in this article is shown;

[0009] Figure 2 A flowchart illustrating a method for displaying information, based on some examples in this article, is shown;

[0010] Figure 3 A schematic diagram illustrating an example of switching between two playback interfaces based on some examples in this article is shown;

[0011] Figure 4A and Figure 4B A schematic diagram illustrating an example of switching between two playback interfaces based on some examples in this article is shown;

[0012] Figure 5 The diagram shows examples of preview and playback interfaces based on some examples in this article;

[0013] Figures 6A to 6D A schematic diagram illustrating examples of switching between interfaces based on some of the examples in this article is shown;

[0014] Figure 7 A schematic diagram illustrating an example of audio generation based on some examples in this article is shown;

[0015] Figure 8 Block diagrams of devices for displaying information, according to some examples herein, are shown; and

[0016] Figure 9 Block diagrams of electronic devices according to some examples in this article are shown. Detailed Implementation

[0017] It is understood that all user-related data involved in this technical solution should be obtained and used only after authorization from the user. This means that if it is necessary to use a user's personal information in this technical solution, the user's explicit consent and authorization are required before obtaining this data; otherwise, no related data collection and use will be carried out. It should also be understood that when implementing this technical solution, relevant laws and regulations should be strictly followed in the process of data collection, use, and storage, and necessary technical measures should be taken to protect user data security and ensure the secure use of data.

[0018] The examples herein will now be described in more detail with reference to the accompanying drawings. While some examples of this document are shown in the drawings, it should be understood that this document can be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, these examples are provided to provide a more thorough and complete understanding of this document. It should be understood that the accompanying drawings and examples are for illustrative purposes only and are not intended to limit the scope of this document.

[0019] In the description of the examples in this document, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "an example" or "the example" should be understood as "at least one example". The terms "first", "second", etc., may refer to different or the same objects unless explicitly stated otherwise. Other explicit and implicit definitions may also be included below.

[0020] As mentioned above, users can conveniently browse current events, industry information, social news, and other media content anytime, anywhere through various online platforms. They can also view friends' updates, bloggers' daily shares, and records of people's lives. The content formats supported by the platform are diverse, covering media content in different languages.

[0021] Building on this foundation, many users with foreign language learning needs have begun to explore the learning value of the platform's native multilingual media content. Compared to the single listening materials in traditional foreign language learning systems, online multilingual media content has a natural advantage in terms of relevance to daily life. Users can subtly acquire listening input, accumulate vocabulary, and develop a sense of language while browsing news or watching entertaining videos. This significantly reduces the tedium of language learning, thus achieving a more engaging and enjoyable foreign language learning experience. However, currently, only mainstream language media content on the platform is typically of high quality, while other languages ​​have fewer high-quality contents. This results in limited content options for users to choose from, impacting their language learning experience through media content.

[0022] Therefore, the examples in this paper provide a scheme for displaying information. In this scheme, a terminal device can play first media content and display a first component on a first interface. The first media content includes first content in a first language. The terminal device can also play second media content in response to an operation on the first component. The second media content includes second content in a second language, and the first content is generated based on the semantic information of the second content.

[0023] In this way, the terminal device can display first content in the first language generated based on the semantic information of the second content in the second language, thus expanding the media content across different languages ​​and facilitating the presentation of high-quality multilingual media content. Furthermore, the terminal device can provide users with a simple interface to switch between the first and second media content through the first component, making it convenient for users to access related multimedia content in different languages ​​and improving the user experience.

[0024] Figure 1 A schematic diagram of an example environment 100 that can be implemented according to some examples in this article is shown. For example... Figure 1As shown, environment 100 includes terminal device 102. Terminal device 102 may include smartphones, tablets, wearable devices, laptops, etc. In environment 100, terminal device 102 can run applications. For example, the application may include social platforms, content publishing platforms, content creation platforms, content editing platforms, etc. For example, an information stream may be displayed in the application, and the information stream may include various types of media content. For example, the information stream may include live broadcasts, videos, audio, images, text, or any combination thereof. For example, video can be played by playing audio in the application. At the same time, one or more media contents from the information stream can be displayed on the application's interface.

[0025] like Figure 1 As shown, terminal device 102 can play first media content 106 and display first component 112 on first interface 104. First media content 106 includes first content 108 in first language 110. First interface 104 can be the playback interface for first media content 106. First media content 106 includes video, audio, images, or text, etc. First content 108 can be an excerpt from first media content 106, or a portion of first media content 106. For example, first content 108 can be subtitles, text, or audio from first media content 106. In some cases, terminal device 102 can use first component 112 to display prompts to indicate the function of first component 112.

[0026] like Figure 1 As shown, terminal device 102 can also respond to an operation on the first component 112 by playing second media content 116 on the second interface 114. The second media content 116 can be published media content. For example, the second media content 116 includes published video, audio, images, or text. The second media content 116 includes second content 118 in a second language 120. In some cases, the second language 120 is different from the first language 110. For example, the second language 120 is Chinese, and the first language 110 is English. Another example is that the second language 120 is English, and the first language 110 is Chinese. In other cases, the first language 110 or the second language 120 can also be a language other than Chinese and English.

[0027] In some cases, the first content 108 is generated based on the semantic information of the second content 118. For example, the first media content 106 includes audio, the second media content 116 includes video, and at least a portion of the audio is generated based on the semantic information in the video. Semantic information refers to the textual information indicated by the media content. In some cases, the semantic information of the first content 108 is similar to the semantic information of the second content 118. That is, at least a portion of the content of the first media content 106 indicates information similar to at least a portion of the content of the second media content 116 indicates information similar to that indicated by at least a portion of the content of the second media content 116. For example, the people, time, or event included in the first media content 106 is the same as the people, time, or event included in the second media content 116.

[0028] In this way, the terminal device can display first content in the first language generated based on the semantic information of the second content in the second language, thus expanding the media content across different languages ​​and facilitating the presentation of high-quality multilingual media content. Furthermore, the terminal device can provide users with a simple interface to switch between the first and second media content through the first component, making it convenient for users to access related multimedia content in different languages ​​and improving the user experience.

[0029] Figure 2 A flowchart of a method 200 for displaying information, based on some examples in this document, is shown. Method 200 can be applied to the audience side. Figure 2 The method 200 shown can be used in, for example Figure 1 This is implemented in environment 100 as shown. Figure 2 The method 200 shown can be used in, for example Figure 1 The terminal device 102 shown executes the commands. Terminal device 102 may include smartphones, tablets, wearable devices, laptops, etc. In environment 100, terminal device 102 may run applications. For example, the application may include social media platforms, content publishing platforms, content creation platforms, content editing platforms, etc. For example, an information stream may be displayed in the application, and the information stream may include various types of media content. For example, the information stream may include live broadcasts, video, audio, images, text, or any combination thereof. At the same time, one or more media contents from the information stream may be displayed on the application's interface.

[0030] In box 202, the terminal device can play first media content and display the first component on the first interface. In such a case... Figure 1In the illustrated environment 100, terminal device 102 can play first media content 106 and display first component 112 on first interface 104. The first media content 106 includes first content 108 in first language 110. First interface 104 can be the playback interface for the first media content 106. The first media content 106 includes video, audio, images, or text, etc. First content 108 can be an excerpt from the first media content 106, or a portion of the first media content 106. For example, first content 108 can be subtitles, text, or audio from the first media content 106. In some cases, terminal device 102 can use the first component 112 to display prompts to indicate the function of the first component 112.

[0031] In box 204, the terminal device can respond to an operation on the first component by playing the second media content. Figure 1 In the illustrated environment 100, terminal device 102 can also respond to an operation on the first component 112 by playing second media content 116 on the second interface 114. The second media content 116 can be published media content. For example, the second media content 116 includes published video, audio, images, or text. The second media content 116 includes second content 118 in a second language 120. In some cases, the second language 120 is different from the first language 110. For example, the second language 120 is Chinese, and the first language 110 is English. Another example is that the second language 120 is English, and the first language 110 is Chinese. In other cases, the first language 110 or the second language 120 can also be a language other than Chinese and English.

[0032] In some cases, the first content 108 is generated based on the semantic information of the second content 118. For example, the first media content 106 includes audio, the second media content 116 includes video, and at least a portion of the audio is generated based on the semantic information in the video. Semantic information refers to the textual information indicated by the media content. In some cases, the semantic information of the first content 108 is similar to the semantic information of the second content 118. That is, at least a portion of the content of the first media content 106 indicates information similar to at least a portion of the content of the second media content 116 indicates information similar to that indicated by at least a portion of the content of the second media content 116. For example, the people, time, or event included in the first media content 106 is the same as the people, time, or event included in the second media content 116.

[0033] In this way, the terminal device can display first content in the first language generated based on the semantic information of the second content in the second language, thus expanding the media content across different languages ​​and facilitating the presentation of high-quality multilingual media content. Furthermore, the terminal device can provide users with a simple interface to switch between the first and second media content through the first component, making it convenient for users to access related multimedia content in different languages ​​and improving the user experience.

[0034] Figure 3 A schematic diagram of example 300 showing switching between two playback interfaces according to some examples in this article is shown. Figure 3 As shown, the terminal device can display a playback interface 304 for playing media content 302. On the playback interface 304, the terminal device can display a player for the media content 302. The media content 302 includes video and audio. For example, the media content 302 can be a podcast. In some cases, the media content 302 includes English content. For example, the media content 302 includes an English podcast.

[0035] like Figure 3 As shown, the terminal device can display the switching component 306 on the playback interface 304, and in response to an operation on the switching component 306, the terminal device can display the playback interface 310 for playing media content 308. The media content 308 can be video, audio, images, text, etc. In some cases, the media content 308 includes Chinese content. For example, the media content 308 can be a Chinese video.

[0036] In some cases, the terminal device can also display a second component on a second interface playing second media content. The terminal device can also play the first media content in response to an operation on the second component. In this way, the terminal device can quickly switch from second media content to first media content via the second component, improving the efficiency of cross-content playback interaction and simplifying the user's operation of switching media content. For example, in situations such as... Figure 3 In Example 300 shown, the terminal device can display the switching component 312 on the playback interface 310 of the media content 308, and in response to the operation of the switching component 312, display the playback interface 304 of the media content 302, thereby realizing the switching between the two playback interfaces.

[0037] In some cases, the primary media content also includes secondary content in a second language, which serves as a prompt for the theme of the secondary media content. By incorporating secondary language content within the primary media content to highlight the theme of the secondary media content, users can quickly grasp the main idea of ​​the primary media content. For example, in situations like... Figure 3In Example 300 shown, media content 302 also includes introductory content in Chinese. The introductory content highlights the theme of media content 302. For example, the introductory content could be a short guide to reading media content 302 that includes the theme of media content 302.

[0038] In some cases, the release time of secondary media content falls within a predetermined timeframe. In this way, the terminal device can limit the release time of secondary media content to a predetermined range, ensuring the timeliness and freshness of the pushed media content. For example, in situations such as... Figure 3 In Example 300, media content 308 can be media content whose publication time falls within a predetermined time range. The predetermined time range can be 60 days, 75 days, 90 days, or 95 days, etc. By generating media content 302 using media content 308 with a more recent publication time, users can be provided with trending media content in different languages.

[0039] In some cases, the primary media content includes audio, and the secondary media content includes video. In this way, the server generates audio based on the video, and then plays the audio through the terminal device, expanding the user's listening scenarios. For example, in situations like... Figure 3 In the example 300 shown, media content 302 can be audio, and media content 308 can be video. That is, audio media content 302 can be generated based on video media content 308.

[0040] Figure 4A and Figure 4B A schematic diagram of example 400 showing switching between two playback interfaces according to some examples in this article is shown. Figure 4A As shown, the terminal device can display a podcast playback interface 402. The podcast is generated based on video using a model. Podcasts may include English content. The terminal device can display a prompt message 404 on the podcast playback interface 402 to indicate that the podcast is generated based on AI. The terminal device can also display the podcast text 406 on the podcast playback interface 402 to provide users with subtitles corresponding to the podcast audio, facilitating user understanding of the podcast content. In some cases, the terminal device can also display a prompt message 408 on the playback interface 402. The prompt message 408 indicates relevant information about the video associated with the podcast.

[0041] like Figure 4A and Figure 4B As shown, the terminal device can also display a switching component 410 on the playback interface 402, and in response to an operation on the switching component 410, display a playback interface 412 for playing the video. The video corresponds to a podcast. In some cases, the video includes Chinese content. In some cases, the terminal device can display the video's cover image 414 and related video information. For example... Figure 4BAs shown, the terminal device can also display the switching component 416, and in response to the operation of the switching component 416, the terminal device can display the playback interface 402, thereby realizing the switching between the playback interface 402 and the playback interface 412.

[0042] Figure 5 A schematic diagram of Example 500, showing a preview interface and a playback interface based on some examples in this article, is provided. Figure 5 As shown, the terminal device can display a preview interface 502. The terminal device can also display media content 504-1, media content 504-2, ..., media content 504-N (collectively referred to as multiple media contents 504) on the preview interface 502. In some cases, the terminal device can also display multiple pieces of information corresponding to the multiple media contents on the preview interface 502. For example, the preview interface 502 can display multiple media contents 504 using a single-column stream, a double-column stream, or a multi-column grid stream. Figure 5 As shown, the terminal device can display a playback interface 506 for playing media content 508 in response to an operation on information associated with media content 504-2. Media content 508 can be generated based on media content 504-2.

[0043] In some cases, the terminal device can also display information associated with multiple media contents, including second media content, on a third interface (also referred to as the preview interface in this document). The terminal device can also display first media content on the first interface in response to an operation on first information associated with the second media content. In this way, the terminal device can provide users with information associated with multiple media contents on the third interface and, in response to user operations, play the first media content associated with the triggered second media content, without requiring the user to enter the playback interface of the second media content and then jump to the first media interface. This achieves a direct connection from the entry point of the second media content to the first media content, simplifying user operations while providing associated information. For example, in situations such as... Figure 5 In Example 500, the terminal device can also display information associated with multiple media contents 504 on the preview interface 502. The terminal device can also display media content 508 on the playback interface 506 in response to an operation on the information associated with media content 504-2.

[0044] In some cases, the terminal device can also display a third component (referred to herein as a list component) on a third interface. The terminal device can also respond to an operation on the third component by displaying media content from a first list, where the media content in the first list shares the same theme, and the first list is associated with the third component. In this way, the terminal device can provide users with a list of media content on the same theme, achieving centralized display of similar content and simplifying user operations. For example, in situations such as... Figure 5 In Example 500, the terminal device can also display list component 510 on preview interface 502. In response to an operation on list component 510, the terminal device can display media content in a list associated with list component 510. In some cases, the terminal device can display multiple list components on preview interface 502.

[0045] like Figure 5 As shown, the terminal device can also display the switching component 512 on the playback interface 506. In response to an operation on the switching component 512, the terminal device can display the playback interface of the media content 504-2.

[0046] In some cases, the terminal device can also display a fourth component (referred to herein as a playback component) on the first interface. In response to an operation on the fourth component, the terminal device can also display information associated with the third media content using a fifth component (referred to herein as a playback panel), which is related to the second media content. In this way, the terminal device can display third media content information associated with the second media content through the fourth component, providing users with a convenient entry point to expand related content and allowing them to directly view media content associated with the second media content. For example, in situations such as... Figure 5 In Example 500, the terminal device may also display a playback component 514 on the playback interface 506. In response to an operation on the playback component 514, the terminal device may display a list panel 516. On the list panel 516, the terminal device may display information related to the media content associated with media content 504-2. For example, on the list panel 516, the terminal device may display information corresponding to multiple media contents 504. As another example, on the list panel 516, the terminal device may display information associated with media content 504-1. It should be noted that, in this document, "panel" refers to a component on which various information or other components can be presented.

[0047] In some cases, the terminal device can also respond to operations on information associated with third media content by playing fourth media content associated with the third media content on a first interface, where at least a portion of the fourth media content is generated based on the third media content. In this way, the terminal device can directly play fourth media content associated with the third media content in response to information operations on the third media content, simplifying user operation. For example, in situations such as... Figure 5 In Example 500, the terminal device can respond to an operation on information associated with media content 504-1 by displaying a playback interface for media content generated based on media content 504-1. In some cases, media content 504-1 can be a Chinese video, and media content generated based on media content 504-1 can be an English podcast.

[0048] Figures 6A to 6D A schematic diagram of example 600 showing interface switching according to some examples in this article is shown. Figure 6A As shown, the terminal device can display a prompt component 604 on the video listening interface 602. In some cases, the terminal device can use the video listening interface 602 to play videos published in the application in audio format. For example... Figure 6B As shown, in response to an operation on the prompt component 604, the terminal device can display a preview interface 606. On the preview interface 606, the terminal device can display multiple related information corresponding to multiple videos (e.g., video 608) using a dual-column stream. The related information is associated with the videos. For example, the related information may include at least one of the video's cover image, title, or the identifier of the posting user (e.g., avatar and nickname).

[0049] like Figure 6B As shown, the terminal device can also display list components (e.g., list component 610) on the preview interface 606. In some cases, the terminal device can use the list component to display prompts to indicate the theme of the videos in the list (e.g., personal growth, film and television commentary, or humanities and history).

[0050] like Figure 6C As shown, the terminal device can respond to operations related to video 608 by displaying a podcast playback interface corresponding to video 608. The podcast is generated based on the video using a model. The podcast may include English content. In some cases, the terminal device can also display a prompt message 614. The prompt message 614 indicates relevant information about the video associated with the podcast. The terminal device can also display the podcast text 616 on the podcast playback interface 612 to provide the user with subtitles corresponding to the podcast audio, facilitating the user's understanding of the podcast content. The terminal device can also display a prompt message 618 on the podcast playback interface 612 to indicate that the podcast is generated based on AI.

[0051] like Figure 6C and Figure 6D As shown, the terminal device can also display a switching component 620 on the playback interface 612, and in response to an operation on the switching component 620, display a playback interface for video 608. Video 608 corresponds to a podcast. In some cases, video 608 includes Chinese content. In some cases, the terminal device can display the cover image of video 608 and related video information.

[0052] like Figure 6D As shown, in response to an operation on playback component 622, the terminal device can display playback panel 624. In the playback panel, the terminal device can display relevant information (e.g., relevant information 628 and relevant information 630) for multiple videos with the same theme as video 608. For example, relevant information 628 indicates information associated with video 608. Relevant information 630 indicates information associated with another video in the list. In some cases, the terminal device can use an icon in relevant information 628 to indicate to the user the video currently being played. In some cases, the terminal device can play a podcast corresponding to relevant information 630 in response to an operation on relevant information 630. This podcast is generated based on the video corresponding to relevant information 630.

[0053] Figure 7 A schematic diagram of example 700, which generates audio according to some examples in this article, is shown. Figure 7 As shown, the server can use a large language model to generate text 704 based on video 702. Text 704 can be an outline of the audio to be generated. For example, text 704 can include at least one of the following: a one-sentence main idea, an opening paragraph summary, a core paragraph summary, or a concluding summary. Text 704 can be in the same language as video 702. For example, both text 704 and video 702 may include Chinese. In some cases, the server can use a large language model to generate text 704 based on relevant information from video 702 (e.g., at least one of title, text, or chapters).

[0054] like Figure 7As shown, the server can also use a large language model to generate text 706 based on text 704. Text 706 can be the complete transcript of the first language portion of the audio to be generated. Thus, in the stage of generating the complete text 706 based on the outline-like text 704, the server can ensure the semantic similarity of the generated transcript to video 702 while maintaining its integrity. The language of text 706 can be the same as the language of text 704. For example, the language of text 706 can be Chinese, just like the language of text 704. In some cases, text 706 can be a transcript that conforms to the podcast style. For example, text 706 includes multiple rhetorical questions and multiple emotion markers (e.g., pauses, chuckles, or sighs). Another example is that text 706 includes conversational content suitable for a solo podcast.

[0055] like Figure 7 As shown, the server can also use a large language model to generate text 708 based on text 706. The language of text 708 can be different from that of text 706. For example, text 708 may be in English, while text 706 may be in Chinese. In some cases, the server can also refine the content of text 706 to generate text 708 that conforms to another language and culture. That is, the translation of text 708 may differ from that of text 706. In some cases, the server can retain sentiment markers (e.g., pauses) from text 706 in the generated text 708.

[0056] like Figure 7 As shown, the server can also use a large language model to generate text 710 based on text 704. Text 710 indicates the topic of the audio to be generated. In some cases, the language of text 710 is the same as that of text 704. For example, if text 704 is Chinese, text 710 can provide a Chinese introduction to the audio to be generated. In some cases, the number of characters in text 710 is less than a preset number to avoid the introduction being too long and affecting the user experience. For example, the number of characters in text 710 is less than 90. Another example is that the number of characters in text 710 is greater than 70 and less than 90.

[0057] like Figure 7 As shown, the server can also utilize text-to-speech (TTS) technology to generate audio 712 based on text 708 and text 710. In some cases, the server can concatenate text 708 and text 710 to obtain the total text, and then generate audio 712 based on the total text. In other cases, the server can convert text 708 and text 710 separately to generate a first converted audio and a second converted audio, and then determine audio 712 based on the first converted audio and the second converted audio. In some cases, the server can also generate audio 714 based on audio 712. For example, the server can also generate audio 714 based on audio 712 and background audio.

[0058] In some cases, the primary media content includes text, and the terminal device can also display the text on the primary interface. This text is generated based on the semantic information of the secondary media content. In this way, the terminal device can intuitively display the text content to the user, facilitating the user's learning of the primary language in conjunction with the text. Furthermore, generating text based on the semantic information of the secondary media content enables a strong correlation between the text and the secondary media content, ensuring the generation of high-quality text. For example, in situations such as... Figure 7 In the example 700 shown, the text may include text 708 and text 710. The terminal device may display at least one of text 708 and text 710 on a first interface. Text 708 and text 710 are generated based on video 702.

[0059] In some cases, the first content includes first audio and first text (e.g., text 708). The text includes the first audio, which is generated based on the first text, and the first text is generated based on the semantic information of the second media content. In this way, the server can generate the first text based on semantic information, and then generate the first audio based on the first text, realizing the generation from semantic information to text and then to audio. This enables the generation of text and audio content with different semantic meanings and enriches the content presentation modality. For example, in... Figure 7 In Example 700 shown, text 708 is generated based on the semantic information of video 702, and audio 712 is generated based on text 708.

[0060] In some cases, the primary media content also includes secondary content in a second language, generated based on the secondary text. In this way, the server can generate secondary content in a second language based on the secondary text, producing prompts in the same language as the secondary media content and ensuring consistency between the prompts and the original semantics. For example, in situations like... Figure 7 In the example 700 shown, text 710 is generated based on text 704, and the language of both text 710 and text 704 can be Chinese.

[0061] In some cases, the second content includes the first audio, and the third content includes the second audio, with different timbres for the first and second audio. This allows the server to distinguish content in different languages ​​using different timbres, enhancing auditory recognition during multilingual playback. Furthermore, presenting the main content and prompts with different timbres improves the user's immersive experience. For example, in situations like... Figure 7 In Example 700 shown, the audio generated based on text 708 (English podcast) and the audio generated based on text 710 (Chinese introduction) have different timbres. For example, the audio generated based on text 710 can have a mechanical timbre tone. The audio generated based on text 708 can have a casual chat timbre tone.

[0062] Based on example 800 of the text generation example in this article, the server can use a large language model 810 to generate outline-style text 812 based on the text 804, title 806, and chapter 808 of video 802. Then, text 814 is generated based on text 812 to obtain the transcript of the audio to be generated. Here, text 812 can be the outline of the audio to be generated, and text 814 can be the complete transcript of the audio to be generated. Text 804 can be the transcript of video 802, and chapter 808 can include multiple chapter information of video 802 (e.g., chapter titles or chapter summaries).

[0063] In some cases, the first text is generated based on the second text, which in turn is generated based on the semantic information of the second media content. In this way, the server can generate an outline-style second text based on semantic information, and then generate the first text based on the second text, achieving hierarchical text generation and improving the controllability and accuracy of text generation. For example, in Example 800, text 814 is generated based on text 812. Text 812 is generated based on the semantic information of video 802.

[0064] In some cases, video 802 can be a published trending video. A trending video is one whose reference metrics (such as views, likes, or favorites) exceed a predetermined threshold. The duration of video 802 can also exceed the predetermined duration. For example, video 802 may be longer than 3 minutes.

[0065] Figure 8 A block diagram of an apparatus for displaying information, according to some examples herein, is shown. The apparatus 900 includes a first display module 902 configured to play first media content and display a first component on a first interface, the first media content including first content in a first language. The apparatus also includes a second display module 904 configured to play second media content in response to an operation on the first component, the second media content including second content in a second language, the first content being generated based on semantic information of the second content.

[0066] In some cases, device 900 also includes a third display module configured to display the second component on a second interface playing the second media content. Device 900 also includes a first playback module configured to play the first media content in response to an operation on the second component. In this way, the terminal device can quickly switch from the second media content to the first media content via the second component, improving the efficiency of cross-content playback interaction and simplifying the user's operation of switching media content.

[0067] In some cases, device 900 also includes a fourth display module configured to display information associated with multiple media contents, including second media content, on a third interface. Device 900 also includes a fifth display module configured to display first media content on a first interface in response to an operation on first information associated with the second media content. In this way, the terminal device can provide the user with information associated with multiple media contents on a third interface and, in response to the user's operation, play the first media content associated with the triggered second media content, without requiring the user to enter the playback interface of the second media content and then jump to the first media interface. This achieves direct connection from the entry point of the second media content to the first media content, simplifying user operation while providing associated information.

[0068] In some cases, device 900 also includes a sixth display module configured to display the fourth component on a first interface. Device 900 also includes a seventh display module configured to, in response to an operation on the fourth component, display information associated with the third media content using a fifth component, the third media content being associated with the second media content. In this way, the terminal device can display third media content information associated with the second media content through the fifth component, providing users with a convenient entry point to expand related content and allowing users to directly view media content associated with the second media content.

[0069] In some cases, device 900 also includes an eighth display module configured to play fourth media content associated with the third media content on a first interface in response to an operation on information related to the third media content, wherein at least a portion of the fourth media content is generated based on the third media content. In this way, the terminal device can directly play the fourth media content associated with the third media content in response to an operation on information related to the third media content, simplifying user operation.

[0070] In some cases, device 900 also includes a ninth display module configured to display the third component on a third interface. Device 900 also includes a tenth display module configured to display media content from a first list in response to an operation on the third component. The media content in the first list has the same theme, and the first list is associated with the third component. In this way, the terminal device can provide users with a list of media content on the same theme, enabling centralized display of similar content and simplifying user operation.

[0071] In some cases, the primary media content also includes secondary content in a second language, which serves as a prompt for the theme of the secondary media content. By incorporating secondary language content within the primary media content to highlight the theme of the secondary media content, users can quickly grasp the main idea of ​​the primary media content.

[0072] In some cases, the release time of secondary media content falls within a predetermined timeframe. In this way, the terminal device can limit the release time of secondary media content to a predetermined range, ensuring the timeliness and freshness of the pushed media content.

[0073] In some cases, the primary media content includes audio, and the secondary media content includes video. In this way, the server generates audio based on the video, and then the audio is played through the terminal device, expanding the user's listening scenarios.

[0074] In some cases, the first media content includes text, and the device 900 also includes an eleventh display module configured to display the text on a first interface. The text is generated based on semantic information from the second media content. In this way, the terminal device can intuitively display the text content to the user, facilitating the user's learning of the first language in conjunction with the text. Furthermore, by generating text based on the semantic information of the second media content, a strong correlation between the text and the second media content can be achieved, ensuring the generation of high-quality text.

[0075] In some cases, the first content includes first audio and first text. The text includes the first audio, which is generated based on the first text, and the first text is generated based on the semantic information of the second media content. In this way, the server can generate the first text based on semantic information, and then generate the first audio based on the first text, realizing the generation from semantic information to text and then to audio. This enables the generation of text and audio content with different semantics and enriches the content presentation modality.

[0076] In some cases, the first text is generated based on the second text, which in turn is generated based on the semantic information of the second media content. In this way, the server can generate an outline-style second text based on semantic information, and then generate the first text based on the second text, achieving hierarchical text generation and improving the controllability and accuracy of text generation.

[0077] In some cases, the primary media content also includes secondary content in a secondary language, which is generated based on the secondary text. In this way, the server can generate secondary content in a secondary language based on the secondary text, producing prompts in the same language as the secondary media content and ensuring consistency between the prompts and the original semantics.

[0078] In some cases, the second content includes the first audio, and the third content includes the second audio, with the first and second audio having different timbres. In this way, the server can use different timbres to distinguish content in different languages, enhancing auditory recognition during multilingual playback. Furthermore, presenting the main content and prompts with different timbres improves the user's immersive experience.

[0079] Figure 9 A block diagram of an electronic device 1000 according to some examples of this document is shown. Figure 9 As shown, the electronic device 1000 includes a central processing unit (CPU) and / or a graphics processing unit (GPU) 1002, which can perform various appropriate actions and processes according to computer program instructions stored in read-only memory (ROM) 1004 or loaded from storage unit 1016 into random access memory (RAM) 1006. Various programs and data required for the operation of the electronic device 1000 can also be stored in RAM 1006. The CPU / GPU 1002, ROM 1004, and RAM 1006 are interconnected via bus 1008. Input / output (I / O) interface 1010 is also connected to bus 1008. Although not shown in... Figure 9 As shown, the electronic device 1000 may also include a coprocessor.

[0080] Multiple components in electronic device 1000 are connected to I / O interface 1010, including: input unit 1012, such as keyboard, mouse, etc.; output unit 1014, such as various types of displays, speakers, etc.; storage unit 1016, such as disk, optical disk, etc.; and communication unit 1018, such as network card, modem, wireless transceiver, etc. Communication unit 1018 allows electronic device 1000 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0081] The various methods or processes described above can be executed by CPU / GPU 1002. For example, in some cases, the methods can be implemented as computer software programs tangibly contained in a machine-readable medium, such as storage unit 1016. In some cases, part or all of the computer program can be loaded and / or installed on electronic device 1000 via ROM 1004 and / or communication unit 1018. When the computer program is loaded into RAM 1006 and executed by CPU / GPU 1002, one or more steps or actions in the methods or processes described above can be performed.

[0082] As described above, it can be understood that the electronic device 1000 of this invention can achieve at least one of the many advantages that can be realized by the methods or processes described above. For example, in this way, the terminal device can display first content in the first language generated based on the semantic information of the second content in the second language, thereby expanding the media content in different languages ​​and facilitating the presentation of high-quality multilingual media content. Furthermore, the terminal device can also provide users with a simple operation entry point for switching between the first and second media content through the first component, making it convenient for users to access related multimedia content in different languages ​​and improving the user experience.

[0083] In some cases, the methods and processes described above can be implemented as a computer program product. The computer program product may include a computer-readable storage medium on which computer-readable program instructions for performing the various aspects of this document are loaded. It is understood that by utilizing the computer program product described herein, at least one of the many advantages achievable by the methods or processes described above can be realized. For example, in this way, a terminal device can display first content in a first language generated based on semantic information of second content in a second language, enabling the expansion of media content in different languages ​​and facilitating the presentation of high-quality multilingual media content. Furthermore, the terminal device can also provide users with a simple operation entry point for switching between first and second media content through a first component, facilitating users' access to associated multimedia content in different languages ​​and improving user experience.

[0084] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example, but not limited to, electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination thereof. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0085] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, a local area network (LAN), a wide area network (WAN), and / or a wireless network, to an external computer or external storage device. The network may include copper cables, fiber optic cables, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0086] The computer program instructions used to perform the operations described herein can be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​and conventional procedural programming languages. The computer-readable program instructions can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider). In some cases, electronic circuits, such as programmable logic circuits, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), can be customized using the status information from the computer-readable program instructions to implement various aspects of this document.

[0087] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0088] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0089] The flowcharts and block diagrams in the accompanying figures illustrate the architecture, functionality, and operation of possible implementations of devices, methods, and computer program products according to several examples herein. In this regard, each box in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions marked in the boxes may occur in a different order than those marked in the figures. For example, two consecutive boxes may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each box in the block diagrams and / or flowcharts, and combinations of boxes in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0090] The examples described above are exemplary and not exhaustive, nor are they limited to the disclosed examples. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the illustrated examples. The terminology used herein is chosen to best explain the principles, practical applications, or technical improvements to technology in the market, or to enable others skilled in the art to understand the examples disclosed herein.

Claims

1. A method for displaying information, comprising: Play first media content and display a first component on a first interface, the first media content including first content in a first language; as well as In response to an operation on the first component, second media content is played, the second media content including second content in a second language, the first content being generated based on semantic information of the second content.

2. The method according to claim 1, further comprising: The second component is displayed on the second interface where the second media content is played; In response to an operation on the second component, the first media content is played.

3. The method according to claim 1, further comprising: The third interface displays information associated with multiple media contents, including the second media content; In response to an operation on first information associated with the second media content, the first media content is displayed on the first interface.

4. The method according to claim 3, further comprising: The third component is displayed on the third interface; In response to an operation on the third component, media content in a first list is displayed, wherein the media content in the first list has the same theme, and the first list is associated with the third component.

5. The method according to claim 1, further comprising: The fourth component is displayed on the first interface; as well as In response to an operation on the fourth component, information associated with the third media content is displayed using the fifth component, the third media content being associated with the second media content.

6. The method according to claim 5, further comprising: In response to an operation on information associated with the third media content, fourth media content associated with the third media content is played on the first interface, and at least a portion of the fourth media content is generated based on the third media content.

7. The method according to claim 1, wherein the first media content further includes third content in the second language, the third content indicating the theme of the second media content.

8. The method according to claim 1, wherein the publication time of the second media content is within a predetermined time range.

9. The method according to claim 1, wherein the first media content includes audio and the second media content includes video.

10. The method of claim 1, wherein the first media content comprises text, and the method further comprises: The text is displayed on the first interface, and the text is generated based on the semantic information of the second media content.

11. The method of claim 10, wherein the first content includes first audio and first text, the text including the first text, the first audio being generated based on the first text, and the first text being generated based on the semantic information of the second media content.

12. The method of claim 11, wherein the first text is generated based on the second text, and the second text is generated based on the semantic information of the second media content.

13. The method of claim 12, wherein the first media content further includes third content in a second language, the third content being generated based on the second text.

14. The method of claim 13, wherein the second content includes a first audio, the third content includes a second audio, and the first audio and the second audio have different timbres.

15. A device for displaying information, comprising: The first display module is configured to play first media content and display a first component on a first interface, wherein the first media content includes first content in a first language; as well as The second display module is configured to play second media content in response to an operation on the first component. The second media content includes second content in a second language, and the first content is generated based on the semantic information of the second content.

16. An electronic device comprising: processor; as well as A memory coupled to the processor, the memory having instructions stored therein, which, when executed by the processor, cause the electronic device to perform the method according to any one of claims 1 to 14.

17. A computer program product comprising computer-executable instructions, wherein the computer-executable instructions are executed by a processor to implement the method according to any one of claims 1 to 14.

Images