Content display method and device and electronic equipment

Abstract

The embodiment of the invention discloses a content display method and device and electronic equipment, in the method, under the condition that first input content is obtained, the first input content can be matched with first prompt content, the matching degree is determined, and second prompt content to be displayed is determined according to the matching degree, different matching degrees correspond to different second prompt contents. By means of the mode, under the condition that the first prompt content is determined, the finally displayed second prompt content can be determined in real time according to the matching degree of the currently obtained first input content and the content included in the first prompt content, and therefore the prompt content display mode is more flexible.

Description

Technical Field

[0001] This application relates to the field of terminal technology, and more specifically, to a content display method, apparatus, and electronic device. Background Technology

[0002] In some situations, when a user is giving a speech or performance, a device (e.g., a teleprompter) can display content relevant to the user's speech (e.g., a script) to provide prompts. However, existing methods for displaying prompts are relatively simple and inflexible. Summary of the Invention

[0003] In view of the above problems, this application proposes a content display method, apparatus, and electronic device to improve the above problems.

[0004] In a first aspect, this application provides a content display method applied to an electronic device, the method comprising: acquiring first input content; matching the first input content with first prompt content and determining the degree of matching; and displaying second prompt content according to the degree of matching, wherein different degrees of matching correspond to different second prompt contents.

[0005] Secondly, this application provides a content display device operating in an electronic device, the device comprising: a content acquisition unit for acquiring first input content; a matching unit for matching the first input content with first prompt content and determining the degree of matching; and a prompt unit for displaying second prompt content according to the degree of matching, wherein different degrees of matching correspond to different second prompt contents.

[0006] Thirdly, this application provides an electronic device including one or more processors and a memory; one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs being configured to perform the methods described above.

[0007] Fourthly, this application provides a computer program product, characterized in that it includes computer program instructions that cause a computer to perform the above-described method.

[0008] Fifthly, this application provides a computer-readable storage medium storing processor-executable program code, the computer-readable storage medium including stored program code, wherein the above-described method is executed when the program code is run.

[0009] This application provides a content display method, apparatus, and electronic device. In this method, upon receiving first input content, the first input content can be matched with determined first prompt content. The matching degree between the content included in the first prompt content and the first input content determines the second prompt content to be displayed. Different matching degrees correspond to different second prompt contents. Therefore, by using the above method, even after the first prompt content has been determined, the final displayed second prompt content is determined in real-time based on the matching degree between the currently obtained first input content and the content included in the first prompt content, thus making the display of prompt content more flexible. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 This illustration shows a schematic diagram of an application scenario of the content display method proposed in an embodiment of this application; Figure 2 A flowchart of a content display method according to an embodiment of this application is shown; Figure 3 A schematic diagram illustrating the first input content and the second input content in an embodiment of this application is shown; Figure 4 A flowchart of a content display method according to another embodiment of this application is shown; Figure 5 A schematic diagram of a second prompt content in an embodiment of this application is shown; Figure 6 A schematic diagram illustrating another type of second prompt content in an embodiment of this application is shown; Figure 7 A schematic diagram of another type of second prompt content in an embodiment of this application is shown; Figure 8 A schematic diagram of another type of second prompt content in an embodiment of this application is shown; Figure 9 A schematic diagram of another type of second prompt content in an embodiment of this application is shown; Figure 10 A flowchart of a content display method according to another embodiment of this application is shown; Figure 11 A schematic diagram of a teleprompter system according to an embodiment of this application is shown; Figure 12A flowchart of a content display method according to another embodiment of this application is shown; Figure 13 This invention provides a structural block diagram of an image processing apparatus according to an embodiment of the present application. Figure 14 This invention illustrates a structural block diagram of an electronic device for performing a content display method according to an embodiment of this invention; Figure 15 This is a storage unit in this application embodiment for storing or carrying program code that implements the content display method according to this application embodiment. Detailed Implementation

[0012] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0013] In scenarios such as speeches, stage performances, or live broadcasts, teleprompters are often used to display speech drafts, key lines, or core points to help users reduce the risk of forgetting their lines and ensure fluent delivery. However, the current prompting methods of these devices have significant limitations. For example, most can only scroll text in a fixed order, resulting in insufficient flexibility and difficulty in adapting to diverse expression needs.

[0014] Therefore, the inventors have proposed a content display method, apparatus, and electronic device as described in this application. In this method, upon receiving first input content, the first input content can be matched with determined first prompt content. The matching degree between the content included in the first prompt content and the first input content determines the second prompt content to be displayed. Different matching degrees correspond to different second prompt contents, and different second prompt contents have different degrees of association with the first prompt content. Thus, by using the above method, even when the first prompt content has been determined, the final displayed second prompt content is determined in real-time based on the matching degree between the currently obtained first input content and the content included in the first prompt content, thereby making the display of prompt content more flexible.

[0015] The application scenarios involved in the embodiments of this application will be introduced below.

[0016] In this embodiment, the content display method can be executed independently by a first electronic device. In this independent execution by the first electronic device, all steps in the content display method provided in this embodiment can be performed by the first electronic device. For example, in the content display method provided in this embodiment, all steps can be executed by an application (e.g., a prompting program) in the first electronic device.

[0017] Alternatively, the content display method provided in this application embodiment can also be executed collaboratively by a first electronic device and a second electronic device. In this method, some steps of the content display method provided in this application embodiment are executed by the first electronic device, while other steps are executed by the second electronic device. For example, as shown... Figure 1 As shown, the first electronic device can perform the steps included in the content display method: upon receiving first input content, matching the first input content with determined first prompt content; determining second prompt content to be displayed based on the degree of matching between the content included in the first prompt content and the first input content. Then, the first electronic device can input the second prompt content to the second electronic device, which can then perform the following: display the second prompt content.

[0018] It should be noted that in this method where the first electronic device and the second electronic device work together, the steps performed by the first electronic device and the second electronic device are not limited to those described in the example above. In practical applications, the steps performed by the first electronic device and the second electronic device can be dynamically adjusted according to the actual situation.

[0019] Furthermore, the application scenarios described above are merely illustrative. For instance, in some cases, when a first electronic device receives a second prompt, the second prompt can be simultaneously transmitted to multiple second electronic devices for display.

[0020] It should be noted that when the content display method is executed independently by the first electronic device, the first electronic device can be a smartphone, tablet, wearable device, etc., or it can be a dedicated teleprompter device. The wearable device can be VR (Virtual Reality) glasses, AR (Augmented Reality) glasses, or MR (Mixed Reality) glasses. When the first electronic device and the second electronic device work together, the second electronic device displaying the second prompt content can be a smartphone, tablet, wearable device, dedicated teleprompter device, etc.

[0021] The embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0022] Please see Figure 2 This application provides a content display method applied to an electronic device, the method comprising: S110: Get the first input content.

[0023] In this embodiment, the first input content is obtained by capturing the user's voice content. For example, when a user is giving a speech (e.g., in a live broadcast, during a lecture, or during a meeting), the first input content obtained by capturing the user's voice represents the content of the user's current speech. The first input content can be the voice content obtained by capturing the user's voice content, or it can be the text content obtained by converting the voice content after capturing it.

[0024] The electronic device can acquire initial input content when the user begins their presentation. Optionally, the electronic device can determine when the user begins their presentation upon the launch of a specific application. For example, this specific application could be an application used to display initial prompts. Optionally, the electronic device can determine when the user begins their presentation upon detecting the activation of a specific function. This specific function may include a presentation prompt function. This specific function can be activated or deactivated by the user.

[0025] S120: Match the first input content with the first prompt content and determine the degree of matching.

[0026] In this embodiment of the application, the first prompt content can be understood as content used to prompt the user. For example, in a speech scenario, the first prompt content can be understood as the speech script determined by the user. Specifically, in a speech scenario, in order to facilitate prompting themselves on the specific content of their speech, the user can pre-determine a speech script including the speech content as the first prompt content.

[0027] As one approach, the initial prompt can be predetermined by the user. For example, a user can determine the initial prompt before giving a presentation. In this case, the user-determined initial prompt can be recorded. When the presentation begins and the first input is received, the user-determined initial prompt can be retrieved from the previously recorded information.

[0028] Once the first input content is obtained, it can be matched with the content included in the first prompt content to determine whether the content currently being presented by the user belongs to the content in the first prompt content, and if the content currently being presented by the user belongs to the first prompt content, to determine which part of the first prompt content it is.

[0029] In one embodiment of this application, a semantic match can be performed between the first input content and the determined first prompt content using a Large Language Model (LLM).

[0030] Large language models (MLMs) are deep learning-based natural language processing models that learn the statistical patterns, semantic structures, and contextual relationships of language through pre-training on massive amounts of text data. One approach is to employ a Transformer architecture, using a self-attention mechanism to process input sequences and generate high-quality semantic representations. The core capability of MLMs lies in their ability to convert natural language (e.g., the first input content involved in this application) into high-dimensional semantic vectors. These high-dimensional semantic vectors preserve the semantic information of the language in mathematical space, making semantically similar sentences closer together in the vector space. The key to MLMs' effective semantic matching lies in their powerful semantic representation capabilities: during pre-training, MLMs learn rich linguistic knowledge through tasks such as masked language modeling and next-sentence prediction, enabling them to understand the deeper meanings of words, sentences, and paragraphs, rather than just surface-level keywords. When MLMs process input content (e.g., the first input content and the first prompt content), they encode the input content into dense vectors that capture multi-dimensional information such as semantics, sentiment, and context. Therefore, in semantic matching tasks, large language models can encode the first input content and the first prompt content as vectors, and then calculate the cosine similarity or Euclidean distance between these two vectors to quantify their semantic similarity. This semantic vector-based matching method surpasses traditional keyword matching, and can handle synonyms, near-synonyms, and content with different expressions but the same meaning.

[0031] S130: Display a second prompt based on the degree of matching, wherein different degrees of matching correspond to different second prompts.

[0032] Given the degree of matching between the content included in the first prompt and the first input content, the final second prompt to be displayed can be determined based on the degree of matching. In other words, in this embodiment, although a first prompt is initially determined, it is not necessarily used directly for display. Instead, it serves as a reference basis for matching the first input content after it has been collected, so that the actual second prompt to be displayed can be determined based on the degree of matching.

[0033] As one approach, different second prompts have varying degrees of relevance to the first prompt. This varying degree of relevance can be understood as the second prompt including different content present in the first prompt, depending on the level of matching.

[0034] Optionally, if the matching degree is high, the content of the second prompt can be entirely the content of the first prompt. In other words, if the matching degree is high, it can be determined that the user is currently giving a speech based on the first prompt, and thus the content of the first prompt can be directly displayed to perform the prompting task. For example, if the matching degree is high, the displayed second prompt can be a sentence or paragraph of text from the first prompt that closely matches the first input content.

[0035] Optionally, in cases of low matching accuracy, a portion of the second prompt content can be from the first prompt content, while another portion may include extended content. Alternatively, in cases of low matching accuracy, the second prompt content may only include extended content. It should be noted that in cases of low matching accuracy, the user may not be currently referring to the first prompt content during their presentation, or may not be completely adhering to it. In such cases, displaying extended content provides the user with more and richer presentation materials, thereby making the content display method provided in this application more adaptable and flexible, and further enhancing the user experience.

[0036] In one approach, the extended content may include content beyond the initial prompt and / or content that provides a deeper explanation of parts of the initial prompt. For example, if the initial input mentions Shenzhen, more Shenzhen-related content can be obtained as extended content. Optionally, the extended content may be derived based on the currently obtained initial input, or it may be derived based on the initial input and a second input obtained prior to the initial input. Here, the initial input is the currently obtained input (or, can be understood as the input obtained in this session), and the second input can be understood as the input obtained after the user begins their presentation but before the initial input.

[0037] For example, such as Figure 3 As shown, if the input content obtained in the current iteration is input content C4, then input content C4 can be understood as the first input content, and the input content C1, input content C2, and input content C3 obtained before input content C4 can be understood as the second input content. For example, if the input content obtained in the current iteration is input content C5, then input content C5 can be understood as the first input content, and the input content C1, input content C2, input content C3, and input content C4 obtained before input content C5 can be understood as the second input content.

[0038] The content display method provided in this embodiment enables the final display of the second prompt content to be determined in real time based on the degree of matching between the currently obtained first input content and the content included in the first prompt content, thus making the display of prompt content more flexible.

[0039] Please see Figure 4 This application provides a content display method, which includes: S210: Obtain the first input content.

[0040] S220: Match the first input content with the first prompt content and determine the degree of matching.

[0041] S230: If the first prompt content includes the first target content, determine that the second prompt content includes the first target content and the first associated content of the first target content, and the degree of matching between the first target content and the first input content is greater than or equal to a first preset threshold.

[0042] Wherein, the degree of matching between the first target content and the first input content is greater than or equal to a first preset threshold, therefore, if the first prompt content includes the first target content, it indicates that the user is currently giving a speech in accordance with the first prompt content. Thus, the first target content and its corresponding first associated content can be displayed as the second prompt content. The first associated content can be understood as content within the first prompt content that is adjacent to the first target content. This adjacent content can include content preceding the first target content and content following the second target content. Alternatively, the first associated content can be content within the first prompt content that is semantically similar to the first target content.

[0043] For example, such as Figure 5 As shown, Figure 5 The leftmost image represents the determined first prompt content, in which the first input content is obtained, such as... Figure 5 In the scenario shown, the final determined second prompt content can be as follows: Figure 5 As shown in the image on the right, it can be observed that the first input content, "Chongqing's new energy vehicle and electronic information manufacturing industries are pillar industries," matches the first prompt content, "Chongqing's main industries include intelligent connected new energy vehicles and next-generation electronic information manufacturing," to a degree greater than the first preset threshold. Therefore, "Chongqing's main industries include intelligent connected new energy vehicles and next-generation electronic information manufacturing" in the first prompt content can be identified as the first target content. This first target content can be identified as a part of the final displayed second prompt content. Furthermore, the second prompt content will also include the content following the first target content in the first prompt content (a kind of first associated content), for example, in... Figure 5 The statement "Chongqing is the birthplace of Bayu culture and the origin of the Hongyan spirit" shown in the image on the right is a primary related content.

[0044] For example, such as Figure 6 As shown, if in Figure 5 After obtaining the first input content again, which is "Chongqing is the birthplace of Bayu culture and the origin of the Hongyan spirit," it can be determined that the matching degree between "Chongqing is the birthplace of Bayu culture and the origin of the Hongyan spirit" in the first prompt content and the first input content obtained this time is greater than or equal to the first preset threshold. Therefore, the displayed second prompt content can be as follows: Figure 6 As shown. Figure 6 As shown in the image on the right, the determined second prompt content changes as the first input content changes, thus adapting to the content the user is currently speaking in real time.

[0045] For example, such as Figure 7 As shown, if in Figure 6After obtaining the first input content again, which is "Chongqing's terrain is mainly mountainous and hilly," the final displayed second prompt content could be as follows: Figure 7 As shown in the image on the right. Figure 7 As shown, even if the position of the content the user is currently presenting (the first input content currently obtained) in the first prompt content is before the position of the previous presentation content (the first input content previously obtained, or, which can be understood as the second input content) in the first prompt content, the second prompt content can still be determined in real time based on the actual content the user is currently presenting, rather than displaying the prompt content in a fixed order.

[0046] Additionally, as a method, when displaying the second prompt, the first target content can be highlighted to emphasize it. This highlighting can include: increasing the font size of the first target content, adding a background color to the first target content (which can be understood as highlighting the first target content), etc. For example, such as... Figure 8 As shown, the first target content can be highlighted by adding a background color that distinguishes it from other content.

[0047] As one approach, if the first target content exists, the determined second prompt content may also include only the first target content.

[0048] S240: If the first prompt content does not include the first target content but includes the second target content, determine that the second prompt content includes the second target content, the second associated content of the second target content, and the extended content, wherein the degree of matching between the second target content and the first input content is greater than or equal to a second preset threshold and less than the first preset threshold; wherein the extended content is obtained through the first input content.

[0049] In this embodiment, the second preset threshold is less than the first preset threshold. This means that if a portion of the first prompt content is identified as the second target content, the matching degree between the second prompt content and the corresponding first input content is not very high. This implies that the user may not be completely following the first prompt content during their presentation. In this case, to provide users with richer materials, in addition to displaying the second target content and the second related content, further extended content can be displayed.

[0050] For example, such as Figure 9As shown, given the first input content is "Chongqing has become quite popular in recent years," although the first suggestion contains tourism-related content, specifically "known as the '8D' magical city with its complex three-dimensional terrain, and a popular international tourist destination," the match between the two does not reach the first preset threshold but is greater than the second preset threshold. Therefore, the phrase "known as the '8D' magical city with its complex three-dimensional terrain, and a popular international tourist destination" can be identified as the second target content. Specifically, since the first input content is related to Chongqing tourism, related content can be searched as expanded content. For example, as... Figure 9 As shown, in Figure 9 The extended content shown includes tourism data for Chongqing in recent years, as well as some well-known tourist attractions, so that users can give more comprehensive presentations based on the tourism data and attractions involved in the extended content.

[0051] In one approach, the second target content, the second associated content, and the extended content of the second target content can be displayed on the same interface, wherein the display areas of the second target content, the second associated content, and the extended content are different. In this embodiment, the second associated content of the second target content may include content in the first prompt content that is located before and / or after the second target content. Alternatively, the second associated content may be content in the first prompt content that is semantically similar to the second target content.

[0052] S250: If no content in the first prompt content matches the first input content to a degree greater than a second preset threshold, determine that the second prompt content includes a first summary content and extended content. The first summary content is obtained through the first input content and the second input content obtained before the first input content. The extended content is obtained through the first input content.

[0053] If no content in the first prompt matches the first input content to a degree greater than the second preset threshold, it means that for the first input content obtained in this instance, the first prompt does not contain either the first target content or the second target content. Furthermore, it also indicates that the user may be giving a speech without notes. In this case, the second prompt displayed may no longer include the content in the first prompt, but may only include the first summary content and extended content.

[0054] In this scenario, the first summary can be obtained by extracting the key points from all the user's presentation content after the start of the speech. The extended content can be understood as content expanded upon based on the user's presentation. For example, the extended content could be based on the first input content received in the current presentation, or it could be based on the first input content and a previously received second input content. When the user is giving a presentation without notes, displaying the first summary reminds the user of the content already presented, thus preventing the user from repeating themselves. Displaying the extended content allows the user to provide richer and more comprehensive explanations.

[0055] S260: Display the second prompt.

[0056] In this embodiment, when matching the first input content with the first prompt content, different second prompt content can be determined based on different matching degrees. Optionally, in this embodiment, even for the same matching degree, the categories of content included in the determined second prompt content can be different under different circumstances.

[0057] In one approach, this application embodiment can be configured with a first generation mode and a second generation mode. The first generation mode can be understood as a mode that makes the generated second prompt content relatively simpler, while the second generation mode can be understood as a mode that makes the generated second prompt content relatively richer.

[0058] Optionally, when the current generation mode is in the first mode, the second prompt content determined for different matching degrees may include: if the first prompt content includes the first target content, the second prompt content displayed includes the first target content; if the first prompt content does not include the first target content but includes the second target content, the second prompt content displayed includes the second target content and extended content; if no content in the first prompt content matches the first input content to a degree greater than a second preset threshold, the second prompt content displayed includes the first summary content and extended content.

[0059] Optionally, when the current generation mode is in the second mode, the second prompt content determined for different matching degrees may include: if the first prompt content includes the first target content, the displayed second prompt content includes the first target content and the first associated content of the first target content; if the first prompt content does not include the first target content but includes the second target content, the displayed second prompt content includes the second target content, the second associated content of the second target content, and extended content; if no content in the first prompt content matches the first input content to a degree greater than a second preset threshold, the displayed second prompt content includes the first summary content and extended content.

[0060] By comparison, it can be found that under different generation modes, even with the same degree of matching, the displayed second prompt content will be different, thus enabling more flexible and diverse prompt content display.

[0061] The generation mode of an electronic device can be configured in several ways.

[0062] As one configuration method, it can be manually configured by the user. In this method, the electronic device can be equipped with a generation mode setting interface, through which the user can manually configure the generation mode to either the first generation mode or the second generation mode. For example, if the user wants to complete the presentation with more concise content, they can configure the generation mode to the first generation mode; if the user wants to make the presentation more comprehensive, they can configure the generation mode to the second generation mode.

[0063] As another configuration method, the electronic device can determine the duration based on a preset presentation time. It's important to note that when the user needs to present more content, the overall presentation time will be longer; conversely, when the content is less, the overall presentation time will be shorter. Therefore, if the preset presentation time is short, displaying relatively abundant content during the secondary display may cause the presentation to run out of time. Conversely, if the preset presentation time is long, displaying the secondary prompts in a simpler way may result in insufficient presentation content.

[0064] In this approach, the electronic device determines the configured generation mode by comparing the difference between the preset speech duration and the estimated speech time of the first prompt content. It should be noted that the length of the content included in the first prompt content can, to some extent, represent the time required to complete the speech. Therefore, the estimated speech time can be estimated based on the length of the first prompt content. If the difference between the preset speech duration and the estimated speech time of the first prompt content is small (e.g., less than a time threshold), it indicates that the content in the first prompt content meets the user's speech duration requirement, and the generation mode can be configured as the first generation mode. If the difference between the preset speech duration and the estimated speech time of the first prompt content is large (e.g., greater than or equal to a time threshold), it indicates that the content in the first prompt content does not meet the user's speech duration requirement, and the generation mode can be configured as the second generation mode.

[0065] The estimated presentation time for the first prompt can be input by the user. For example, the user can manually input the estimated presentation time directly through the interactive interface, such as specifying a specific number of minutes (e.g., "15 minutes") through the text input box in the interactive interface, or quickly setting it through voice commands (e.g., "estimated 20 minutes"). This method is suitable for scenarios where the user has a clear time target or a clear understanding of the content length.

[0066] Alternatively, electronic devices can determine the speaking speed by statistically analyzing the user's speech rate. For example, electronic devices can automatically calculate a user's historical speaking speed using speech recognition and speech rate analysis functions. Specifically, the user can first conduct a trial lecture or reading test. The device collects voice data through a microphone, analyzes the number of words output per unit time, the frequency of pauses, and changes in intonation, calculates the average speaking speed using natural language processing technology, and then extrapolates the theoretical time consumption based on the total number of words in the initial prompt. This method is particularly suitable for scenarios where the duration is not planned in advance and needs to be dynamically adjusted according to individual speaking habits. It avoids the subjective bias of manual input and provides more accurate time consumption predictions through a data-driven approach.

[0067] As another configuration method, the electronic device can determine the generation pattern based on the user's speaking habits. In this way, the electronic device can record the initial prompts determined by the user each time they give a speech, as well as the entire content of the final speech.

[0068] As the number of recordings accumulates (e.g., after a user completes 5 or more presentations), an analysis process can be initiated. First, natural language processing technology can be used to compare the matching degree between the actual content of each presentation and the initial prompt, calculating key indicators such as "prompt coverage ratio" (i.e., the percentage of the actual content directly related to the prompt) and "additional content increment" (i.e., the number of words or sentences added beyond the prompt's scope). Next, clustering algorithms can be used to perform pattern recognition on multiple recordings. For example, if in 80% of presentation cases, the prompt coverage ratio of the user's actual content is less than 60%, and the average proportion of additional content reaches 35%, the system determines that the user is "extended type," meaning they are accustomed to actively supplementing new information after completing the presentation with the initial prompt. Conversely, if the coverage ratio is consistently above 90% and the proportion of additional content is less than 10%, they are classified as "contrast type," meaning they are accustomed to strictly following the prompt structure. This analysis not only quantifies users' expression preferences but also uncovers deeper patterns, such as users being more likely to expand content on specific topics (e.g., technical explanations or storytelling) or to improvise less in stressful situations (e.g., timed presentations).

[0069] If it is determined that the user's speaking habit is to give a speech based on the first prompt, then the generation mode can be determined as the first generation mode. If it is determined that the user's habit is to add some other content, then the generation mode can be determined as the second generation mode.

[0070] This embodiment provides a content display method that, by means of the above method, once the first prompt content has been determined, the final displayed second prompt content is determined in real time based on the degree of matching between the currently obtained first input content and the content included in the first prompt content. This makes the display of prompt content more flexible. Furthermore, in this embodiment, the determined second prompt content, based on the degree of matching between the first input content and the first prompt content, may only include the content in the first prompt content, or it may also include generated extended content or summary content, thereby making the display of prompt content richer and more flexible.

[0071] Please see Figure 10 This application provides a content display method, which includes: S310: Get the first input content.

[0072] S320: Check if there is a definite first prompt message.

[0073] Optionally, it can detect whether there is a specific first prompt content, which can be understood as detecting whether the user has pre-selected the first prompt content.

[0074] S330: If a first prompt exists, match the first input content with the determined first prompt.

[0075] S331: Display a second prompt based on the degree of matching, wherein different degrees of matching correspond to different second prompts, and different degrees of association between the second prompts and the first prompts are different.

[0076] S340: If the first prompt content is not available, display the second summary content, which is generated by the first input content and the second input content obtained in the past.

[0077] In this embodiment, upon receiving the first input content, it can first be checked whether a first prompt has been determined. If the first prompt exists (e.g., the user has pre-selected the speech), the first input content can be matched with the first prompt to determine the final second prompt to be displayed. If the first prompt does not exist (e.g., the user has not pre-selected the speech), the second prompt to be displayed may include a second summary.

[0078] In one approach, in the absence of initial prompt content, in addition to displaying the second summary content, extended content can also be displayed. For example, the extended content can be derived based on the initial input content obtained in the current instance, or it can be derived based on the initial input content and the previously obtained second input content.

[0079] In this embodiment, extended content can be obtained based on RAG (Retrieval-Augmented Generation). The working principle of RAG can be summarized as three closely collaborative core stages: retrieval, enhancement, and generation. First, in the question understanding stage, the input content is analyzed, rewritten, and reconstructed to make it more conducive to subsequent retrieval. Second, in the retrieval recall stage, based on the processed query, the system searches and filters the most relevant text fragments in an external knowledge base, integrating these results with the original question to form enhanced prompts. Finally, in the answer generation stage, the large language model receives enhanced prompts containing the original question and relevant background information, and generates the final answer based on this information.

[0080] The specific content included in the generated extended content can be determined in several ways.

[0081] One approach is to determine the content based on its popularity. In this method, when expanding on a specific topic, the most popular content related to that topic can be selected as the final expanded content to be displayed. This allows users to engage with the audience through currently trending content, thus enhancing the presentation's impact. For example, when generating expanded content for a specific city, information about its currently popular restaurants and attractions could be selected as the expanded content.

[0082] Another approach is to determine the content to be expanded upon based on the current audience. It's important to note that audiences of different ages or backgrounds may have different interests. For example, from an age perspective, teenagers tend to prefer content relevant to their own growth, such as methods for managing academic pressure and connecting hobbies with future development—content that directly addresses their current concerns. Younger adults focus on practical life and career development, such as career advancement skills, industry trend analysis, practical methods for managing family relationships, or strategies for coping with mid-life crises. Older audiences, on the other hand, are often interested in quality of life, such as scientific health maintenance knowledge, time planning after retirement, and sharing memories related to their own experiences—content that quickly resonates with them. In this approach, given the age composition of the audience, the age of the majority of the audience can be determined, allowing for the creation of expanded content based on this age group.

[0083] This embodiment provides a content display method that, in the aforementioned manner, when the first prompt content has been determined, determines the final displayed second prompt content in real time based on the degree of matching between the currently obtained first input content and the content included in the first prompt content. This makes the prompt content display method more flexible. Furthermore, this embodiment further distinguishes between whether the first prompt content is determined and whether it is not determined, and thus provides different methods for obtaining the second prompt content in different situations, further highlighting the adaptability and flexibility of the solution.

[0084] Next, we will proceed through... Figure 11 This application provides an example of an intelligent teleprompter system.

[0085] in, Figure 11 The provided intelligent teleprompter system adopts a modular design, with the teleprompter arrangement center as the core, coordinating the efficient operation of various functional modules. Its system architecture includes the following five core modules: 1. Central prompting and editing system The prompting and editing center is positioned as the "brain" and "command center" of the system. Its core responsibilities include: a) Receiving and distributing: Receives real-time transcribed text (which can be understood as the aforementioned first input content) from the "Speech Acquisition and Recognition Module" and, as the task initiator, distributes processing requests to the "Semantic Understanding and Alignment Module" and the "Knowledge Expansion Module".

[0086] b) Decision and Judgment: Based on the results returned by the semantic alignment module, decide which part of the manuscript (first prompt content) should be displayed (which can be understood as determining the content included in the second display content); or determine whether the speaker is improvising and decide whether to initiate knowledge expansion.

[0087] c) Content arrangement and synthesis: Integrate the key information from the manuscript and the auxiliary information generated by the knowledge expansion module, and intelligently arrange the final display layout (such as the layout of primary and secondary content, highlighting prompts, etc.).

[0088] d) Instruction issuance: Send the final arranged content instructions to the "Dynamic Display Module" for rendering.

[0089] 2. Voice Acquisition and Recognition Module The voice acquisition and recognition module acts as the system's "ears." Its core responsibilities include: a) Real-time capture: The speaker's voice stream is clearly captured through a high-fidelity microphone array.

[0090] b) Automatic Speech Recognition (ASR): Utilizing a low-latency, high-accuracy speech recognition engine, it quickly converts real-time speech streams into text data (which can be understood as the first input content in text form).

[0091] c) Data reporting: The transcribed text stream is sent to the prompting and editing center for processing in real time and continuously.

[0092] 3. Semantic Understanding and Alignment Module The semantic understanding and alignment module is positioned as the system's "reading comprehension expert." Its core responsibilities include: a) Receive instruction: Receive speech text fragments sent by the prompting center.

[0093] b) Semantic matching: Utilizing the natural language understanding capabilities of large language models, the input text is matched with the pre-set teleprompter for deep semantic matching, rather than simple keyword comparison.

[0094] c) Result Reporting: Reports matching results to the prompting and editing center, such as: "Matched the second sentence of the third paragraph of the manuscript, with a similarity of 95%" or "No strongly related content was found in the manuscript." It does not make decisions, but only provides accurate analysis results.

[0095] 4. Knowledge Extension Module The knowledge extension module is positioned as the system's "external brain" and "think tank." Its core responsibilities include: a) Receiving instructions: Receive knowledge retrieval and generation requests issued by the prompting and arrangement center (e.g., based on a keyword or a context of impromptu writing).

[0096] b) Information Retrieval: Utilize RAG technology to quickly retrieve relevant information from internal corporate knowledge bases (such as product data and historical events) and / or external knowledge indexes (such as internet search engines and knowledge graphs).

[0097] c) Content Generation: The retrieved information is filtered and summarized, and a large model is used to generate concise and suitable supplementary content for on-the-spot prompts (such as famous quotes, key data, background explanations, etc.).

[0098] d) Result reporting: Return the generated content to the prompting and editing center.

[0099] 5. Dynamic Display Module The dynamic display module serves as both the system's "screen" and "interactive interface." Its core responsibilities include: a) Receiving instructions: As a pure rendering engine, it receives and parses the final content and layout instructions from the prompting and layout center.

[0100] b) Content rendering: Clearly and smoothly display the prompting content and auxiliary information on various terminals such as teleprompter screens, tablets, and AR glasses.

[0101] c) Dynamic adjustment: Execute visual operations such as scrolling, jumping, highlighting, and split-screen display according to instructions to ensure that the speaker has the best visual experience.

[0102] Next, let's combine... Figure 12 This application describes a content display method based on an embodiment. For example... Figure 12 As shown: exist Figure 12 In the illustrated process, the speaker's (which can be understood as the user mentioned in the aforementioned embodiments) speech is first collected. The collected speech is then processed by a speech-to-text module to achieve real-time speech-to-text conversion. The converted text can be understood as a primary input content.

[0103] Given the text converted from speech (the first input content), it can be determined whether a teleprompter script (the first prompt content) exists.

[0104] When a prompting script exists, the converted text can be semantically matched with the content in the prompting script. For example, the prompting and arrangement center can initiate a semantic matching request, and the semantic understanding module can perform the semantic matching.

[0105] If the matching degree is greater than or equal to 'a', the page can jump to the corresponding paragraph in the document for display. The corresponding paragraph can be understood as the first target content in this embodiment of the application.

[0106] In cases where the matching degree is less than 'a' but greater than or equal to 'b', it can be determined that the speaker is currently in a semi-descriptive state. In this case, in addition to displaying the content in the manuscript that corresponds to the aforementioned converted text (content with a matching degree less than 'a' but greater than or equal to 'b'), auxiliary prompts (extended content) will also be obtained through the knowledge extension module. Conversely, if the matching degree is less than 'b', it can be determined that the speaker is currently in a fully descriptive state. In this case, the knowledge extension module can generate the first summary content and the extended content. Here, 'a' can be understood as the aforementioned first preset threshold, and 'b' can be understood as the aforementioned second preset threshold. For example, 'a' can be 0.7-0.9, and 'b' can be 0.4-0.6. For instance, in one case, 'a' can be 0.8, and 'b' can be 0.6.

[0107] If no prompting text is available, it can be determined that the current mode is without a prompt. The free speech retrieval process can be initiated to generate a second summary and extended content through the knowledge expansion module.

[0108] Please see Figure 13 This application provides a content display device 400, which operates in an electronic device. The device 400 includes: Content acquisition unit 410 is used to acquire the first input content; The matching unit 420 is used to match the first input content with the first prompt content and determine the degree of matching.

[0109] The prompt unit 430 is used to display a second prompt based on the degree of matching, wherein different degrees of matching correspond to different second prompts.

[0110] In one manner, the prompting unit 430 is specifically used to determine, when the first prompting content includes the first target content, that the second prompting content includes the first target content and the first associated content of the first target content, the degree of matching between the first target content and the first input content is greater than or equal to a first preset threshold, and to display the second prompting content.

[0111] In one approach, the prompting unit 430 is specifically used to determine, when the first prompting content does not include the first target content but includes the second target content, that the second prompting content includes the second target content, the second associated content of the second target content, and extended content, wherein the degree of matching between the second target content and the first input content is greater than or equal to a second preset threshold and less than the first preset threshold; wherein the extended content is obtained through the first input content.

[0112] In one approach, the prompting unit 430 is specifically used to determine that the second prompting content includes a first summary content and extended content when no content in the first prompting content matches the first input content to a degree greater than a second preset threshold. The first summary content is obtained through the first input content and the second input content obtained before the first input content, and the extended content is obtained through the first input content.

[0113] In one approach, the matching unit 420 is specifically used to match the first input content with the first prompt content when the first prompt content exists, and to determine the degree of matching; in this approach, the prompting unit is specifically used to display second summary content when the first prompt content does not exist, the second summary content being generated from the first input content and historically obtained second input content.

[0114] In one approach, the matching unit 420 is specifically used to perform semantic matching between the first input content and the determined first prompt content using a large language model.

[0115] This embodiment provides a content display device that, when the first prompt content has been determined, determines the final second prompt content to be displayed in real time based on the degree of matching between the currently obtained first input content and the content included in the first prompt content, thereby making the way of displaying prompt content more flexible.

[0116] It should be noted that the device embodiments in this application correspond to the aforementioned method embodiments. The specific implementation principles of each unit in the device embodiments are similar to those in the aforementioned method embodiments. The specific content in the device embodiments can be found in the method embodiments, but will not be repeated in the device embodiments.

[0117] The following will combine Figure 14 This application describes an electronic device.

[0118] Please see Figure 14 Based on the aforementioned content display method and apparatus, this application embodiment also provides an electronic device 1000 capable of executing the aforementioned content display method. The electronic device 1000 includes one or more (only one shown in the figure) processors 105, a memory 104, an audio playback module 106, and an audio acquisition device 108 coupled together. The memory 104 stores programs capable of executing the content described in the aforementioned embodiments, and the processor 105 can execute the programs stored in the memory 104.

[0119] The processor 105 may include one or more processing cores. The processor 105 connects to various parts within the electronic device 1000 using various interfaces and lines, and performs various functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 104, and by calling data stored in the memory 104. Optionally, the processor 105 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 105 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the displayed content; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 105 and may be implemented separately using a communication chip.

[0120] The memory 104 may include random access memory (RAM) or read-only memory (ROM). The memory 104 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 104 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as touch functionality, sound playback functionality, image playback functionality, etc.), and instructions for implementing the various method embodiments described below.

[0121] Furthermore, in addition to the aforementioned devices, the electronic device 1000 may also include a network module 110 and a sensor module 112.

[0122] The network module 110 is used to enable information interaction between the electronic device 1000 and other devices. For example, it can establish connections with other audio playback devices or other electronic devices and interact with information based on the established connections. As one approach, the network module 110 of the electronic device 1000 is a radio frequency (RF) module. This RF module is used to receive and transmit electromagnetic waves, realizing the mutual conversion between electromagnetic waves and electrical signals, thereby enabling communication with communication networks or other devices. The RF module may include various existing circuit elements used to perform these functions, such as antennas, RF transceivers, digital signal processors, encryption / decryption chips, SIM cards, memory, etc. For example, this RF module can interact with external devices through transmitted or received electromagnetic waves.

[0123] Sensor module 112 may include at least one sensor. Specifically, sensor module 112 may include, but is not limited to, pressure sensors, motion sensors, acceleration sensors, and other sensors.

[0124] The pressure sensor is a sensor that detects pressure generated by pressing on the electronic device 1000. That is, the pressure sensor detects pressure generated by contact or pressing between the user and the electronic device 1000, such as pressure generated by contact or pressing between the user's ear and the electronic device 1000. Therefore, the pressure sensor can be used to determine whether contact or pressing has occurred between the user and the electronic device 1000, and the magnitude of the pressure.

[0125] The accelerometer can detect the magnitude of acceleration in various directions (generally three axes), and when stationary, it can detect the magnitude and direction of gravity. It can be used for applications such as identifying the posture of the electronic device 1000 (e.g., screen orientation switching, related games, magnetometer posture calibration), and vibration recognition functions (e.g., pedometer, tapping). Additionally, the electronic device 1000 can also be equipped with other sensors such as a gyroscope, barometer, hygrometer, and thermometer, which will not be elaborated upon here.

[0126] The audio acquisition device 108 is used to acquire audio signals. Optionally, the audio acquisition device 108 includes multiple audio acquisition devices, which may be microphones.

[0127] Please refer to Figure 15This diagram illustrates a structural block diagram of a computer-readable storage medium provided in an embodiment of this application. The computer-readable medium 1100 stores program code that can be called by a processor to execute the methods described in the above method embodiments.

[0128] The computer-readable storage medium 1100 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. Optionally, the computer-readable storage medium 1100 includes a non-transitory computer-readable storage medium. The computer-readable storage medium 1100 has storage space for program code 1110 that performs any of the method steps described above. This program code can be read from or written to one or more computer program products. The program code 1110 may, for example, be compressed in a suitable form.

[0129] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0130] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0131] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the function involved, as will be understood by those skilled in the art to which embodiments of this application pertain.

[0132] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus or device (such as a computer-based system, a processor-included system or other system that can fetch and execute instructions from, an instruction execution system, apparatus or device).

[0133] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0134] In summary, the content display method, apparatus, and electronic device provided in this application, when a first input content is obtained, can match the first input content with a determined first prompt content. This allows for the determination of a second prompt content to be displayed based on the degree of matching between the content included in the first prompt content and the first input content. Different degrees of matching correspond to different second prompt contents, and different degrees of association between the second prompt contents and the first prompt content also differ. Therefore, by employing the above method, even when the first prompt content has been determined, the final displayed second prompt content is determined in real-time based on the degree of matching between the currently obtained first input content and the content included in the first prompt content, thus making the display of prompt content more flexible.

[0135] In one implementation, this application revolutionizes the traditional prompting model, innovatively proposing non-linear real-time adaptive and knowledge-expanding delivery of speech content. In the prompting system proposed in this application, a central prompting hub, based on a large model's deep semantic understanding of the speech content, dynamically jumps to relevant segments of the script on-site. When impromptu delivery or going off-script is detected, high-value supplementary information consistent with the context (company history, product facts, outstanding achievements, famous quotes, historical anecdotes, etc.) is instantly retrieved and generated, enhancing the speech quality and information density in real time without interrupting the main script.

[0136] In one implementation, this application enables non-linear, semantically driven real-time alignment: replacing sequential pagination and keyword matching with sentence / segment embedding and contextual understanding. In another implementation, this application enables real-time knowledge augmentation generation: strategic selection between enterprise knowledge and publicly available external knowledge, with a large model instantly assembling / generating credible and citationable extended prompts. In yet another implementation, this application enables a prompting and arrangement hub: a unified command center for receiving, deciding, arranging, and issuing instructions, ensuring efficient collaboration between the main text and extended information.

[0137] In one implementation, this application can enhance the freedom of speech, allowing speakers to speak without notes while still receiving teleprompter support. It can improve improvisation capabilities by providing relevant background information or key phrases in real-time through a large language model. It can reduce speech preparation costs by minimizing redundant content that must be included in the prepared script. It can improve the audience experience, making the speech more natural, fluent, and informative.

[0138] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical feature diagrams. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A content display method characterized by, The method is applied to an electronic device, and the method comprises: obtaining first input content; matching the first input content with first prompt content and determining a matching degree; displaying second prompt content according to the matching degree, wherein the second prompt content corresponding to different matching degrees is different.

2. The method of claim 1, wherein, The displaying of the second prompt content according to the matching degree comprises: in the case that the first prompt content comprises first target content, determining that the second prompt content comprises the first target content and first associated content of the first target content, and the matching degree of the first target content with the first input content is greater than or equal to a first preset threshold value; displaying the second prompt content.

3. The method of claim 2, wherein, The displaying of the second prompt content according to the matching degree further comprises: in the case that the first prompt content does not comprise the first target content and comprises second target content, determining that the second prompt content comprises the second target content, second associated content of the second target content and expansion content, the matching degree of the second target content with the first input content is greater than or equal to a second preset threshold value and less than the first preset threshold value, and the expansion content is obtained through the first input content.

4. The method of claim 3, wherein, The displaying of the second prompt content comprises: displaying the second target content, the second associated content and the expansion content comprised in the second prompt content in the same interface, wherein the display areas of the second target content, the second associated content and the expansion content are different.

5. The method of claim 3, wherein, The displaying of the second prompt content according to the matching degree further comprises: in the case that no content in the first prompt content has a matching degree with the first input content greater than the second preset threshold value, determining that the second prompt content comprises first abstract content and expansion content, wherein the first abstract content is obtained through the first input content and second input content obtained before the first input content, and the expansion content is obtained through the first input content.

6. The method of claim 1, wherein, The matching of the first input content with the first prompt content and the determination of the matching degree comprises: in the case that there is first prompt content, matching the first input content with the first prompt content and determining the matching degree; in the case that there is no first prompt content, displaying second abstract content, which is generated through the first input content and second input content obtained historically.

7. The method according to any of claims 1 to 6, characterized in that The matching of the first input content with the first prompt content and the determination of the matching degree comprises: matching the first input content with the first prompt content and determining the matching degree through a large language model.

8. A content display device, characterized by comprising: The device runs on an electronic device, and the device comprises: a content obtaining unit configured to obtain first input content; a matching unit configured to match the first input content with first prompt content and determine a matching degree; a prompt unit configured to display second prompt content according to the matching degree, wherein the second prompt content corresponding to different matching degrees is different.

9. An electronic device, comprising: one or more processors and a memory; One or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs being configured to perform the method of any one of claims 1-7.

10. A computer program product, characterised in that, It includes computer program instructions that cause a computer to perform the method as described in any one of claims 1-7.

Images