Prompting method and electronic device

Abstract

The present disclosure provides a prompting method, comprising: obtaining input information in a first session; determining target sub-content matched with the input information in session content of the first session based on the input information; determining a target time corresponding to the target sub-content in the first session based on the target sub-content and the session content, the target time being a time at which the target sub-content is explained / demonstrated in the first session; and generating prompting information based on the target sub-content and the target time. The present disclosure also provides an electronic device for executing the method.

Description

Technical Field

[0001] This disclosure relates to the field of information interaction, and more specifically, to a prompting method and an electronic device. Background Technology

[0002] In interactive scenarios such as online training and web-based sharing sessions, while the speaker is explaining, the audience can interact in real time by inputting text messages or questions through chat rooms, Q&A areas, etc. If the audience's messages or questions cannot be responded to promptly, it may force the speaker to frequently interrupt the presentation to respond to the audience's questions. Furthermore, if the audience does not receive a response for an extended period, they may mistakenly feel ignored, significantly reducing the fluency and overall experience of the conversation. Summary of the Invention

[0003] In view of this, this disclosure provides a prompting method and an electronic device.

[0004] One aspect of this disclosure provides a prompting method, comprising: acquiring input information in a first session; determining, based on the input information, a target sub-content in the session content of the first session that matches the input information; determining, based on the target sub-content and the session content, a target time corresponding to the target sub-content in the first session, wherein the target time is the time when the target sub-content is explained or displayed in the first session; and generating prompting information based on the target sub-content and the target time.

[0005] According to embodiments of this disclosure, the first session is a real-time interactive session, and the session content includes multimedia presentation information of the first session and explanation information of the first object regarding the multimedia presentation information. The input information is input by the second object. The prompting method further includes: determining the first session content corresponding to the first moment based on the first moment when the second object inputs the input information in the first session; determining the target moment corresponding to the target sub-content in the first session, including: determining the first explanation moment corresponding to the target sub-content in the first session based on the target sub-content and the first session content, wherein the target moment includes the first explanation moment of the target sub-content in the first session; generating prompting information based on the target sub-content and the target moment, including: generating first prompting information based on the target sub-content and the target moment, wherein the first prompting information indicates that the explanation moment of the target sub-content is the first explanation moment.

[0006] According to embodiments of this disclosure, a prompt message is generated based on the target sub-content and the target time, including: in response to the current time being the second time, determining the second session content corresponding to the second time, wherein the second time is the time before the target time and the time difference of a preset duration from the target time; determining the second expected explanation time corresponding to the target sub-content based on the second time and the second session content; if the second expected explanation time matches the first explanation time, generating the second prompt message based on the first explanation time, wherein the second prompt message is used to prompt the first object and / or the second object that the target sub-content is about to be explained; if the second expected explanation time does not match the first explanation time, adjusting the target time based on the second expected explanation time; and generating the second prompt message based on the adjusted target time.

[0007] According to embodiments of this disclosure, a first session includes multiple second objects, and a prompt message is generated based on the target sub-content and the target time, including: in response to the number of second objects that input information for the same target sub-content being greater than or equal to a number threshold, the prompt message is generated based on the target sub-content, the target time, and the number.

[0008] According to embodiments of this disclosure, the prompting method further includes: determining multimedia presentation information of a first session, dividing the multimedia presentation information into multiple sub-contents through a target model; determining the themes corresponding to the multiple sub-contents respectively through the multimedia presentation information; and determining the target sub-contents in the session content of the first session that match the input information, including: matching the input information with the themes corresponding to each sub-content to determine the target sub-contents in the session content that match the input information.

[0009] According to embodiments of this disclosure, generating prompt information based on target sub-content and target time includes: in response to the current time being a first explanation time, generating third prompt information and / or fourth prompt information based on target sub-content and target time; the third prompt information is used to prompt the input information corresponding to the first object target sub-content; the fourth prompt information is used to prompt the target sub-content corresponding to the second object input information being explained; and / or, the prompting method further includes: changing the presentation state of the multimedia presentation content in the target sub-content that matches the input information, so that the presentation state of the multimedia presentation content that matches the input information is different from that of other content in the session content.

[0010] According to embodiments of this disclosure, generating prompt information based on target sub-content and target time includes: generating fifth prompt information based on target sub-content and target time, the fifth prompt information being used to prompt the second object the expected explanation time of the target sub-content, and / or the location of the target sub-content; and / or, the prompting method further includes: presenting the target sub-content to the second object.

[0011] According to embodiments of this disclosure, multiple sub-contents are arranged in a preset order, and the method further includes: in response to the current session content being adjacent sub-content, generating a sixth prompt message based on the target sub-content, the sixth prompt message being used to prompt that the target sub-content is about to be explained; adjacent sub-contents are the sub-contents adjacent to the target sub-content.

[0012] According to embodiments of this disclosure, the prompt further includes: if the target sub-content cannot be matched based on the input information, generating a seventh prompt message based on the input information, the seventh prompt message being used to prompt the first object for input information.

[0013] Another aspect of this disclosure provides a prompting device, comprising: an acquisition module for acquiring input information in a first session; a first determination module for determining, based on the input information, a target sub-content in the session content of the first session that matches the input information; a second determination module for determining, based on the target sub-content and the session content, a target time corresponding to the target sub-content in the first session, wherein the target time is the time when the target sub-content is explained or displayed in the first session; and a generation module for generating prompting information based on the target sub-content and the target time.

[0014] Another aspect of this disclosure provides an electronic device, including: at least one processor; and a memory connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the following operations: acquiring input information in a first session; determining, based on the input information, a target sub-content in the session content of the first session that matches the input information; determining, based on the target sub-content and the session content, a target time corresponding to the target sub-content in the first session, the target time being the time when the target sub-content is explained / displayed in the first session; and generating prompt information based on the target sub-content and the target time.

[0015] Another aspect of this disclosure provides a computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to perform a prompting method according to any of the foregoing embodiments.

[0016] Another aspect of this disclosure provides a computer program product, including a computer program / instructions, characterized in that the computer program / instructions, when executed by a processor, implement the operation of the method indicated in any of the foregoing embodiments. Attached Figure Description

[0017] The above and other objects, features and advantages of this disclosure will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0018] Figure 1A flowchart illustrating a prompting method according to an embodiment of the present disclosure is shown schematically;

[0019] Figure 2 Another flowchart illustrating a prompting method according to an embodiment of the present disclosure is shown schematically;

[0020] Figure 3 A flowchart illustrating the generation of a second prompt message in a prompting method according to an embodiment of the present disclosure is shown schematically.

[0021] Figure 4 Another flowchart illustrating a prompting method according to an embodiment of the present disclosure is shown schematically;

[0022] Figure 5 Another flowchart illustrating a prompting method according to an embodiment of the present disclosure is shown schematically;

[0023] Figure 6 Another flowchart illustrating a prompting method according to an embodiment of the present disclosure is shown schematically;

[0024] Figure 7 Another flowchart illustrating a prompting method according to an embodiment of the present disclosure is shown schematically;

[0025] Figure 8 Another flowchart illustrating a prompting method according to an embodiment of the present disclosure is shown schematically;

[0026] Figure 9 Another flowchart illustrating a prompting method according to an embodiment of the present disclosure is shown schematically;

[0027] Figure 10 A block diagram schematically illustrates a prompting device according to an embodiment of the present disclosure; and

[0028] Figure 11 A block diagram of an electronic device suitable for implementing the methods described above, according to embodiments of the present disclosure, is illustrated schematically. Detailed Implementation

[0029] The embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0030] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0031] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0032] When using expressions such as "at least one of A, B and C", they should generally be interpreted in accordance with the meaning that is commonly understood by those skilled in the art (e.g., "a system having at least one of A, B and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B and C, etc.).

[0033] In the embodiments disclosed herein, the collection, updating, analysis, processing, use, transmission, provision, disclosure, and storage of data (e.g., including but not limited to user personal information) comply with relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. In particular, necessary measures have been taken to prevent unauthorized access to user personal information data and to safeguard user personal information security, network security, and national security.

[0034] Embodiments of this disclosure provide a prompting method, including: acquiring input information in a first session; determining, based on the input information, a target sub-content in the session content of the first session that matches the input information; determining, based on the target sub-content and the session content, a target time corresponding to the target sub-content in the first session, wherein the target time is the time when the target sub-content is explained / displayed in the first session; and generating prompting information based on the target sub-content and the target time.

[0035] Figure 1 A flowchart illustrating a prompting method according to an embodiment of the present disclosure is shown schematically.

[0036] like Figure 1 As shown, the prompting method may include at least operations S110 to S140.

[0037] In operation S110, input information from the first session is acquired. This input information encompasses the data stream submitted by participants through various input terminals during the interaction. It can be presented as unstructured text, transcribed speech data, or pre-defined interaction commands. Acquiring input information typically involves real-time monitoring of the interactive interface to capture questions, suggestions, or comments initiated by participants. For example, capturing textual inquiries about technical parameters sent by participants in the discussion area, or verbal questions captured by a speech acquisition device.

[0038] In operation S120, based on the input information, the target sub-content that matches the input information in the first session's content is determined. The session content includes the entire set of information involved in the first session. This set of information constitutes the session's complete knowledge set in the time dimension, including but not limited to historical content that has already been explained, currently presented content, and content pre-set to be shown in subsequent stages. Each independent information unit or its logical combination can be considered a sub-content. The matching process can be through semantic parsing or keyword extraction to locate specific units logically related to the input information from the aforementioned complete information set and determine them as target sub-content. For example, associating a participant's question about "system architecture" with the corresponding relevant page or chapter in the presentation document, or matching inquiries about specific business logic to the corresponding presentation materials.

[0039] In operation S130, based on the target sub-content and the session content, the target time corresponding to the target sub-content in the first session is determined. The target time is the moment when the target sub-content is explained or displayed in the first session. The target time reflects the temporal attribute of the target sub-content on the timeline of the first session, representing the logical position of the sub-content in the session flow. The process of determining the target time is based on the temporal analysis of the session structure to obtain the coordinates of the target sub-content in the time dimension. These coordinates are used to define the order in which the content is accessed or the specific node. For example, based on the session record or the preset logical architecture, the position point corresponding to a specific sub-content on the session timeline is determined; or based on the current display progress, the time offset of the target unit relative to the reference node is obtained.

[0040] In operation S140, a prompt message is generated based on the target sub-content and the target time. The prompt message, acting as a feedback medium, carries the attribute of indicating the matching result and its relationship on the timeline. The process of generating the prompt message involves logically associating the time-series data of the target time with the index data of the target sub-content to construct an interactive element that indicates the conversational location or relational state pointed to by the input information. For example, the prompt message can manifest as a feedback message presented on the interactive interface, guiding participants to focus on a specific content unit related to the input information and its actual explanation time; alternatively, the prompt message can also manifest as a logical identifier, used to establish the relationship between the current input and the target content in terms of explanation progress.

[0041] According to embodiments of this disclosure, by automatically associating input information with all conversation content covering both historical and future events, and accurately determining the corresponding target time, the system can ensure that after capturing input information such as questions, it generates prompts associated with the target time and provides timely feedback to the relevant audience, thereby effectively alleviating the anxiety caused by a lack of transparency in information access. Simultaneously, because this prompting mechanism logically aligns questions with subsequent or specific explanation points, the speaker does not need to frequently interrupt the original narrative rhythm to handle disorganized questions during the explanation process. Instead, the speaker can respond naturally at the most appropriate content point based on the system's guidance, thus ensuring timely response to audience demands while also maintaining the coherence of the speaker's explanation logic and the overall efficiency of the meeting.

[0042] Figure 2 Another flowchart illustrating a prompting method according to an embodiment of the present disclosure is shown schematically.

[0043] like Figure 2 As shown, based on the aforementioned embodiments, the first session is a real-time interactive session. The session content includes multimedia presentation information of the first session and explanation information from the first object regarding the multimedia presentation information. Input information is provided by the second object. Real-time interactive sessions typically refer to online communication scenarios with continuous information transmission and feedback. The multimedia presentation information covers the basic visual or auditory materials displayed in this scenario, while the explanation information is an oral explanation or supplementary description of these materials. The first object is the information outputter or leader, and the second object is the information receiver or participant. For example, in a large-scale online technical training session, the first object can be the speaker, the multimedia presentation information is the shared presentation slides, the explanation information is the speaker's voice broadcast data, and the second object is the audience submitting questions.

[0044] The prompting method may include operation S210, operation S130 may include operation S220, and operation S140 may include operation S230.

[0045] In operation S210, based on the first moment when the second object inputs information in the first session, the content of the first session corresponding to the first moment is determined. The first moment represents the specific time node when the input operation is triggered; it is not only an absolute timestamp but also identifies the specific context in which the interaction occurs. The content of the first session represents the presentation materials and corresponding explanatory information that are active or displayed at that time node. For example, the current time when the listener sends a text inquiry in the chat box is obtained, and the specific demo page being displayed at that time and the corresponding speech-to-text are extracted as the base content.

[0046] In operation S220, based on the target sub-content and the first session content, the first explanation time corresponding to the target sub-content in the first session is determined. The target time includes the first explanation time of the target sub-content in the first session. The first explanation time represents the initial assessment time when the target sub-content is formally explained as planned. This time node can be either a baseline timestamp predicted in advance and assigned to each information unit based on the overall logical structure and historical experience of the material before the multimedia presentation material is actually used; or it can be an expected node derived in real time during the interaction process, relying on the current progress baseline established by the first session content. By extracting the pre-set time node or measuring the progress span between the target sub-content and the current baseline content, the absolute position or relative waiting time of the target sub-content on the timeline can be accurately determined. For example, if it has been pre-calculated that the chapter involving "operational process" will be explained 30 minutes after the start of the session, this pre-set time node can be directly extracted as the first explanation time when a question is received; or, taking the 3rd page being displayed when the question occurs as the progress starting point, combined with the pre-statistical average time per page, the relative time difference at which the 10th page content, which closely matches the question, will be reached can be calculated.

[0047] In operation S230, based on the target sub-content and the target time, a first prompt message is generated. This first prompt message indicates that the explanation time for the target sub-content is the first explanation time. The first prompt message is feedback data with a strong time-oriented attribute, used to clearly convey the planned explanation time of the matching content to the information input party. By encapsulating the calculated first explanation time into an interactive interface element, the second object can obtain a timeliness commitment for its specific input, establishing accurate content expectations. For example, a feedback pop-up window containing the text "Your question will be explained in approximately 15 minutes" can be generated, or an automatic reply message carrying a specific explanation timestamp can be sent individually to the corresponding audience.

[0048] According to embodiments of this disclosure, by introducing scenario elements of real-time interactive sessions and establishing the current explanation progress benchmark based on the first moment triggered by the input action, the precise first explanation moment is calculated and corresponding first prompt information is generated, directly resulting in a significant improvement in the timeliness of question feedback. This allows listeners to receive an immediate response with a clear time expectation after asking a question, greatly alleviating the feeling of being ignored and anxiety caused by not receiving feedback for a long time, thus improving the meeting experience. At the same time, since listeners know the explanation timing in advance, they avoid asking a large number of repetitive questions in the chat area, which also allows the speaker to avoid temporarily interrupting the original narrative rhythm to explain "what will be discussed later" one by one, ensuring the smoothness of the overall explanation process.

[0049] According to embodiments of this disclosure, the prompting method may further include: in response to the target time being earlier than the first time, determining that the target sub-content is already explained content; generating first prompting information based on the target sub-content and its position in the session content, the first prompting information being used to prompt the second object that the target sub-content is already explained content and the position of the target sub-content.

[0050] When the target moment is prior to the current interaction point on the timeline, it indicates that the knowledge unit pointed to by the input information has already been presented for the first time in terms of physical progress. The first prompt at this point serves as a retrospective guide, alleviating any doubts the audience may have about "missing" the content by clearly informing them of its historical state. This prompt uses the logical or physical location of the target sub-content (such as PPT page numbers, document chapters, etc.) as a visual element, giving the audience the ability to retrospectively review the information.

[0051] For example, when the system detects that the target sub-content of an audience member's question about "the principles of data encryption" is located on page 2 of the presentation, while the current speaker has already covered page 10, a prompt message will automatically pop up on the questioner's screen: "The encryption principle section you are interested in has been explained on page 2. You can click to view the corresponding replay or page"; or a "Presented" label with a page number will be displayed below the corresponding question.

[0052] Figure 3 A flowchart illustrating the generation of a second prompt message in a prompting method according to an embodiment of the present disclosure is shown.

[0053] like Figure 3 As shown, based on the aforementioned embodiments, operation S140 may include operations S310 to S350.

[0054] In operation S310, in response to the current time being the second time, the second session content corresponding to the second time is determined. The second time is the time before the target time, which is a preset duration difference from the target time. The second time constitutes a preliminary time checkpoint, which is set by shifting a fixed time window forward from the expected target time. The second session content represents the information carrier that is actually being processed or displayed in the session when this checkpoint is triggered. The introduction of the preset duration difference is to reserve sufficient buffer space for subsequent interactive responses. For example, if the preset duration difference is set to 2 minutes, when the timeline reaches the node with 2 minutes remaining before the originally scheduled first explanation time, the currently playing audio segment and the displayed page screen are obtained as the second session content.

[0055] In operation S320, the second estimated explanation time corresponding to the target sub-content is determined based on the second time point and the second session content. The second estimated explanation time represents the time node at which the target sub-content will be reached, recalculated after real-time progress verification. This determination process measures the remaining span between the actual logical position (second session content) at the checkpoint (second time point) and the position to be reached (target sub-content), and recalculates it in conjunction with the real-time information progress rate, thereby transforming the initial expectation into an expectation based on real-time dynamic calibration. For example, based on a checkpoint with 2 minutes remaining, if analysis of the currently displayed page reveals that the speaker's speaking speed has slowed down or the dwell time has increased, the target sub-content will actually require another 4 minutes to be reached, and this newly calculated time node will be used as the second estimated explanation time.

[0056] In operation S330, if the second expected explanation time matches the first explanation time, a second prompt message is generated based on the first explanation time. This second prompt message is used to alert the first object and / or the target sub-content of the second object that it is about to be explained. Operation S330 is used to check whether the recalculated progress is consistent with the initial assessed progress within the tolerance range. The second prompt message serves as a proximity warning signal to alert the information provider or receiver in advance. When the actual pace of the verification session does not deviate significantly, the initial time anchor is directly used to construct this warning signal, ensuring that relevant participants have a smooth psychological expectation before the content officially appears.

[0057] For example, if the recalculated time is within 30 seconds of the initial time, a floating reminder will be generated to show the audience "The part related to your question is about to be explained, please pay attention"; or a memo will be generated to show the speaker.

[0058] In operation S340, if the second estimated explanation time does not match the first explanation time, the target time is adjusted based on the second estimated explanation time. The "mismatch" state reflects an acceleration in pace, delay, or content jump during the session's execution, causing the actual progress to deviate from the initial setting. In this case, the original time anchor is overwritten or corrected by using the expected node re-acquired based on the real-time progress, eliminating timing errors caused by changes in the explanation pace and maintaining strict alignment between the logical chain and the time chain. For example, if skipping some content causes the recalculated estimated arrival time to be significantly earlier, the original first explanation time is discarded, and the earlier time node is updated to the new target time.

[0059] When operating S350, a second prompt message is generated based on the adjusted target time. By using a dynamically calibrated time base to trigger the proximity warning signal, it is ensured that regardless of fluctuations in the session flow, the warning operation is always executed within the most appropriate real-time window from the target sub-content, avoiding invalid or delayed interactive feedback. For example, relying on the pre-updated time node, a pre-event reminder is accurately sent to the questioner just before the actual content is about to appear, rather than rigidly waiting for the original time.

[0060] According to embodiments of this disclosure, by setting checkpoints containing preset duration differences before the target time arrives, and dynamically recalculating the expected presentation time based on the actual conversation content at that time, adaptive calibration of the conversation progress is achieved. This effectively overcomes the problem of initial prediction failure caused by the speaker temporarily changing the presentation rhythm or skipping content. This, in turn, enables extremely accurate proximity reminders, avoiding issuing invalid reminders to the audience too early or too late. Simultaneously, since the triggering of the warning signal is always highly synchronized with the actual logical progress, it not only provides participants with personalized attention prompts but also enhances meeting focus, optimizing the reliability of intelligent meeting assistance methods and the participant experience.

[0061] Figure 4 Another flowchart illustrating a prompting method according to an embodiment of the present disclosure is shown schematically.

[0062] like Figure 4 As shown, based on the aforementioned embodiments, the first session includes multiple second objects, and operation S140 may include operation S410.

[0063] In operation S410, in response to the number of second objects of input information targeting the same target sub-content being greater than or equal to a threshold, a prompt message is generated based on the target sub-content, the target time, and the number. "The same target sub-content" refers to a specific information unit that is jointly mapped or associated by multiple different independent input data, indicating that the information unit has high group attention or belongs to a common focus of question. The process of generating the prompt message not only integrates the semantic features of the target content (target sub-content) and the expected temporal location (target time), but also explicitly introduces a measure of the size of the attention group (number).

[0064] For example, in a large-scale technical sharing session, if it is detected that more than 5 attendees have posted inquiries related to "parameter tuning," and these inquiries all point to a specific chapter to be presented later, then the common semantics of these inquiries and the statistical number "5" are extracted. Combined with the expected reach time of that chapter, a summary summary prompt containing phrases such as "5 participants are interested in tuning methods" is generated and displayed in an appropriate interactive interface.

[0065] According to embodiments of this disclosure, by introducing an input statistics mechanism involving multiple second objects, and generating a prompt message containing large-scale data when the number of inputs pointing to the same content reaches a threshold, automatic identification and structured summarization of frequently asked common questions are achieved, effectively avoiding the disorderly clutter of the conversation interface by a massive number of repetitive or similar questions. This allows the speaker to intuitively and quickly grasp the common needs and focus of the participants without manual filtering and summarization, enabling them to elaborate in a focused and targeted manner at the corresponding target time. This not only reduces the speaker's cognitive burden but also significantly improves the overall meeting's interactive efficiency and content delivery quality.

[0066] Following the above embodiments, the display method may further include: in response to the fact that the number of second objects receiving input information for the same target sub-content is greater than or equal to a number threshold, and the explanation or display time corresponding to the target sub-content is before the first time, generating prompt information based on the target sub-content, the target time, and the number. This prompt information is used to suggest a re-explanation of the target sub-content to the first object.

[0067] When the frequency of interactions for the same specific information unit (target sub-content) reaches a preset scale (number threshold), and the unit has been marked as "explained" in physical time sequence (i.e., the target time is earlier than the first moment triggered by the current input), that is, when monitoring the "hot spots" of questions for the explained content, it is transformed into a perceptible feedback element. This aims to inform the first subject which knowledge points belong to the category of "generally not mastered" or "not explained thoroughly", thereby prompting the first subject to conduct a second explanation or key review of the historical content.

[0068] For example, in a training session, the presenter has reached page 20 of the presentation, but backend statistics show that 12 people have asked questions about the "model algorithm" section on page 5 (exceeding the preset threshold of 10). At this point, based on page 5 (the target sub-content), its corresponding historical timestamp (the target time), and the number of questions (12), a high-priority prompt can be generated in the presenter's interactive sidebar: "12 participants have raised questions about page 5. The audience's understanding is low; we suggest you pause here and reiterate." Alternatively, the presenter's progress bar can highlight page 5 as a "high-frequency question area" and include a reiteration button.

[0069] According to embodiments of this disclosure, by introducing statistical warnings and re-examination suggestions for already explained content based on the identification of common problems among multiple users, the "perception blind spot" problem—where the presenter cannot perceive the audience's understanding status in real time—is solved. Quantitative data feedback replaces vague experience-based guesses, enabling the presenter to accurately identify parts that are too difficult or unclearly expressed. This allows the presenter to dynamically adjust the pace of the presentation and fill in gaps in real time, ensuring both the quality of information delivery and the audience's sense of accomplishment, while avoiding the inefficiency caused by frequently dealing with trivial historical questions, thus ensuring a balance in large-scale, highly interactive sessions.

[0070] Figure 5 Another flowchart illustrating a prompting method according to an embodiment of the present disclosure is shown schematically.

[0071] like Figure 5 As shown, based on the aforementioned embodiments, the prompting method may include operations S510 to S520, and operation S120 may include operation S530.

[0072] In operating S510, the multimedia presentation information for the first session is determined, and the target model divides this information into multiple sub-contents. This multimedia presentation information can be global presentation materials or visual foundational materials loaded before or at the beginning of the session, often in an initial, undisplayed stacked state. The target model refers to an intelligent network architecture with cross-modal data processing and deep semantic parsing capabilities, such as a large-scale pre-trained model integrating natural language processing and computer vision feature extraction. The global multimedia presentation information is input into the target model, which intelligently parses the material's layout, visual arrangement, text paragraphs, and contextual coherence, precisely cutting it into multiple independent and semantically complete basic information units based on its inherent logical boundaries. For example, in the preparation stage, the loaded complete presentation is imported into the multimodal large model. Based on the physical pagination, content layout, and logical transitions of the slides, the model intelligently divides this long document into multiple page units or chapter blocks with independent content.

[0073] When operating the S520, multiple sub-content topics are determined through multimedia presentation of information. A topic represents the core idea, category attribute, or key semantic summary of the corresponding information unit; it is a highly condensed and abstracted structured feature tag. The process of determining the topic essentially involves deep feature extraction and semantic summarization of each segmented independent information unit. By stripping away redundant decorative or transitional descriptions from each sub-content, an index identifier that accurately represents the essence of the unit is extracted, thereby constructing a structured mapping dictionary or index database of "sub-content—semantic tags" on top of the disorganized presentation material. For example, for an independent page unit containing complex formulas and performance comparison charts, the topic tags "algorithm parameters" or "test metrics" are generated and assigned by analyzing the text and image features; or for a page describing application cases, the topic "application scenario" is automatically extracted.

[0074] In operation S530, based on the input information, it matches each sub-content with its corresponding topic to determine the target sub-content in the conversation content that matches the input information. This matching process can be based on direct comparison of literal characters or fixed rules, or it can be based on deep correlation calculation and intent alignment in the latent semantic space, or a combination of multiple matching dimensions.

[0075] Using a pre-built structured mapping dictionary, the matching degree or relevance between the input information and various preset topics is calculated. In specific implementations, this can be achieved by extracting key terms from the input information and searching the mapping dictionary for topic tags containing the same, similar, or synonymous terms; or by transforming the input information into a feature representation that characterizes its true intent and calculating its semantic distance to the preset topics. Finally, the information units corresponding to the topics with the highest matching degree or relevance scores crossing a preset confidence threshold are identified as target sub-content capable of responding to or answering the current input information.

[0076] For example, when the text question "data preprocessing methods" is obtained, it is directly matched with page units with the topic tag "data preprocessing" by comparing strings or keywords. Or, when the colloquial and divergent question "how to make the model generalize more effectively" is obtained, it is converted into a semantic vector and the similarity of the vector space with the topic tags of each page is calculated. When it is found that the similarity between the question and the topic "parameter tuning and regularization" of a page to be displayed exceeds a preset threshold, the page to be displayed is then identified as a highly matched target sub-content.

[0077] According to embodiments of this disclosure, by introducing a target model to perform pre-processing intelligent layout segmentation and topic extraction of multimedia presentation information, and performing multi-dimensional association matching based on topics, a deep structured understanding and dynamic index construction of static conversation materials are achieved. This not only enables efficient processing of standardized questions through rapid literal or keyword comparison, but also overcomes the shortcomings of existing technologies in understanding complex, divergent, or colloquial questions by utilizing semantic-level intent alignment, significantly improving the accuracy and applicability of the association between question data and explanation materials. Simultaneously, because a highly condensed topic index database is pre-built for the original materials, the computational load of the matching process during the meeting is significantly compressed, thereby achieving low latency while ensuring high-precision matching.

[0078] Figure 6 Another flowchart illustrating a prompting method according to an embodiment of the present disclosure is shown schematically.

[0079] like Figure 6 As shown, based on the aforementioned embodiments, operation S140 may include operation S610, and the prompting method may also include operation S620.

[0080] In operation S610, in response to the current time being the first explanation moment, a third prompt message and / or a fourth prompt message are generated based on the target sub-content and the target time. The third prompt message is used to indicate the input information corresponding to the first object's target sub-content, and the fourth prompt message is used to indicate that the target sub-content corresponding to the second object's input information is being explained. Reaching the first explanation moment trigger condition signifies that the actual progress axis of the session has been strictly aligned with the preset display node of the target sub-content, at which point the substantive content interaction window is entered. At this precise synchronization node, by generating multi-dimensional prompt messages, an instant context mapping can be established between the information outputter and the inputter.

[0081] The third prompt, serving as supplementary reference data for the information provider, re-emerges the accumulated interaction needs (i.e., input information) in the most appropriate context, thereby empowering the provider to provide a natural response within the current content framework. The fourth prompt, acting as a positive confirmation signal for the information input provider, anchors their attention within the massive information flow, clearly informing them that the content they care about has entered the substantive explanation stage. These two types of prompts can be generated independently to serve a single entity, or generated simultaneously to build a two-way collaborative perception.

[0082] For example, when the session timeline reaches the preset "Algorithm Application" section, a floating window is generated and displayed above the control screen in front of the speaker, showing "Audience Questions Related to the Current Page: What are the Specific Application Scenarios?" as the third prompt. At the same time, in the sidebar of the viewing interface of the specific audience member who submitted the question, a pop-up message appears: "The part related to your question is being explained" as the fourth prompt, while the screens of other audience members who did not ask questions remain empty.

[0083] In operation S620, the presentation state of the multimedia content matching the input information in the target sub-content is changed so that the presentation state of the multimedia content matching the input information is different from that of other content in the session content. The change in presentation state involves a local reload of the visual or auditory rendering parameters of a specific information unit. Its purpose is to break the homogeneous presentation of the original interface and construct a high-contrast visual or auditory anchor point by creating sensory differences.

[0084] This modification can be applied to the entire target sub-content block to emphasize macro-level information nodes, or it can be applied only to local elements within the target sub-content that have a direct semantic mapping relationship with the input information to precisely isolate micro-level key information. By giving these blocks or local elements special attributes that distinguish them from the surrounding regular content (such as color variations, dynamic effects, or hierarchical leaps), the audience's attention can be guided to penetrate the cluttered background and quickly land on the relevant data.

[0085] For example, in the currently displayed demo page, you can either add a prominent global glowing border to the entire page or adjust the overall page background color to indicate that the entire page is highly relevant to the question; or you can only change the specific data table that answers the audience's question about "performance metrics" to a highlighted and flashing state, or enlarge the font size of specific text paragraphs, while keeping the other regular text and charts on the page in their original default static and color presentation.

[0086] According to the embodiments of this disclosure, by generating bidirectional or unidirectional synchronous prompts at precise times when the presentation actually arrives, and flexibly coordinating differentiated changes to the presentation status of overall content blocks or local elements, the presenter can naturally respond to previously accumulated questions in the most appropriate context, avoiding abrupt answers or disruptions to the flow due to detachment from the context. It also allows the audience to receive "customized" instant feedback amidst the complex presentation flow, without constantly needing to be on edge to find the answers they care about. Simultaneously, by providing presentation modification methods such as multi-level highlighting from the global page to local charts, it not only provides highly personalized visual guidance for questioners but also perfectly accommodates the different granularity of interactive needs under a large number of participants, ensuring the overall smoothness of the meeting.

[0087] Figure 7 Another flowchart illustrating a prompting method according to an embodiment of the present disclosure is shown schematically.

[0088] like Figure 7 As shown, based on the aforementioned embodiments, operation S140 may include operation S710, and the prompting method may also include operation S720.

[0089] During operation S710, a fifth prompt message is generated based on the target sub-content and the target time. This fifth prompt message indicates the expected explanation time of the target sub-content and / or the location of the target sub-content. As a forward-looking navigation guide, the fifth prompt message transforms the system's internal time-series calculations and structural analysis results into spatiotemporal coordinates easily perceived by the user. The expected explanation time represents the anticipated reach point of the target content on the timeline, which can be represented as an absolute timestamp or a relative countdown; while the location reflects the spatial distribution or logical hierarchy of the target content within the entire material, such as physical page numbers, chapter numbers, or content topology indexes.

[0090] For example, if an audience member asks a question about "hardware interfaces" during a technical sharing session, the system can generate a purely time-based text reply for that audience member stating, "I expect to answer your question in 5 minutes." Alternatively, when the pace of the conversation fluctuates greatly and it is inconvenient to provide a precise time, the system can generate a purely location-based navigation tag containing "The relevant answer is on page 12 of the presentation." Or, the system can construct a comprehensive forward-looking card containing "The interface diagram you are interested in is in Chapter 3 and is expected to be discussed at 14:30."

[0091] When operating the S720, the target sub-content is presented to the second recipient. That is, a specific multimedia unit, pre-locked and containing answer information, is transformed into a rendered form that can be perceived visually or audibly, and then output to the terminal device of the corresponding information input party. This presentation mechanism can be either synchronous rendering following the speaker's progress, where the sub-content is displayed sequentially in the main view area of ​​the second recipient's viewing interface as the session progresses to the target moment; or a decoupled independent push, where the target content is asynchronously distributed to the specific second recipient who raised the question, in the form of a secondary screen display, a separate pop-up window, or a private chat panel, without interfering with the current global display of the main venue; or a proactive view jump mechanism, which directly changes or intervenes in the second recipient's current viewing focus, instantly switching their viewing screen or document progress and positioning them at the specific location of the target sub-content.

[0092] For example, when the actual explanation progress reaches the predetermined target time, a high-definition system architecture diagram that answers their questions is automatically and synchronously displayed on the listener's main live broadcast screen; or, after receiving a question and completing the matching, a specific demonstration page containing the answer information is pushed in advance as an interactive thumbnail in the listener's personal interactive sidebar for the listener to check in advance; or, when the listener receives a prompt containing location information, based on the listener's click authorization or automatic triggering mechanism, the document screen currently displayed on their device is instantly redirected to the target page containing the answer content.

[0093] According to embodiments of this disclosure, by sending navigational guidance containing the expected time or location of the explanation to the questioner before the formal delivery of the answer, and ultimately completing the targeted presentation of the target content, clear spatiotemporal coordinates replace the unknown and blind waiting in traditional conversations. This, in turn, allows the audience to autonomously plan their attention allocation based on precise prompts (e.g., handling other tasks before the expected time arrives), significantly improving the participants' experience and information reception efficiency.

[0094] Figure 8 Another flowchart illustrating a prompting method according to an embodiment of the present disclosure is shown schematically.

[0095] like Figure 8As shown, based on the aforementioned embodiments, multiple sub-contents are arranged in a preset order, and the prompting method may include operation S810.

[0096] In operation S810, in response to the current session content as adjacent sub-content, a sixth prompt message is generated based on the target sub-content. This sixth prompt message indicates that the target sub-content will be explained soon. Adjacent sub-content refers to the sub-content immediately preceding the target sub-content. The preset order represents the natural sequential arrangement of multimedia presentation information in the logical structure or physical layout, such as the ascending page number sequence of a presentation, the scrolling display sequence of a long document, or the chapter directory structure of a standard course. Adjacent sub-content refers to the independent information unit that is immediately adjacent to and directly preceding the target sub-content in the aforementioned preset order.

[0097] Responding to the current presentation's arrival at adjacent sub-content can be understood as a deterministic early warning mechanism based on physical or logical progression nodes. In this case, instead of relying on dynamic calculations of the speaker's pace or future duration, it monitors content switching commands in real time (such as page turning, scroll bar position, or table of contents navigation). Once it detects that the currently displayed information unit is the direct preceding node of the target sub-content, it uses this as a definite trigger anchor point to generate a sixth prompt message. This sixth prompt message, as a "next item is coming" proximity warning, uses established structural adjacency relationships to convey a highly reliable timing expectation to relevant audiences.

[0098] For example, when the target sub-content for answering a question is pre-determined to be on page 10 of the presentation, the page number status is monitored in real time. The moment the presenter switches the screen to page 9 (i.e., the adjacent sub-content), a pre-show reminder containing the words "The content you are interested in will be explained to you on the next page" is generated. Or, in a training session that proceeds in chapter order, if the target sub-content is "the content of section 3.2", when "the content of section 3.1" is detected to be unfolded, a sixth reminder message "The answer will be given to you soon, please stay tuned" is sent to the specific audience.

[0099] According to embodiments of this disclosure, by introducing adjacent sub-content based on a preset arrangement order as triggering conditions, this method does not rely on time extrapolation and is immune to interference from fluctuations in the speaker's speaking speed, temporary pauses, or lengthy ramblings on the time prediction algorithm. As long as the progress reaches the immediately preceding node, the warning can be triggered with 100% accuracy. This allows listeners to receive timely and unbiased attention at the last moment before the core answer appears, avoiding both premature prompts and waiting fatigue caused by inaccurate time prediction, and missed answers due to delayed prompts. Furthermore, it saves on the resource overhead and response delays associated with time prediction.

[0100] Figure 9Another flowchart illustrating a prompting method according to an embodiment of the present disclosure is shown schematically.

[0101] like Figure 9 As shown, based on the foregoing embodiments, the prompting method may further include operation S910.

[0102] In operation S910, if the target sub-content cannot be matched based on the input information, a seventh prompt message is generated based on the input information. The seventh prompt message is used to prompt the first object with the input information. "Failed to match the target sub-content" indicates that the semantic intent or interactive request contained in the input information exceeds the coverage of the multimedia presentation information or expected explanation logic of the first session, and belongs to unplanned or out-of-scope discrete data. In response to the matching failure state, the automatic temporal deduction and audience waiting expectation construction for this input information are no longer performed. Instead, this abnormal input that cannot be automatically processed by the system is directly transformed into an explicit notification presented to the information output party (i.e., the first object).

[0103] For example, during a product presentation, if an audience member asks a question about "comparison of competitor market share," and a search of the preset presentation slides reveals that none of the pages cover this topic, it is determined that there is no match. In this case, based on the textual question, a text message about the question is generated and displayed as a seventh prompt in the "Unplanned Questions" panel on the teleprompter screen or control panel in front of the presenter, to alert the presenter that there is an audience question that was not covered in the materials.

[0104] According to embodiments of this disclosure, by introducing a fallback mechanism for unmatched input information and directly generating specific prompts for the first target when matching fails, comprehensive management of all elements of the conversational interaction is achieved. This effectively avoids the awkward situation where reasonable questions from the audience are ignored due to exceeding the scope of the presentation materials, thus eliminating blind spots when facing divergent or overly complex questions. Furthermore, it allows the presenter to promptly detect and capture special needs that cannot be answered through a step-by-step explanation, enabling the presenter to flexibly decide whether to provide impromptu supplements or answer questions after the meeting, thereby improving the robustness and user-friendliness of the overall intelligent meeting support system.

[0105] Figure 10 A block diagram of a prompting device according to an embodiment of the present disclosure is shown schematically.

[0106] like Figure 10 As shown, the prompting device 1000 may include an acquisition module 1010, a first determination module 1020, a second determination module 1030, and a generation module 1040.

[0107] The acquisition module 1010 is used to acquire input information in the first session. In some embodiments, the acquisition module 1010 may be used to perform operation S110 in the above prompting method, which will not be described in detail here.

[0108] The first determining module 1020 is used to determine, based on the input information, the target sub-content in the session content of the first session that matches the input information. In some embodiments, the first determining module 1020 may be used to perform operation S120 in the above-described prompting method, which will not be elaborated here.

[0109] The second determining module 1030 is used to determine the target time corresponding to the target sub-content in the first session based on the target sub-content and the session content. The target time is the moment when the target sub-content is explained or displayed in the first session. In some embodiments, the second determining module 1030 can be used to perform operation S130 in the above-described prompting method, which will not be elaborated here.

[0110] The generation module 1040 is used to generate prompt information based on the target sub-content and the target time. In some embodiments, the generation module 1040 can be used to perform operation S140 in the above prompting method, which will not be described in detail here.

[0111] Any one or more of the modules, submodules, units, and subunits according to embodiments of the present disclosure, or at least part of the functions of any one or more of them, can be implemented in one module. Any one or more of the modules, submodules, units, and subunits according to embodiments of the present disclosure can be implemented by dividing them into multiple modules. Any one or more of the modules, submodules, units, and subunits according to embodiments of the present disclosure can be at least partially implemented as hardware circuitry, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a System-on-Chip, a System-on-a-Substrate, a System-on-Package, an Application-Specific Integrated Circuit (ASIC), or implemented in hardware or firmware by any other reasonable means of integrating or packaging circuitry, or implemented in software, hardware, or firmware, or in any suitable combination of any of these three implementation methods. Alternatively, one or more of the modules, submodules, units, and subunits according to embodiments of the present disclosure can be at least partially implemented as computer program modules, which, when run, can perform corresponding functions.

[0112] For example, any plurality of the acquisition module 1010, the first determination module 1020, the second determination module 1030, and the generation module 1040 can be combined into one module / unit / subunit, or any one of these modules / units / subunits can be split into multiple modules / units / subunits. Alternatively, at least part of the functionality of one or more of these modules / units / subunits can be combined with at least part of the functionality of other modules / units / subunits and implemented in one module / unit / subunit. According to embodiments of this disclosure, at least one of the acquisition module 1010, the first determination module 1020, the second determination module 1030, and the generation module 1040 can be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or any other reasonable means of integrating or packaging circuitry, or implemented in software, hardware, or firmware, or in any one of the three implementation methods or a suitable combination of any of them. Alternatively, at least one of the acquisition module 1010, the first determination module 1020, the second determination module 1030, and the generation module 1040 can be at least partially implemented as a computer program module, which can perform corresponding functions when the computer program module is run.

[0113] It should be noted that the data processing system part in the embodiments of this disclosure corresponds to the data processing method part in the embodiments of this disclosure. The specific description of the data processing system part is referred to in the data processing method part, and will not be repeated here.

[0114] Figure 11 A block diagram of an electronic device suitable for implementing the methods described above, according to embodiments of the present disclosure, is illustrated schematically. Figure 11 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0115] like Figure 11 As shown, an electronic device 1100 according to an embodiment of the present disclosure includes a processor 1101, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1102 or a program loaded from a storage portion 1108 into a random access memory (RAM) 1103. The processor 1101 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 1101 may also include onboard memory for caching purposes. The processor 1101 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0116] RAM 1103 stores various programs and data required for the operation of electronic device 1100. Processor 1101, ROM 1102, and RAM 1103 are interconnected via bus 1104. Processor 1101 performs various operations of the method flow according to embodiments of the present disclosure by executing programs in ROM 1102 and / or RAM 1103. It should be noted that the programs may also be stored in one or more memories other than ROM 1102 and RAM 1103. Processor 1101 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in said one or more memories.

[0117] According to embodiments of this disclosure, the electronic device 1100 may further include an input / output (I / O) interface 1105, which is also connected to a bus 1104. The electronic device 1100 may also include one or more of the following components connected to the input / output (I / O) interface 1105: an input section 1106 including a keyboard, mouse, etc.; an output section 1107 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1108 including a hard disk, etc.; and a communication section 1109 including a network interface card such as a LAN card, modem, etc. The communication section 1109 performs communication processing via a network such as the Internet. A drive 1110 is also connected to the input / output (I / O) interface 1105 as needed. A removable medium 1111, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 1110 as needed so that computer programs read from it can be installed into the storage section 1108 as needed.

[0118] According to embodiments of this disclosure, the method flow according to embodiments of this disclosure can be implemented as a computer software program. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable storage medium, the computer program containing program code for performing the methods shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network via communication section 1109, and / or installed from removable medium 1111. When the computer program is executed by processor 1101, it performs the functions defined in the system of embodiments of this disclosure. According to embodiments of this disclosure, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0119] This disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs that, when executed, implement the method according to the embodiments of this disclosure.

[0120] According to embodiments of this disclosure, the computer-readable storage medium can be a non-volatile computer-readable storage medium. Examples include, but are not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0121] For example, according to embodiments of this disclosure, a computer-readable storage medium may include one or more memories other than the ROM 1102 and / or RAM 1103 described above and / or ROM 1102 and RAM 1103.

[0122] Embodiments of this disclosure also include a computer program product comprising a computer program containing program code for performing the methods provided in the embodiments of this disclosure. When the computer program product is run on an electronic device, the program code is used to enable the electronic device to implement the prompting methods provided in the embodiments of this disclosure.

[0123] When the computer program is executed by the processor 1101, it performs the functions defined in the system / apparatus of this disclosure embodiments. According to embodiments of this disclosure, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0124] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices or magnetic storage devices. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and downloaded and installed via communication section 1109, and / or installed from removable medium 1111. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof. According to embodiments of this disclosure, program code for executing the computer programs provided in embodiments of this disclosure can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code may be executed entirely on a user computing device, partially on a user device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing devices can be connected to user computing devices via any type of network, including local area networks (LANs) or wide area networks (WANs), or they can be connected to external computing devices (e.g., via the Internet using an Internet service provider).

[0125] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks 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 block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions. Those skilled in the art will understand that the features described in the various embodiments of the present disclosure can be combined and / or combined in various ways, even if such combinations are not explicitly described in the present disclosure. In particular, the features described in the various embodiments of this disclosure may be combined and / or combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.

[0126] The embodiments of this disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of this disclosure. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of this disclosure, and all such substitutions and modifications should fall within the scope of this disclosure.

Claims

1. A prompting method, comprising: Retrieve input information from the first session; Based on the input information, target sub-content in the session content of the first session that matches the input information is determined; Based on the target sub-content and the session content, the target time corresponding to the target sub-content in the first session is determined, and the target time is the time when the target sub-content is explained or displayed in the first session; Based on the target sub-content and the target time, a prompt message is generated.

2. The method according to claim 1, wherein the first session is a real-time interactive session, the session content includes multimedia presentation information of the first session and explanation information of the first object regarding the multimedia presentation information, and the input information is input by the second object; The method also includes: Based on the first moment when the second object inputs the input information in the first session, determine the content of the first session corresponding to the first moment; Determining the target time corresponding to the target sub-content in the first session includes: Based on the target sub-content and the first session content, determine the first explanation time corresponding to the target sub-content in the first session, wherein the target time includes the first explanation time of the target sub-content in the first session; The step of generating prompt information based on the target sub-content and the target time includes: Based on the target sub-content and the target time, a first prompt message is generated, wherein the first prompt message indicates that the explanation time of the target sub-content is the first explanation time.

3. The method according to claim 2, wherein generating prompt information based on the target sub-content and the target time includes: In response to the current time being the second time, the second session content corresponding to the second time is determined, where the second time is the time before the target time and the time difference from the target time by a preset duration; The second expected explanation time corresponding to the target sub-content is determined based on the second time and the second session content; If the second expected explanation time matches the first explanation time, a second prompt message is generated based on the first explanation time. The second prompt message is used to prompt the first object and / or the target sub-content of the second object that it is about to be explained. If the second expected explanation time does not match the first explanation time, the target time shall be adjusted based on the second expected explanation time; Based on the adjusted target time, a second prompt message is generated.

4. The method according to claim 2, wherein the first session includes a plurality of second objects, and the step of generating prompt information based on the target sub-content and the target time includes: In response to the number of second objects that input the input information for the same target sub-content being greater than or equal to a number threshold, a prompt message is generated based on the target sub-content, the target time, and the number.

5. The method according to claim 1, further comprising: Determine the multimedia presentation information of the first session, and divide the multimedia presentation information into multiple sub-contents using the target model; The themes corresponding to the multiple sub-contents are determined by the multimedia presentation information; The step of determining the target sub-content in the session content of the first session that matches the input information includes: Based on the input information, the target sub-content in the conversation content that matches the input information is determined by matching the topics corresponding to each of the sub-contents.

6. The method according to claim 2, wherein generating prompt information based on the target sub-content and the target time includes: In response to the current time being the first explanation time, a third prompt message and / or a fourth prompt message are generated based on the target sub-content and the target time; The third prompt information is used to prompt the input information corresponding to the target sub-content of the first object; The fourth prompt message is used to indicate to the second object that the target sub-content corresponding to the input information is being explained; And / or, the method further includes: Change the presentation state of the multimedia presentation content in the target sub-content that matches the input information, so that the presentation state of the multimedia presentation content that matches the input information is different from that of other content in the session content.

7. The method according to claim 2, wherein generating prompt information based on the target sub-content and the target time includes: Based on the target sub-content and the target time, a fifth prompt message is generated. The fifth prompt message is used to prompt the second object the expected explanation time of the target sub-content and / or the location of the target sub-content. And / or, the method further includes: presenting the target sub-content to the second object.

8. The method according to claim 5, wherein the plurality of sub-contents are arranged according to a preset order, and the method further comprises: In response to the fact that the current session content is a neighboring sub-content, a sixth prompt message is generated based on the target sub-content. The sixth prompt message is used to indicate that the target sub-content is about to be explained. The neighboring sub-content is the sub-content that precedes the target sub-content.

9. The method according to claim 2, further comprising: If the target sub-content cannot be matched based on the input information, a seventh prompt message is generated based on the input information. The seventh prompt message is used to prompt the first object with the input information.

10. An electronic device, comprising: At least one processor; as well as The memory connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor. These instructions, when executed by the at least one processor, enable the at least one processor to perform the following operations: acquire input information in a first session; based on the input information, determine a target sub-content in the session content of the first session that matches the input information; based on the target sub-content and the session content, determine a target time corresponding to the target sub-content in the first session, the target time being the moment when the target sub-content is explained or displayed in the first session; and generate prompt information based on the target sub-content and the target time.

Images