Information processing method and electronic equipment

Abstract

The invention provides an information processing method and electronic equipment. The information processing method comprises the steps of displaying a first session window, wherein the first session window is used for presenting session information of a first session; in response to the first operation, determining first session information in session information of the first session; determining at least one piece of second session information based on the first session information, the second session information being session information associated with a target session theme corresponding to the first session information; and displaying the second session information.

Description

Technical Field

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

[0002] With the widespread adoption of instant messaging technology, various instant messaging software and office collaboration platforms have become core tools for daily communication and work. However, in practical applications, especially in active group chats or long conversation histories, multiple different discussion topics often intertwine and are discussed in parallel, or messages on the same topic are buried under a large amount of irrelevant information such as small talk, resulting in the physical dispersion and fragmentation of contextual information belonging to the same topic. When users need to trace the complete context of a specific topic or find the background of a message, they have to perform tedious manual browsing and visual filtering through massive amounts of irrelevant historical records, greatly reducing the efficiency of information retrieval and reading, and easily leading to the omission of key information. Summary of the Invention

[0003] In view of this, the present disclosure provides an information processing method and an electronic device.

[0004] One aspect of this disclosure provides an information processing method, comprising: displaying a first session window for presenting session information of a first session; determining first session information from the session information of the first session in response to a first operation; determining at least one second session information based on the first session information, the second session information being session information associated with a target session topic corresponding to the first session information; and displaying the second session information.

[0005] According to embodiments of this disclosure, displaying second session information includes: locating the session position of the second session information in the session information; displaying the second session information in a first session window based on the session position; or, extracting the second session information from the first session; and displaying the second session information in a target display window, wherein the target display window is different from the first session window.

[0006] According to embodiments of this disclosure, displaying second session information includes: determining third session information in each of the second session information; displaying each of the second session information starting from the third session information; wherein the third session information is determined based on the time information corresponding to each of the second session information, or the third session information is determined based on the degree of association between each of the second session information and the target session topic.

[0007] According to embodiments of this disclosure, displaying second session information includes: displaying the second session information in a second mode, the second mode being different from a first mode for displaying session information other than the second session information; the second session information includes end session information, the end session information being the session information closest to the current time point among all the second session information; after displaying the second session information, the method further includes: responding to a second operation, the second operation causing the first session information or the end session information to move to the first session window, and switching the display mode of each session information to the same display mode.

[0008] According to embodiments of this disclosure, the second session information includes end session information, which is the session information closest to the current time point among all the second session information. The second session information also includes start session information, which is the session information farthest from the current time point among all the second session information. After displaying the second session information, the method further includes: in response to the fourth session information moving to the first session window and the second session information moving out of the first session window, determining at least one session topic based on each fourth session information, wherein the fourth session information is the session information after the end session information or the session information before the start session information; generating prompt information based on each session topic; re-determining the target session topic in response to receiving feedback information for the prompt information; and re-determining the second session information based on the re-determined target session topic.

[0009] According to embodiments of this disclosure, the first operation includes a selection operation on target session information and a selection operation on target control. The selection operation includes at least one of the following: maintaining the target session information in the first session window for a preset duration; browsing historical session information prior to the target session information after the target session information is displayed in the first session window; clicking on the target control or the target session information; and determining the first session information corresponding to the first operation in the session information of the first session in response to the first operation, including at least one of the following: determining the target session information as the first session information in response to the selection operation on the target session information; and determining the first session information from the session information displayed in the first session window in response to the selection operation on the target control.

[0010] According to an embodiment of this disclosure, determining at least one second session information based on first session information includes: determining N consecutive session information in the first session, starting from the first session information, where the number N of session information matches the context length of the target model; and using the first session information and the N session information as input to the target model to determine at least one second session information.

[0011] According to embodiments of this disclosure, taking first session information and N session information as input to a target model, and determining at least one second session information includes: inputting the first session information and N session information into the target model; determining a label corresponding to each of the N session information based on the target session topic of the first session information; the label includes: a first label indicating that the session information is not related to the target session topic; a second label indicating that the session information is related to the target session topic; and determining the session information as the second session information in response to the second label being the label of the session information.

[0012] According to embodiments of this disclosure, the tags further include: a third tag indicating that the session information is related to the target session topic and is the starting session information related to the target session topic; a fourth tag indicating that the session information is related to the target session topic and is the ending session information related to the target session topic; the information processing method further includes: in response to the fact that the tags corresponding to each session information in the N session information do not include the third tag, determining N consecutive untagged session information before the first session information in the first session; inputting the first session information and the N consecutive untagged session information before the first session information into the target model; in response to the fact that the tags corresponding to each session information in the N session information do not include the fourth tag, determining N consecutive untagged session information after the first session information in the first session; inputting the first session information and the N consecutive untagged session information after the first session information into the target model.

[0013] Another aspect of this disclosure provides an information processing apparatus, comprising: a first display module for displaying a first session window, the first session window being used to present session information of a first session; a first determination module for determining first session information from the session information of the first session in response to a first operation; a second determination module for determining at least one second session information based on the first session information, the second session information being session information associated with a target session topic corresponding to the first session information; and a second display module for displaying the second session information.

[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 at least one of the following operations: displaying a first session window for presenting session information of a first session; determining first session information from the session information of the first session in response to a first operation; determining at least one second session information based on the first session information, the second session information being session information associated with a target session topic corresponding to the first session information; and displaying the second session information.

[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 an information processing 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 information processing method of 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 1 A flowchart illustrating an information processing method according to an embodiment of the present disclosure is shown schematically.

[0019] Figure 2 A flowchart illustrating the display of second session information in an information processing method according to an embodiment of the present disclosure is shown schematically.

[0020] Figure 3 This schematically illustrates another flowchart of the information processing method for displaying second session information according to an embodiment of the present disclosure;

[0021] Figure 4 Another flowchart of an information processing method according to an embodiment of the present disclosure is illustrated schematically;

[0022] Figure 5 Another flowchart of an information processing method according to an embodiment of the present disclosure is illustrated schematically;

[0023] Figure 6 A flowchart illustrating the determination of second session information in an information processing method according to an embodiment of the present disclosure is shown schematically.

[0024] Figure 7 This schematically illustrates another flowchart of determining second session information in an information processing method according to an embodiment of the present disclosure;

[0025] Figure 8 Another flowchart of an information processing method according to an embodiment of the present disclosure is illustrated schematically;

[0026] Figure 9 A block diagram schematically illustrates an information processing apparatus according to embodiments of the present disclosure; and

[0027] Figure 10 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

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.).

[0032] 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.

[0033] Embodiments of this disclosure provide an information processing method, including: displaying a first session window, the first session window being used to present session information of a first session; in response to a first operation, determining first session information from the session information of the first session; based on the first session information, determining at least one second session information, the second session information being session information associated with a target session topic corresponding to the first session information; and displaying the second session information.

[0034] Figure 1A flowchart illustrating an information processing method according to an embodiment of the present disclosure is shown schematically.

[0035] like Figure 1 As shown, the information processing method may include at least operations S110 to S140.

[0036] In operation S110, the first session window is displayed, which presents the session information of the first session. The first session window can be the user interface of an instant messaging application, collaborative office software, social networking application, or other application with messaging functionality running on the terminal device. Session information can include, but is not limited to, interactive data in various formats such as text, voice, images, videos, file links, and instant status notifications. The presentation of session information involves displaying the historical interaction content of the first session in chronological or logical order using lists, bubbles, or other visual formats. For example, a group chat interface of an instant messaging software displayed on a smartphone contains text messages and image messages sent by multiple group members.

[0037] In operation S120, in response to the first operation, the first session information is determined from the session information of the first session. The first operation is an interactive instruction triggered by the user to indicate attention to specific session content or to request topic revisiting. The first session information is the target session record that serves as the benchmark for the current topic analysis, typically session content that the user is interested in or that is currently in focus in the window. The device receives instructions from the user regarding session content or function options in the interface, and determines specific information in the current context as the benchmark object for topic analysis based on these instructions. For example, the user executes a selection instruction on a message of interest displayed in the current interface; or the user triggers a context analysis instruction for the currently viewed content, and the device responds by determining the specific message in the current window as the first session information.

[0038] In operation S130, based on the first session information, at least one second session information is determined. The second session information is session information associated with the target session topic corresponding to the first session information. The target session topic refers to the semantic content or discussion topic pointed to by the first session information. Determining at least one second session information means filtering session information belonging to the same category as the topic in the session records. For example, the discussion item involved in the first session information is identified, and all messages interacting around the discussion item are retrieved from the history as the second session information.

[0039] In operation S140, the second session information is displayed. The determined information is presented to the user, for example, by controlling the display device to output the identified second session information, or by adjusting the presentation content of the current interface to include the second session information.

[0040] According to embodiments of this disclosure, by determining baseline information in response to user actions and automatically filtering and presenting related information belonging to the same topic as the baseline information, users can quickly focus on specific topics of interest in complex chat environments filled with a large amount of irrelevant content, multiple topics, or lengthy historical records. This eliminates the need for users to manually browse through massive amounts of historical records or piece together context from memory, effectively reducing the interaction cost of information retrieval, improving the efficiency of users obtaining effective information, and solving the problem of difficulty in quickly locating and recalling specific discussion topics in group chats due to information overload.

[0041] Figure 2 A flowchart illustrating the display of second session information in an information processing method according to an embodiment of the present disclosure is shown schematically.

[0042] like Figure 2 As shown, based on the aforementioned embodiments, operation S140 may include operations S210~S220, or may include operations S230~S240.

[0043] In operation S210, the session position of the second session information is located within the session information. The session position refers to the sequence number, storage index, or coordinate parameter of the second session information within the overall historical message sequence of the first session. Locating the session position of the second session information within the session information involves finding and determining the specific area or starting point of the message associated with the target session topic within the large historical message queue contained in the first session. For example, calculating the row index of the first message related to the current topic in the current chat history list; or determining the pixel coordinate position of the message related to that topic in the scrolling view.

[0044] In operation S220, based on the session position, the second session information is displayed in the first session window. By controlling the view scrolling component or rendering engine of the first session window, the visible area is moved to the determined session position, thereby presenting the second session information or the area where the second session information is located within the content displayed in the window. For example, the chat interface can be controlled to automatically scroll upwards, directly jumping to and stopping at the beginning of the message related to the topic, allowing the user to see the content of the topic in the current chat flow.

[0045] In operation S230, information from the second session is extracted from the first session. Extraction refers to separately copying, filtering, or indexing the data content belonging to the second session from the complete data stream of the first session, forming an independent data set. Specifically, the records of the first session are traversed, and message content that meets the criteria is retrieved and temporarily stored in a separate cache or a new display list is built, without changing the original data arrangement in the first session window. For example, all text and image messages identified as having the topic "project discussion" are copied from the group chat records.

[0046] In operation S240, the second session information is displayed in the target display window, which is different from the first session window. The target display window refers to a display area independent of the first session window at the graphical user interface level, including but not limited to a floating window, sidebar, pop-up layer, or independent application page. For example, a new view container is rendered on the screen, and the extracted second session information is filled into this container for display. This new view container overlays on or is located to the side of the first session window. Specifically, for example, a sidebar is expanded on the right side of the current chat window, displaying only the extracted messages related to the topic in chronological order; or a separate reading card pops up to display this content.

[0047] According to embodiments of this disclosure, by displaying the content in the original window, the continuity of the conversation environment can be maintained, allowing users to quickly revisit the topic without switching contexts. By displaying the content in a new window, the content of a specific topic can be extracted from the complex original chat stream, achieving clean reading. At the same time, it allows users to retain their browsing progress in the original chat window, facilitating parallel operations between "browsing current messages" and "reviewing specific topics," thereby improving the efficiency and experience of information reading.

[0048] Figure 3 Another flowchart illustrating the display of second session information in an information processing method according to an embodiment of the present disclosure is shown schematically.

[0049] like Figure 3 As shown, based on the aforementioned embodiments, operation S140 may include operations S310 to S320.

[0050] In operation S310, the third session information within each second session information is determined. This third session information is determined either based on the time information corresponding to each second session information, or based on the degree of relevance between each second session information and the target session topic. The third session information refers to a specific information entry selected as a visual anchor or reading starting point from the set of all second session information related to the topic. Specifically, the generation timestamp of each second session information is obtained, and the information with the earliest timestamp is determined as the third session information, serving as the logical starting point for the topic discussion; alternatively, a semantic similarity score between each second session information and the target session topic is calculated using a semantic analysis algorithm, and the information with the highest score is determined as the third session information, serving as the core content or key node for the topic discussion.

[0051] For example, sort all the filtered second conversation messages in chronological order and select the message at the top; or select the message with the highest semantic score that best represents the current discussion conclusion or core viewpoint.

[0052] In operation S320, each second conversation message is displayed starting with the third conversation message. The visible area of ​​the display window is adjusted to place the third conversation message in a specific position (such as the top or center) within the window, and subsequent or surrounding second conversation messages are displayed based on that position. This ensures that when a user opens or jumps to relevant content, they first see the third conversation message, thus guiding them to start reading from that point. For example, the chat window can be controlled to automatically scroll so that the earliest relevant message is at the top of the screen, allowing the user to read the entire topic from there; or the user can be directly positioned to jump to the most relevant key message, with other relevant messages displayed around it.

[0053] According to embodiments of this disclosure, by flexibly selecting between time-based or relevance-based determination of the starting display position, different user reading needs can be accommodated. Time-based positioning helps users quickly find the beginning of a topic, solving the problem of difficulty in tracing the origin of a topic in long chat logs and reconstructing the ins and outs of the discussion; relevance-based positioning helps users directly access the most core and valuable information segments of the topic, further improving the efficiency and accuracy of information acquisition.

[0054] Figure 4 Another flowchart of an information processing method according to an embodiment of the present disclosure is illustrated schematically.

[0055] like Figure 4 As shown, based on the foregoing embodiments, operation S140 may include operation S410.

[0056] When operating S410, the second session information is displayed in a second mode, which differs from the first mode, which displays session information other than the second session information. The first and second modes refer to different visual styles, rendering parameters, or layouts used to present session information in the graphical user interface. When rendering session information, it is determined whether the current information belongs to the second session information. If it does, display attributes that distinguish it from other information are applied, using visual contrast to highlight the target content or weaken non-target content.

[0057] For example, adjust the font color of non-second session information to gray or reduce its transparency, while keeping the second session information displayed as normal black with high contrast; or add a specific background highlight color (such as light yellow) to all second session information, while keeping the default background of other session information; or collapse non-related information located in the middle of consecutive second session information, keeping only a one-line summary or placeholder, while keeping the second session information fully expanded; or use any combination of the above methods, such as both collapsing non-related information and highlighting related information.

[0058] The second session information includes the last session information, which is the session information closest to the current time point among all the second session information. Operation S140 may also include operation S420.

[0059] The end-of-session message refers to the message that is at the end of the logical chronological sequence of the target session topic, marking the end of the discussion on that topic. Identify the latest timestamped message in the second set of session messages and mark it as the anchor object for monitoring and displaying the resumption trigger condition. For example, mark the last message sent by the department manager in the discussion topic "Annual Meeting Planning" as the end-of-session message.

[0060] In operation S420, in response to the second operation, the first or last session information is moved to the first session window, and the display mode of all session information is switched to the same display mode. The second operation refers to the user's action to browse more content, such as interface scrolling or view movement. Restoring the display mode means canceling the previous visual distinction effect and restoring all information to the default standard display state.

[0061] The coordinates of the content displayed in the first session window are monitored in real time. When the first or last session information, which serves as the anchor point, enters the visible area of ​​the window (or reaches a specific position in the visible area, such as the bottom or middle) after scrolling, an interface redraw instruction is triggered to unify the display style of all session information.

[0062] For example, when a user swipes down on the screen during reading, and the end of the conversation, representing the end of the topic, appears from the bottom of the screen and is fully visible, all previously grayed-out or collapsed messages in the interface automatically return to their normal display and expanded state; or when a user swipes up to find the starting point of the topic, and the first selected conversation information returns to the screen's view, the highlighting or graying effect is canceled, and normal browsing is restored.

[0063] According to embodiments of this disclosure, by employing differentiated display modes (such as graying out, folding, or highlighting), visual interference can be effectively filtered, helping users focus on specific topics within a complex chat flow. Simultaneously, combined with an automatic recovery mechanism based on window position monitoring, users can seamlessly transition back to a normal chat browsing experience after reading the entire content of the current topic, without needing to perform additional exit or reset operations, thus improving the smoothness and intelligence of human-computer interaction.

[0064] Figure 5 Another flowchart of an information processing method according to an embodiment of the present disclosure is illustrated schematically.

[0065] like Figure 5As shown, based on the aforementioned embodiment, the second session information includes the end session information, which is the session information closest to the current time point among all the second session information. The second session information includes the start session information, which is the session information farthest from the current time point among all the second session information. After operation S140, the information processing method may further include operations S510 to S540.

[0066] The start and end session information define the beginning and end boundaries of the current target session topic on the timeline. Based on this, the information processing method should be implicitly included in the interface that has already presented messages related to the current topic, continuously monitoring the user's scrolling behavior and changes in the visible content within the interface.

[0067] In operation S510, in response to the fourth session information moving into the first session window and the second session information moving out of the first session window, at least one session topic is determined based on each fourth session information. The fourth session information is either session information following the last session information or session information preceding the first session information. The fourth session information refers to other historical messages that are immediately outside the current target session topic in the time sequence and have not yet been identified as the current focus of attention. This situation typically occurs when the user scrolls the screen extensively to view the context, causing messages related to the current topic to completely leave the visible area, and the screen is filled with messages not related to the current topic (i.e., fourth session information).

[0068] The system monitors the content displayed in the first conversation window in real time. When it detects that messages on the current topic have scrolled off the screen and the screen is filled with historical messages (fourth conversation information), it analyzes the content of these messages. If these messages belong to the same context, they are identified as one conversation topic; if these messages belong to different contexts (e.g., the upper half of the screen belongs to the previous topic, and the lower half belongs to an earlier topic), they are identified as multiple conversation topics. For example, if the user swipes up to review the history, and the screen displays only grayed-out messages that are not on the current topic, analysis reveals that the upper half of the messages on the screen belongs to the "product quotation" topic, and the lower half belongs to the "contract approval" topic, thus identifying these two conversation topics.

[0069] When operating the S520, prompts are generated based on each session topic. These prompts are interactive feedback elements that inform the user of the topic category of the currently displayed content area and provide quick navigation options. When multiple topics are identified, the prompt includes several options for the user to choose from. For example, a dynamic prompt control can be overlaid on the interface, listing one or more identified new topic names and an interactive entry point guiding the user to the beginning of the corresponding topic.

[0070] For example, a floating panel pops up at the bottom of the screen, displaying the text "Entering the history message area. The following topics have been identified. Do you want to jump to the beginning?", and showing two clickable option buttons: "[Product Quotation]" and "[Contract Approval]".

[0071] In operation S530, in response to receiving feedback information regarding the prompt, the target session topic is redefined. Feedback information can refer to the user's confirmation or selection instruction regarding the prompt. Redefining the target session topic means switching the focus to the new topic specified by the user based on their selection. For example, detecting a user's click on a specific option in the prompt control and responding to this action, updating the target session topic in the internal state to the topic selected by the user. Specifically, for example, if the user clicks the "[Contract Approval]" button in the floating panel, "Contract Approval" is updated to the current target session topic.

[0072] In operation S540, the second session information is redefined based on the redefined target session topic. After operation S540 is used to re-execute information aggregation for the new topic selected by the user and determine the new second session information, the process of displaying the second session information (such as operation S140 and its sub-steps) in the aforementioned embodiments can be repeated. For example, all messages about "contract approval" are retrieved, the window is automatically scrolled to the first message of the "contract approval" topic, and the messages of that topic are restored to the normal display mode, while other irrelevant messages, including "product quotation," are processed into a second mode (such as gray).

[0073] According to embodiments of this disclosure, by intelligently identifying one or more potential topics on the screen and proactively providing prompts when a user scrolls and leaves the current topic, the problem of users easily getting "lost" in long chat logs with multiple interwoven topics can be solved. Especially when multiple historical topics appear on the screen simultaneously, by providing interactive prompts with multiple options, users are given the right to choose, allowing them to accurately jump from their current position to the beginning of any historical topic of interest, thus improving the flexibility and convenience of cross-topic reading.

[0074] Based on the foregoing embodiments, the first operation includes a selection operation on the target session information and a selection operation on the target control. The selection operation includes at least one of the following: maintaining the target session information in the first session window for a preset duration; browsing the historical session information before the target session information after the target session information is displayed in the first session window; and clicking on the target control or the target session information.

[0075] The system maintains the target conversation information in the first conversation window for a preset duration. When a user stops scrolling and lingers on a particular section of content for an extended period, it usually indicates that the content has piqued their interest or prompted their thought. The system detects the scrolling status of the first conversation window; when scrolling stops and a particular conversation message (the target message) remains within the visible area (e.g., the center of the screen or a specific reading area) for more than a preset threshold (e.g., 3 or 5 seconds), it is considered a selection operation. For example, a user quickly browsing group chat history might suddenly stop scrolling, focus their gaze on a message about "API interface changes" in the center of the screen, and remain still for more than 3 seconds.

[0076] The process involves browsing through previous conversations after the target conversation is displayed in the first conversation window. When a user sees a message, immediately scrolling up through the history usually indicates that the user wants to understand the context of that message. For example, after a conversation (the target conversation) is detected entering the visible area of ​​the first conversation window, within a preset time period, a scrolling command is detected that moves the conversation content downwards (i.e., the window moves upwards to view earlier content). Specifically, for instance, after seeing a message at the bottom of the screen saying "Then we'll proceed with this plan," the user immediately scrolls down to view earlier chat history at the top of the screen, trying to figure out which plan was chosen.

[0077] Clicking on target controls or target session information; users interact with interface elements by clicking, long-pressing, or double-clicking using input devices such as physical buttons, touchscreens, or mice. For example, a user right-clicks a message and selects the "View Full Topic" option from the context menu; or a user clicks the "Tracing Source" button floating on the side of the chat window.

[0078] Operation S120 may include at least one of the following: in response to a selection operation on target session information, determining the target session information as first session information; in response to a selection operation on a target control, determining the first session information from the session information displayed in the first session window.

[0079] In response to the selection of target session information, the target session information is identified as the first session information. In this case, the user's operation object is clear, so the session information where the user's interaction focus is directly used as the benchmark for topic analysis. For example, the text message that the user long-pressed, or the image message that the user's gaze lingers on and reads, is identified as the first session information.

[0080] In response to the selection of the target control, the first session information is determined from the session information displayed in the first session window. In this case, the user's operation object is a functional control rather than a specific message. Therefore, it is necessary to select the most representative or the message that best matches the user's current reading focus from the currently visible area according to preset rules. All session information in the currently visible area of ​​the first session window is obtained, and the first session information is determined from it according to position rules (such as the bottom, top, or center message), time rules (such as the latest message), or content distribution rules (such as the main topic). Specifically, semantic feature extraction and cluster analysis can be performed on all session information in the currently visible area of ​​the first session window to statistically analyze the distribution of different semantic clusters. The semantic cluster containing the most messages or with the highest weight is determined as the main session topic, and a specific message under this main session topic (such as the one located in the center or bottom of the visible area under this topic) is determined as the first session information.

[0081] For example, when a user clicks the "Analyze Current Topic" button in the sidebar, the system identifies that 8 out of the 10 messages currently displayed on the screen belong to the "Test Progress" topic and 2 belong to the "Administrative Notice" topic. It determines that "Test Progress" is the main topic and selects the last message on the screen that belongs to the "Test Progress" topic as the first conversation message.

[0082] According to embodiments of this disclosure, by supporting multiple dimensions of operation methods, such as explicit (e.g., click) and implicit (e.g., pause, scrolling back), the ways for users to trigger functions are enriched. Especially in scenarios involving control triggering, a topic recognition mechanism based on visible area content analysis is introduced. This mechanism can intelligently filter out distracting information on the screen (such as occasionally interspersed irrelevant messages), accurately locking onto the mainstream topics in the user's current field of vision as the analysis benchmark. This avoids potential misjudgments that may result from mechanically selecting locations alone, further improving the accuracy of intent recognition and user experience.

[0083] Figure 6 A flowchart illustrating the determination of second session information in an information processing method according to an embodiment of the present disclosure is shown.

[0084] like Figure 6 As shown, based on the aforementioned embodiments, operation S120 may include operations S610 to S620.

[0085] In operation S610, based on the first session information, N consecutive session information points are determined starting from the first session information. The number of session information points N matches the context length of the target model. The target model refers to an artificial intelligence model that has been pre-trained on massive amounts of text data and is capable of understanding natural language semantics and contextual relationships, especially a large-scale language model with long text processing capabilities. The context length refers to the maximum number of characters or tags that the target model can accommodate and process in a single inference process. Matching the number of session information points N with the context length of the target model means that when constructing the input data, the total number of tags in the session information is calculated to ensure that the total number of selected N session information points is less than or equal to the maximum input limit of the target model, and that as much context information as possible is included within the limit. Starting from the first session information usually means tracing back from this information or truncating forward from this information, thereby defining a continuous dialogue history as an analysis sample. For example, assuming the external large language model interface supports a maximum of 4096 input tags, and each message occupies an average of 20 tags, then starting from the message currently selected by the user, we index backwards in the historical record database and extract 200 consecutive messages as the input data block for this analysis.

[0086] In operation S620, the first session information and N other session information are used as input to the target model to determine at least one second session information. The extracted text data is packaged according to the format required by the target model and sent to the model through the application programming interface. The target model uses its internal attention mechanism or semantic analysis algorithm to determine which content among these N session information has a semantic relationship with the topic to which the first session information belongs. For example, a data packet containing the corresponding format of the aforementioned 200 messages is sent to the large language model, and the model returns a list containing index numbers, which indicates which of the 200 messages are related to the topic of "weekend dinner".

[0087] According to embodiments of this disclosure, considering that conversation records in instant messaging scenarios are typically cumulative and massive, far exceeding the input capacity limit of a single processing cycle of a neural network model, by using the user's focus (first conversation information) as an anchor point and extracting continuous data blocks matching the model's context window size for batch or local processing, it is possible to prioritize the analysis of the local context most relevant to the user's current situation while meeting the model's technical constraints. This solves the problem that large models cannot be directly used for full analysis due to excessively long chat records, and achieves efficient semantic retrieval under limited computing resources and input window limitations.

[0088] Figure 7 Another flowchart illustrating the determination of second session information in an information processing method according to an embodiment of the present disclosure is shown.

[0089] like Figure 7 As shown, based on the aforementioned embodiments, operation S620 may include operations S710 to S720.

[0090] In operation S710, the first session information and N session information are input into the target model. Based on the target session topic of the first session information, the label corresponding to each session information in the N session information is determined. The label includes: a first label, which indicates that the session information is not related to the target session topic; and a second label, which indicates that the session information is related to the target session topic.

[0091] The first and second labels refer to the logical identifiers output by the target model to identify semantic categories. They can be Boolean values, numeric codes, or specific text strings. The target session topic based on the first session information refers to the semantic distance or logical attribution relationship between the model and other session information, using the semantic vector of the first session information as a benchmark.

[0092] Specifically, an input sequence containing prompts is constructed. These prompts instruct the model to determine whether each input message belongs to the discussion topic of the first conversation and require the model to return a classification result for each message. For example, the user-selected message "planning proposal for the annual meeting" is used as a baseline, and it is packaged together with 50 previous and subsequent historical messages and sent to the large language model. After analysis, the model outputs a label "1" (second label) for messages semantically related to the planning proposal, such as "received" or "okay," and outputs a label "0" (first label) for irrelevant messages such as "what to eat for lunch."

[0093] In operation S720, in response to the label of the session information being the second label, the session information is determined to be the second session information. Each label result is traversed, and the original session information sequence is filtered, retaining all entries marked as "relevant," and their state attributes are set to the second session information. For example, upon receiving the label list "[0, 0, 1, 1, 0]" returned by the model, the third and fourth elements in the list are identified as "1," and thus the third and fourth messages in the input sequence are determined to be the second session information to be displayed.

[0094] According to embodiments of this disclosure, by utilizing artificial intelligence models to perform deep semantic understanding of natural language and outputting judgment results in the form of structured labels, it is possible to accurately identify semantically related contexts that differ literally (e.g., a simple reply "okay"), overcoming the limitations of traditional keyword matching techniques. Transforming complex semantic analysis into standardized classification labels (relevant / irrelevant) simplifies and programmes subsequent information processing and display logic, improving the accuracy of conversation topic recognition and the efficiency of automated processing.

[0095] Figure 8 Another flowchart of an information processing method according to an embodiment of the present disclosure is illustrated schematically.

[0096] like Figure 8 As shown, based on the aforementioned embodiments, the tags further include: a third tag representing that the conversation information is related to the target conversation topic and is the starting conversation information related to the target conversation topic; and a fourth tag representing that the conversation information is related to the target conversation topic and is the ending conversation information related to the target conversation topic. The third and fourth tags are special semantic identifiers used to define topic boundaries. The starting conversation information usually corresponds to statements that initiate a topic, ask a question, or open a new topic; the ending conversation information usually corresponds to statements that conclude a topic, say goodbye, or transition to the next topic. A classification category representing temporal boundaries has been added to the tag system output by the model, instructing the model not only to determine "relevance" but also to determine "whether it is the beginning" or "whether it is the end".

[0097] For example, use the tag "START" as the third tag to identify the message "Anyone free to have dinner together tonight?"; use the tag "END" as the fourth tag to identify the message "Okay, let's meet at 7 pm then".

[0098] The information processing method may also include operations S810 to S840.

[0099] In operation S810, in response to the fact that the tags corresponding to each of the N session messages do not include the third tag, the N consecutive untagged session messages preceding the first session message are identified in the first session. This operation corresponds to the trigger condition of "look back". If, in the currently analyzed N messages, the model has identified relevant messages but has not found the starting point of the topic, it means that the beginning of the topic is at an earlier time point than the current batch. For example, after analyzing the currently displayed 50 messages, it is found that although there is discussion about "dinner", they are all interludes in the middle process, and the original suggestion of dinner is not found. Therefore, the program automatically reads another 50 historical records before these 50 messages.

[0100] In operation S820, the first session information and N consecutive unlabeled session information preceding it are input into the target model. The newly acquired earlier historical message blocks are then recombined with the first session information used as the analysis benchmark to construct a new model input sequence, requesting the model to continue searching for the starting point of the topic. If the starting point of the topic is still not found in this round of operations, then operations S810~S820 can be repeated until a third label appears in the model's output labels, that is, the starting point of the topic is found.

[0101] In operation S830, in response to the fact that the fourth tag is not included among the tags corresponding to each of the N session messages, N consecutive untagged session messages following the first session message are identified in the first session. This operation corresponds to the trigger condition of "extending backwards". If the model does not find the end point of the topic in the currently analyzed N messages, it means that the topic continues after the current batch. For example, if the model analysis determines that the last message in the current batch is still a heated discussion about "dinner" and there is no closing statement, the program automatically reads another 50 records after these 50 messages.

[0102] In operation S840, the first session information and the N consecutive unlabeled session information following it are input into the target model. Similar to forward tracing, the newly acquired subsequent message blocks are combined with the first session information to construct a new input sequence, requesting the model to continue searching for the end point of the topic. If the starting point of the topic is still not found in this round of operation, then operations S830~S840 can be repeated until the fourth label appears in the model's output labels, that is, the end point of the topic is found.

[0103] According to embodiments of this disclosure, a complete topic retrieval mechanism based on "batch iteration" or "sliding window" is provided. When the entire chat history cannot be input at once due to limitations in model context length, the mechanism intelligently determines whether to continue expanding the search in the historical or future direction by detecting the appearance of "start" and "end" tags. This ensures that even in extremely long conversations, the complete context of the topic can be reconstructed (i.e., the true beginning and end can be found), without the topic being truncated due to the limitation of single input length.

[0104] Figure 9 A block diagram of an information processing apparatus according to an embodiment of the present disclosure is shown schematically.

[0105] like Figure 9 As shown, the information processing device 900 may include a first display module 910, a first determination module 920, a second determination module 930, and a second display module 940.

[0106] The first display module 910 is used to display a first session window, which is used to present session information of the first session. In some embodiments, the first display module 910 can be used to perform operation S110 in the above information processing method, which will not be described in detail here.

[0107] The first determining module 920 is used to determine first session information from the session information of the first session in response to the first operation. In some embodiments, the first determining module 920 may be used to perform operation S120 in the above information processing method, which will not be described in detail here.

[0108] The second determining module 930 is used to determine at least one second session information based on the first session information. The second session information is session information associated with the target session topic corresponding to the first session information. In some embodiments, the second determining module 930 may be used to perform operation S130 in the above information processing method, which will not be described in detail here.

[0109] The second display module 940 is used to display the second session information. In some embodiments, the second display module 940 may be used to perform operation S140 in the above information processing method, which will not be described in detail here.

[0110] Any one or more of the modules, submodules, units, and subunits according to embodiments of this 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 this 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 this 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 this disclosure can be at least partially implemented as computer program modules, which, when run, can perform corresponding functions.

[0111] For example, any plurality of the first display module 910, the first determining module 920, the second determining module 930, and the second display module 940 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 first display module 910, the first determining module 920, the second determining module 930, and the second display module 940 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 implemented in hardware or firmware by any other reasonable means of integrating or packaging the circuitry, or implemented in software, hardware, or firmware, or in any suitable combination of any of these three implementation methods. Alternatively, at least one of the first display module 910, the first determining module 920, the second determining module 930, and the second display module 940 may be at least partially implemented as a computer program module, which can perform corresponding functions when the computer program module is run.

[0112] 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.

[0113] Figure 10 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 10 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0114] like Figure 10 As shown, an electronic device 1000 according to an embodiment of the present disclosure includes a processor 1001, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage portion 1008 into a random access memory (RAM) 1003. The processor 1001 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 1001 may also include onboard memory for caching purposes. The processor 1001 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.

[0115] RAM 1003 stores various programs and data required for the operation of electronic device 1000. Processor 1001, ROM 1002, and RAM 1003 are interconnected via bus 1004. Processor 1001 performs various operations of the method flow according to embodiments of the present disclosure by executing programs in ROM 1002 and / or RAM 1003. It should be noted that the programs may also be stored in one or more memories other than ROM 1002 and RAM 1003. Processor 1001 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.

[0116] According to embodiments of this disclosure, the electronic device 1000 may further include an input / output (I / O) interface 1005, which is also connected to a bus 1004. The electronic device 1000 may also include one or more of the following components connected to the input / output (I / O) interface 1005: an input section 1006 including a keyboard, mouse, etc.; an output section 1007 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network interface card such as a LAN card, modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to the input / output (I / O) interface 1005 as needed. A removable medium 1011, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 1010 as needed so that computer programs read from it can be installed into the storage section 1008 as needed.

[0117] 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 1009, and / or installed from removable medium 1011. When the computer program is executed by processor 1001, 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.

[0118] 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.

[0119] 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.

[0120] For example, according to embodiments of this disclosure, a computer-readable storage medium may include the ROM 1002 and / or RAM 1003 described above and / or one or more memories other than ROM 1002 and RAM 1003.

[0121] 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 information processing methods provided in the embodiments of this disclosure.

[0122] When the computer program is executed by the processor 1001, 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.

[0123] 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 1009, and / or installed from removable medium 1011. 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).

[0124] 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.

[0125] 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. An information processing method, comprising: Display the first session window, which is used to present the session information of the first session; In response to the first operation, the first session information is determined from the session information of the first session; Based on the first session information, at least one second session information is determined, wherein the second session information is session information associated with the target session topic corresponding to the first session information; Display the second session information.

2. The method according to claim 1, wherein displaying the second session information includes: Locate the session position of the second session information within the session information; Based on the session location, the second session information is displayed in the first session window; or, Extract the second session information from the first session; The second session information is displayed in a target display window, which is different from the first session window.

3. The method according to claim 1, wherein displaying the second session information includes: Determine the third session information in each of the second session information; The second session information is displayed starting from the third session information; The third session information is determined based on the time information corresponding to each of the second session information, or the third session information is determined based on the degree of association between each of the second session information and the target session topic.

4. The method according to claim 1, wherein displaying the second session information includes: The second session information is displayed in a second mode, which is different from the first mode that displays session information other than the second session information. The second session information includes end session information, which is the session information closest to the current time point among all the second session information; After displaying the second session information, the method further includes: In response to a second operation, the first session information or the last session information is moved to the first session window, and the display mode of each session information is switched to the same display mode.

5. The method according to claim 1, wherein the second session information includes end session information, the end session information being the session information closest to the current time point among all the second session information, and the second session information includes start session information, the start session information being the session information farthest from the current time point among all the second session information. After displaying the second session information, the method further includes: In response to the fourth session information moving into the first session window and the second session information moving out of the first session window, at least one session topic is determined based on each of the fourth session information, wherein the fourth session information is the session information after the last session information, or the fourth session information is the session information before the start session information; Based on the respective conversation topics, generate prompt messages; In response to receiving feedback information regarding the prompt, the target session topic is redefined; Based on the redefined target session topic, the second session information is redefined.

6. The method according to claim 1, wherein the first operation includes a selection operation on target session information and a selection operation on target controls, the selection operation including at least one of the following: The operation of keeping the target session information in the first session window for a preset duration; After the target session information is displayed in the first session window, the operation of browsing the historical session information before the target session information is performed. Click operations on target controls or target session information; The step of responding to the first operation by determining the first session information corresponding to the first operation from the session information of the first session includes at least one of the following: In response to the selection operation of the target session information, the target session information is determined to be the first session information; In response to the selection of the target control, the first session information is determined from the session information displayed in the first session window.

7. The method according to any one of claims 1 to 6, wherein determining at least one second session information based on the first session information includes: Based on the first session information, N consecutive session information are determined in the first session, starting from the first session information, and the number N of the session information matches the context length of the target model. Using the first session information and the N session information as input to the target model, at least one second session information is determined.

8. The method according to claim 7, The step of using the first session information and the N session information as input to the target model to determine at least one second session information includes: The first session information and the N session information are input into the target model. Based on the target session topic of the first session information, a label corresponding to each of the N session information is determined. The label includes: a first label, indicating that the session information is not related to the target session topic; and a second label, indicating that the session information is related to the target session topic. In response to the fact that the tag of the session information is a second tag, the session information is determined to be the second session information.

9. The method according to claim 8, wherein the label further comprises: The third tag indicates that the session information is related to the target session topic and is the starting session information related to the target session topic; The fourth tag indicates that the session information is related to the target session topic and is the end session information related to the target session topic; The method further includes: In response to the fact that the tags corresponding to each of the N session information do not include a third tag, the N consecutive untagged session information preceding the first session information are determined in the first session; The first session information and the N consecutive unlabeled session information preceding the first session information are input into the target model; In response to the fact that the fourth tag is not included in the tags corresponding to each of the N session information, N consecutive untagged session information after the first session information are determined in the first session; The first session information and the N consecutive unlabeled session information following the first session information are input into the target model.

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, which, when executed by the at least one processor, enable the at least one processor to perform at least one of the following operations: displaying a first session window for presenting session information of a first session; determining first session information from the session information of the first session in response to a first operation; determining at least one second session information based on the first session information, the second session information being session information associated with a target session topic corresponding to the first session information; and displaying the second session information.

Images