Methods, apparatuses, devices, media, and products for interface interaction

Abstract

A method, apparatus, device, storage medium, and computer program product for interface interaction are provided. The method includes displaying a plurality of components in a first interface, the plurality of components being indicative of a plurality of topics. The method also includes receiving a first operation, the first operation being directed to a first component of the plurality of components, the first component corresponding to a first topic. The method further includes displaying a first message set in a second interface, the first message set being associated with the first topic and including one or more messages of interaction with an intelligent system.

Description

Technical Field

[0001] This relates to the field of computers, and more specifically to methods, apparatus, devices, computer-readable storage media, and computer program products for user interface interaction. Background Technology

[0002] With the continuous exploration and innovation in the field of artificial intelligence, machine learning technology has become an important direction. Machine learning technology enables intelligent processing and analysis of various types of data and information.

[0003] The industry has conducted extensive research on the applicability and stability of machine learning technology, and various lightweight and precise algorithm solutions have emerged. The application boundaries of machine learning technology have continued to expand, and rich technical accumulation has been formed in many technical fields. Summary of the Invention

[0004] A method, apparatus, device, computer storage medium, and computer program product for interface interaction are provided.

[0005] In a first aspect, a method for interface interaction is provided, comprising displaying multiple components in a first interface, the multiple components indicating multiple topics. The method further comprises receiving a first operation, the first operation targeting a first component among the multiple components, the first component corresponding to a first topic. The method also comprises displaying a first message set associated with the first topic in a second interface, the first message set being associated with the first topic and including one or more messages interacting with an intelligent system. This method can aggregate and display scattered historical interaction messages by topic dimension, enabling users to quickly locate and obtain message sets for specific topics through topic components without having to search through message streams arranged chronologically, thus achieving higher information processing efficiency and improving user experience.

[0006] In a second aspect, an apparatus for interface interaction is provided. The apparatus includes a first display module configured to display multiple components on a first interface, the multiple components indicating multiple topics. The apparatus also includes a first receiving module configured to receive a first operation targeting a first component among the multiple components, the first component corresponding to a first topic. The apparatus further includes a second display module configured to display a first message set associated with the first topic on a second interface. The first message set is associated with the first topic and includes one or more messages interacting with an intelligent system. This apparatus can aggregate and display scattered historical interaction messages by topic dimension, allowing users to quickly locate and obtain message sets on specific topics through topic components without having to search through message streams arranged chronologically. Therefore, it has high information processing efficiency and improves user experience.

[0007] In a third aspect, an electronic device is provided, comprising: at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform a method for interface interaction when executed by the at least one processing unit. The method includes displaying a plurality of components in a first interface, the plurality of components indicating a plurality of topics. The method further includes receiving a first operation targeting a first component among the plurality of components, the first component corresponding to a first topic. The method also includes displaying a first set of messages associated with the first topic in a second interface, the first set of messages being associated with the first topic and including one or more messages interacting with an intelligent system. This electronic device is capable of aggregating and displaying scattered historical interaction messages by topic dimension, enabling users to quickly locate and obtain message sets for specific topics through topic components without having to search through message streams arranged chronologically, thus achieving higher information processing efficiency and improving user experience.

[0008] In a fourth aspect, a computer-readable storage medium is provided having machine-executable instructions stored thereon, which, when executed by a device, cause the device to perform a method for interface interaction. The method includes displaying a plurality of components in a first interface, the plurality of components indicating a plurality of topics. The method also includes receiving a first operation directed to a first component among the plurality of components, the first component corresponding to a first topic. The method further includes displaying a first set of messages associated with the first topic in a second interface, the first set of messages being associated with the first topic and including one or more messages interacting with an intelligent system. This computer-readable storage medium is capable of aggregating and displaying scattered historical interaction messages by topic dimension, enabling users to quickly locate and obtain message sets for specific topics through topic components without having to search through message streams arranged chronologically, thus achieving higher information processing efficiency and improving user experience.

[0009] In a fifth aspect, a computer program product is provided, including computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement a method for interface interaction. The method includes displaying multiple components in a first interface, the multiple components indicating multiple topics. The method also includes receiving a first operation, the first operation targeting a first component among the multiple components, the first component corresponding to a first topic. The method further includes displaying a first message set associated with the first topic in a second interface, the first message set being associated with the first topic and including one or more messages interacting with an intelligent system. This computer program product can aggregate and display scattered historical interaction messages by topic dimension, enabling users to quickly locate and obtain message sets for specific topics through topic components without having to search through message streams arranged chronologically, thus achieving higher information processing efficiency and improving user experience.

[0010] The summary section is provided to introduce a series of concepts in a simplified form, which will be further described in the detailed description below. The summary section is not intended to identify key or essential features, nor is it intended to limit the scope. Other features will become readily apparent from the following description. Attached Figure Description

[0011] Figure 1A A schematic diagram of an example environment that can be implemented in one scenario is shown;

[0012] Figure 1B A schematic diagram of the first interface is shown;

[0013] Figure 1C A schematic diagram of the second interface is shown;

[0014] Figure 2 A flowchart of the method for interface interaction is shown;

[0015] Figure 3 Another schematic diagram of the first interface is shown;

[0016] Figure 4 A schematic diagram illustrating the process of generating aggregate cards is shown;

[0017] Figure 5 A schematic diagram illustrating the process of aggregating messages is shown;

[0018] Figure 6A A schematic diagram illustrating the process of synchronizing messages is shown;

[0019] Figure 6B A schematic diagram of the input component is shown;

[0020] Figure 6C A diagram illustrating the dialogue in the details interface is shown;

[0021] Figure 6D This diagram illustrates the result of switching back to the main dialog interface;

[0022] Figure 7 A schematic block diagram of a device for interface interaction is shown; and

[0023] Figure 8 A block diagram of an electronic device is shown.

[0024] In all the accompanying figures, the same or similar reference numerals denote the same or similar elements. Detailed Implementation

[0025] The names of messages or information exchanged between multiple devices in the implementation are for illustrative purposes only and are not intended to limit the scope of these messages or information. It is understood that before using the technical solutions disclosed in each situation, users should be informed of the type, scope of use, and usage scenarios of the personal information involved, and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0026] For example, upon receiving a user's active request, a prompt message can be sent to the user, explicitly informing them that the requested operation will require the acquisition and use of their personal information. This allows the user to choose whether to provide personal information to the software or hardware such as the electronic device, application, server, or storage medium performing the relevant operation, based on the prompt message. As an optional but non-limiting implementation, the prompt message can be sent to the user in the form of a pop-up window, which can present the prompt message in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0027] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation method. Other methods that comply with relevant laws and regulations may also be applied in various situations.

[0028] The various scenarios will now be described in more detail with reference to the accompanying drawings. While some scenarios are shown in the drawings, it should be understood that implementations can take many forms and should not be construed as limited to the one scenario described herein. Rather, these scenarios are provided to provide a more thorough and complete understanding of the technical content. It should be understood that the drawings and scenarios are for illustrative purposes only and are not intended to limit the scope of protection.

[0029] In the descriptions of each situation, the term "comprising" and similar expressions should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The terms "a situation" or "the situation" should be understood as "at least one situation". The terms "first", "second", etc., may refer to different or the same objects unless explicitly stated. Other explicit and implicit definitions may also be included below.

[0030] In related technical solutions, developers can set up intelligent systems in software applications to assist users in using them. For example, users can interact with this intelligent system. After prolonged use, users may need to review messages on a specific topic, but these messages are displayed individually with timestamps, making it difficult to quickly retrieve a collection of messages related to a specific topic. This results in low information processing efficiency and a poor user experience.

[0031] To address this, a method for interface interaction is proposed. When viewing interaction messages with an intelligent system, this method displays multiple components indicating various topics on a first interface. In response to operations on the first component, a set of messages associated with the first topic is displayed on a second interface. This method aggregates and displays scattered historical interaction messages by topic, allowing users to quickly locate and retrieve message sets on specific topics through topic components, without having to search through a time-ordered message stream. Therefore, it has high information processing efficiency and improves the user experience.

[0032] Figure 1A A schematic diagram of an example environment 100 that can be implemented in one scenario is shown. For ease of description, the first task is described in some cases as an editing task for media content, but it should be understood that this is only an example and does not constitute a limitation on the method. For example, the first task could also be a response task, a data retrieval task, a data processing task, etc. The example environment 100 includes a user device 130, a server 140, and a user 150. An intelligent system can be deployed on the server 140, which can call deep learning models (such as multimodal models, large language models, etc.) to perform tasks. An application 110 (such as a content application, including social applications, media applications, short video applications, etc.) can be installed on the user device 130. This application 110 serves as the execution carrier of the method, undertaking tasks such as acquiring, processing, displaying, and responding to user interactions related to the media content stream.

[0033] In some scenarios, application 110 can be installed on user device 130, for example, as a software application. User 150 can use user device 130 to launch application 110. Application 110 can communicate with server 140 via a network. In some scenarios, user 150 operates application 110 on user device 130 to initiate a business request; user device 130 encapsulates the request and sends it to server 140 via the network; server 140 parses the received request, executes the corresponding business processing operation (such as data query, logical operation, content delivery, submitting messages to the intelligent system, etc.), and returns the processing result to user device 130; user device 130 visualizes the processing result through application 110 for user 150 to view, thereby completing the interaction between the client side and the server side.

[0034] In some scenarios, application 110 can provide works by various objects for user 150 to consume within the interface. Application 110 can present a content stream within the interface. This content stream can include multiple media contents, and user 150 can switch between different media contents in the content stream through interactive operations within the interface (e.g., swiping). Such media contents can include, but are not limited to, image works, video works, live streams, content cards, etc. After user 150 launches application 110, without any additional complex operations, they can directly view the continuously loaded media content within application 110. Each media content can be played according to preset playback rules (e.g., autoplay, click play, etc.) in the display area of ​​the interface (e.g., the center of the interface, occupying the main display space), presented in real time in user 150's field of vision for viewing, information retrieval, or entertainment. For convenience, aggregated cards are used instead of components for description, but this does not constitute a limitation on this method; other examples of components are also possible.

[0035] Figure 1B A schematic diagram of the first interface is shown. In some cases, application 110 can display multiple aggregated cards on the first interface, with each card indicating a different topic. For example, application 110 can display two aggregated cards in the main dialogue interface with the intelligent system. One aggregated card might have the topic "Comparison of fat-burning effects of running and swimming; 1 hour of swimming…", while the other might have the topic "Differences in battery performance of overseas versions of mobile phone A; Analysis:…". This presentation of aggregated cards breaks away from the limitations of traditional linear chronological arrangement, allowing user 150 to easily identify the distribution of different topics. In some cases, the topic title on each card is automatically generated by the intelligent system, aiming to summarize the discussion points and help user 150 quickly determine whether a historical conversation is of interest to them.

[0036] In some scenarios, application 110 can receive a first operation, which targets a first aggregated card among multiple aggregated cards, corresponding to a first topic. For example, user 150 can click on aggregated card 112 to enter the details interface (i.e., the second interface) of that aggregated card. In some cases, this first operation is a click, but it can also be a long press or swipe gesture; the specific interaction method can be flexibly configured according to the application scenario. In some scenarios, after clicking on an aggregated card, application 110 can record the identifier of that topic and use this identifier to retrieve the complete set of messages under that topic from the local machine or the server, preparing for subsequent display.

[0037] Figure 1C A schematic diagram of the second interface is shown. In some cases, application 110 can display a first set of messages associated with the first topic in the details interface. The first set of messages includes one or more messages interacting with the intelligent system. For example... Figure 1C As shown, the first message set can include four messages: two questions from user 150 and two answers from the intelligent system. In some cases, user 150 can send a message referencing the cover image 114 of the media content, allowing the intelligent system to use the media content as context in its response. In some cases, in the details interface, all messages are arranged from top to bottom in their original chronological order, reconstructing the complete evolution of the dialogue and facilitating user 150's review of the context. The ability to reference media content enhances the richness of the question-and-answer process, enabling the intelligent system to not only process text but also provide more accurate responses by combining multimedia information such as images or videos. Although the above describes the interaction scenario between user 150 and the intelligent system, this method is not limited to this; user 150 can utilize the intelligent system to perform any type of task, such as programming, data retrieval, or data processing.

[0038] In the above scenario, this method significantly improves the efficiency of users locating specific topics in massive historical interaction messages, reduces the cognitive burden of searching through each message, and comprehensively optimizes the fluency and richness of human-computer collaboration by leveraging intelligent summary generation, multimodal contextual references, and flexible interactive gestures, ultimately bringing users a more efficient, intuitive, and intelligent interactive experience.

[0039] As understood by those skilled in the art, an instance of server 140 may be a single physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, and data processing and artificial intelligence platforms.

[0040] User equipment 130 can be any type of mobile computing device, including mobile computers (e.g., personal digital assistants, laptops, notebooks, tablets, netbooks, etc.), mobile phones (e.g., cellular phones, smartphones, etc.), wearable computing devices (e.g., smartwatches, head-mounted devices, including smart glasses, etc.) or other types of mobile devices. In some cases, user equipment 130 can also be a fixed computing device, such as a desktop computer, game console, smart TV, etc. It should be understood that the above operations can be performed jointly by user equipment 130 and server 140.

[0041] It should be understood that the architecture and functionality in the example environment are described for illustrative purposes only and do not imply any limitation on the scope. This scenario can also be applied to other environments with different structures and / or functionalities.

[0042] The processes of each scenario will be described in detail below with reference to other accompanying drawings. For ease of understanding, the specific data mentioned in the following description are exemplary and are not intended to limit the scope of protection. It is understood that the scenarios described below may also include additional actions not shown and / or the actions shown may be omitted, and their scope is not limited in this respect.

[0043] Figure 2 A flowchart of a method 200 for interface interaction is shown. In this case, it can be... Figure 1A The method is executed by application 110 on user equipment 130. The method performs the steps shown in boxes 202-206 in the first dialog interface, as follows:

[0044] In box 202, multiple components are displayed in the first interface, each indicating a different topic. In some cases, the first interface is the main dialogue interface between the user and the intelligent system. The multiple components can be multiple aggregated cards, each corresponding to a topic. This topic can be automatically generated by the intelligent system based on historical dialogue messages, aiming to summarize the discussion points and help the user quickly determine if a historical dialogue is of interest to them. For example, the intelligent system can cluster dialogue messages about "sports and health" into a topic based on the user's historical interaction records and generate corresponding components. This component can be displayed as a card, with the card title automatically generated by the intelligent system, such as "Comparison of fat-burning effects of running and swimming; 1 hour of swimming…".

[0045] In box 204, a first operation is received. This first operation targets the first component among multiple components, and the first component corresponds to the first topic. In some cases, the first operation is a user click on the first component, but it could also be a long press or swipe gesture. This first component may correspond to the first topic, such as the "Sports and Health" topic. In some cases, in response to the user's click on the first component, the application may record the topic's identifier and use this identifier to retrieve the complete set of messages under that topic from local storage or a server, preparing for subsequent display.

[0046] In box 206, the second interface displays a first message set associated with the first topic. This first message set is associated with the first topic and includes one or more messages interacting with the intelligent system. The intelligent system can be an intelligent execution entity with autonomous task scheduling and model invocation capabilities. It can proactively invoke suitable models (such as deep learning models) and tools according to actual task requirements, relying on the model's semantic understanding and logical reasoning capabilities to complete various tasks such as information parsing, instruction execution, content generation, logical judgment, and tool invocation, thereby achieving automated task flow and intelligent processing. In some cases, the second interface is a details interface for specific components, used to display the complete message set associated with the first topic. This first message set can include multi-turn dialogue messages between the user and the intelligent system, such as user questions and the intelligent system's answers. Although the above describes a question-and-answer interaction scenario between the user and the intelligent system, this method is not limited to this. Users can utilize the intelligent system to perform any type of task, such as programming tasks, data retrieval tasks, and data processing tasks.

[0047] Figure 2 The method described above aggregates and displays scattered historical interaction messages by topic, allowing users to quickly locate and retrieve message sets on specific topics through topic components without having to search through message streams arranged chronologically. This results in higher information processing efficiency and an improved user experience. Furthermore, by aggregating and displaying multiple components by topic on the first interface, this method avoids the traditional method where users need to scroll through all historical messages one by one, triggering numerous data requests and interface rendering operations. This significantly reduces unnecessary data transfer, memory usage, and GPU rendering overhead, especially reducing processor resource consumption caused by frequent view reuse and redrawing during long list scrolling.

[0048] For convenience, aggregate cards will be used instead of components in the following descriptions, but this does not limit this method. Other examples of components can also be included, such as buttons, banners, etc. Figure 3Another schematic diagram of the first interface is shown. In some cases, application 310 can display a second message set on the first interface, where the second message set includes messages generated within the most recent time period, and the second message set is displayed as individual messages. As shown in the figure, assuming the current time is 9:00 AM on July 5th, messages from July 1st (i.e., messages within the historical event period) are aggregated into an aggregate card. Messages generated within the most recent time period (e.g., within the last 24 hours) are not aggregated, but are displayed one by one in their original chronological order as individual messages. Figure 3 The 8:00 AM message "How's the weather today?" and its corresponding reply "Today's weather is sunny turning cloudy..." allow users to quickly view and continue the latest conversation activity of the day. This design, which avoids aggregating messages from the same day, prevents semantic fragmentation caused by forcibly categorizing new conversations that haven't yet been processed into topic cards. It also allows users to seamlessly continue their real-time communication within the main conversation interface without needing to switch to another app.

[0049] In some scenarios, the first message set is associated with a first object, or the semantics of the first message set are associated with a first topic. This association can include two dimensions: first, object-level association, where the media content and topic materials involved in the message set all belong to the same object (e.g., the same video or the same image); second, semantic-level association, where the intelligent system, through semantic understanding of historical messages, groups question-and-answer pairs that semantically point to the same topic into aggregation cards for that topic. For the first dimension, for example, if the messages in the message set all have a unique identifier for a specific object, the intelligent system identifies this identifier and groups the originally scattered question-and-answer pairs under the same topic category. Through these two association methods, the system can flexibly adapt to aggregation needs in different scenarios. It can organize multiple follow-up questions from users regarding specific content by object dimension, and it can also extract high-level topics across objects by semantic dimension, thereby improving the coverage and accuracy of the aggregation logic. In some cases, if an aggregation card is associated with a video, the video's cover image can be integrated into the aggregation card for easy viewing of the content.

[0050] In some scenarios, a first message set is associated with a first object, and the application can display a second component on the first interface. This second component corresponds to a second topic, which is associated with a third message set. The third message set is associated with the first object and originates from messages generated within a second time period, which differs from the first time period. This means that for the same object, the system can simultaneously display multiple topic components on the first interface, each corresponding to a message set generated within a different time period. For example, the first component might cover multiple messages from yesterday, and the second component might cover multiple messages from the day before yesterday. This design allows users to longitudinally compare historical discussion points across different time periods for the same object, thus gaining a more comprehensive understanding of changes in focus regarding that object, and also facilitating cross-period knowledge backtracking and tracing.

[0051] In some cases, the first topic includes first information and second information. The first information indicates the task corresponding to the first message set, and the second information indicates the description of the task. The first information serves as a summary of the topic title, usually presented as a short keyword or task name (e.g., "Comparison of Fat-Burning Effects of Running and Swimming"). The second information serves as a subtitle providing supplementary information, such as a detailed description of the task or key conclusions (e.g., "One hour of swimming is more efficient at burning fat than the same amount of running, and the weather was also suitable for swimming that day"). This two-tiered structure of main and subtitles ensures quick identification of the topic while providing sufficient contextual preview information, helping users to roughly understand the topic content before clicking to enter the details page, thereby reducing unnecessary jumps and loading operations.

[0052] Figure 4 A schematic diagram illustrating the process of generating aggregate cards is shown. At point 402, the user can initiate a dialogue with the intelligent system based on the comment section tag entry. For example, the user can click the comment control of the currently displayed media content to display the comment section, and then click the tag within the comment section to enter a window for dialogue with the intelligent system. Simultaneously, the intelligent system can automatically provide analysis of the currently displayed media content. This window can be a separate dialogue window from the main dialogue interface, and it can display or hide aggregate cards and historical messages.

[0053] At position 404, users can initiate a conversation with the intelligent system via the bottom toolbar entry. This bottom toolbar entry can be located at the bottom of the currently displayed media content. After clicking this entry, the user enters a window to converse with the intelligent system, which can automatically provide analysis of the currently displayed media content. Similarly, this window can be a separate conversation window from the main interface, and it can display or hide aggregate cards and historical messages.

[0054] At point 406, users can initiate a dialogue with the intelligent system via a search interface entry. For example, a user can perform a search within the application, and an entry point will be displayed on the search results screen. After clicking this search interface entry point, the user can enter a window to dialogue with the intelligent system, which can automatically provide analysis of the currently displayed media content. Similarly, this window can be a separate dialogue window from the main dialogue interface, and it can display or hide aggregated cards and historical messages.

[0055] At point 408, users can initiate a conversation with the intelligent system via the message interface. The message interface can display various messages related to the user, such as friend messages, system messages, interactive messages, and notification messages. Applications can display an entry point for conversing with the intelligent system within the message interface. After clicking this entry point, the user can enter the interface for conversing with the intelligent system, such as the main conversation interface.

[0056] At point 410, the message collection module is responsible for capturing historical dialogue messages between users and the intelligent system from various interaction entry points (including the aforementioned comment section tag entry, bottom toolbar entry, search interface entry, message interface entry, etc.), and aggregating these messages in the background for subsequent processing. In some cases, the first message set includes messages from multiple interaction entry points within the first time period. This means that the system does not collect messages from a single dialogue channel, but can include messages generated by users within the first time period through different interaction entry points (such as comment section tag entry, bottom toolbar entry, search interface entry, message interface entry, etc.) into the same message set. This cross-entry point aggregation method breaks down the barriers between interaction channels, enabling users to achieve a coherent review under a unified theme regardless of where they initiate a dialogue with the intelligent system, avoiding the fragmentation of historical records caused by dispersed entry points.

[0057] At point 412, the aggregation module begins executing aggregation logic on the collected messages, determining which messages need to be aggregated together to generate aggregation cards categorized by topic. At point 414, the aggregation module first segments the messages by date, dividing them into different time periods based on their timestamps. For example, it distinguishes today's messages from yesterday's and earlier historical messages, laying the foundation for subsequent differentiated processing.

[0058] At point 416, for messages with tags, the aggregation module aggregates them according to the tag, grouping question-answer pairs belonging to the same session or the same content object together, thus ensuring the integrity of messages under the same topic at the object level. At point 418, for messages without tags, the aggregation module aggregates them according to time and semantics. That is, based on the temporal proximity of the messages and the similarity after the intelligent system's semantic understanding of the message content, messages that semantically point to the same topic are grouped into the same topic, thus covering the message organization needs in untagged scenarios.

[0059] At point 420, after processing through the two paths of identifier aggregation and semantic aggregation, the system outputs several sets of categorized messages. Each set corresponds to an independent historical dialogue topic, which serves as the data basis for generating aggregation cards in the future.

[0060] At point 422, the copywriting generation module retrieves the aforementioned message sets and utilizes the natural language generation capabilities of the lightweight model on the user's device to extract and summarize the dialogue content in each message set. At point 424, based on the extraction results, the copywriting generation module generates corresponding titles and subtitles for each message set. The title summarizes the core theme, while the subtitle supplements key information, thus forming the copywriting content of the aggregated card.

[0061] At point 426, the aforementioned message set, along with its corresponding title and subtitle, is encapsulated into a complete aggregate card. Each aggregate card represents an independent topic and is ready to be rendered onto the interface for user viewing and interaction. At point 428, the dialogue interface rendering module is responsible for rendering the generated aggregate cards into the corresponding areas of the main dialogue interface according to the interface layout rules (e.g., displaying today's messages individually and historical messages in aggregate card format). It is also responsible for responding to subsequent user clicks, long presses, and other interactive operations, navigating to the corresponding details interface and displaying the complete message set.

[0062] In some scenarios, at least one interactive entry point includes a first interactive entry point (such as a message interface entry point), which is configured to trigger the display of a first interface. In some scenarios, in response to the display of the first component, the application can update a timestamp, where the timestamp is the timestamp of the first interactive entry point. At 430, after the system completes the organization of historical message aggregation cards the following day, the entry point floating module determines it as a valid trigger, updates the latest timestamp of the message interface entry point, and enables the message interface entry point to participate in the sorting of various dialogue entry points based on the latest timestamp, thereby achieving a dynamic floating effect of the message interface entry point. That is, in the message interface, compared to other dialogue entry points (such as the entry point for chatting with friends), the message interface entry point that triggers the chat with the intelligent system can be displayed first based on the latest timestamp.

[0063] Figure 5 The diagram illustrates the message aggregation process. At point 510, the system first acquires historical messages generated by the user with the intelligent system across various interaction points; these messages serve as the raw data source for subsequent aggregation processing. At point 512, the system performs date checks on the acquired historical messages, verifying whether they originated on the same day, using this as a preliminary filtering condition for whether to perform aggregation. At point 514, for messages belonging to different dates, the system determines that they will not be aggregated, because these cross-date messages lack immediate correlation in the time dimension and are more suitable to be presented in an independent form or categorized separately according to their respective dates.

[0064] At point 516, for messages from the same day, the system further determines whether each message carries an identifier to decide which aggregation strategy to use. At point 518, for messages without identifiers, the system aggregates them based on temporal proximity and semantic similarity; that is, based on the chronological order of message generation and the relevance of the message content after semantic understanding by the intelligent system, messages semantically pointing to the same topic are grouped into the same topic. At point 520, for messages with identifiers, the system directly aggregates them according to the identifier, merging question-answer pairs belonging to the same session identifier together.

[0065] At point 522, during the aggregation process by identifier, even if messages with the same identifier come from different interaction entry points (e.g., some from comment section tag entry points and others from bottom toolbar entry points), the system can still identify and aggregate them together, thus ensuring that messages under the same session topic are not fragmented and stored due to dispersed entry points. At point 524, after processing by the above aggregation logic, the system generates corresponding aggregation cards for each group of categorized message sets. Each card represents an independent topic and is ready for the subsequent rendering module to display on the interface.

[0066] In some scenarios, the application can receive a fourth action, which is associated with the first component; and a reference to the first component in the input area. This fourth action could be long-pressing an aggregate card and selecting the "Reference" button from the pop-up menu. Upon triggering this, the system can automatically fill the input box with the current aggregate card as a reference block, along with the aggregate card's identifier as a reference marker. When a user sends a new message based on this reference, the intelligent system can directly locate the corresponding message set through the reference identifier, thus accurately inheriting the message set of that topic as context in subsequent question-and-answer sessions, without requiring the user to manually repeat previous discussion content.

[0067] Figure 6AThe diagram illustrates the process of synchronizing messages. At point 602, the user clicks on an aggregated card in the main chat interface, triggering entry into the details screen corresponding to that card. At point 604, the application responds to this click operation and navigates to the details screen (i.e., the second screen), which is specifically used to display the complete history of conversations under that topic.

[0068] At point 606, after entering the details interface, the application displays all historical Q&A messages related to the topic in their original chronological order, from oldest to newest, reconstructing the complete evolution of the conversation and allowing users to review the context from the beginning. In some cases, the application can receive a third operation, which is associated with the first component and deletes it. This third operation can be long-pressing an aggregated card and selecting the "Delete" button from the pop-up menu. After the deletion operation is triggered, the application will synchronously remove the component from the local database and the server, and the messages under that topic will also be deleted. At point 610, users can long-press any historical message or aggregated card in the details interface to trigger the operation menu and select to delete the corresponding message or card; if an aggregated card is deleted, the messages under that topic will be unaggregated and revert to single message format.

[0069] At point 608, users can enter new questions or instructions in the input box at the bottom of the details page to follow up on the topic. The intelligent system will use the historical message set carried by the current details page as context, combine it with the user's input to generate a new answer and display it in the details page. Figure 6B A schematic diagram of the input component is shown. After the user clicks the input box at the bottom, a virtual keyboard pops up, allowing the user to type, for example, "So what's the price?" as a third message and send it.

[0070] In some scenarios, application 620 can receive a third message based on the second interface; and display a fourth message on the second interface. This fourth message is a message obtained by the intelligent system based on the first context and the third message. The first context includes the first message set. This means that when the user continues to ask follow-up questions in the input box at the bottom of the details interface, the intelligent system can automatically use the first message set corresponding to the current details interface as the basic context, and then combine it with the newly entered third message for comprehensive understanding and reasoning. This mechanism ensures that the dialogue background does not need to be constructed from scratch for each follow-up question, while excluding messages outside the aggregated card, thus achieving context pruning. Figure 6C A schematic diagram of a dialogue in the details interface is shown. After the user sends the third message 622, the intelligent system can generate a fourth message 624 based on the first context and the third message 622. This fourth message 624, for example, introduces some information about the selling price.

[0071] In some scenarios, the first message set is associated with the first media content, and the first context also includes the first media content. When messages in the first message set involve references to specific media content (e.g., these messages bear the identifier of a certain media content), the feature data of that media content is also included as part of the first context within the processing scope of the intelligent system. In this way, the intelligent system simultaneously references historical message sets and associated media content, uses a multimodal model to parse non-textual information such as images and video frames, and integrates visual features with textual history for understanding, thereby providing responses that are more closely aligned with the original context and possess multimodal perception capabilities.

[0072] In some scenarios, application 620 can receive a fifth operation, used to switch from the second interface to the first interface; and to display a third and fourth message on the first interface, where the third message references the first component. This fifth operation can be triggered automatically by the user clicking the back button or performing a swipe-to-return gesture, automatically refreshing the message refresh mechanism of the main dialog interface after exiting the details interface. Application 620 can synchronize the latest third and fourth messages generated in the details interface to the message stream of the main dialog interface, while attaching a reference identifier to the third message in the main dialog interface, clearly pointing to the associated first component, allowing the user to intuitively identify the dialog topic to which the message belongs in the main dialog interface. This two-way synchronization mechanism effectively avoids message loss or context breakage caused by page switching, ensuring the consistency of data state between the main dialog interface and the details interface, while reducing the need for users to repeatedly enter topic references or manually copy historical content to continue the same topic, thereby improving the continuity and operational efficiency of interaction in multi-interface scenarios.

[0073] At point 612, for follow-up questions generated within the same day, application 620 can automatically synchronize them to the main chat interface for display. At the same time, the follow-up question message will be accompanied by a reference mark pointing to the first component in the main interface, so that users can clearly track the topic to which the message belongs in the main interface. Figure 6D This diagram illustrates the result of switching back to the main dialog interface. (For example...) Figure 6D As shown, the third message 622 and the fourth message 624 are still displayed in the style of single messages, but the third message 622 is displayed as a reference to the corresponding aggregate card. At 614, after application 620 completes the aggregation card organization of the day's messages the next day, these follow-up questions will be included in the newly generated aggregate card along with other conversations from the day, participating in a new round of topic classification and display.

[0074] In some scenarios, the application can receive a second operation associated with the first component, and pin the first message set to the top of the first interface. This second operation could be a user long-pressing the aggregated card and selecting the "pin" button from the operation menu, or performing a specific upward swipe gesture on the card to trigger the pinning command. After the pinning operation is executed, the topic corresponding to the first component and its associated first message set will be fixed in the top area of ​​the main chat interface. Even if the user subsequently generates new chat messages or the application generates new aggregated cards, the pinned topic will still occupy the top position of the interface until the user manually unpins it. This pinning mechanism allows users to keep frequently accessed or unprocessed historical topics in the most prominent position, avoiding repetitive operations of repeatedly searching for the same topic in the message stream, while also reducing the consumption of computing resources caused by list scrolling and view redrawing.

[0075] In some scenarios, the application can receive a sixth action, which is associated with the first component; and copy the first message set. This sixth action could be the user long-pressing the aggregated card and selecting the "Copy" button from the action menu. Upon triggering this, the application will copy the complete historical Q&A content corresponding to the first component in text format to the application clipboard. This allows users to quickly forward message sets on specific topics to other chat windows, significantly improving the efficiency of cross-scenario reuse of historical messages.

[0076] Figure 7 A schematic block diagram of a device 700 for user interface interaction is shown. Device 700 can be implemented through software, hardware, or a combination of both. Figure 7 As shown, the device 700 includes a first display module 710, a first receiving module 720, and a second display module 730.

[0077] In some cases, the first display module 710 may be configured to display multiple components on a first interface, the multiple components indicating multiple topics. The first receiving module 720 may be configured to receive a first operation, the first operation being directed to a first component among the multiple components, the first component corresponding to a first topic. The second display module 730 may be configured to display a first message set associated with the first topic on a second interface, the first message set being associated with the first topic and including one or more messages interacting with the intelligent system.

[0078] In some cases, the first message set is associated with a first object, or the semantics of the first message set is associated with a first topic.

[0079] In some cases, the first message set includes messages based on multiple interaction points within a first time period.

[0080] In some cases, the device 700 further includes a second message display module configured to display a second message set on a first interface, wherein the second message set includes messages generated within the most recent time period, and the second message set is displayed as a single message.

[0081] In some cases, the first message set is associated with a first object, and the device 700 further includes: a second component module configured to display a second component on a first interface, wherein the second component corresponds to a second topic, the second topic is associated with a third message set, the third message set is associated with the first object, and the third message set comes from messages generated within a second time period, the second time period being different from the first time period.

[0082] In some cases, the first topic includes first information and second information, where the first information indicates the task corresponding to the first message set and the second information indicates the description of the task.

[0083] In some cases, the device 700 further includes: a second receiving module configured to receive a third operation associated with the first component; and a deletion module configured to delete the first component.

[0084] In some cases, the device 700 further includes: a fourth operation module configured to receive a fourth operation associated with the first component; and a referencing module configured to reference the first component in an input area.

[0085] In some cases, the device 700 further includes: a third receiving module configured to receive a third message based on a second interface; and a fourth message module configured to display a fourth message on the second interface, wherein the fourth message is a message obtained by the intelligent system based on a first context and the third message, and the first context includes a first message set.

[0086] In some cases, the first message set is associated with the first media content, and the first context also includes the first media content.

[0087] In some cases, the device 700 further includes: a fourth receiving module configured to receive a fifth operation, wherein the fifth operation is used to switch from a second interface to a first interface; and a fourth display module configured to display a third message and a fourth message on the first interface, wherein the third message references a first component.

[0088] In some cases, at least one of the interactive entry points includes a first interactive entry point configured to trigger the display of a first interface, and the device 700 further includes an update module configured to update a timestamp in response to the display of the first component, wherein the timestamp is the timestamp of the first interactive entry point.

[0089] In some cases, the device 700 further includes: a second operation module configured to receive a second operation associated with the first component; and a top-mount module configured to top the first message set on the first interface.

[0090] In some cases, the device 700 further includes: a sixth operation module configured to receive a sixth operation associated with the first component; and a copy module configured to copy the first message set.

[0091] The division of modules or units in each scenario is illustrative and represents only one logical functional division. In actual implementation, other division methods are possible. Furthermore, the functional units in each scenario can be integrated into one unit, exist as separate physical entities, or combine two or more units into one unit. The integrated units described above can be implemented in hardware or as software functional units.

[0092] Figure 8 A block diagram of electronic device 800 is shown. It should be understood that... Figure 8 The device 800 shown is merely an example and should not be construed as limiting the functionality and scope of the described implementation. For example, device 800 could correspond to... Figure 1A The user equipment described above can be used to perform the above-described... Figures 1A to 6D The process. For example, device 800 may correspond to the electronic device of the third aspect of the invention.

[0093] like Figure 8 As shown, device 800 is in the form of a general-purpose computing device. Components of device 800 may include, but are not limited to, one or more processors or processing units 810, memory 820, storage device 830, one or more communication units 840, one or more input devices 850, and one or more output devices 860. Processing unit 810 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 820. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of device 800.

[0094] Device 800 typically includes multiple computer storage media. Such media can be any available media accessible to device 800, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 820 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof). Storage device 830 can be removable or non-removable media and may include machine-readable media, such as flash drives, disks, or any other media capable of storing information and / or data (e.g., training data for training) and accessible within device 800.

[0095] Device 800 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not explicitly stated... Figure 8 As shown, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks can be provided. In these cases, each drive can be connected to a bus (not shown) via one or more data media interfaces. Memory 820 may include computer program product 825 having one or more program modules configured to perform various methods or actions in various implementations.

[0096] The communication unit 840 enables communication with other computing devices via a communication medium. Additionally, the functionality of the components of device 800 can be implemented as a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, device 800 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.

[0097] Input device 850 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 860 can be one or more output devices, such as a monitor, speaker, printer, etc. Device 800 can also communicate as needed with one or more external devices (not shown) via communication unit 840. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with device 800, or with any device that enables device 800 to communicate with one or more other computing devices (e.g., network card, modem, etc.). Such communication can be performed via an input / output (I / O) interface (not shown).

[0098] Furthermore, a computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the method described above. This computer-readable storage medium may be a non-transitory computer-readable storage medium. Furthermore, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the method described above. Additionally, a computer program product is provided that stores a computer program thereon, which, when executed by a processor, implements the method described above.

[0099] This document describes various aspects of the scenarios with reference to flowcharts and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to the various scenarios. It should be understood that each block of the flowcharts and / or block diagrams, as well as combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0100] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0101] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0102] The flowcharts and block diagrams in the accompanying figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products based on multiple implementations. In this respect, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the figures. For example, two consecutive 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 the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0103] The various scenarios have been described above. The foregoing description is exemplary and not exhaustive, nor is it limited to the disclosed scenarios. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described scenarios. The terminology used is chosen to best explain the principles, practical applications, or technical improvements to technology in the market, or to enable others skilled in the art to understand the scenarios.

Claims

1. A method for user interface interaction, comprising: The first interface displays multiple components, which indicate multiple topics; Receive a first operation, the first operation being directed to a first component among the plurality of components, the first component corresponding to a first topic; as well as The second interface displays a first message set, which is associated with the first topic and includes one or more messages that interact with the intelligent system.

2. The method of claim 1, wherein the first message set is associated with the first object, or the semantics of the first message set is associated with the first topic.

3. The method according to claim 2, wherein the first message set includes messages based on multiple interaction entry points within a first time period.

4. The method according to claim 3, further comprising: The first interface displays a second message set, which includes messages generated within the most recent time period, and the second message set is displayed as a single message.

5. The method of claim 4, wherein the first message set is associated with the first object, and the method further comprises: The first interface displays a second component, wherein the second component corresponds to a second topic, the second topic is associated with a third message set, the third message set is associated with the first object, and the third message set comes from messages generated within a second time period, which is different from the first time period.

6. The method according to claim 3, wherein the plurality of interactive entry points includes a first interactive entry point, the first interactive entry point being configured to trigger the display of the first interface, and the method further includes: In response to the display of the first component, the timestamp is updated, wherein the timestamp is the timestamp of the first interaction entry.

7. The method of claim 6, further comprising: Receive a second operation, which is associated with the first component; as well as The first message set is pinned to the top of the first interface.

8. The method according to claim 1, wherein the first topic includes first information and second information, the first information indicating a task corresponding to the first message set, and the second information indicating a description of the task.

9. The method according to claim 1, further comprising: Receive a third operation, which is associated with the first component; as well as Delete the first component.

10. The method of claim 1, further comprising: Receive a fourth operation, which is associated with the first component; as well as Reference the first component in the input area.

11. The method of claim 1, further comprising: Receive the third message based on the second interface; as well as The second interface displays a fourth message, which is a message obtained by the intelligent system based on the first context and the third message, wherein the first context includes the first message set.

12. The method of claim 11, wherein the first message set is associated with the first media content, and the first context further includes the first media content.

13. The method of claim 11, further comprising: Receive a fifth operation, wherein the fifth operation is used to switch from the second interface to the first interface; as well as The third message and the fourth message are displayed on the first interface, wherein the third message refers to the first component.

14. The method of claim 1, further comprising: Receive a sixth operation, which is associated with the first component; as well as Copy the first message set.

15. A device for interface interaction, comprising: The first display module is configured to display multiple components in a first interface, the multiple components indicating multiple themes; A first receiving module is configured to receive a first operation, the first operation being directed to a first component among the plurality of components, the first component corresponding to a first topic; as well as The second display module is configured to display a first message set in a second interface, the first message set being associated with the first topic and including one or more messages interacting with the intelligent system.

16. An electronic device comprising: At least one processing unit; At least one memory coupled to the at least one processing unit and storing operations to be performed by the at least one processing unit, the operations causing the electronic device to perform the method according to any one of claims 1 to 14 when performed by the at least one processing unit.

17. A computer-readable storage medium having machine-executable instructions stored thereon, which, when executed by a device, cause the device to perform the method according to any one of claims 1-14.

18. A computer program product having a computer program stored thereon, the computer program implementing the method according to any one of claims 1 to 14 when executed by a processor.

Images