Content-based interaction method and device, computer equipment and readable storage medium

Abstract

The invention relates to a content-based interaction method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the steps that a content link item set is displayed, and each content link item in the content link item set is used for responding to content browsing operation to trigger and display linked content; displaying a content abstract acquisition entry in at least one content link item in the content link item set; and in response to a trigger operation for a content abstract acquisition entry displayed by a target content link item in the at least one content link item, displaying a content abstract extracted from the content linked by the target content link item. By adopting the method, continuous occupation of resources of the hardware equipment supporting content abstract display can be reduced, so that resource waste of the hardware equipment is reduced.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a content-based interactive method, apparatus, computer device, computer-readable storage medium, and computer program product. Background Technology

[0002] With the development of computer technology, more and more applications have become widely used, including information-providing applications. These applications are often called news apps or information apps, and they provide users with news, articles, blogs, videos, and other forms of content. Their main purpose is to deliver timely and accurate information to users.

[0003] In traditional technology, news applications typically use information streams to display a series of articles. In response to a user's selection of any article, the corresponding article details page is displayed. If the user wants to view the summary information of the article content on the details page, they need to copy the article content or the link to the article content to another application with summary extraction capabilities, so that the application can extract the summary information of the article content and display it to the user.

[0004] However, traditional methods require users to perform operations such as copying and pasting, and to switch between two application interfaces in order to extract and display the summary information of the article content. This results in a continuous occupation of the resources of the hardware device that supports the content summary display, which is a waste of hardware resources. Summary of the Invention

[0005] Therefore, it is necessary to provide a content-based interaction method, apparatus, computer device, computer-readable storage medium, and computer program product that can reduce the waste of hardware resources in response to the above-mentioned technical problems.

[0006] Firstly, this application provides a content-based interaction method, including:

[0007] Display a set of content link items, each of which is used to trigger the display of the linked content in response to a content browsing operation;

[0008] At least one content link item in the set of content link items displays a content summary retrieval entry point;

[0009] In response to a triggered operation on the content summary retrieval entry displayed by the target content link item in the at least one content link item, a content summary extracted from the content linked by the target content link item is displayed.

[0010] Secondly, this application also provides a content-based interactive device, comprising:

[0011] The link item display module is used to display a set of content link items, wherein each content link item in the set of content link items is used to trigger the display of the linked content in response to a content browsing operation;

[0012] The summary retrieval entry display module is used to display the content summary retrieval entry for at least one content link item in the content link item set.

[0013] The content summary display module is used to display a content summary extracted from the content linked by the target content link in response to a trigger operation on the content summary retrieval entry displayed by the target content link in the at least one content link item.

[0014] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0015] Display a set of content link items, each of which is used to trigger the display of the linked content in response to a content browsing operation;

[0016] At least one content link item in the set of content link items displays a content summary retrieval entry point;

[0017] In response to a triggered operation on the content summary retrieval entry displayed by the target content link item in the at least one content link item, a content summary extracted from the content linked by the target content link item is displayed.

[0018] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0019] Display a set of content link items, each of which is used to trigger the display of the linked content in response to a content browsing operation;

[0020] At least one content link item in the set of content link items displays a content summary retrieval entry point;

[0021] In response to a triggered operation on the content summary retrieval entry displayed by the target content link item in the at least one content link item, a content summary extracted from the content linked by the target content link item is displayed.

[0022] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0023] Display a set of content link items, each of which is used to trigger the display of the linked content in response to a content browsing operation;

[0024] At least one content link item in the set of content link items displays a content summary retrieval entry point;

[0025] In response to a triggered operation on the content summary retrieval entry displayed by the target content link item in the at least one content link item, a content summary extracted from the content linked by the target content link item is displayed.

[0026] The aforementioned content-based interactive method, apparatus, computer device, computer-readable storage medium, and computer program product display a set of content link items. Each content link item in the set is used to trigger the display of linked content in response to a content browsing operation. It can provide users with a content preview for browsing through the content link item set. By displaying a content summary retrieval entry point in at least one content link item in the set, it can provide users with a way to quickly obtain a content summary extracted from the content linked by the content link item when the content link item is displayed. Furthermore, when the user needs to obtain a content summary, in response to a trigger operation on the content summary retrieval entry point displayed for a target content link item in at least one content link item, it can display a content summary extracted from the content linked by the target content link item. Throughout the entire process, while the content link item is displayed, the rapid retrieval and display of the content summary is achieved through the displayed content summary retrieval entry point, which can reduce the continuous occupation of resources of the hardware device supporting content summary display, thereby reducing the waste of hardware resources. Attached Figure Description

[0027] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0028] Figure 1 This is a diagram illustrating an application scenario of a content-based interaction method in one embodiment.

[0029] Figure 2 This is a diagram illustrating the application environment of a content-based interaction method in one embodiment.

[0030] Figure 3 This is a flowchart illustrating a content-based interaction method in one embodiment;

[0031] Figure 4 This is a schematic diagram of a content link item in one embodiment;

[0032] Figure 5 This is a schematic diagram of a set of content link items in one embodiment;

[0033] Figure 6 This is a schematic diagram of a set of content link items in another embodiment;

[0034] Figure 7 This is a schematic diagram illustrating a response to a content browsing operation in one embodiment;

[0035] Figure 8 This is a schematic diagram showing the content summary retrieval entry point in one embodiment;

[0036] Figure 9 This is a schematic diagram showing the content summary retrieval entry point in another embodiment;

[0037] Figure 10 This is a schematic diagram showing a content summary in one embodiment;

[0038] Figure 11 This is a schematic diagram showing the content summary retrieval entry point in yet another embodiment;

[0039] Figure 12 This is a schematic diagram showing the content summary retrieval entry point in another embodiment;

[0040] Figure 13 This is a schematic diagram showing the content summary retrieval entry point in another embodiment;

[0041] Figure 14 This is a schematic diagram showing the content summary retrieval entry point in yet another embodiment;

[0042] Figure 15 This is a schematic diagram showing at least one first recommended content link item in one embodiment;

[0043] Figure 16 This is a schematic diagram showing at least one second recommended content link item in one embodiment;

[0044] Figure 17 This is a schematic diagram showing the question-and-answer interaction area in one embodiment;

[0045] Figure 18 This is a schematic diagram of a content-based interaction method in one embodiment;

[0046] Figure 19 This is a schematic diagram of a content-based interaction method in another embodiment;

[0047] Figure 20This is a flowchart illustrating a content-based interaction method in another embodiment;

[0048] Figure 21 This is a structural block diagram of a content-based interactive device in one embodiment;

[0049] Figure 22 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0051] The content-based interaction method provided in this application can be applied to, for example... Figure 1 In the application scenario shown, terminal 102 is equipped with a client for content-based interaction. This client can be an application for browsing content, a web client, or a sub-application running in the environment of a parent application. Terminal 102 displays a set of content link items. Each content link item in the set is triggered to display the linked content in response to a content browsing operation. At least one content link item in the set displays a content summary retrieval entry. In response to a trigger operation on the content summary retrieval entry displayed for a target content link item in at least one content link item, a content summary extracted from the content linked by the target content link item is displayed. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, projection devices, etc. Portable wearable devices can be smartwatches, smart bracelets, head-mounted devices, etc. Head-mounted devices can be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc.

[0052] The content-based interaction method provided in this application can be applied to, for example... Figure 2In the application environment shown, terminal 202 communicates with server 204 via a network. A data storage system can store the data that server 204 needs to process. The data storage system can be integrated onto server 204 or placed on a cloud or other network server. Terminal 202 obtains a set of content link items from server 204, displays the set of content link items, and each content link item in the set is used to trigger the display of the linked content in response to a content browsing operation. At least one content link item in the set displays a content summary retrieval entry. In response to a trigger operation on the content summary retrieval entry displayed for a target content link item in at least one content link item, terminal 202 obtains a content summary extracted from the content linked by the target content link item from server 204 and displays the content summary.

[0053] The terminal 202 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle systems, and projection devices. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted displays. Head-mounted displays can be virtual reality (VR) devices, augmented reality (AR) devices, and smart glasses. The server 204 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0054] In one exemplary embodiment, such as Figure 3 As shown, a content-based interaction method is provided. This method can be executed by the terminal or the server alone, or by the terminal and the server collaboratively. This method can be applied to... Figure 1 Taking the terminal in the example, the explanation includes the following steps 302 to 306. Wherein:

[0055] Step 302: Display a set of content link items, where each content link item in the set is used to display the linked content in response to a content browsing operation.

[0056] In this context, a content link item set refers to a group of content items with linking properties. Each content link item in the set points to the linked content and is used to trigger the display of the linked content in response to content browsing operations. A content link item is an element that guides a user to jump from one page or view to another. In this embodiment, it is an element that guides the user from the page displaying the content link item set to the page displaying the content linked by the content link item. Content link items can be in text form, such as underlined hyperlinks or descriptive information describing the topic of the linked content. Content link items can also be images or other visual elements, or they can be in a combination of text and images or other visual elements.

[0057] The linked content refers to a specific resource on the network that the content link points to, such as a webpage, article, video, or image. For example, if the linked content is a video, the content link could be an image or other visual element, such as... Figure 4 As shown, a content link item can specifically be a video's thumbnail. For another example, when the linked content is news or information, the content link item can be in text format, such as... Figure 4 As shown, content links can specifically be descriptive information describing the topic of news news, such as the title of the news article. Furthermore, content links can also be in image and text format, such as... Figure 4 As shown, the content link item can specifically be descriptive information about the topic of the news article, including the title of the news article and an image describing the news article, specifically an image within the news article. For example, ... Figure 4 As shown, when the linked content is a novel, the content link can be in the form of an image and text, specifically the novel's cover and synopsis.

[0058] For example, the terminal displays a set of content link items, each of which is used to display the linked content in response to a content browsing operation. In specific applications, each content link item in the set can be displayed in a list, grid, or other layout format, and arranged in order of the popularity index of the content linked to by each content link item.

[0059] The popularity index, also known as the online dissemination popularity index, is an index derived by extracting information related to a specified event, person, brand, or region from massive amounts of information collected from internet platforms, and then standardizing and calculating the extracted information. The popularity index objectively reflects the degree of attention an event, person, brand, or region receives on the internet. In this embodiment, the popularity index is derived by standardizing and calculating the content linked by a content link item based on massive amounts of information collected from internet platforms; this popularity index objectively reflects the degree of attention the content linked by the content link item receives on the internet.

[0060] In practical applications, content link items can be squares, rectangles, circles, etc. This embodiment does not limit the shape of the content link items. For example, taking a rectangular content link item as an example, and displaying each content link item in the set in list format, the displayed set of content link items could be as follows: Figure 5 As shown, these are content links arranged vertically. It should be noted that, as... Figure 5 As shown, when displaying a collection of content link items, there may be content link items that cannot be displayed completely.

[0061] To illustrate further, taking a rectangular set of content links as an example, and displaying each content link item in the set as a list, the displayed set of content link items could be as follows: Figure 6 As shown, this is a list of content links arranged horizontally. It should be noted that, as... Figure 6 As shown, when displaying a collection of content link items, there may be content link items that cannot be displayed completely.

[0062] In specific applications, such as Figure 7 As shown, in the display of a collection of content link items (such as...) Figure 7 In the case shown, including content link item 1, content link item 2, content link item 3, and content link item 4, in response to any content link item (such as...) Figure 7 The diagram shows the content browsing operation for content link item 3. The terminal will display the content linked by content link item 3. Specifically, the content browsing operation for any content link item can be a click operation on any content link item.

[0063] Step 304: Display the content summary retrieval entry for at least one content link item in the content link item set.

[0064] The content summary access point refers to the entry point that allows users to quickly access and view content summaries extracted from the content linked by the content link item.

[0065] For example, when displaying a set of content link items, the terminal will display a content summary retrieval entry point in at least one of the content link items in the set of content link items, so as to instruct the user to quickly access and view the content summary extracted from the content linked by the content link item where the content summary retrieval entry point is located.

[0066] In practical applications, at least one content link item can refer to all content link items in the set of content link items, such as... Figure 8 As shown, each content link item in the content link item set displays a content summary retrieval entry. At least one content link item can also refer to a content link item in the content link item set that meets the condition for displaying the summary retrieval entry. For example... Figure 9 As shown, in the set of content link items, only a portion of the content link items (such as...) Figure 9 As shown, content link items 2 and 3 have access to the content summary; the remaining content link items do not have access to the content summary.

[0067] The summary retrieval entry display conditions refer to the conditions that a content link item must meet when displaying the content summary retrieval entry. These conditions can be configured according to the actual application scenario. For example, the summary retrieval entry display conditions could be that the content link item is the one selected by the user; that is, when a content link item is selected by the user, the terminal will display the content summary retrieval entry on that selected content link item. Another example is that the summary retrieval entry display conditions could be that the content link item is the one whose display duration reaches a preset time; that is, when the display duration of a content link item reaches the preset time, the terminal will display the content summary retrieval entry on that content link item.

[0068] In practical applications, for each content link item in at least one content link item, the content summary retrieval entry can either cover the currently displayed content in the targeted content link item, or it can display in the blank area of ​​the targeted content link item without affecting the currently displayed content in the targeted content link item.

[0069] Step 306: In response to a triggering operation on the content summary retrieval entry displayed for the target content link item in at least one content link item, display the content summary extracted from the content linked by the target content link item.

[0070] Specifically, the triggering operation for the content summary retrieval entry can be one of the following operations: single click, double click, long press, etc.

[0071] For example, if at least one content link item in the content link item set displays a content summary retrieval entry, a user can quickly access and view the content summary extracted from the content linked by the target content link item indicated by the triggering operation by initiating a triggering operation on the content summary retrieval entry displayed by any content link item. In response to the triggering operation on the content summary retrieval entry displayed by the target content link item in at least one content link item, the terminal will display the content summary extracted from the content linked by the target content link item.

[0072] In specific applications, such as Figure 10 As shown, at least one content link item in the content link item set (such as...) Figure 10 As shown in content link item 2 and content link item 3), if a content summary retrieval entry is displayed, in response to the target content link item (such as...) in at least one content link item... Figure 10 The image shows the trigger operation for obtaining the content summary entry displayed by content link item 2). The terminal will display the content summary extracted from the content linked by the target content link item.

[0073] In practical applications, the extracted content summary can be generated using a pre-trained summary generation model. This is achieved by inputting the content linked by the target content link into the pre-trained model. It's important to note that if the target content link is in text format, it can be directly input into the pre-trained model. However, if the target content link is in multimedia format such as video, it's necessary to first obtain the text form of the linked content through multimedia content recognition methods such as speech recognition and subtitle recognition before inputting that text form into the pre-trained model.

[0074] Summarization models are an important technology in the field of natural language processing, capable of extracting key information from long texts and generating concise summaries. In recent years, with the development of deep learning technology, summarization models have made significant progress, especially driven by pre-trained language models (such as BERT (Bidirectional Encoder Representations from Transformers, a pre-trained language representation model based on the Transformer architecture) and GPT (Generative Pre-trained Transformer, a pre-trained language model based on the Transformer architecture)).

[0075] In a specific application, the summary generation model in this embodiment can be either an extractive summary generation model or a generative summary generation model. The extractive summary generation model generates a summary by selecting key sentences or phrases from the original text; in this embodiment, it selects key sentences or phrases from the content linked by the target content links. The generative summary generation model generates a summary by reorganizing language using natural language generation techniques. It should be noted that the pre-trained summary generation model can be trained according to the actual application scenario; this embodiment does not impose specific limitations here.

[0076] The aforementioned content-based interaction method displays a set of content link items. Each content link item in the set is used to trigger the display of the linked content in response to a content browsing operation. This method provides users with a content preview for browsing. By displaying a content summary retrieval entry point in at least one content link item, it provides users with a quick way to obtain a content summary extracted from the content linked by the content link item. Furthermore, when a user needs to obtain a content summary, in response to a trigger operation on the content summary retrieval entry point displayed for a target content link item, the method displays a content summary extracted from the content linked by the target content link item. Throughout this process, while displaying content link items, the method achieves rapid retrieval and display of content summaries through the displayed content summary retrieval entry point, reducing the continuous resource consumption of the hardware device supporting content summary display and thus minimizing hardware resource waste.

[0077] In one exemplary embodiment, displaying a content summary retrieval entry point for at least one content link item in the content link item set includes:

[0078] In response to a selection operation on a content link item in a set of content link items, a content summary retrieval entry is displayed for at least one content link item selected by the selection operation.

[0079] For example, when a set of content link items is displayed, users can select content link items as needed to quickly access and view the content summary extracted from the content linked by the selected content link item. In response to the selection operation for the content link item in the set of content link items, the terminal will display a content summary retrieval entry point for at least one content link item selected by the selection operation.

[0080] In practical applications, a selection action can be understood as a triggered action on a content link, specifically one of the following: single click, double click, long press, etc. It's important to note that selecting a content link and browsing the content are triggered in different ways. For example, if browsing is a single click, the selection action can be a double click or a long press. Similarly, if browsing is a double click, the selection action can be a single click or a long press. And again, if browsing is a long press, the selection action can be a single click or a double click.

[0081] In this embodiment, in response to a selection operation on a content link item in the content link item set, a content summary retrieval entry is displayed for at least one content link item selected by the selection operation. The content summary retrieval entry can be displayed according to the user's intention, and the content summary can be quickly retrieved and displayed through the displayed content summary retrieval entry. This reduces the continuous occupation of resources of the hardware device that supports content summary display, thereby reducing the waste of hardware device resources.

[0082] In one exemplary embodiment, when at least one content link item is selected in the selection operation, displaying a content summary retrieval entry point includes:

[0083] For each of the at least one content link items selected by the selection operation, if the content link item displays content description information describing the topic of the linked content, the content summary retrieval entry will cover the content description information display.

[0084] The theme of the linked content refers to its central concept, which is the main information or argument that the linked content attempts to convey. It can include the following aspects: central idea, keywords, main issues, sentiment, purpose, background information, scope, and perspective. Specifically: Central idea: The main viewpoint or information that the linked content wants to express. Keywords: Words closely related to the theme, usually used to describe or summarize the theme. Main issues: The central problem or topic discussed in the linked content. Sentiment: The emotional tone or attitude expressed by the linked content, such as optimistic, pessimistic, or neutral. Purpose: The purpose or goal of creating the linked content, such as education, persuasion, or entertainment. Background information: The historical, cultural, or situational context provided for understanding the theme. Scope: The range or depth of the theme, which can be a broad discussion or in-depth analysis. Perspective: The specific perspective or stance adopted by the linked content, such as personal experience or professional analysis.

[0085] Content description information refers to information that describes the topic of the linked content. For example, it could be the title of the linked content. Alternatively, it could include the title of the linked content and an image within it; the image could also be called a content description image. It's important to note that content description information can be understood as a summary of the linked content, but it differs from a summary extracted from the linked content. In other words, the information richness of content description information is less than that of the content summary extracted from the linked content; that is, the content summary contains more information than the content description information. Furthermore, the content description information is shorter than the content summary extracted from the linked content.

[0086] For example, for each of the at least one content link items selected by the selection operation, if the content link item displays content description information describing the topic of the linked content, the terminal will overlay the content summary retrieval entry on the content description information display.

[0087] In specific applications, such as Figure 11 As shown, for each content link item (e.g., in the at least one content link item selected by the selection operation) Figure 11 As shown in content link item 2), if the content link item displays content description information describing the topic of the linked content, the terminal will cover the content description information display with the content summary retrieval entry.

[0088] In this embodiment, the content summary retrieval entry point can be highlighted in at least one content link item, allowing users to intuitively view the content summary retrieval entry point and quickly retrieve and display the content summary through the displayed entry point. This reduces the continuous occupation of resources on the hardware device that supports content summary display, thereby reducing the waste of hardware resources.

[0089] In one exemplary embodiment, the content-based interaction method further includes:

[0090] When the content description information includes a content description image, the content summary retrieval entry will cover at least a portion of the content description image displayed in the content description information.

[0091] The content description image refers to an image that describes the linked content; specifically, it can be an image within the linked content. For example, if the linked content is a video, the content description image could be the video's cover image. Similarly, if the linked content is news or information, the content description image could be an image within the news or information. And if the linked content is a novel, the content description image could be the novel's cover.

[0092] For example, when the content description information includes a content description image, the terminal will display at least a portion of the content description image in the content description information by covering the content summary retrieval entry point. In a specific application, the terminal will display the central region of the image in the content description image within the content description information by covering the content summary retrieval entry point.

[0093] The image center region refers to the visual center of the content description image. Specifically, it can be defined as the area centered on the geometric center of the content description image and occupying a predetermined first proportion within the image. This predetermined first proportion can be configured according to the actual application scenario; for example, it could be 25%. It is understood that the image center region is equidistant from the top and bottom of the content description image, and its size is positively correlated with the size of the content description image—the larger the content description image, the larger the image center region; conversely, the smaller the content description image, the smaller the image center region.

[0094] In practical applications, for each of the at least one content link selected by the selection operation, if auxiliary information describing the linked content is displayed in the selected content link, the terminal can also cover the auxiliary information display with the content summary retrieval entry, or display the auxiliary information and the content summary retrieval entry side by side. It can be understood that by displaying the content summary retrieval entry with reference to the area displaying the auxiliary information, the display of the content summary retrieval entry can be achieved while minimizing the impact of the content summary retrieval entry's display on the content description information displayed in the content link.

[0095] In this embodiment, by using this method, the display of the content summary retrieval entry can be achieved while minimizing the impact of the display of the content description information displayed in the content link item. This allows users to intuitively view the content summary retrieval entry and quickly retrieve and display the content summary through the displayed content summary retrieval entry. This reduces the continuous occupation of resources on the hardware device that supports content summary display, thereby reducing the waste of hardware resources.

[0096] In one exemplary embodiment, displaying a content summary retrieval entry point for at least one content link item in the content link item set includes:

[0097] At least one content link in the content link set that has been displayed for a preset duration will display an entry point for obtaining the content summary.

[0098] Dwell time, as a metric for measuring user interaction with content links, refers to the time a user spends on a content link. In this embodiment, dwell time specifically refers to the duration the content link is displayed in the user's field of vision, that is, the duration the content link is displayed on the terminal's screen.

[0099] For example, when a set of content links is displayed, the terminal will count the duration each content link in the set is displayed on the screen. For at least one content link whose display duration reaches a preset duration, a content summary retrieval entry will be displayed. The preset duration can be configured according to the actual application scenario. For example, if the preset duration is 3 seconds, the terminal will display the content summary retrieval entry for at least one content link in the set whose display duration reaches 3 seconds.

[0100] In this embodiment, by displaying a content summary retrieval entry point in the content link item based on the displayed dwell time, the intuitive display of the content summary retrieval entry point can be achieved with full prediction of user intent. In turn, the content summary can be quickly retrieved and displayed through the displayed content summary retrieval entry point, which can reduce the continuous occupation of resources of the hardware device that supports content summary display, thereby reducing the waste of hardware device resources.

[0101] In an exemplary embodiment, for at least one content link item in the content link item set whose dwell time reaches a preset duration, the content summary retrieval entry point includes:

[0102] For each content link item in the content link item set whose dwell time reaches a preset time, if the content link item displays auxiliary information describing the linked content, the content summary retrieval entry will cover the auxiliary information display.

[0103] In this context, "auxiliary information" refers to information displayed in content links, in addition to the content description information, to aid in understanding the linked content. For example, auxiliary information might include details that enhance user understanding or provide additional background, data, analysis, or commentary. For instance, auxiliary information might include information describing the source of the linked content. The source of the linked content refers to its original origin or producer. For example, when the linked content is news, the source might specifically refer to the original website where the linked content was published, the publication time, or the author and publication time of the linked content. For example, auxiliary information might specifically describe the original source or producer of the linked content, the publication time, etc. For example, when the linked content is news, auxiliary information might specifically include the original website where the news was published, the publication time, etc.

[0104] For example, for each content link item in the content link item set whose dwell time reaches a preset time, if the targeted content link item displays auxiliary information describing the linked content, the terminal will cover the auxiliary information display with the content summary retrieval entry.

[0105] In specific applications, such as Figure 12 As shown, for each content link item in the content link item set whose displayed dwell time reaches a preset duration (e.g., ...), Figure 12 As shown in content link item 2), if the target content link item displays auxiliary information describing the linked content, the terminal will cover the auxiliary information display with the content summary retrieval entry.

[0106] In this embodiment, by displaying the content summary retrieval entry point with reference to the area displaying auxiliary information, the display of the content summary retrieval entry point can be achieved while minimizing the impact of its display on the information displayed in the content link items.

[0107] In an exemplary embodiment, for at least one content link item in the content link item set whose dwell time reaches a preset duration, the content summary retrieval entry point includes:

[0108] For each content link item in the content link item set that has a dwell time of at least one preset duration, if the content link item displays auxiliary information describing the linked content, the auxiliary information and the content summary access point are displayed side by side.

[0109] For example, for each content link item in the set of content links that has a display duration of at least one preset duration, if the targeted content link item displays auxiliary information describing the linked content, the terminal will display the auxiliary information and the content summary retrieval entry side by side. In specific applications, the content summary retrieval entry can be displayed to the right of the auxiliary information or to the left of the auxiliary information.

[0110] In practical applications, for example, the content summary retrieval entry can be displayed on the right side of the auxiliary information, such as... Figure 13 As shown, in the targeted content link item (such as...) Figure 13 If the content link item 2 shown contains auxiliary information describing the linked content, the terminal will display the content summary retrieval entry on the right side of the auxiliary information.

[0111] In this embodiment, by displaying the content summary retrieval entry point with reference to the area displaying auxiliary information, the display of the content summary retrieval entry point can be achieved while minimizing the impact of its display on the information displayed in the content link items.

[0112] In one exemplary embodiment, the content-based interaction method further includes:

[0113] For each content link item in the content link item set whose dwell time reaches a preset time, if the targeted content link item displays a content description image describing the topic of the linked content, the content summary retrieval entry will cover at least a portion of the display of the content description image.

[0114] For example, for each content link item in the set of content link items whose dwell time reaches a preset duration, if the targeted content link item displays a content description image describing the topic of the linked content, the terminal will display at least a portion of the content description image in the content description information overlaid by the content summary retrieval entry. In a specific application, the terminal will display the central region of the image in the content description image overlaid by the content summary retrieval entry.

[0115] In specific applications, such as Figure 14 As shown, assuming the targeted content link item is content link item 2, if the targeted content link item displays a content description image describing the topic of the linked content, the terminal will cover at least a portion of the content description image in the content description information with the content summary retrieval entry.

[0116] In this embodiment, by using this method, the display of the content summary retrieval entry can be achieved while minimizing the impact of the display of the content description information displayed in the content link item. This allows users to intuitively view the content summary retrieval entry and quickly retrieve and display the content summary through the displayed content summary retrieval entry. This reduces the continuous occupation of resources on the hardware device that supports content summary display, thereby reducing the waste of hardware resources.

[0117] In an exemplary embodiment, for at least one content link item in the content link item set whose dwell time reaches a preset duration, the content summary retrieval entry point includes:

[0118] At least one content link item that is located in the center of the content link item collection and whose display duration reaches a preset duration will display a content summary retrieval entry.

[0119] The "collection center display area" refers to the visual center of the collection of content links. Specifically, it can be the area centered on the collection center position and occupying a predetermined second proportion within the collection of content links. The collection center position can specifically refer to the geometric center of the collection of content links. For example, when the collection of content links is displayed in full-screen mode, the collection center position can be the center of the screen. The predetermined second proportion can be configured according to the actual application scenario; for example, it could be 25%.

[0120] It is understandable that the center display area of ​​the collection is equidistant from the top and bottom of the content link item collection, and the size of the center display area is positively correlated with the size of the display area of ​​the content link item collection. That is, the larger the display area of ​​the content link item collection, the larger the center display area, and the smaller the display area of ​​the content link item collection, the smaller the center display area.

[0121] For example, when a set of content link items is displayed, the terminal obtains the screen coordinates of each content link item in the set. Based on the screen coordinates, it determines at least one content link item within the central display area of ​​the set and counts the display duration of each content link item on the screen. For the at least one content link item within the central display area that has a display duration of at least 3 seconds, the terminal displays the content summary retrieval entry point for that content link item.

[0122] In this embodiment, by displaying a content summary retrieval entry point in the content link item based on the central display area and the display dwell time, the intuitive display of the content summary retrieval entry point can be achieved with full prediction of user intent. In this way, the content summary can be quickly retrieved and displayed through the displayed content summary retrieval entry point, which can reduce the continuous occupation of resources of the hardware device that supports content summary display, thereby reducing the waste of hardware device resources.

[0123] In an exemplary embodiment, for at least one content link item in the content link item set that is located in the central display area of ​​the set and whose display dwell time reaches a preset duration, the content summary retrieval entry point includes:

[0124] Get the screen coordinates of each content link item in the set of content link items, and determine at least one content link item in the center display area of ​​the set based on the screen coordinates.

[0125] For at least one content link item, create a timed task with a preset execution delay;

[0126] For each of the at least one content link items, when the displayed dwell time reaches the preset duration, the corresponding delay task for the targeted content link item is executed so that the content summary retrieval entry is displayed on the targeted content link item without changing the screen coordinate position of the targeted content link item.

[0127] Delayed tasks refer to tasks or operations that are executed after a specific delay. In this embodiment, it refers to tasks executed after a preset time has elapsed since creation. The screen coordinate position of a content link item refers to its display position on the terminal's screen, which can be represented by a pair of coordinate values ​​and the width and height of the content link item. For example, the screen coordinate position can be in the form of (x, y, w, h), where x and y are a pair of coordinate values ​​representing the origin of the content link item. In this embodiment, the origin of the content link item can be configured according to the actual application scenario; for example, the origin can be the top-left corner, top-right corner, etc. of the content link item. x represents the horizontal position, and y represents the vertical position. w is the width of the content link item, and h is the height of the content link item.

[0128] It should be noted that the coordinate values, width, and height in this embodiment are all measured in pixels. Specifically, the origin of the content link item is x pixels away from the origin of the coordinate system in the horizontal direction and y pixels away in the vertical direction. The width of the content link item is w pixels, and the height is h pixels. The origin of the coordinate system can be configured according to the actual application scenario; for example, the origin can be the top-left corner or top-right corner of the screen.

[0129] For example, the terminal obtains the screen coordinate position of each content link item in the content link item set, determines the set center position of the content link item set based on the screen coordinate position, determines the set center display area in the content link item set based on the set center position and a preset second ratio, and finally determines at least one content link item located within the set center display area by comparing the set center display area with the screen coordinate position of each content link item.

[0130] For example, when at least one content link item is identified, the terminal creates a delayed task with a preset execution delay for each of the at least one content link item. This delayed task allows the display of a content summary retrieval entry point on each of the at least one content link item. For each of the at least one content link item, starting from the creation of the delayed task, when the displayed dwell time reaches the preset duration, the corresponding delayed task for that content link item is executed. It is then determined whether the screen coordinate position of the targeted content link item has changed. If the screen coordinate position of the targeted content link item has not changed, the content summary retrieval entry point is displayed on that content link item. In other words, the function of the delayed task is to allow the display of the content summary retrieval entry point on the targeted content link item if the screen coordinate position of the targeted content link item has not changed and remains within the central display area of ​​the collection.

[0131] In this embodiment, by utilizing the screen coordinates of each content link item in the content link item set, it is possible to determine at least one content link item located in the central display area of ​​the set. Furthermore, by creating a delayed task with a preset execution delay for each of the at least one content link item, and using the delayed task to control whether the content summary retrieval entry is displayed for the content link item, it is possible to accurately display the content summary retrieval entry while accurately predicting the user's intent.

[0132] In one exemplary embodiment, the content-based interaction method further includes:

[0133] If a delayed task with a preset execution delay is created for at least one content link item, the delayed task with the preset execution delay created for each of the at least one content link item is canceled in response to a content update operation.

[0134] The "display content update operation" refers to the operation of updating the set of displayed content links. For example, a display content update operation can specifically be a swipe operation triggered on the set of content links. This swipe operation instructs the display set of content links to be updated in the direction indicated by the swipe. For instance, an upward swipe operation instructs the display set of content links to be updated by swiping upwards. Similarly, a downward swipe operation instructs the display set of content links to be updated by swiping downwards.

[0135] It should be noted that updating the set of displayed content links means updating at least a portion of the content links in the set, causing at least a portion of the content links to be de-displayed and displaying other content links. For example, if the content link set contains content link 1, content link 2, content link 3, and content link 4, in response to the display content update operation, the terminal will update at least a portion of the content link set, causing content link 1 and content link 2 to be de-displayed and content link 5 and content link 6 to be displayed. That is, at this time, the content link set contains content link 3, content link 4, content link 5, and content link 6.

[0136] For example, when a delayed task with a preset execution delay is created for at least one content link item, the terminal monitors the user's display content update operation. When the user triggers the display content update operation, the terminal cancels the delayed task with the preset execution delay created for at least one content link item in response to the display content update operation.

[0137] Understandably, if a user triggers a content update operation, indicating that the user intends to view other content links besides the currently displayed content link, the terminal can determine that the user does not need to quickly access and view the content summary extracted from the content linked by the currently displayed content link. Therefore, the terminal will cancel the delayed tasks with the preset execution delay created for each of the at least one content link.

[0138] In this embodiment, by responding to the display content update operation, the delayed tasks with a preset execution delay created for at least one content link item are canceled. The display content update operation can be used to control whether the delayed tasks are executed. In this way, by canceling the delayed tasks, the display control of the content summary acquisition entry can be achieved when the user's intention is accurately predicted. This can reduce the continuous occupation of the resources of the hardware device that supports the display of the content summary, thereby reducing the waste of hardware device resources.

[0139] In one exemplary embodiment, the content-based interaction method further includes:

[0140] If at least one content link item in the content link item set displays a summary retrieval entry, the summary retrieval entry is deselected in response to a content update operation.

[0141] For example, if at least one content link item in the content link item set displays a summary retrieval entry, the terminal monitors the user's content update operation. When the user triggers a content update operation, the terminal cancels the display of the summary retrieval entry in response to the content update operation. It is understood that if, when at least one content link item in the content link item set displays a summary retrieval entry, the user triggers a content update operation, indicating an intention to view other content link items besides the currently displayed content link item, the terminal can determine that the user does not need to further access and view the content summary extracted from the content linked by the content link item where the summary retrieval entry is located through the summary retrieval entry. Therefore, the terminal cancels the display of the summary retrieval entry.

[0142] In this embodiment, by canceling the display summary acquisition entry in response to the display content update operation, the display content update operation can be used to achieve display control of the content summary acquisition entry when the user's intention is accurately predicted. This can reduce the continuous occupation of resources of the hardware device that supports content summary display, thereby reducing the waste of hardware device resources.

[0143] In one exemplary embodiment, the content-based interaction method further includes:

[0144] When displaying a content summary extracted from the content linked by the target content link, at least one first recommended content link associated with the content linked by the target content link is displayed; the content linked by the first recommended content link and the content linked by the target content link belong to the same technical field.

[0145] In response to a first selection operation on any first recommended content link item, display the content linked to the first recommended content link item selected by the first selection operation.

[0146] The first recommended content link is a type of content link recommended to users, whose linked content and the target content link belong to the same technical field. Here, "linked content belonging to the same technical field" means that the content linked by the first recommended content link and the content linked by the target content link belong to the same technical field, sharing a specific theme, discipline, or area of ​​interest.

[0147] It should be noted that the technical field can be defined at different levels based on its scope and specificity, ranging from a narrow, specific technical field to a broad, general field. For example, the technical field in this embodiment can refer to broad fields such as basic science, engineering disciplines, computer science, and information technology. Alternatively, the technical field in this embodiment can also refer to a narrow, specific technical field such as artificial intelligence, big data analytics, cloud computing, and the Internet of Things.

[0148] For example, when displaying a content summary extracted from the content linked by the target content link, the terminal will display at least one first recommended content link associated with the content linked by the target content link. The content linked by the first recommended content link and the content linked by the target content link belong to the same technical field. If a user wants to view the content linked by any first recommended content link, a first selection operation can be triggered on any first recommended content link. In response to the first selection operation on any first recommended content link, the terminal will display the content linked by the first recommended content link selected by the first selection operation.

[0149] In specific applications, such as Figure 15 As shown, taking the linked content as an example, where the linked content belongs to the same technical field, and that technical field is computer science, the content summary extracted from the content linked by the target content item is as follows: Figure 15 In the scenario shown, the terminal will display at least one first recommended content link associated with the content linked to the target content link (e.g., ...). Figure 15 As shown, there are three links, with the first link linking to chip-related content, and the second and third links linking to artificial intelligence-related content. Furthermore, a switching entry is displayed below at least one of the recommended content links, allowing users to switch between displaying different recommended content links.

[0150] In this embodiment, by doing so, related content belonging to the same technical field can be provided to users while they are viewing the content summary, so that users can consume more extensive and in-depth content and improve the efficiency of content consumption.

[0151] In one exemplary embodiment, the content-based interaction method further includes:

[0152] When displaying a content summary extracted from the content linked from the target content link, at least one second recommended content link associated with the content summary is displayed; the second recommended content link displays prediction question information associated with the content summary.

[0153] In response to a second selection operation on any second recommended content link item, display the content linked to the second recommended content link item selected by the second selection operation;

[0154] The selected second recommended content link item displays the answer information corresponding to the predicted question information.

[0155] The second recommended content link item is a type of content link recommended to users. This second recommended content link item displays predicted question information related to the content summary. This predicted question information refers to questions that users are predicted to ask based on the content summary. For example, the predicted question information could specifically be questions about proper nouns appearing in the content summary. Or, it could specifically be questions about problems present in the content summary.

[0156] For example, when displaying a content summary extracted from the content linked by the target content link, the terminal displays at least one second recommended content link associated with the content summary. The second recommended content link displays prediction question information associated with the content summary. If the user wants to view the answer information corresponding to the prediction question information displayed in any second recommended content link, a second selection operation can be triggered on any second recommended content link. In response to the second selection operation on any second recommended content link, the terminal displays the content linked by the second recommended content link selected by the second selection operation. In the content linked by the selected second recommended content link, the answer information corresponding to the prediction question information is displayed.

[0157] In practical applications, the predicted question information can be generated based on a pre-trained question prediction model. This model predicts potential questions or text-related inquiries based on given text content. In this embodiment, the question prediction model predicts potential questions or text-related inquiries from the user based on the content summary.

[0158] The pre-trained question prediction model can be trained according to the actual application scenario; this embodiment does not impose specific limitations. The key technologies and methods for constructing the question prediction model mainly include: First, text understanding. The question prediction model needs to understand the meaning of the input text, which typically involves word embeddings and contextual understanding, and may also use pre-trained models like BERT to obtain deep language representations. Second, attention mechanisms. Through attention mechanisms, the question prediction model can identify key information in the text, which is particularly important for predicting relevant questions because it helps the model focus on the parts of the text most relevant to question generation. Third, sequence generation models. Sequence generation models are needed to process sequential data and generate coherent question sequences. During training, the sequence generation model learns patterns in the text and generates possible questions during the prediction phase.

[0159] In specific applications, content summaries, such as... Figure 16 For example, if the content summary includes a basic introduction to the principles, applications, and development prospects of GPT technology, then at least one second recommended content link associated with the content summary can be as follows: Figure 16 As shown ( Figure 16 The middle section contains three links to the second recommended content. Within these links, information about predicted questions related to the content summary is displayed. Figure 16 The topics covered include "A detailed introduction to the era of large models," "How will the development of AI (Artificial Intelligence) affect our lives," and "How to view the development prospects of AI in China."

[0160] In this embodiment, this method can predict the questions that users may ask while viewing the content summary, allowing users to quickly understand the content related to the summary, facilitating broader and deeper content consumption, and improving content consumption efficiency.

[0161] In one exemplary embodiment, the content-based interaction method further includes:

[0162] When displaying a content summary extracted from the content linked from the target content link item, a question-and-answer interaction area is displayed;

[0163] In response to a question input triggered in the question-and-answer interaction area, display the entered question information;

[0164] In response to the end of question input triggered in the question-and-answer interaction area, the answer information corresponding to the entered question information is displayed.

[0165] The question-and-answer interaction area refers to the area where users can interact by entering question information.

[0166] For example, when displaying a content summary extracted from the content linked from the target content link, the terminal displays a question-and-answer interaction area, allowing users to continue asking questions about the content after viewing the summary, thus enabling broader and deeper content consumption. When a user needs to continue asking questions about the content, they can trigger a question input trigger operation in the question-and-answer interaction area. In response, the terminal displays the entered question information. Once the user confirms that the entered question information is correct, they can trigger a question input end operation in the question-and-answer interaction area. In response, the terminal displays the answer information corresponding to the entered question.

[0167] In practical applications, the question-and-answer interaction area includes a first area indicating voice input for asking questions and a second area indicating text input for asking questions. The question input trigger can be triggered at any location within the interaction area. In response to a user's question input trigger within the interaction area, the terminal displays a question information input control. Furthermore, in response to a user's input of a question into the question information input control, the terminal displays the entered question information. Moreover, in response to triggering actions in areas within the interaction area indicating different question formats, the terminal can display different question information input controls.

[0168] For example, in response to a trigger operation on the first area of ​​the question-and-answer interaction zone that indicates voice input, the terminal will display a question information input control for voice input. With the question information input control displayed, the user can initiate a trigger operation on the control to begin voice input, and upon ending voice input, initiate a second trigger operation on the control. In response to this second trigger operation, the terminal will convert the user's voice input into text and display the entered question information, i.e., the converted text.

[0169] For example, in response to a triggering operation in the second area of ​​the question-and-answer interaction area that indicates the input text for asking a question, the terminal will display a question information input control for inputting text. This question information input control can be a virtual keyboard or other virtual input tool. When a virtual keyboard is displayed, the user can use the virtual keyboard to input question information. While the user is using the virtual keyboard to input question information, the terminal will display the question information input through the virtual keyboard in real time, that is, display the input question information.

[0170] In practical applications, the answer information corresponding to the input question can be generated by a pre-trained answer generation model. This model can automatically generate a suitable answer based on the given question. In this embodiment, the answer information can be automatically generated based on the input information. The pre-trained answer generation model can be trained according to the actual application scenario; this embodiment does not impose specific limitations. The key technologies and methods for constructing the answer generation model mainly include: First, question understanding. The answer generation model first needs to understand the intent and context of the question, which typically involves text preprocessing, part-of-speech tagging, and named entity recognition. Second, information retrieval. In some cases, the answer generation model may need to retrieve relevant information from a large amount of text, requiring the use of search engine technology or knowledge-based retrieval systems. Third, semantic matching. The answer generation model needs to be able to identify the semantic relationship between the question and the answer, which may involve semantic similarity calculation or vector space models. Fourth, deep learning. The answer generation model typically uses deep learning techniques, such as recurrent neural networks (RNNs), long short-term memory networks (LSTMs), or Transformer architectures to capture deep-level features of the text. Fifth, sequence generation. Answer generation can be viewed as a sequence generation task; the answer generation model needs to generate coherent and grammatically correct text sequences. This typically involves decoding algorithms, such as beam search or sampling methods.

[0171] In specific applications, such as Figure 17 As shown, when displaying a content summary extracted from the content linked from the target content link, the terminal will display a question-and-answer interaction area, allowing users to continue asking questions about the content after viewing the summary, thereby consuming the content more broadly and in-depth.

[0172] In this embodiment, this approach allows users to ask questions while viewing content summaries, and displays corresponding answers based on the user's input. This enables users to consume content more broadly and deeply, thereby improving content consumption efficiency.

[0173] In an exemplary embodiment, the content-based interaction method of this application is described using an information application that provides information in a terminal as an example.

[0174] The inventors believe that traditional methods, which require users to first access the article details page before obtaining the content summary, suffer from a lengthy content summary retrieval process and prevent further in-depth consumption of the article's related topics. This leads to a break in the continuous consumption path. Therefore, this application provides a content-based interaction method. Applying this method to news applications provides a way to quickly access the main interface and obtain the content summary within the news feed interface without entering the article details page. This shortens the content summary retrieval process, allowing users to quickly obtain the summary from the news feed filter list (i.e., the set of content links) without having to enter the details page, thus improving content consumption efficiency. Furthermore, this method facilitates continuous consumption; after obtaining the content summary, users can continue to ask questions related to the article or topic on the page displaying the summary, thus enabling broader and deeper consumption. This embodiment provides two methods for displaying the content summary, each described below.

[0175] In specific applications, such as Figure 18 As shown, the terminal displays an information feed filter list (i.e., a set of content links). Each article item (i.e., a content link) in the information feed filter list is used to trigger the display of the linked article content in response to a content browsing operation. This is in response to the user's selection of any article item (e.g., ...). Figure 18 The image shows the selection operation for article item 3). The terminal will display a content summary retrieval entry for article item 3 selected in the selection operation. Further, as... Figure 18 As shown, article item 3 displays a content description of the linked content's topic. The terminal will overlay the content description information with the content summary retrieval entry. In response to a trigger operation on the content summary retrieval entry displayed in article item 3, the terminal will display a content summary extracted from the content linked from article item 3.

[0176] In a specific application, such as Figure 18As shown, in response to a trigger operation targeting the content summary retrieval entry point displayed for article 3, the terminal displays an intelligent agent dialogue page. This page displays a content summary extracted from the content linked to article 3, at least one first recommended content link associated with the content linked to article 3, at least one second recommended content link associated with the content summary, and a question-and-answer interaction area. The content linked to by the first recommended content link belongs to the same technical field as the content linked to article 3. The second recommended content link displays predicted question information associated with the content summary. The question-and-answer interaction area allows users to ask questions. In response to a user's question input trigger operation in the question-and-answer interaction area, the terminal displays the entered question information. In response to a user's question input end trigger operation in the question-and-answer interaction area, the terminal displays the answer information corresponding to the entered question information.

[0177] The intelligent agent dialogue page refers to a page that allows users to interact and converse with an intelligent agent. This page can be embedded in news applications to provide various services and information. In this embodiment, the intelligent agent can be a chatbot, a virtual assistant, or other forms of artificial intelligence. The main features of the intelligent agent dialogue page include: Interactive interface: Providing a text input box and / or voice input functionality, allowing users to communicate with the intelligent agent. Real-time feedback: The intelligent agent can respond to user input questions or commands in real time and display answers or feedback on the dialogue page. Multi-turn dialogue: Supporting continuous multi-turn dialogues with users to complete more complex tasks or provide more detailed information. Personalized experience: The intelligent agent can provide personalized responses based on the user's historical interactions, preference settings, or current context. Contextual understanding: Able to understand the context of the dialogue, making the conversation more natural and coherent. Problem solving: The intelligent agent can understand user problems and provide solutions, whether for frequently asked questions or more complex problem-solving. Information retrieval: Access to a large amount of information and databases, providing users with accurate data and information. Language processing: Possessing natural language processing capabilities, capable of understanding and generating natural language text. User Guidance: Guided questions and suggestions help users communicate more effectively with the agent. Ease of Use: A clean and intuitive design allows for easy use by all types of users. Feedback Mechanism: Allows users to provide feedback, which the agent can then use to learn and improve. Security and Privacy Protection: Ensures the security of user data and complies with relevant privacy regulations. Accessibility: The dialogue page should consider the needs of different users, including those with visual, hearing, or motor impairments. Service Integration: It can be integrated with other services or applications to provide a seamless user experience. Multilingual Support: To serve global users, the agent dialogue page may support multiple languages.

[0178] In specific applications, such as Figure 19As shown, the terminal displays an information feed filter list (i.e., a collection of content links). Each article item (i.e., a content link) in the information feed filter list is used to trigger the display of the linked article content in response to a content browsing operation. If the user has not selected an article item, and there is at least one article item in the information feed filter list that is located in the center display area of ​​the list (i.e., the center display area of ​​the collection) and whose display duration reaches a preset duration (e.g., ...), the link will be displayed. Figure 19 As shown in article item 3), the terminal will display the content summary retrieval entry for article item 3.

[0179] In a specific application, such as Figure 19 As shown, the content-based interaction method of this application provides three ways to display the content summary retrieval entry in article item 3. One method involves displaying auxiliary information describing the linked content (such as...) in article item 3. Figure 19 In the case where the linked content's original website (name), number of comments (4 comments), and publication time (3 hours ago, where the publication time is the difference from the current time) are displayed, the terminal will cover the auxiliary information display with the content summary retrieval entry. In the second method, if auxiliary information describing the linked content is displayed in article item 3, the terminal will display the auxiliary information and the content summary retrieval entry side-by-side. In the third method, if article item 3 displays a content description image describing the topic of the linked content, the terminal will cover at least a portion of the content description image with the content summary retrieval entry.

[0180] In a specific application, such as Figure 19 As shown, in response to a trigger operation targeting the content summary retrieval entry point displayed for article 3, the terminal displays an intelligent agent dialogue page. This page displays a content summary extracted from the content linked to article 3, at least one first recommended content link associated with the content linked to article 3, at least one second recommended content link associated with the content summary, and a question-and-answer interaction area. The content linked to by the first recommended content link belongs to the same technical field as the content linked to article 3. The second recommended content link displays predicted question information associated with the content summary. The question-and-answer interaction area allows users to ask questions. In response to a user's question input trigger operation in the question-and-answer interaction area, the terminal displays the entered question information. In response to a user's question input end trigger operation in the question-and-answer interaction area, the terminal displays the answer information corresponding to the entered question information.

[0181] In a specific application, such as Figure 20 The technical implementation flow of the content-based interaction method of this application is illustrated below. Specifically, it includes the following key parts:

[0182] First, list item selection event handling: For article items displayed in the information feed filter list, if the user selects any displayed article item when the information feed filter list stops scrolling, a content summary access point will be displayed for the selected article item. Here, the list item refers to the article item, and the selection operation can be a long press operation on an article item.

[0183] Second, the handling of list item dwell position and exposure: When the information feed filter list stops scrolling, based on the actual coordinate position (i.e., screen coordinate position) of the list view in the cached view of each article item on the page, it is determined whether the article item is in the center position of the information feed filter list (i.e., the collection center display area). If it is in the center position, a delayed task is thrown in the UI (User Interface) thread with a delay of a preset time (specifically 3 seconds). When the delayed task is executed, if the current position of the list view has not changed and is still in the center position, the content summary retrieval entry is allowed to appear. If there is a scrolling event callback in the information feed filter list within the preset time (i.e., the display content update operation is triggered), the delayed task is canceled.

[0184] Thirdly, the handling of content summary retrieval entry style changes: The technical solution of this application provides two styles of content summary retrieval entry points in the auxiliary information section through a tag experiment platform. These styles can be randomly displayed to users based on experimental control. If the user selects experiment group A, the content summary retrieval entry point will completely cover the auxiliary information. This style requires the UI level of the content summary retrieval entry point to be above the auxiliary information. If the user selects experiment group B, the content summary retrieval entry point will be displayed side-by-side with the auxiliary information, appearing after the auxiliary information, with the UI level being the same as the auxiliary information. The text is inserted in the form of tags (used to insert text with applicable styles or to mark text as elements with specific attributes). Furthermore, the technical solution of this application also provides a third style for the content summary retrieval entry point. Specifically, if the user selects experimental group C, and the article item's style is text plus an image (specifically, it can be text on the left and image on the right, or image on the left and text on the right), the content summary retrieval entry point is displayed in the middle of the image (i.e., the content description image) shown in the article item, with the UI layer located above the image.

[0185] Fourth, the process of redirecting to the intelligent agent dialogue page when the content summary retrieval entry is triggered: In response to the trigger operation of the content summary retrieval entry displayed for the target article item, the terminal will enter the intelligent agent dialogue page. On the intelligent agent dialogue page, the content summary extracted from the content linked to the target article item is displayed. At this time, the terminal will also carry over the relevant information of the article that needs to be synchronized (including but not limited to the article title, author, publication time, related tags, etc.) to facilitate a more accurate content summary generated by the intelligent agent.

[0186] It is understandable that the content-based interaction method provided in this application can enrich the types of content summary access points displayed in article items, reduce the cost for users to obtain content summaries, and improve the efficiency of user content consumption.

[0187] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0188] Based on the same inventive concept, this application also provides a content-based interaction device for implementing the content-based interaction method described above. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations in one or more content-based interaction device embodiments provided below can be found in the limitations of the content-based interaction method described above, and will not be repeated here.

[0189] In one exemplary embodiment, such as Figure 21 As shown, a content-based interactive device is provided, including: a link item display module 2102, a summary acquisition entry display module 2104, and a content summary display module 2106, wherein:

[0190] The link item display module 2102 is used to display a set of content link items, and each content link item in the set of content link items is used to trigger the display of the linked content in response to a content browsing operation;

[0191] Summary retrieval entry display module 2104 is used to display the content summary retrieval entry for at least one content link item in the content link item set;

[0192] The content summary display module 2106 is used to display a content summary extracted from the content linked by the target content link item in response to a trigger operation on the content summary retrieval entry displayed by the target content link item in at least one content link item.

[0193] The aforementioned content-based interactive device displays a set of content link items. Each content link item in the set is used to trigger the display of the linked content in response to a content browsing operation. It can provide users with a content preview for browsing through the content link item set. By displaying a content summary retrieval entry point in at least one content link item in the set, it provides users with a way to quickly obtain a content summary extracted from the content linked by the content link item while the content link item is displayed. Furthermore, when the user needs to obtain a content summary, in response to a trigger operation on the content summary retrieval entry point displayed for a target content link item, it displays a content summary extracted from the content linked by the target content link item. Throughout this process, while the content link item is displayed, the display of the content summary retrieval entry point enables rapid retrieval and display of the content summary, reducing the continuous occupation of resources on the hardware device supporting content summary display, thereby reducing resource waste on the hardware device.

[0194] In an exemplary embodiment, the summary retrieval entry display module is further configured to, in response to a selection operation for a content link item in the content link item set, display a content summary retrieval entry for at least one content link item selected by the selection operation.

[0195] In an exemplary embodiment, the summary retrieval entry display module is further configured to, for each of the at least one content link items selected by the selection operation, display the content summary retrieval entry over the content description information if the content description information describing the linked content is displayed in the targeted content link item.

[0196] In an exemplary embodiment, the summary retrieval entry display module is further configured to, when the content description information contains a content description image, cover at least a portion of the content description image in the content description information with the content summary retrieval entry.

[0197] In an exemplary embodiment, the summary retrieval entry display module is further configured to display a content summary retrieval entry for at least one content link item in the content link item set whose dwell time reaches a preset duration.

[0198] In an exemplary embodiment, the summary retrieval entry display module is further configured to, for each of at least one content link item in the content link item set whose dwell time reaches a preset time, if auxiliary information describing the linked content is displayed in the targeted content link item, cover the auxiliary information display with the content summary retrieval entry.

[0199] In an exemplary embodiment, the summary retrieval entry display module is further configured to, for each of at least one content link item in the content link item set whose dwell time reaches a preset duration, display auxiliary information and the content summary retrieval entry side by side, provided that auxiliary information describing the linked content is displayed in the targeted content link item.

[0200] In an exemplary embodiment, the summary retrieval entry display module is further configured to, for each of at least one content link item in the content link item set whose dwell time reaches a preset duration, cover at least a portion of the display of the content description image with the content summary retrieval entry if the content link item displays a content description image describing the topic of the linked content.

[0201] In an exemplary embodiment, the summary retrieval entry display module is further configured to display a content summary retrieval entry for at least one content link item in the content link item set that is located in the central display area of ​​the set and whose display dwell time reaches a preset duration.

[0202] In an exemplary embodiment, the summary acquisition entry display module is further configured to acquire the screen coordinate position of each content link item in the content link item set, determine at least one content link item located in the central display area of ​​the set based on the screen coordinate position, create a delay task with an execution delay of a preset duration for each of the at least one content link item, and execute the corresponding delay task for each content link item when the display dwell time reaches the preset duration, so as to display the content summary acquisition entry on the content link item without changing the screen coordinate position of the content link item.

[0203] In an exemplary embodiment, the summary acquisition entry display module is further configured to, in response to a display content update operation, cancel the delayed tasks with a preset execution delay created for each of the at least one content link item when a delayed task with a preset execution delay is created for each of the at least one content link item.

[0204] In an exemplary embodiment, the summary retrieval entry display module is further configured to, in response to a content update operation, cancel the display of the summary retrieval entry when at least one content link item in the content link item set displays a summary retrieval entry.

[0205] In an exemplary embodiment, the content-based interactive device further includes a recommendation display module, which is configured to display at least one first recommended content link associated with the content linked by the target content link when displaying a content summary extracted from the content linked by the target content link, wherein the content linked by the first recommended content link and the content linked by the target content link belong to the same technical field, and in response to a first selection operation on any first recommended content link, display the content linked by the first recommended content link selected by the first selection operation.

[0206] In an exemplary embodiment, the recommendation item display module is further configured to, when displaying a content summary extracted from the content linked by the target content link item, display at least one second recommended content link item associated with the content summary, wherein the second recommended content link item displays prediction question information associated with the content summary; in response to a second selection operation on any second recommended content link item, display the content linked by the second recommended content link item selected by the second selection operation, and display the answer information corresponding to the prediction question information in the content linked by the selected second recommended content link item.

[0207] In one exemplary embodiment, the content-based interactive device further includes a question-and-answer interaction module, which is configured to display a question-and-answer interaction area when displaying a content summary extracted from the content linked from the target content link item, display the input question information in response to a question input triggering operation triggered in the question-and-answer interaction area, and display the answer information corresponding to the input question information in response to a question input end operation triggered in the question-and-answer interaction area.

[0208] The modules in the aforementioned content-based interactive device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can invoke and execute the operations corresponding to each module.

[0209] In one exemplary embodiment, a computer device is provided. This computer device can be a terminal or a server. Taking the computer device as a terminal as an example, its internal structure diagram can be as follows: Figure 22 As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a content-based interactive method. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0210] Those skilled in the art will understand that Figure 22 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0211] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0212] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0213] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0214] It should be noted that the data involved in this application (including but not limited to data used for analysis, data stored, data displayed, etc.) are all data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0215] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0216] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0217] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A content-based interaction method, characterized in that, The method includes: Display a set of content link items, each of which is used to trigger the display of the linked content in response to a content browsing operation; At least one content link item in the set of content link items displays a content summary retrieval entry point; In response to a triggered operation on the content summary retrieval entry displayed by the target content link item in the at least one content link item, a content summary extracted from the content linked by the target content link item is displayed.

2. The method according to claim 1, characterized in that, The content summary retrieval entry point for at least one content link item in the content link item set includes: In response to a selection operation on a content link item in the set of content link items, a content summary retrieval entry is displayed for at least one content link item selected in the selection operation.

3. The method according to claim 2, characterized in that, The step of displaying a content summary retrieval entry for at least one content link selected in the selection operation includes: For each of the at least one content link items selected in the selection operation, if the content link item displays content description information describing the topic of the linked content, the content summary retrieval entry will cover the display of the content description information.

4. The method according to claim 3, characterized in that, The method further includes: When the content description information includes a content description image, the content summary retrieval entry will cover at least a portion of the content description image in the content description information.

5. The method according to claim 1, characterized in that, The content summary retrieval entry point for at least one content link item in the content link item set includes: At least one content link in the set of content links that has been displayed for a preset duration will display a content summary retrieval entry.

6. The method according to claim 5, characterized in that, The content summary retrieval entry point for at least one content link item in the content link item set that has a dwell time of up to a preset duration includes: For each content link item in the set of content link items whose dwell time reaches a preset time, if the content link item displays auxiliary information describing the linked content, the content summary retrieval entry will cover the display of the auxiliary information.

7. The method according to claim 5, characterized in that, The content summary retrieval entry point for at least one content link item in the content link item set that has a dwell time of up to a preset duration includes: For each content link item in the set of content link items whose dwell time reaches a preset time, if the content link item displays auxiliary information describing the linked content, the auxiliary information and the content summary retrieval entry are displayed side by side.

8. The method according to claim 5, characterized in that, The method further includes: For each content link item in the set of content link items where the dwell time reaches a preset time, if the content link item displays a content description image describing the topic of the linked content, the content summary retrieval entry will cover at least a portion of the display of the content description image.

9. The method according to claim 5, characterized in that, The content summary retrieval entry point for at least one content link item in the content link item set that has a dwell time of up to a preset duration includes: At least one content link item in the set of content links that is located in the central display area of ​​the set and whose display duration reaches a preset duration will display a content summary retrieval entry.

10. The method according to claim 9, characterized in that, The content summary retrieval entry for at least one content link item that is located in the central display area of ​​the content link item set and whose display dwell time reaches a preset duration includes: Obtain the screen coordinate position of each content link item in the set of content link items, and determine at least one content link item located in the central display area of ​​the set based on the screen coordinate position; For each of the at least one content link item, create a timed task with an execution delay of a preset duration; For each of the at least one content link item, when the displayed dwell time reaches the preset duration, the corresponding delay task for the content link item is executed so that, without changing the screen coordinate position of the content link item, the content summary retrieval entry is displayed for the content link item.

11. The method according to claim 10, characterized in that, The method further includes: In the case where a delayed task with a preset execution delay is created for each of the at least one content link items, the delayed task with the preset execution delay created for each of the at least one content link items is cancelled in response to the display content update operation.

12. The method according to any one of claims 1 to 11, characterized in that, The method further includes: If at least one content link item in the set of content link items displays a summary retrieval entry, the summary retrieval entry is de-displayed in response to a content update operation.

13. The method according to any one of claims 1 to 11, characterized in that, The method further includes: When displaying a content summary extracted from the content linked by the target content link, at least one first recommended content link associated with the content linked by the target content link is displayed; the content linked by the first recommended content link and the content linked by the target content link belong to the same technical field. In response to a first selection operation on any first recommended content link item, the content linked by the first recommended content link item selected by the first selection operation is displayed.

14. The method according to any one of claims 1 to 11, characterized in that, The method further includes: When displaying a content summary extracted from the content linked from the target content link, at least one second recommended content link associated with the content summary is displayed; the second recommended content link displays prediction question information associated with the content summary; In response to a second selection operation on any second recommended content link item, display the content linked to the second recommended content link item selected by the second selection operation; The answer information corresponding to the predicted question information is displayed in the content linked by the selected second recommended content link item.

15. The method according to any one of claims 1 to 11, characterized in that, The method further includes: When displaying a content summary extracted from the content linked from the target content link item, a question-and-answer interaction area is displayed; In response to a question input triggering operation in the question-and-answer interaction area, the entered question information is displayed; In response to the question input end operation triggered in the question-and-answer interaction area, the answer information corresponding to the input question information is displayed.

16. A content-based interactive device, characterized in that, The device includes: The link item display module is used to display a set of content link items, wherein each content link item in the set of content link items is used to trigger the display of the linked content in response to a content browsing operation; The summary retrieval entry display module is used to display the content summary retrieval entry for at least one content link item in the content link item set. The content summary display module is used to display a content summary extracted from the content linked by the target content link in response to a trigger operation on the content summary retrieval entry displayed by the target content link in the at least one content link item.

17. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 15.

18. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 15.

19. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 15.

Images